1. Introduction

2. Methods for Improving Monitoring and Control in Smart Greenhouses

2.1. Classical control approaches

-

ON/OFF control

The ON/OFF control model is a fundamental feedback mechanism used in control loops, particularly in systems where precise control is not required [42]. This control device operates with a binary output, where the system’s operation is either turned on or off, without any intermediate states [43]. The ON/OFF controller responds by switching the output when the controlled variable crosses the set-point threshold [44]. The following figure presents a descriptive diagram of an ON/OFF control system.

Figure 4. ON/OFF control system.

Figure 4. ON/OFF control system.

One of the significant advantages of the ON/OFF control model is its simplicity and ease of implementation, particularly in cases where the mathematical model of the system is unknown or complex, making controller tuning challenging [45]. This model is commonly used in greenhouse environments to regulate various environmental factors such as temperature, humidity, CO₂ concentration, light, moisture, ventilation, irrigation, and heating [46,47].

The ON/OFF control model is suitable for systems that cannot handle frequent on/off switching of energy or have a large mass resulting in slow changes in process variables [48]. It has demonstrated good performance and energy conservation capabilities in numerous studies [49]. For instance, it has been successfully applied to achieve energy-efficient climate control in greenhouses, leading to optimized crop growth and reduced energy consumption.

The energy-saving feature of the ON/OFF controller allows for a versatile strategy that can be easily adjusted to meet specific performance requirements [50]. This adaptability enables efficient and cost-effective control of greenhouse environmental factors, contributing to sustainable agriculture practices.

In recent years, many studies have focused on the application of ON/OFF control in greenhouses, the study proposed by [51] examined the performance of a greenhouse climate control strategy that incorporated on/off control using Variable Frequency Drive (VFD) controllers. The strategy considered plant transpiration, heating, variable vent configurations, and a fogging system. Computer simulations were conducted in two locations with different climates. The results demonstrated that the set points for cooling demands were effectively maintained, with the crop’s transpiration playing a crucial role in adding water vapor to the atmosphere. However, in high humidity outside air conditions, achieving set points was challenging without the addition of dehumidification action to the strategy. This study highlights the importance of on/off control and flexible climate control systems, such as VFD controllers, in extreme greenhouse environments.

Temperature and humidity management in greenhouses significantly impact crop growth. The study presented by [52] evaluated the performance of a small-scale suspension-type dehumidifier with a heating module in terms of temperature and humidity changes over time. A remote monitoring and control system utilizing 27 sensor nodes and an on/off controller was implemented. The results demonstrated satisfactory performance of the on/off control strategy, with successful remote operation of the dehumidifier and heating module. The temperature and humidity exhibited spatial and vertical variability, with greater changes observed in the middle section of the greenhouse. The study provides insights into the utilization of on/off control for temperature and humidity management in greenhouses during different seasons.

Energy consumption is a significant concern in greenhouse temperature control. This study [53] proposes a model-based predictive control strategy using switch actuators to regulate greenhouse temperature. The strategy calculates optimal on/off actuator switch combinations based on control precision and energy loss, considering a weighting factor for cost performance. Simulation results demonstrate that the developed control algorithm achieves set point tracking with reduced energy consumption. Compared to a common model predictive controller, the proposed strategy achieves an operating consumption of only 61.5%.

In another study presented by [54], The authors explore the application of IoT in remotely monitoring and controlling greenhouse parameters such as CO₂, soil moisture, temperature, and light. The IoT system enables farmers to gather information through cloud accounts and internet connections, eliminating the need for physical visits to the field. Additionally, the system facilitates automated actions such as rolling on/off greenhouse windows/doors based on soil moisture levels. The results illustrate the effectiveness of the proposed IoT system in maintaining precise greenhouse parameters, resulting in increased yield.

-

Proportional Integral Derivative (PID) control

PID controllers are widely used in smart greenhouses due to their simplicity and proven effectiveness [55]. The PID controller adjusts environmental parameters such as temperature, humidity, and lighting in real-time based on specific crop requirements. It consists of three components: the proportional part, which responds to the current error; the integral part, which corrects accumulated past errors, and the derivative part, which anticipates future error variations [56]. This combination enables precise and stable regulation of environmental conditions, contributing to optimal energy utilization in smart greenhouses.

A Proportional-Integral-Derivative (PID) controller utilizes feedback to continuously compute an error value, which represents the difference between a desired reference value (r(t)) and the measured variable (y(t)). The control function in a continuous-time system is expressed as:

$$u\left(t\right)=K_{p}e\left(t\right)+K_i{\int }_0^{T}e\left(\tau \right)d\tau +K_d\frac{de\left(t\right)}{dt}$$

where $e\left(t\right)=y\left(t\right)-r\left(t\right)$, and $K_p$, $K_i$ and $K_d$ are respectively the proportional, integrative, and derivative gains. Adjusting these control parameters is necessary to enhance system performance. While stability is a fundamental requirement, different gain values can lead to variations in settling times, overshooting, and other characteristics. As a result, tuning a PID controller can be a challenging process. Figure 5 presents an example of a PID controller.

In this context, many studies have focused on the application of PID control in greenhouses, the study proposed by [57] presents an intelligent control system for greenhouse temperature, humidity, and light, utilizing an internal incremental PID control algorithm. By considering the variation of output as the transmission signal, the algorithm achieves precise control without the need for repeated integration operations. Through simulation and analysis, it is observed that the design scheme based on the internal incremental PID control algorithm outperforms the traditional position PID control algorithm in terms of response speed and sampling frequency. The study utilizes MATLAB software to simulate incremental PID control and selects environmental temperature as the influencing factor for parameter adjustment. Additionally, a multi-factor monitoring system for the greenhouse environment is developed, demonstrating the effectiveness of the internal incremental PID control algorithm in achieving precise measurement and control of multiple factors.

In the study conducted by authors [58], a parameter Self-Tuning PID control approach (STPID) is proposed to address the challenges faced in greenhouse climate control. The primary objective is to enhance the reliability of controllers while maintaining satisfactory control performance. The proposed approach involves the transformation of the interconnected greenhouse climate system into four individual single-input single-output (SISO) subsystems, employing PID controllers for regulating heating, fogging, CO₂ injection, and ventilation. The adaptive parameter tuning is accomplished using the Levenberg-Marquardt (LM) algorithm, which takes into account real weather data. The effectiveness of the proposed method is demonstrated through a comparative analysis of two existing approaches, CAAC (Control Allocation based Adaptive Control) and NNOC (NN-approximation–based optimal control). It should be noted, however, that in terms of control accuracy, STPID may not be as optimal as CAAC and NNOC. The limitations of STPID include its reliance on the LM optimization algorithm and the trade-off between the controlled outputs. Nevertheless, the method exhibits applicability in complex control systems that are challenging to model, providing generality and wide-ranging suitability in various domains such as irrigation control and beneficiation control.

Another study presented by [59] focuses on the cultivation of paprika in a greenhouse system, which offers controlled environmental conditions conducive to its growth. The hardware setup includes Nodemcu ESP8266 as the central controller, a 12v DC water pump for temperature cooling, IBT_2 motor driver for pump speed control, BME280 sensor for temperature and humidity readings, and a 100W 220V lamp for temperature increase. The system utilizes Arduino IDE, MIT App Inventor for monitoring, and Firebase as a database. Apart from temperature control, remote monitoring of temperature and humidity using a mobile device is also possible. The testing results indicate that with PID control based on the Nodemcu ESP8266 Microcontroller and the parameter values of Kp = 10, Ki = 0.5, and Kd = 45, the system effectively maintains the desired air temperature in the greenhouse. The Steady State Error (Ess) values obtained in high-temperature and low-temperature conditions were 0.41% and 0.17%, respectively, demonstrating high accuracy rates of 99.59% and 99.83%. The system’s performance was monitored by farmers through the MIT App Inventor mobile application, providing them with real-time data. Additionally, the air humidity levels were maintained within the range of 70-84%. Overall, the intelligent paprika greenhouse system successfully controls the air temperature in accordance with the specified set point, offering reliable and accurate performance under various conditions.

Another study presented by [60] proposes a detailed design of a greenhouse control system using a PID controller. Unlike previous systems, this new system focuses on minimizing energy costs for crop growth in a greenhouse. It consists of two important processes: the Greenhouse Control Process (GCP) and the Crop Growth Process (CGP). Data from these processes, including crop status information and climate set-point information, are stored in a database. The PID controller operates within the GCP, while the environment control decision-making takes place in the CGP. By using different combinations of PID controllers (P, PI, PD, and PID), users can simulate energy costs and optimize controller design for their greenhouse system. This proposed system offers a feasible solution for reducing energy costs in greenhouses and promoting the development of various greenhouse-related applications.

The focus of the study conducted by [61] is on a smart greenhouse implementation using PID and fuzzy logic controllers. The study introduces a novel observer design for controlling various parameters in a greenhouse, with the aim of increasing crop yield and facilitating indoor breeding and planting. Control actions are based on the fusion of different parameters to optimize energy consumption and water use. MATLAB Simulink models are utilized to design PID controllers for humidity and temperature, while a fuzzy inference system is developed for carbon dioxide enrichment. This integrated approach enables efficient control of greenhouse conditions, leading to improved resource utilization and plant growth.

2.3. Intelligent control approaches

Intelligent greenhouse control approaches comprise various techniques that exploit advanced algorithms and computational methods to optimize and automate the control of greenhouse environments. These include Fuzzy Logic Control (FLC), Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), and Genetic Algorithms (GA).

-

Fuzzy Logic Control (FLC)

Fuzzy Logic Control (FLC) is a computational approach that uses linguistic variables and fuzzy sets to model and control complex systems [80]. In greenhouse control systems based on FLC, fuzzy rules are used to capture expert knowledge and make decisions based on linguistic descriptions of input and output variables, enabling flexible and adaptive control strategies [81]. A typical FLC system is shown in Figure 9.

In this study [82], an advanced modeling and management system was developed to improve greenhouse cultivation by maintaining an optimal microclimate for plant growth. The system utilizes an enhanced intermediate model implemented in MATLAB/Simulink to simulate the energy balance and a Fuzzy Logic Controller (FLC) to regulate greenhouse actuators. Real-time data monitoring and IoT technology were integrated to enhance system control. Testing in a greenhouse in Tunisia demonstrated the effectiveness of the FLC in controlling humidity levels by accurately managing actuators. The implementation of the FLC on a Raspberry Pi 3 using Python and fuzzy modules reduced overall costs while achieving excellent results. The system enables real-time monitoring, addresses data recording challenges, and provides opportunities for ongoing analysis and improvement.

In another study [83], the climate control of a plant factory system is investigated with the aim of effectively regulating temperature and humidity levels. The research introduces a Fuzzy Logic Controller (FLC) optimized using Particle Swarm Optimization (PSO), which focuses on controlling the actuators, air-conditioners, and incoming-outgoing fans. Computer simulations demonstrate that the proposed FLC with PSO achieves superior temperature and humidity regulation compared to existing controllers, while also being more energy efficient. The results suggest that this approach offers an accurate and efficient method for controlling the indoor climate in crop production, making it a valuable option for plant factory systems.

In addition, in article [84], the authors present an optimized hybrid power system for an agricultural greenhouse, integrating a wind turbine and a PV generator, with control provided by a fuzzy logic-based Maximum Power Point Tracking (MPPT) algorithm. This system was simulated and validated in the MATLAB/Simulink environment. Their results demonstrate the effectiveness of the proposed system in effectively controlling the greenhouse microclimate throughout the different seasons. The hybrid power system, coupled with the greenhouse actuators, improves energy consumption, and ensures the stable operation of the heating and ventilation system.

-

Artificial neural networks (ANN)

Artificial Neural Networks (ANNs) provide computer models inspired by the structure and function of the human neuron [85]. In greenhouse control, ANNs are trained using historical data to learn relationships between environmental variables and control actions [86]. From this, ANNs can predict and optimize control actions based on real-time sensor data, facilitating adaptive, data-driven control strategies [87]. Figure 10 shows a schematic representation of the ANN controller.

In their article [88], the authors provide a comprehensive review of artificial neural networks (ANNs) applications in greenhouse technology, highlighting the predominance of feed-forward architectures in the work analyzed. Furthermore, the review explores different network training techniques and the feasibility of using optimization models for the learning process. The pros and cons of ANNs are observed in various greenhouse applications, including microclimate prediction, energy optimization, and carbon dioxide control. This study analyzes 35 works, revealing that the majority (74%) focus on microclimate description and prediction, while 9% concentrate on energy optimization, and 17% cover other greenhouse network applications. Among the investigated NN (Neural Networks) types, feedforward networks account for 46%, while RNNs (Recurrent Neural Network) represent 20% and other NN types make up 32%. This analysis provides valuable information for developers of intelligent protected agricultural systems, particularly those incorporating 4.0 technologies.

In addition, in a study by [89], the authors present an IoT-based smart greenhouse system that integrates monitoring, alerting, cloud storage, automation, and disease prediction for improved crop production. To ensure optimal growing conditions, the system continuously monitors environmental variables and uses automated irrigation management. In addition, disease detection is achieved through the use of deep learning models analyzing leaf pictures. The results demonstrate the effectiveness of deep neural networks in accurately predicting disease and underline the importance of selecting optimal parameters to achieve high accuracy. The research has important implications for the future automation of agriculture and offers farmers the possibility of rapidly identifying diseases using mobile applications.

In the [90] study, an artificial neural network (ANN) model was developed to predict the temperature and relative humidity inside a greenhouse as a function of various input variables. The model is intended to support a Decision Support System (DSS) for maintaining optimal greenhouse conditions with minimal energy consumption. The study uses a multilayer perceptron neural network (MLP-NN) trained with the Levenberg-Marquardt backpropagation algorithm. The model demonstrates excellent accuracy with maximum errors of 0.877 K and 2.838% for temperature and relative humidity, respectively. The coefficients of determination (R2) are 0.999 for both parameters. The low prediction errors and high statistical values indicate the model’s ability to contribute effectively to a DSS for greenhouse management. This study provides valuable insights into the optimization of greenhouse conditions and energy efficiency through the integration of ANN models and decision support systems.

In this research paper [91], a robust system for smart irrigation in greenhouses using artificial neural networks (ANNs) and an Internet of Things (IoT) architecture is presented. This system uses four soil sensors to predict future moisture levels, demonstrating superior performance compared to Support Vector Regression (SVR) methods. The proposed system uses transfer learning to address challenges such as limited training data, the low processing power of state-of-the-art devices, and the integration of climate sensors. On the other hand, the proposed IoT architecture offers a complete solution for efficient and accurate greenhouse irrigation. This study concludes by highlighting the commercialization and actual implementation of the techniques, suggesting potential directions for improvement and extension of the approach to different environments and adaptive sensor selection based on soil types and cost considerations.

-

Particle swarm optimization (PSO)

Particle Swarm Optimization (PSO) is a stochastic population-based optimization algorithm inspired by the collective behavior of social organisms, such as flocks of birds or schools of fish [92]. In the control of greenhouses, PSO algorithms search for optimal control parameters by iteratively updating a population of candidate solutions in a big search space [93]. PSO-based approaches can efficiently optimize control actions to minimize energy consumption, maximize crop yield or maintain desired environmental conditions [93]. Figure 11 shows a schematic diagram of particle swarm optimization.

Within this framework, a study by [94] presents a robust model predictive control (MPC) strategy based on particle swarm optimization (PSO) for greenhouse temperature systems. The strategy uses a nonlinear affine physical temperature model and solves a minimax online optimal control problem to achieve a trade-off between setpoint tracking and cost reduction. The reformulated optimization problem is solved using PSO, and a constraint fitness priority ranking is proposed to ensure constraint satisfaction. Simulation results demonstrate the effectiveness of the proposed control system in achieving set points, offering improved control variables, accuracy, and robustness over conventional MPC.

In another study by [95], the researchers focus on sustainable agriculture based on adaptive particle swarm optimization (PSO) and artificial neural networks (ANN). The proposed approach combines incoming datasets with existing ones without the need for dataset summarization. The PSO algorithm identifies and retains influential records while deleting less important ones. The adaptive PSO-ANN architecture incorporates an adaptive input and output layer to continuously update datasets without restoring the system. Comparative studies demonstrate the effectiveness of the proposed approach, achieving high accuracy of 94.8%, precision of 91.15%, recall, and F1 score in classification tasks. A case study on smart olive cultivation using adaptive PSO-ANN and IoT technologies presents improved agricultural production and water consumption efficiency. The research highlights the potential of smart agriculture to meet the challenges of climate change and increase productivity.

In addition, this study [96] addresses the challenges of path loss in Wireless Sensor Networks (WSNs) deployed in agricultural fields. A new two path loss models using ZigBee WSNs in an agricultural field are formulated. The models, based on exponential and polynomial functions, are optimized using the particle swarm optimization (PSO) algorithm to determine the optimal coefficients. The hybrid EXP-PSO and POLY-PSO models significantly improve the coefficient of determination (R2) and achieve a lower Mean Absolute Error (MAE) than previous models. Accurate path loss models are crucial for the successful deployment of WSN nodes in smart farming applications, guaranteeing reliable data communication without packet loss between nodes.

-

Genetic algorithms (GA)

Genetic algorithms (GAs) are search and optimization algorithms for difficult problems inspired by the principles of genetic selection breeding [97]. GA-based greenhouse control approaches encode control strategies in chromosome form and apply genetic operators, such as selection, crossover, and mutation, to evolve and improve control policies over time [98]. GA algorithms can explore a vast space of solutions to find optimal or near-optimal control actions [99].

Figure 12. General schematic diagram of Genetic Algorithm.

Figure 12. General schematic diagram of Genetic Algorithm.

In their work [100], the authors propose an intelligent agricultural system that uses data mining technology and the ZigBee wireless sensor network to monitor and control various aspects of agricultural production. The system integrates a three-layer structure consisting of a data acquisition network, a communication layer with gateways and servers, and an application layer with mobile terminal control. Data mining techniques are used to analyze and process the collected data, providing reliable information for farm management. To optimize the weights and thresholds of a BP (Back Propagation) neural network, the paper proposes the use of a single-crossing Multi-Generation Genetic Algorithm Back Propagation, leading to the establishment of the MGABP model. The analytical hierarchy process is presented as a guiding mechanism for the neural network. Experimental analysis confirms the performance of the proposed model, demonstrating practical effectiveness in the intelligent agricultural system. However, this research contributes to a comprehensive and integrated approach to agricultural data monitoring and analysis, incorporating state-of-the-art technologies for better decision-making in sustainable agriculture.

Another study [101] focuses on the design of an intelligent control system for agricultural greenhouses using an improved adaptive genetic algorithm. An experimental platform is developed and tested to validate the feasibility of the system. The results demonstrate that intelligent control of agricultural greenhouses achieves a stable air temperature deviation of less than 0.5°C, an air humidity deviation of less than 1% RH (Relative Humidity) and small fluctuations in carbon dioxide concentration. Finally, this article highlights the overall function and structure of the system, underlining its benefits in improving crop yields and quality. The intelligent control system is recommended for its reasonable structure, accurate data collection, stable communication, and comprehensive control capabilities. Although some areas for improvement are recognized, the paper’s design and method present advanced features and practical functionality in greenhouse control, contributing to the advancement of intelligent agricultural production.

Furthermore, the paper by [102] proposes an agricultural water-efficient irrigation prediction algorithm that combines the genetic algorithm (GA) with a BP neural network. The algorithm uses factors such as humidity and light intensity as inputs to the neural network and optimizes weights and thresholds using GA’s global search capability. The model is tested using data from an experimental field base, and an intelligent farm environment acquisition system is implemented using IoT technology. Results highlight the high accuracy of the GA-BP neural network algorithm in predicting crop water demand and its effectiveness in achieving water-efficient irrigation. The algorithm demonstrates high adaptability and contributes to the goal of efficient water use in agriculture.

The table below shows the main advantages, limitations, and challenges of each of these approaches.

Table 1. Advantages and limitations of the methods for monitoring and control in intelligent greenhouses.

Table 1. Advantages and limitations of the methods for monitoring and control in intelligent greenhouses.

Methods		Advantages	Limitations and Challenges
Classical control Methods	ON/OFF control	Simplicity: ON/OFF control is simple to implement and requires minimal computing resources. Energy savings: ON/OFF control enables efficient energy saving by activating or deactivating control devices as required, thus reducing energy consumption during periods of stability. Cost-efficiency: ON/OFF control is a cost-effective solution, which makes it accessible to greenhouse operators with limited resources. Reliability: ON/OFF controllers provide reliability and have been widely used in various industries, with a proven track record of performance.	Hysteresis: With ON/OFF control, the control output may oscillate around the setpoint because of switching thresholds, which might affect stability and accuracy. Overshoot and Settling Time: The discrete nature of ON/OFF control can lead to overshooting when switching occurs, resulting in a prolonged settling period before the system reaches stability at the desired setpoint. Limited Precision: When compared to more advanced control systems, ON/OFF control may exhibit greater fluctuations around the setpoint, resulting in less precise regulation of environmental conditions. Handling Nonlinearities: The basic ON/OFF control mechanism may encounter challenges in effectively managing nonlinear behaviors and intricate interactions within the greenhouse system.
	PID control	Simplicity: The PID controller’s algorithm is easy to understand and implement, making it accessible for greenhouse operators with varying levels of expertise. Robustness: PID control exhibits robust performance, effectively handling disturbances and uncertainties commonly encountered in greenhouse environments. Reliability: PID controllers have been extensively used in industrial settings and have a long-standing reputation for reliability and stability in controlling various systems. Adaptability: PID parameters can be tuned and adjusted to suit different greenhouse setups, crop types, and desired environmental conditions, allowing for flexibility and customization.	Non-linearities: greenhouse environments present non-linear behaviors, such as time-varying dynamics and coupling effects, which can limit PID controller performance. Setpoint changes: A PID controller may experience transient responses and significant delays when adapting to sudden setpoint changes. External disturbances: PID control’s ability to maintain desired conditions may be affected by environmental disturbances, such as weather fluctuations or equipment failure. Wind-up effects:PID control’s integral term can lead to wind-up effects, thus causing overshoot and instability in the system.
Advanced control Methods	MPC Control	Dynamic adaptability: MPC considers the dynamic behavior of the greenhouse system involved and adapts control actions in real-time, which means it is ideally suited to the management of complex, time-varying dynamics. Optimal control: allows MPC to optimize control actions over a prediction horizon, considering constraints and objectives, resulting in improved performance and energy efficiency. Robustness: for robust and reliable control under variable operating conditions, MPC can handle system uncertainties, disturbances, and model inaccuracies. Flexibility: MPC can solve multivariable control problems, enabling simultaneous regulation of several environmental parameters in order to achieve optimal growing conditions.	Model accuracy: MPC requires precise mathematical models of the greenhouse system, and any discrepancies between the model and the real system can affect control performance. Computational complexity: MPC requires an optimization problem to be solved at each time step, so it can be computationally demanding, requiring efficient algorithms for real-time implementation. Model updating: Greenhouse system dynamics can change over time, making periodic model updates necessary to guarantee accurate predictions and monitor performance.
	Adaptive control	Adaptability: It can adapt to varying operating conditions, enabling effective control to be maintained even in the presence of uncertainties and changes in greenhouse dynamics. Robustness: it can handle uncertainties and model disturbances, guaranteeing reliable control performance against unpredictable factors. Energy efficiency: Adaptive control can minimize energy consumption while maintaining desired climatic conditions, by continuously optimizing control actions based on real-time feedback. Fault tolerance: It can detect and compensate for greenhouse system faults or deviations, improving system resilience and reducing crop losses.	Model complexity: It can be difficult to develop accurate mathematical models that capture the complex dynamics and interactions within the greenhouse system. Adaptation rate: control algorithm adaptation rates must be carefully tuned to strike a balance between responsiveness and stability. Sensor selection and reliability: adaptive control relies on accurate and reliable sensor measurements, requiring careful sensor selection and maintenance.
	Robust control	Stability: Reliable control techniques ensure stability in the presence of uncertainties and disturbances, avoiding system instabilities and guaranteeing reliable performance. Performance:With robust control, desired control objectives can be achieved in the presence of uncertainties, providing accurate and robust regulation of greenhouse climatic variables. Adaptability: Designed to control a wide range of uncertainties and disturbances, robust control is suitable for variable greenhouse conditions and dynamic operating environments. Fault tolerance: Robust control is able both to detect and compensate for faults or deviations occurring in the greenhouse system, providing system resilience, and minimizing crop losses.	Modeling uncertainties: It can be difficult to accurately characterize and model uncertainties in the greenhouse system, which requires robust control design methods that account for a wide range of uncertainties. Controller complexity: robust control designs may require a lot of computation and detailed system models, which can pose challenges in real-time implementation and practical application. Sensitivity to modeling errors: the performance of robust controls can be affected by modeling errors and mismatches between assumed uncertainties and actual system behavior.
Intelligent control Methods	Fuzzy logic control	Non-linearity management: fuzzy logic control can handle non-linearities and complex relationships involving input and output variables, thus enabling it to be adapted to greenhouse systems with non-linear dynamics. Linguistic representation: fuzzy logic control enables the intuitive, human representation of control rules, making it easier to interpret and understand control strategies. Integration of expert knowledge: fuzzy logic control can integrate expert knowledge and experience into control design, leveraging domain expertise for effective control strategies.	Designing the rule base: building an appropriate rule base for fuzzy logic control requires specialized knowledge and careful consideration of the system’s behavior and objectives. Membership function design: it can be difficult to design membership functions that accurately represent the system’s input and output variables and require careful iterative refinement. System complexity: increasing the complexity of the greenhouse system, the design and tuning of fuzzy logic control may be more complex and more computationally demanding.
	Artificial Neural Networks	Non-linear modeling: ANNs are able to capture and model the non-linear relationships and dynamics inherent in greenhouse systems, that make them suitable for monitoring and controlling complex, non-linear climate variables. Adaptive learning: It can adapt and learn from environmental feedback, enabling them to adjust control strategies in real time in response to changing conditions. Data-driven approach: they use historical data to learn patterns and relationships, which enables them to generalize control strategies on the basis of previous experience. Fault tolerance: ANNs can handle sensor failures or noisy data using redundancy and distributed processing.	Availability of training data: Adequate and representative training data are essential for developing accurate and reliable ANN models. It can be difficult to obtain complete and diverse data sets in greenhouses. Model complexity and interpretability: complex ANN architectures will be difficult to interpret, which makes it hard to understand the underlying decision-making process. Over-fitting and generalization: precautions must be taken to avoid over-fitting, where the network becomes too specialized for training data and performs poorly on new or unseen data.
	Particle Swarm Optimization	Global search capability: its ability to explore the global search space enables PSO to find optimal or near-optimal solutions, also in highly non-linear and complex greenhouse control problems. Adaptive and dynamic optimization: in response to changing environmental conditions, PSO can dynamically adapt its search behavior, adapting it to real-time control in dynamic greenhouse systems. Fast convergence: In many applications, PSO algorithms converge relatively quickly, enabling efficient optimization and control adjustments in real-time applications. Noisy environment robustness: with its population approach and exploration-exploitation balance, PSO is robust to the noisy and uncertain sensor data frequently encountered in greenhouse environments.	Parameter tuning: the selection of appropriate PSO algorithm parameters, such as inertia weight swarm size and acceleration coefficients, can have a significant impact on both optimization performance and convergence speed. Premature convergence: premature convergence can occur when the swarm is trapped in local optima and fails at exploring the entire search space. In order to overcome this challenge, careful parameter tuning, and exploration strategies are essential. Computational complexity: as the number of control variables and the complexity of the optimization problem increase, so do the computational requirements of PSO. For greenhouse control applications on a large scale, efficient implementation techniques need to be considered.
	Genetic Algorithms	Global search capability: they can explore the search space on a global scale, enabling them to find optimal or near-optimal solutions, even in complex, highly non-linear greenhouse control problems. Adaptive and dynamic optimization: they can adapt their population to changing environmental conditions, which makes them suitable for real-time control in dynamic greenhouse systems. Robustness to local optima: GAs use population-based search, avoiding trapping in local optima and allowing exploration of diverse solutions. Constraint management: GA systems can incorporate constraints on control variables, such as maximum and minimum limits, thus ensuring that the solutions generated satisfy the operational constraints of the greenhouse system.	Parameter tuning: the selection of appropriate GA parameters, such as crossover and mutation rates, population size, and selection mechanisms, can have a significant impact on optimization performance and speed of convergence. Computational complexity: GAs can be computationally intensive, particularly for problems involving large-scale greenhouse control with a high number of control variables and complex fitness functions. Therefore, it is important to consider efficient implementation techniques. Speed of convergence: Many generations may be required to converge on an optimal solution, and premature convergence may occur. It is essential to balance exploration and exploitation through rigorous selection mechanisms and operator choices.

3. Greenhouse Towards Near Zero Energy Consumption

4. Conclusions

Nomenclature

References

1. Karanisa, T.; Achour, Y.; Ouammi, A.; Sayadi, S. Smart Greenhouses as the Path towards Precision Agriculture in the Food-Energy and Water Nexus: Case Study of Qatar. Environment Systems and Decisions 2022 42:4 2022, 42, 521–546, . [CrossRef]
2. Oukil, A.; Nourani, A.; Bencheikh, A.; Soltani, A.A. Using Inverse Data Envelopment Analysis to Evaluate Potential Impact of Mergers on Energy Use Optimization - Application in the Agricultural Production. J Clean Prod 2022, 381, 135199, . [CrossRef]
3. Soheilifard, F.; Taki, M.; van Zelm, R. Impact of Energy Flow Optimization on the Mitigation of Environmental Consequences and Costs in Greenhouse Cucumber Production. Environmental Science and Pollution Research 2021, 28, 8421–8433, . [CrossRef]
4. Kavga, A.; Thomopoulos, V.; Barouchas, P.; Stefanakis, N.; Liopa-Tsakalidi, A. Research on Innovative Training on Smart Greenhouse Technologies for Economic and Environmental Sustainability. Sustainability 2021, Vol. 13, Page 10536 2021, 13, 10536, . [CrossRef]
5. Vadiee, A.; Martin, V. Thermal Energy Storage Strategies for Effective Closed Greenhouse Design. Appl Energy 2013, 109, 337–343, . [CrossRef]
6. Zhang, Y.; Henke, M.; Li, Y.; Xu, D.; Liu, A.; Liu, X.; Li, T. Towards the Maximization of Energy Performance of an Energy-Saving Chinese Solar Greenhouse: A Systematic Analysis of Common Greenhouse Shapes. Solar Energy 2022, 236, 320–334, . [CrossRef]
7. Golzar, F.; Heeren, N.; Hellweg, S.; Roshandel, R. A Novel Integrated Framework to Evaluate Greenhouse Energy Demand and Crop Yield Production. Renewable and Sustainable Energy Reviews 2018, 96, 487–501, . [CrossRef]
8. Tong, G.; Christopher, D.M.; Li, T.; Wang, T. Passive Solar Energy Utilization: A Review of Cross-Section Building Parameter Selection for Chinese Solar Greenhouses. Renewable and Sustainable Energy Reviews 2013, 26, 540–548, . [CrossRef]
9. Zhang, M.; Yan, T.; Wang, W.; Jia, X.; Wang, J.; Klemeš, J.J. Energy-Saving Design and Control Strategy towards Modern Sustainable Greenhouse: A Review. Renewable and Sustainable Energy Reviews 2022, 164, 112602, . [CrossRef]
10. Maraveas, C. Environmental Sustainability of Greenhouse Covering Materials. Sustainability 2019, Vol. 11, Page 6129 2019, 11, 6129, . [CrossRef]
11. Sangpradit, K. Study of the Solar Transmissivity of Plastic Cladding Materials and Influence of Dust and Dirt on Greenhouse Cultivations. Energy Procedia 2014, 56, 566–573, . [CrossRef]
12. Balocco, C.; Mercatelli, L.; Azzali, N.; Meucci, M.; Grazzini, G. Experimental Transmittance of Polyethylene Films in the Solar and Infrared Wavelengths. Solar Energy 2018, 165, 199–205, . [CrossRef]
13. Ouammi, A.; Achour, Y.; Dagdougui, H.; Zejli, D. Optimal Operation Scheduling for a Smart Greenhouse Integrated Microgrid. Energy for Sustainable Development 2020, 58, 129–137, . [CrossRef]
14. Reddy, P.P. Greenhouse Technology. Sustainable Crop Protection under Protected Cultivation 2016, 13–22, . [CrossRef]
15. Figueiroa, V.; Torres, J.P.N. Simulation of a Small Smart Greenhouse. Designs 2022, Vol. 6, Page 106 2022, 6, 106, . [CrossRef]
16. Achour, Y.; Ouammi, A.; Zejli, D. Technological Progresses in Modern Sustainable Greenhouses Cultivation as the Path towards Precision Agriculture. Renewable and Sustainable Energy Reviews 2021, 147, 111251, . [CrossRef]
17. Alsanius, B.W.; Bergstrand, K.J.; Hartmann, R.; Gharaie, S.; Wohanka, W.; Dorais, M.; Rosberg, A.K. Ornamental Flowers in New Light: Artificial Lighting Shapes the Microbial Phyllosphere Community Structure of Greenhouse Grown Sunflowers (Helianthus Annuus L.). Sci Hortic 2017, 216, 234–247, . [CrossRef]
18. Paradiso, R.; Proietti, S. Light-Quality Manipulation to Control Plant Growth and Photomorphogenesis in Greenhouse Horticulture: The State of the Art and the Opportunities of Modern LED Systems. J Plant Growth Regul 2022, 41, 742–780, . [CrossRef]
19. Badji, A.; Benseddik, A.; Bensaha, H.; Boukhelifa, A.; Hasrane, I. Design, Technology, and Management of Greenhouse: A Review. J Clean Prod 2022, 373, 133753, . [CrossRef]
20. Katzin, D.; Marcelis, L.F.M.; van Mourik, S. Energy Savings in Greenhouses by Transition from High-Pressure Sodium to LED Lighting. Appl Energy 2021, 281, 116019, . [CrossRef]
21. He, F.; Zeng, L.; Li, D.; Ren, Z. Study of LED Array Fill Light Based on Parallel Particle Swarm Optimization in Greenhouse Planting. Information Processing in Agriculture 2019, 6, 73–80, . [CrossRef]
22. Tang, Y.; Jia, M.; Mei, Y.; Yu, Y.; Zhang, J.; Tang, R.; Song, K. 3D Intelligent Supplement Light Illumination Using Hybrid Sunlight and LED for Greenhouse Plants. Optik (Stuttg) 2019, 183, 367–374, . [CrossRef]
23. Iddio, E.; Wang, L.; Thomas, Y.; McMorrow, G.; Denzer, A. Energy Efficient Operation and Modeling for Greenhouses: A Literature Review. Renewable and Sustainable Energy Reviews 2020, 117, 109480, . [CrossRef]
24. Mashonjowa, E.; Ronsse, F.; Milford, J.R.; Pieters, J.G. Modelling the Thermal Performance of a Naturally Ventilated Greenhouse in Zimbabwe Using a Dynamic Greenhouse Climate Model. Solar Energy 2013, 91, 381–393, . [CrossRef]
25. Xu, J.; Li, Y.; Wang, R.Z.; Liu, W.; Zhou, P. Experimental Performance of Evaporative Cooling Pad Systems in Greenhouses in Humid Subtropical Climates. Appl Energy 2015, 138, 291–301, . [CrossRef]
26. Van Beveren, P.J.M.; Bontsema, J.; Van Straten, G.; Van Henten, E.J. Minimal Heating and Cooling in a Modern Rose Greenhouse. Appl Energy 2015, 137, 97–109, . [CrossRef]
27. Rafiee, M.R.; Mahmoodi-Eshkaftaki, M. Optimization of Irrigation Management and Environmental Assessment Using the Water Cycle Algorithm. Soil Use Manag 2023, 39, 917–932, . [CrossRef]
28. Wu, Y.; Yan, S.; Fan, J.; Zhang, F.; Xiang, Y.; Zheng, J.; Guo, J. Responses of Growth, Fruit Yield, Quality and Water Productivity of Greenhouse Tomato to Deficit Drip Irrigation. Sci Hortic 2021, 275, 109710, . [CrossRef]
29. Shamshiri, R.R. and H.I.A. and T.K.R. and B.S.K. and S.S. and F.M. and S.M. and M.B. and S.S. Greenhouse Automation Using Wireless Sensors and IoT Instruments Integrated with Artificial Intelligence. Next-generation greenhouses for food security} 2021.
30. Hosseini-Fashami, F.; Motevali, A.; Nabavi-Pelesaraei, A.; Hashemi, S.J.; Chau, K. Energy-Life Cycle Assessment on Applying Solar Technologies for Greenhouse Strawberry Production. Renewable and Sustainable Energy Reviews 2019, 116, 109411, . [CrossRef]
31. Kumar, P.; Saroj, S.; Kumar, S.; Azad, C. Automated Monitoring and Regulation of User-Friendly Greenhouse Using Arduino. In; 2021; pp. 43–59.
32. Garlando, U.; Bar-On, L.; Avni, A.; Shacham-Diamand, Y.; Demarchi, D. Plants and Environmental Sensors for Smart Agriculture, an Overview. In Proceedings of the 2020 IEEE SENSORS; IEEE, October 25 2020; pp. 1–4.
33. Amani, M.; Foroushani, S.; Sultan, M.; Bahrami, M. Comprehensive Review on Dehumidification Strategies for Agricultural Greenhouse Applications. Appl Therm Eng 2020, 181, 115979, . [CrossRef]
34. Gunarathne, K.; Welihinda, D.; Erandima, T.; Mendis, J.; Vanderbona, D.; Thabrew, A.; Hydher, H. PID Controlled Autonomous Urban Greenhouse Complex. In Proceedings of the 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS); IEEE, August 11 2021; pp. 440–445.
35. Yano, A.; Cossu, M. Energy Sustainable Greenhouse Crop Cultivation Using Photovoltaic Technologies. Renewable and Sustainable Energy Reviews 2019, 109, 116–137, . [CrossRef]
36. Zhang, S.; Guo, Y.; Zhao, H.; Wang, Y.; Chow, D.; Fang, Y. Methodologies of Control Strategies for Improving Energy Efficiency in Agricultural Greenhouses. J Clean Prod 2020, 274, 122695, . [CrossRef]
37. Aghaseyedabdollah, Mh.; Alaviyan, Y.; Yazdizadeh, A. IoT Based Smart Greenhouse Design with an Intelligent Supervisory Fuzzy Optimized Controller. In Proceedings of the 2021 7th International Conference on Web Research (ICWR); IEEE, May 19 2021; pp. 311–317.
38. Zhang, C. Greenhouse Intelligent Control System Based on Microcontroller.; 2018; p. 040033.
39. Bersani, C.; Ruggiero, C.; Sacile, R.; Soussi, A.; Zero, E. Internet of Things Approaches for Monitoring and Control of Smart Greenhouses in Industry 4.0. Energies (Basel) 2022, 15, 3834, . [CrossRef]
40. Maroli, A.; Narwane, V.S.; Gardas, B.B. Applications of IoT for Achieving Sustainability in Agricultural Sector: A Comprehensive Review. J Environ Manage 2021, 298, 113488, . [CrossRef]
41. Maraveas, C. Incorporating Artificial Intelligence Technology in Smart Greenhouses: Current State of the Art. Applied Sciences 2022, 13, 14, . [CrossRef]
42. Åström, K.J., & M.R.M. Feedback Systems: An Introduction for Scientists and Engineers; Princeton university press., 2021;
43. Wiegart, T.; Steiner, F.; Schulte, P.; Yuan, P. Shaped On–Off Keying Using Polar Codes. IEEE Communications Letters 2019, 23, 1922–1926, . [CrossRef]
44. Homod, R.Z.; Gaeid, K.S.; Dawood, S.M.; Hatami, A.; Sahari, K.S. Evaluation of Energy-Saving Potential for Optimal Time Response of HVAC Control System in Smart Buildings. Appl Energy 2020, 271, 115255, . [CrossRef]
45. Faizollahzadeh Ardabili, S.; Mahmoudi, A.; Mesri Gundoshmian, T.; Roshanianfard, A. Modeling and Comparison of Fuzzy and on/off Controller in a Mushroom Growing Hall. Measurement 2016, 90, 127–134, . [CrossRef]
46. Ali, M.; Chowdhury, M.; Islam, M.N.; Islam, S.; Kiraga, S.; Jeong, J.H.; Chung, S.O. Irrigation Control and Image Acquisition for Rice Cultivation in UAE Desert Soil. IOP Conf Ser Earth Environ Sci 2021, 924, 012018, . [CrossRef]
47. Abbassy, M.M.; Ead, W.M. Intelligent Greenhouse Management System. In Proceedings of the 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS); IEEE, March 2020; pp. 1317–1321.
48. Serale, G.; Gnoli, L.; Giraudo, E.; Fabrizio, E. A Supervisory Control Strategy for Improving Energy Efficiency of Artificial Lighting Systems in Greenhouses. Energies (Basel) 2021, 14, 202, . [CrossRef]
49. Liang, Y.; Pan, Y.; Yuan, X.; Yang, Y.; Fu, L.; Li, J.; Sun, T.; Huang, Z.; Kosonen, R. Assessment of Operational Carbon Emission Reduction of Energy Conservation Measures for Commercial Buildings: Model Development. Energy Build 2022, 268, 112189, . [CrossRef]
50. Sumalan, R.L.; Stroia, N.; Moga, D.; Muresan, V.; Lodin, A.; Vintila, T.; Popescu, C.A. A Cost-Effective Embedded Platform for Greenhouse Environment Control and Remote Monitoring. Agronomy 2020, 10, 936, . [CrossRef]
51. Villarreal-Guerrero, F.; Pinedo-Alvarez, A.; Flores-Velázquez, J. Control of Greenhouse-Air Energy and Vapor Pressure Deficit with Heating, Variable Fogging Rates and Variable Vent Configurations: Simulated Effectiveness under Varied Outside Climates. Comput Electron Agric 2020, 174, 105515, . [CrossRef]
52. Islam, M.N.; Iqbal, M.Z.; Ali, M.; Jang, B.-E.; Chowdhury, M.; Kabir, M.S.N.; Jang, S.-H.; Chung, S.-O. Performance Evaluation of a Suspension-Type Dehumidifier with a Heating Module for Smart Greenhouses. Journal of Biosystems Engineering 2020, 45, 155–166, . [CrossRef]
53. Liang, M.-H.; Chen, L.-J.; He, Y.-F.; Du, S.-F. Greenhouse Temperature Predictive Control for Energy Saving Using Switch Actuators. IFAC-PapersOnLine 2018, 51, 747–751, . [CrossRef]
54. Pallavi, S.; Mallapur, J.D.; Bendigeri, K.Y. Remote Sensing and Controlling of Greenhouse Agriculture Parameters Based on IoT. In Proceedings of the 2017 International Conference on Big Data, IoT and Data Science (BID); IEEE, December 2018; pp. 44–48.
55. Zaguia, A. Smart Greenhouse Management System with Cloud-Based Platform and IoT Sensors. Spatial Information Research 2023, . [CrossRef]
56. Gonzalez-Amarillo, C.A.; Corrales-Munoz, J.C.; Mendoza-Moreno, M.A.; Gonzalez Amarillo, A. maria; Hussein, A.F.; Arunkumar, N.; Ramirez-Gonzalez, G. An IoT-Based Traceability System for Greenhouse Seedling Crops. IEEE Access 2018, 6, 67528–67535, . [CrossRef]
57. Niu, H.; Liao, X.; Dai, Y.; Hu, C.; Zhang, L.; Chen, S. A Multi-Factor Control System in Greenhouse Based on The Internal Incremental PID Algorithm. In Proceedings of the 2021 International Conference on Electronic Information Technology and Smart Agriculture (ICEITSA); IEEE, December 2021; pp. 99–105.
58. Su, Y.; Yu, Q.; Zeng, L. Parameter Self-Tuning PID Control for Greenhouse Climate Control Problem. IEEE Access 2020, 8, 186157–186171, . [CrossRef]
59. Effendi, D.H.; Kamelia, L.; Faroqi, A.; Ulhaq, M.I.Z. Pepper Greenhouse Condition Control System Using the Proportional Integral Derivative (PID) Methods. In Proceedings of the 2022 8th International Conference on Wireless and Telematics (ICWT); IEEE, July 21 2022; pp. 1–5.
60. Vasanth Ragu; Chang-Sun Shin; 박장우; 이명배; Yongyun Cho A Greenhouse Control System Based on Best-Fitted PID Controller to Minimize Energy Cost. Journal of Knowledge Information Technology and Systems 2018, 13, 1–9, . [CrossRef]
61. Chaudhary, G.; Kaur, S.; Mehta, B.; Tewani, R. Observer Based Fuzzy and PID Controlled Smart Greenhouse. Journal of Statistics and Management Systems 2019, 22, 393–401, . [CrossRef]
62. Howard, D.A.; Ma, Z.; Veje, C.; Clausen, A.; Aaslyng, J.M.; Jørgensen, B.N. Greenhouse Industry 4.0 – Digital Twin Technology for Commercial Greenhouses. Energy Informatics 2021, 4, 37, . [CrossRef]
63. Xie, P.; Tan, S.; Guerrero, J.M.; Vasquez, J.C. MPC-Informed ECMS Based Real-Time Power Management Strategy for Hybrid Electric Ship. Energy Reports 2021, 7, 126–133, . [CrossRef]
64. Endo, A.; Parra, S.; Cartagena, O.; Sáez, D.; Muñoz, C.; Huircan, J.I. Energy–Water Management System Based on MPC for a Greenhouse in a Mapuche Indigenous Community. Applied Sciences 2023, 13, 4734, . [CrossRef]
65. Ouammi, A.; Achour, Y.; Zejli, D.; Dagdougui, H. Supervisory Model Predictive Control for Optimal Energy Management of Networked Smart Greenhouses Integrated Microgrid. IEEE Transactions on Automation Science and Engineering 2020, 17, 117–128, . [CrossRef]
66. Mahmood, F.; Govindan, R.; Bermak, A.; Yang, D.; Khadra, C.; Al-Ansari, T. Energy Utilization Assessment of a Semi-Closed Greenhouse Using Data-Driven Model Predictive Control. J Clean Prod 2021, 324, 129172, . [CrossRef]
67. Bersani, C.; Fossa, M.; Priarone, A.; Sacile, R.; Zero, E. Model Predictive Control versus Traditional Relay Control in a High Energy Efficiency Greenhouse. Energies (Basel) 2021, 14, 3353, . [CrossRef]
68. Lin, D.; Zhang, L.; Xia, X. Model Predictive Control of a Venlo-Type Greenhouse System Considering Electrical Energy, Water and Carbon Dioxide Consumption. Appl Energy 2021, 298, 117163, . [CrossRef]
69. Chen, W.-H.; You, F. Smart Greenhouse Control under Harsh Climate Conditions Based on Data-Driven Robust Model Predictive Control with Principal Component Analysis and Kernel Density Estimation. J Process Control 2021, 107, 103–113, . [CrossRef]
70. Kim, D.; Wang, Z.; Brugger, J.; Blum, D.; Wetter, M.; Hong, T.; Piette, M.A. Site Demonstration and Performance Evaluation of MPC for a Large Chiller Plant with TES for Renewable Energy Integration and Grid Decarbonization. Appl Energy 2022, 321, 119343, . [CrossRef]
71. Zhang, G.; Zhang, L.; Li, X.; Gong, Z.; Dong, Y. An Adaptive Control Method for the Covers on the South Roof of Chinese Solar Greenhouses: A Case Study of Insulation Blankets. Comput Electron Agric 2023, 209, 107861, . [CrossRef]
72. Li, Z.; Ding, Z.; Wang, M.; Oko, E. Model-Free Adaptive Control for MEA-Based Post-Combustion Carbon Capture Processes. Fuel 2018, 224, 637–643, . [CrossRef]
73. Wang, L.; Wang, B. Construction of Greenhouse Environment Temperature Adaptive Model Based on Parameter Identification. Comput Electron Agric 2020, 174, 105477, . [CrossRef]
74. Wang, Y.; Lu, Y.; Xiao, R. Application of Nonlinear Adaptive Control in Temperature of Chinese Solar Greenhouses. Electronics (Basel) 2021, 10, 1582, . [CrossRef]
75. Tian, Y. Adaptive Control and Supply Chain Management of Intelligent Agricultural Greenhouse by Intelligent Fuzzy Auxiliary Cognitive System. Expert Syst 2022, . [CrossRef]
76. Ahirwar, M.; Mahia, R.N. An Evaluation of Techniques for Controlling and Monitoring Greenhouse. In Proceedings of the 2023 International Conference for Advancement in Technology (ICONAT); IEEE, January 24 2023; pp. 1–8.
77. Subin, M.C.; Singh, A.; Kalaichelvi, V.; Karthikeyan, R.; Periasamy, C. Design and Robustness Analysis of Intelligent Controllers for Commercial Greenhouse. Mechanical Sciences 2020, 11, 299–316, . [CrossRef]
78. Chen, W.-H.; You, F. Semiclosed Greenhouse Climate Control Under Uncertainty via Machine Learning and Data-Driven Robust Model Predictive Control. IEEE Transactions on Control Systems Technology 2022, 30, 1186–1197, . [CrossRef]
79. Chen, W.-H.; You, F. Smart Greenhouse Control under Harsh Climate Conditions Based on Data-Driven Robust Model Predictive Control with Principal Component Analysis and Kernel Density Estimation. J Process Control 2021, 107, 103–113, . [CrossRef]
80. Mostafa, S.A.; Mustapha, A.; Mohammed, M.A.; Ahmad, M.S.; Mahmoud, M.A. A Fuzzy Logic Control in Adjustable Autonomy of a Multi-Agent System for an Automated Elderly Movement Monitoring Application. Int J Med Inform 2018, 112, 173–184, . [CrossRef]
81. Ben Ali, R.; Bouadila, S.; Mami, A. Development of a Fuzzy Logic Controller Applied to an Agricultural Greenhouse Experimentally Validated. Appl Therm Eng 2018, 141, 798–810, . [CrossRef]
82. Belkadi, A.; Sghaier, N.; Hassine, I. Ben; Mezghanni, D.; Mami, A. Humidity Control Inside Smart Greenhouse Using a Raspberry Pi Card by Applying FLC Technique. In Proceedings of the 2023 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET); IEEE, April 29 2023; pp. 1–6.
83. Chinsuwan, N.; Radpukdee, T. Mathematical Modeling of a Plant Factory System for Optimal Fuzzy Logic Control. In Proceedings of the 2020 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS); IEEE, June 2020; pp. 195–200.
84. Riahi, J.; Vergura, S.; Mezghani, D.; Mami, A. A Combined PV-Wind Energy System for an Energy Saving Greenhouse. In Proceedings of the 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe); IEEE, June 2020; pp. 1–6.
85. Villarrubia, G.; De Paz, J.F.; Chamoso, P.; la Prieta, F. De Artificial Neural Networks Used in Optimization Problems. Neurocomputing 2018, 272, 10–16, . [CrossRef]
86. Hadidi, A.; Saba, D.; Sahli, Y. The Role of Artificial Neuron Networks in Intelligent Agriculture (Case Study: Greenhouse). In; 2021; pp. 45–67.
87. Manonmani, A.; Thyagarajan, T.; Elango, M.; Sutha, S. Modelling and Control of Greenhouse System Using Neural Networks. Transactions of the Institute of Measurement and Control 2018, 40, 918–929, . [CrossRef]
88. Escamilla-García, A.; Soto-Zarazúa, G.M.; Toledano-Ayala, M.; Rivas-Araiza, E.; Gastélum-Barrios, A. Applications of Artificial Neural Networks in Greenhouse Technology and Overview for Smart Agriculture Development. Applied Sciences 2020, 10, 3835, . [CrossRef]
89. Pothuganti, K.; Sridevi, B.; Seshabattar, P. IoT and Deep Learning Based Smart Greenhouse Disease Prediction. In Proceedings of the 2021 International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT); IEEE, August 27 2021; pp. 793–799.
90. Petrakis, T.; Kavga, A.; Thomopoulos, V.; Argiriou, A.A. Neural Network Model for Greenhouse Microclimate Predictions. Agriculture 2022, 12, 780, . [CrossRef]
91. Risheh, A.; Jalili, A.; Nazerfard, E. Smart Irrigation IoT Solution Using Transfer Learning for Neural Networks. In Proceedings of the 2020 10th International Conference on Computer and Knowledge Engineering (ICCKE); IEEE, October 29 2020; pp. 342–349.
92. Wang, D.; Tan, D.; Liu, L. Particle Swarm Optimization Algorithm: An Overview. Soft comput 2018, 22, 387–408, . [CrossRef]
93. Ullah, I.; Fayaz, M.; Aman, M.; Kim, D. An Optimization Scheme for IoT Based Smart Greenhouse Climate Control with Efficient Energy Consumption. Computing 2022, 104, 433–457, . [CrossRef]
94. Chen, L.; Du, S.; He, Y.; Liang, M.; Xu, D. Robust Model Predictive Control for Greenhouse Temperature Based on Particle Swarm Optimization. Information Processing in Agriculture 2018, 5, 329–338, . [CrossRef]
95. Tawfeek, M.A.; Alanazi, S.; El-Aziz, A.A.A. Smart Greenhouse Based on ANN and IOT. Processes 2022, 10, 2402, . [CrossRef]
96. Jawad, H.M.; Jawad, A.M.; Nordin, R.; Gharghan, S.K.; Abdullah, N.F.; Ismail, M.; Abu-AlShaeer, M.J. Accurate Empirical Path-Loss Model Based on Particle Swarm Optimization for Wireless Sensor Networks in Smart Agriculture. IEEE Sens J 2020, 20, 552–561, . [CrossRef]
97. Mirjalili, S. Genetic Algorithm. Evolutionary Algorithms and Neural Networks. Studies in Computational Intelligence 2019, 780, . [CrossRef]
98. Lambora, A.; Gupta, K.; Chopra, K. Genetic Algorithm- A Literature Review. In Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon); IEEE, February 2019; pp. 380–384.
99. Maraveas, C.; Asteris, P.G.; Arvanitis, K.G.; Bartzanas, T.; Loukatos, D. Application of Bio and Nature-Inspired Algorithms in Agricultural Engineering. Archives of Computational Methods in Engineering 2023, 30, 1979–2012, . [CrossRef]
100. Liu, W. Smart Sensors, Sensing Mechanisms and Platforms of Sustainable Smart Agriculture Realized through the Big Data Analysis. Cluster Comput 2021, . [CrossRef]
101. Chen, Q.; Hu, X. Design of Intelligent Control System for Agricultural Greenhouses Based on Adaptive Improved Genetic Algorithm for Multi-Energy Supply System. Energy Reports 2022, 8, 12126–12138, . [CrossRef]
102. Yang, Y. Research and Implementation of Agricultural Water-Saving Irrigation Prediction Algorithm Based on GA-BP Neural Network. In Proceedings of the 2022 13th Asian Control Conference (ASCC); IEEE, May 4 2022; pp. 2454–2459.
103. Ullah, K.R.; Prodanovic, V.; Pignatta, G.; Deletic, A.; Santamouris, M. Technological Advancements towards the Net-Zero Energy Communities: A Review on 23 Case Studies around the Globe. Solar Energy 2021, 224, 1107–1126, . [CrossRef]
104. Bersani, C.; Ouammi, A.; Sacile, R.; Zero, E. Model Predictive Control of Smart Greenhouses as the Path towards Near Zero Energy Consumption. Energies (Basel) 2020, 13, 3647, . [CrossRef]
105. Gorjian, S.; Ebadi, H.; Najafi, G.; Singh Chandel, S.; Yildizhan, H. Recent Advances in Net-Zero Energy Greenhouses and Adapted Thermal Energy Storage Systems. Sustainable Energy Technologies and Assessments 2021, 43, 100940, . [CrossRef]
106. Ouammi, A. Model Predictive Control for Optimal Energy Management of Connected Cluster of Microgrids with Net Zero Energy Multi-Greenhouses. Energy 2021, 234, 121274, . [CrossRef]
107. Ravishankar, E.; Booth, R.E.; Saravitz, C.; Sederoff, H.; Ade, H.W.; O’Connor, B.T. Achieving Net Zero Energy Greenhouses by Integrating Semitransparent Organic Solar Cells. Joule 2020, 4, 490–506, . [CrossRef]
108. Mohsenipour, M.; Ebadollahi, M.; Rostamzadeh, H.; Amidpour, M. Design and Evaluation of a Solar-Based Trigeneration System for a Nearly Zero Energy Greenhouse in Arid Region. J Clean Prod 2020, 254, 119990, . [CrossRef]
109. Syed, A.M.; Hachem, C. Net-Zero Energy Design and Energy Sharing Potential of Retail - Greenhouse Complex. Journal of Building Engineering 2019, 24, 100736, . [CrossRef]
110. Jiang, W.; Jin, Y.; Liu, G.; Ju, Z.; Arıcı, M.; Li, D.; Guo, W. Net-Zero Energy Optimization of Solar Greenhouses in Severe Cold Climate Using Passive Insulation and Photovoltaic. J Clean Prod 2023, 402, 136770, . [CrossRef]
111. Engler, N.; Krarti, M. Optimal Designs for Net Zero Energy Controlled Environment Agriculture Facilities. Energy Build 2022, 272, 112364, . [CrossRef]
112. Boccalatte, A.; Fossa, M.; Sacile, R. Modeling, Design and Construction of a Zero-Energy PV Greenhouse for Applications in Mediterranean Climates. Thermal Science and Engineering Progress 2021, 25, 101046, . [CrossRef]
113. Ouammi, A.; Zejli, D. Centralized Controller for the Optimal Operation of a Cooperative Cluster of Connected Microgrids Powered Multi-Greenhouses. Sustainable Computing: Informatics and Systems 2022, 33, 100641, . [CrossRef]
114. Cafuta, D.; Dodig, I.; Cesar, I.; Kramberger, T. Developing a Modern Greenhouse Scientific Research Facility—A Case Study. Sensors 2021, 21, 2575, . [CrossRef]
115. Long, H.; Fu, X.; Kong, W.; Chen, H.; Zhou, Y.; Yang, F. Key Technologies and Applications of Rural Energy Internet in China. Information Processing in Agriculture 2022, . [CrossRef]
116. Ren, Z.; Dong, Y.; Lin, D.; Zhang, L.; Fan, Y.; Xia, X. Managing Energy-Water-Carbon-Food Nexus for Cleaner Agricultural Greenhouse Production: A Control System Approach. Science of The Total Environment 2022, 848, 157756, . [CrossRef]
117. Hassabou, A.M.; Khan, M.A. Towards Autonomous Solar Driven Agricultural Greenhouses in Qatar - Integration with Solar Cooling. In Proceedings of the 2019 7th International Renewable and Sustainable Energy Conference (IRSEC); IEEE, November 2019; pp. 1–8.