A greenhouse (GH) system is a multi-input/multi-output (MIMO), dynamic, and energy-intensive environment that requires precise control for achieving optimal plant growing while minimizing energy consumption. Energy consumed by a GH system has indirect effects on the overall profitability. Determining optimal setpoints for a GH environment is challenging for traditional proportional–integral–derivative (PID) controllers, particularly for MIMO systems to reduce their energy consumption. A hybrid approach combining reinforcement learning (RL) with a radial basis function neural network (RBFNN), called neuro-tuner optimization (NTO), is proposed to control the GH climate and maximize energy efficiency. Herein, RL was developed using Q-learning, a popular algorithm, exhibiting high performance with a root mean square error of 0.013 in the testing phase and a correlation coefficient of 1. To validate and improve the effectiveness of the proposed NTO system, it was compared with another optimal control strategy. The proposed NTO system showed good results and enhanced energy efficiency by 19.7% (average), whereas the optimal control strategy improved energy efficiency by 3.6% (average). These results demonstrate the ability of the proposed NTO system to handle non-linear dynamic systems and enhance their overall performance. Thus, the proposed NTO system met the study objectives by improving the PID performance of a dynamic system while maximizing its energy efficiency.

1. [1] Food and Agriculture Organization of the United Nations (FAO), “Unlocking the potential of protected agriculture in the countries of Gulf Cooperation Council – Saving water and improving nutrition,” 2021. https://doi.org/10.4060/cb4070en
2. [2] N. Sabir and B. Singh, “Protected cultivation of vegetables in global arena: A review,” Indian J. Agric. Sci., Vol.83, No.2, pp. 123-135, 2013.
3. [3] “Good Agricultural Practices for greenhouse vegetable crops: Principles for Mediterranean climate areas,” FAO, 2013.
4. [4] M. Ghoulem, K. El Moueddeb, E. Nehdi, R. Boukhanouf, and J. K. Calautit, “Greenhouse design and cooling technologies for sustainable food cultivation in hot climates: Review of current practice and future status,” Biosyst. Eng., Vol.183, pp. 121-150, 2019. https://doi.org/10.1016/j.biosystemseng.2019.04.016
5. [5] M. Amani, S. Foroushani, M. Sultan, and M. Bahrami, “Comprehensive review on dehumidification strategies for agricultural greenhouse applications,” Appl. Therm. Eng., Vol.181, Article No.115979, 2020. https://doi.org/10.1016/j.applthermaleng.2020.115979
6. [6] B. A. Kimball, “Simulation of the energy balance of a greenhouse,” Agric. Meteorol., Vol.11, pp. 243-260, 1973. https://doi.org/10.1016/0002-1571(73)90067-8
7. [7] A.-M. N. Dimitropoulou, V. Z. Maroulis, and E. N. Giannini, “A simple and effective model for predicting the thermal energy requirements of greenhouses in Europe,” Energies, Vol.16, No.19, Article No.6788, 2023. https://doi.org/10.3390/en16196788
8. [8] J. J. Moghaddam, G. Zarei, D. Momeni, and H. Faridi, “Non-linear control model for use in greenhouse climate control systems,” Res. Agric. Eng., Vol.68, No.1, pp. 9-17, 2022. https://doi.org/10.17221/37/2021-RAE
9. [9] J. Li, Y. Dai, X. Su, and W. Wu, “Efficient dual-branch bottleneck networks of semantic segmentation based on CCD camera,” Remote Sens., Vol.14, No.16, Article No.3925, 2022. https://doi.org/10.3390/rs14163925
10. [10] N. T. Nguyen, “Lyapunov stability theory,” N. T. Nguyen, “Model-reference adaptive control: A primer,” pp. 47-81, Springer, 2018. https://doi.org/10.1007/978-3-319-56393-0_4
11. [11] F. Alyoussef and I. Kaya, “A review on nonlinear control approaches: Sliding mode control, back-stepping control and feedback linearization control,” Int. Eng. Nat. Sci. Conf. (IENSC 2019), pp. 608-619, 2019.
12. [12] I. S. Laktionov, O. V. Vovna, M. M. Kabanets, M. A. Derzhevetska, and A. A. Zori, “Mathematical model of measuring monitoring and temperature control of growing vegetables in greenhouses,” Int. J. Des. Nat. Ecodynamics, Vol.15, No.3, pp. 325-336, 2020. https://doi.org/10.18280/ijdne.150306
13. [13] S. B. Joseph, E. G. Dada, A. Abidemi, D. O. Oyewola, and B. M. Khammas, “Metaheuristic algorithms for PID controller parameters tuning: Review, approaches and open problems,” Heliyon, Vol.8, No.5, Article No.e09399, 2022. https://doi.org/10.1016/j.heliyon.2022.e09399
14. [14] E. Abbasi and N. Naghavi, “Offline auto-tuning of a PID controller using extended classifier system (XCS) algorithm,” J. Adv. Comput. Eng. Technol., Vol.3, No.1, pp. 41-44, 2017.
15. [15] N. M. Nouri, H. M. Abbood, M. Riahi, and S. H. Alagheband, “A review of technological developments in modern farming: Intelligent greenhouse systems,” AIP Conf. Proc., Vol.2631, No.1, Article No.030012, 2023. https://doi.org/10.1063/5.0142153
16. [16] Y. Jia, “Design of an intelligent greenhouse remote control system based on a fuzzy neural network,” Int. J. Automation Technol., Vol.15, No.2, pp. 243-248, 2021. https://doi.org/10.20965/IJAT.2021.P0243
17. [17] S. Zhong, Y. Huang, and L. Guo, “New tuning methods of both PID and ADRC for MIMO coupled nonlinear uncertain systems,” IFAC-PapersOnLine, Vol.53, No.2, pp. 1325-1330, 2020. https://doi.org/10.1016/j.ifacol.2020.12.1867
18. [18] J. G. Ziegler and N. B. Nichols, “Optimum settings for automatic controllers,” Trans. Am. Soc. Mech. Eng., Vol.64, No.8, pp. 759-765, 1942. https://doi.org/10.1115/1.4019264
19. [19] M. Korkmaz, Ö. Aydoğdu, and H. Doğan, “Design and performance comparison of variable parameter nonlinear PID controller and genetic algorithm based PID controller,” 2012 Int. Symp. Innov. Intell. Syst. Appl., 2012. https://doi.org/10.1109/INISTA.2012.6246935
20. [20] K. S. Chia, “Ziegler-Nichols based proportional-integral-derivative controller for a line tracking robot,” Indones. J. Electr. Eng. Comput. Sci., Vol.9, No.1, pp. 221-226, 2018. https://doi.org/10.11591/ijeecs.v9.i1.pp221-226
21. [21] F. Isdaryani, F. Feriyonika, and R. Ferdiansyah, “Comparison of Ziegler-Nichols and Cohen Coon tuning method for magnetic levitation control system,” J. Phys.: Conf. Ser., Vol.1450, Article No.012033, 2020. https://doi.org/10.1088/1742-6596/1450/1/012033
22. [22] W. K. Ho, C. C. Hang, and J. H. Zhou, “Performance and gain and phase margins of well-known PI timing formulas,” IEEE Trans. Control Syst. Technol., Vol.3, No.2, pp. 245-248, 1995. https://doi.org/10.1109/87.388135
23. [23] L. Wang and P. C. Young, “An improved structure for model predictive control using non-minimal state space realisation,” J. Process Control, Vol.16, No.4, pp. 355-371, 2006. https://doi.org/10.1016/j.jprocont.2005.06.016
24. [24] R. Zhang, A. Xue, R. Lu, P. Li, and F. Gao, “Real-time implementation of improved state-space MPC for air supply in a coke furnace,” IEEE Trans. Ind. Electron., Vol.61, No.7, pp. 3532-3539, 2014. https://doi.org/10.1109/TIE.2013.2284142
25. [25] L. Hewing, J. Kabzan, and M. N. Zeilinger, “Cautious model predictive control using Gaussian process regression,” IEEE Trans. Control Syst. Technol., Vol.28, No.6, pp. 2736-2743, 2020. https://doi.org/10.1109/TCST.2019.2949757
26. [26] X. Hu and L. Wang, “Improved robust constrained model predictive control design for industrial processes under partial actuator faults,” IEEE Access, Vol.7, pp. 34095-34103, 2019. https://doi.org/10.1109/ACCESS.2019.2893454
27. [27] J. Tao, Z. Yu, and Y. Zhu, “PFC based PID design using genetic algorithm for chamber pressure in a coke furnace,” Chemom. Intell. Lab. Syst., Vol.137, pp. 155-161, 2014. https://doi.org/10.1016/j.chemolab.2014.07.003
28. [28] N. Bigdeli, “The design of a non-minimal state space fractional-order predictive functional controller for fractional systems of arbitrary order,” J. Process Control, Vol.29, pp. 45-56, 2015. https://doi.org/10.1016/j.jprocont.2015.03.004
29. [29] Z. Guan and T. Yamamoto, “Design of a reinforcement learning PID controller,” IEEJ Trans. Electr. Electron. Eng., Vol.16, No.10, pp. 1354-1360, 2021. https://doi.org/10.1002/tee.23430
30. [30] Y. Yang, Y. Gao, J. Wu, Z. Ding, and S. Zhao, “Improving PID controller performance in nonlinear oscillatory automatic generation control systems using a multi-objective marine predator algorithm with enhanced diversity,” J. Bionic Eng., Vol.21, No.5, pp. 2497-2514, 2024. https://doi.org/10.1007/s42235-024-00548-w
31. [31] G. Ali, H. Aly, and T. Little, “Automatic generation control of a multi-area hybrid renewable energy system using a proposed Novel GA-fuzzy logic self-tuning PID controller,” Energies, Vol.17, No.9, Article No.2000, 2024. https://doi.org/10.3390/en17092000
32. [32] S. Huang, H. Xiang, C. Leng, T. Dai, and G. He, “Intelligent regulation of temperature and humidity in vegetable greenhouses based on single neuron PID algorithm,” Electronics, Vol.13, No.11, Article No.2083, 2024. https://doi.org/10.3390/electronics13112083
33. [33] H. Mo and G. Farid, “Nonlinear and adaptive intelligent control techniques for quadrotor UAV – A survey,” Asian J. Control, Vol.21, No.2, pp. 989-1008, 2019. https://doi.org/10.1002/asjc.1758
34. [34] L. B. Salah and F. Fourati, “A greenhouse modeling and control using deep neural networks,” Appl. Artif. Intell., Vol.35, No.15, pp. 1905-1929, 2021. https://doi.org/10.1080/08839514.2021.1995232
35. [35] A. Ajagekar and F. You, “Deep reinforcement learning based automatic control in semi-closed greenhouse systems,” IFAC-PapersOnLine, Vol.55, No.7, pp. 406-411, 2022. https://doi.org/10.1016/j.ifacol.2022.07.477
36. [36] A. Ajagekar, N. S. Mattson, and F. You, “Energy-efficient AI-based control of semi-closed greenhouses leveraging robust optimization in deep reinforcement learning,” Adv. Appl. Energy, Vol.9, Article No.100119, 2023. https://doi.org/10.1016/j.adapen.2022.100119
37. [37] L. Chen, L. Xu, and R. Wei, “Energy-saving control algorithm of Venlo greenhouse skylight and wet curtain fan based on reinforcement learning with soft action mask,” Agriculture, Vol.13, No.1, Article No.141, 2023. https://doi.org/10.3390/agriculture13010141
38. [38] D. D. Uyeh et al., “A reinforcement learning approach for optimal placement of sensors in protected cultivation systems,” IEEE Access, Vol.9, pp. 100781-100800, 2021. https://doi.org/10.1109/ACCESS.2021.3096828
39. [39] M. A. Adesanya et al., “Deep reinforcement learning for PID parameter tuning in greenhouse HVAC system energy Optimization: A TRNSYS-Python cosimulation approach,” Expert Syst. Appl., Vol.252, Part A, Article No.124126, 2024. https://doi.org/10.1016/j.eswa.2024.124126
40. [40] F. Rodríguez, M. Berenguel, J. L. Guzmán, and A. Ramírez-Arias, “Modeling and control of greenhouse crop growth,” Springer, 2015. https://doi.org/10.1007/978-3-319-11134-6
41. [41] S. Ding, W.-H. Chen, K. Mei, and D. J. Murray-Smith, “Disturbance observer design for nonlinear systems represented by input-output models,” IEEE Trans. Ind. Electron., Vol.67, No.2, pp. 1222-1232, 2020. https://doi.org/10.1109/TIE.2019.2898585
42. [42] J. B. Cunha, “Greenhouse climate models: An overview,” EFITA 2003 Conf., pp. 823-829, 2003. https://automatica.dei.unipd.it/old/public/Schenato/TESI/Tosin_2009/materiale/GREENHOUSE%20CLIMATE%20MODELS(stamp).pdf [Accessed November 2, 2025]
43. [43] F. Tap, “Economics-based optimal control of greenhouse tomato crop production,” Ph.D. thesis, Wageningen University, 2000.
44. [44] L. D. Albright, K. G. Arvanitis, and A. E. Drysdale, “Environmental control for plants on Earth and in space,” IEEE Control Syst. Mag., Vol.21, No.5, pp. 28-47, 2001. https://doi.org/10.1109/37.954518
45. [45] M. A. Koutb, N. M. El-Rabaie, H. A. Awad, and I. A. A. El-Hamid, “Environmental control for plants using intelligent control systems,” IFAC Proc. Vol., Vol.37, No.2, pp. 101-106, 2004. https://doi.org/10.1016/s1474-6670(17)38698-6
46. [46] A. Raczek and E. Wachowicz, “Heat and mass exchange model in the air inside a greenhouse,” Agric. Eng., Vol.1, No.149, pp. 185-195, 2014.
47. [47] M. Jomaa, M. Abbes, F. Tadeo, and A. Mami, “Greenhouse modeling, validation and climate control based on fuzzy logic,” Eng. Technol. Appl. Sci. Res., Vol.9, No.4, pp. 4405-4410, 2019. https://doi.org/10.48084/etasr.2871
48. [48] H.-G. Hu, L.-H. Xu, R.-H. Wei, and B.-K. Zhu, “RBF network based nonlinear model reference adaptive PD controller design for greenhouse climate,” Int. J. Adv. Comput. Technol., Vol.3, No.9, pp. 357-366, 2011. https://doi.org/10.4156/ijact.vol3.issue9.43
49. [49] G. D. Pasgianos, K. G. Arvanitis, P. Polycarpou, and N. Sigrimis, “A nonlinear feedback technique for greenhouse environmental control,” Comput. Electron. Agric., Vol.40, Nos.1-3, pp. 153-177, 2003. https://doi.org/10.1016/S0168-1699(03)00018-8
50. [50] M. Chalaris and A. Koufou, “Antoine equation coefficients for Novichok Agents (A230, A232, and A234) via molecular dynamics simulations,” Physchem, Vol.3, No.2, pp. 244-258, 2023. https://doi.org/10.3390/physchem3020017
51. [51] H. M. Abbood, N. M. Nouri, M. Riahi, and S. H. Alagheband, “An intelligent monitoring model for greenhouse microclimate based on RBF Neural Network for optimal setpoint detection,” J. Process Control, Vol.129, Article No.103037, 2023. https://doi.org/10.1016/j.jprocont.2023.103037
52. [52] M. C. Subin, A. Singh, V. Kalaichelvi, R. Karthikeyan, and C. Periasamy, “Design and robustness analysis of intelligent controllers for commercial greenhouse,” Mech. Sci., Vol.11, No.2, pp. 299-316, 2020. https://doi.org/10.5194/ms-11-299-2020
53. [53] M. Baltieri and C. L. Buckley, “PID control as a process of active inference with linear generative models,” Entropy, Vol.21, No.3, Article No.257, 2019. https://doi.org/10.3390/e21030257
54. [54] Z.-L. Gaing, “A particle swarm optimization approach for optimum design of PID controller in AVR system,” IEEE Trans. Energy Convers., Vol.19, No.2, pp. 384-391, 2004. https://doi.org/10.1109/TEC.2003.821821
55. [55] P. N. Paraskevopoulos, “Modern control engineering,” CRC Press, 2001.
56. [56] R. C. Dorf and R. H. Bishop, “Modern control systems,” 13th edition, Pearson Education Ltd., 2017.
57. [57] F. Bourdin et al., “Measurements of plastic localization by heaviside-digital image correlation,” Acta Mater., Vol.157, pp. 307-325, 2018. https://doi.org/10.1016/j.actamat.2018.07.013
58. [58] V. Valle, S. Hedan, P. Cosenza, A. L. Fauchille, and M. Berdjane, “Digital image correlation development for the study of materials including multiple crossing cracks,” Exp. Mech., Vol.55, No.2, pp. 379-391, 2015. https://doi.org/10.1007/s11340-014-9948-1
59. [59] D. Harel, H. Fadida, A. Slepoy, S. Gantz, and K. Shilo, “The effect of mean daily temperature and relative humidity on pollen, fruit set and yield of tomato grown in commercial protected cultivation,” Agronomy, Vol.4, No.1, pp. 167-177, 2014. https://doi.org/10.3390/agronomy4010167
60. [60] R. R. Shamshiri et al., “Review of optimum temperature, humidity, and vapour pressure deficit for microclimate evaluation and control in greenhouse cultivation of tomato: A review,” Int. Agrophys., Vol.32, No.2, pp. 287-302, 2018. https://doi.org/10.1515/intag-2017-0005