Evaluating Climate Uncertainty Effects on Optimized Cloud-Fog Configurations for Energy Management in Photovoltaic Buildings

Ahmed  Kareem Alzeyadi; Hasan Ziafat; Jafaar  Fahad A.Rida; Mahdi  Mosleh

Authors

Ahmed Kareem Alzeyadi Department of Computer Engineering, Isf.C., Islamic Azad University, Isfahan, Iran Author https://orcid.org/0000-0002-6354-254X
Hasan Ziafat Department of Computer Engineering, Kas.C., Islamic Azad University, Kashan, Iran Corresponding author https://orcid.org/0000-0001-6078-8088
Jafaar Fahad A.Rida Department of Communication Engineering, College of Engineering, University of Sumer, Dhiqar, Iraq Author https://orcid.org/0009-0007-7442-0314
Mahdi Mosleh Department of Computer Engineering, Isf.C., Islamic Azad University, Isfahan, Iran Author https://orcid.org/0000-0003-0419-1142

Keywords:

Cloud-fog architecture; Deep reinforcement learning (DDPG); Building energy management; PV uncertainty; Thermal comfort optimization; Edge computing; Microgrid resilience

Abstract

This paper presents a novel cloud-fog computing framework for real-time energy management in building-integrated photovoltaic (PV) systems, addressing the critical challenges of operational uncertainty arising from dust-induced soiling and unpredictable cloud transients. The proposed architecture employs a Deep Deterministic Policy Gradient (DDPG) reinforcement learning agent operating within a hierarchical edge-cloud infrastructure that strategically distributes computational intelligence to balance latency constraints and processing demands. The framework integrates an adaptive thermal comfort model and a Prediction Interval Coverage Probability (PICP)-based uncertainty quantifier, formulating the optimization problem as a Markov Decision Process to enable holistic scheduling decisions that jointly optimize economic costs, occupant well-being, and system reliability. A dual-track learning mechanism, incorporating both global replay buffers and localized episodic memory, ensures rapid edge-level responsiveness while maintaining globally optimal scheduling capabilities. Experimental validation under two challenging scenarios heavy dust aggregation and persistent cloudy weather demonstrates significant performance improvements over traditional non-adaptive architectures. The proposed system achieved transmission latency reductions exceeding 54% at the fog layer and 30% at the cloud layer, maintained stable processing times despite fluctuating irradiance conditions, and delivered substantial energy savings, including a 51.4% reduction in cloud-layer energy consumption under data-intensive dusty conditions. These results establish the proposed framework as a scalable, energy-conscious, and resilient solution for smart building energy management, with future extensions envisioned for multi-agent coordination across microgrid networks and enhanced data privacy through federated learning approaches.

References

[1] F. Minelli, D. D'Agostino, V. J. Reddy, and P. Michailidis, "Towards Resilient Cities: Robust Selection of Rooftop Renewable Energy Technologies in Mediterranean Multifamily Buildings," Energy Engineering: Journal of the Association of Energy Engineers, vol. 123, no. 6, 2026, doi: 10.32604/ee.2026.074048.

[2] P. Adigun, D. Koji, A. T. Ogunrinde, X. Xue, and P. Ebiendele, "Extreme Weather and Cascading Photovoltaic Power Vulnerabilities under Climate Change," Sustainable Energy Technologies and Assessments, vol. 85, p. 104776, 2026, doi: 10.1016/j.seta.2025.104776.

[3] H. A. Kazem, S. Al-Bahri, S. Al-Badi, H. Al-Mahkladi, and A. H. Al-Waeli, "Dust Effect on the Performance of Photovoltaic," Advanced Materials Research, vol. 875, pp. 1908-1911, 2014, doi: 10.4028/www.scientific.net/AMR.875-877.1908.

[4] T. Khatib, H. Kazem, K. Sopian, F. Buttinger, W. Elmenreich, and A. S. Albusaidi, "Effect of Dust Deposition on the Performance of Multi-Crystalline Photovoltaic Modules Based on Experimental Measurements," International Journal of Renewable Energy Research, vol. 3, no. 4, pp. 850-853, 2013.

[5] M. Mani and R. Pillai, "Impact of Dust on Solar Photovoltaic (PV) Performance: Research Status, Challenges and Recommendations," Renewable and Sustainable Energy Reviews, vol. 14, no. 9, pp. 3124-3131, 2010, doi: 10.1016/j.rser.2010.07.065.

[6] A. Bonkaney, S. Madougou, and R. Adamou, "Impacts of Cloud Cover and Dust on the Performance of Photovoltaic Module in Niamey," Journal of Renewable Energy, vol. 2017, no. 1, p. 9107502, 2017, doi: 10.1155/2017/9107502.

[7] F. H. Merie and O. K. Ahmed, "Experimental Assessment of the Performance of the PV/Solar Chimney under the Cloudy Weather," Results in Engineering, vol. 23, p. 102605, 2024, doi: 10.1016/j.rineng.2024.102605.

[8] K. Yin, F. Yao, N. Luo, M. Gao, X. Lu, and B. Yi, "Substantial Reduction of Solar Photovoltaic Potential in China by an Extreme Dust Event," Communications Earth & Environment, vol. 7, no. 1, p. 44, 2026, doi: 10.1038/s43247-025-03123-1.

[9] X. Hu and C. Gong, "A High Voltage Gain DC-DC Converter Integrating Coupled-Inductor and Diode-Capacitor Techniques," IEEE Transactions on Power Electronics, vol. 29, no. 2, pp. 789-800, 2013, doi: 10.1109/TPEL.2013.2257870.

[10] M. A. Barrios, V. Cárdenas, J. M. Sandoval, J. M. Guerrero, and J. C. Vasquez, "A Cascaded DC-AC-AC Grid-Tied Converter for PV Plants with AC-Link," Electronics, vol. 10, no. 4, p. 409, 2021, doi: 10.3390/electronics10040409.

[11] F. Moulay, A. Habbati, and A. Lousdad, "The Design and Simulation of a Photovoltaic System Connected to the Grid Using a Boost Converter," Journal Européen des Systèmes Automatisés, vol. 55, no. 3, p. 367, 2022, doi: 10.18280/jesa.550309.

[12] M. A. B. Siddique, D. Zhao, A. U. Rehman, K. Ouahada, and H. Hamam, "An Adapted Model Predictive Control MPPT for Validation of Optimum GMPP Tracking under Partial Shading Conditions," Scientific Reports, vol. 14, no. 1, p. 9462, 2024, doi: 10.1038/s41598-024-59304-z.

[13] M. N. I. Jamaludin, M. F. N. Tajuddin, T. Younis, S. B. Thanikanti, and M. Khishe, "Hybrid Salp Swarm Maximum Power Point Tracking Algorithm for Photovoltaic Systems in Highly Fluctuating Environmental Conditions," Scientific Reports, vol. 15, no. 1, p. 650, 2025, doi: 10.1038/s41598-024-84333-z.

[14] M. Eskandari, A. Rajabi, A. V. Savkin, M. H. Moradi, and Z. Y. Dong, "Battery Energy Storage Systems (BESSs) and the Economy-Dynamics of Microgrids: Review, Analysis, and Classification for Standardization of BESSs Applications," Journal of Energy Storage, vol. 55, p. 105627, 2022, doi: 10.1016/j.est.2022.105627.

[15] W. Hu, P. Wang, and H. B. Gooi, "Toward Optimal Energy Management of Microgrids via Robust Two-Stage Optimization," IEEE Transactions on Smart Grid, vol. 9, no. 2, pp. 1161-1174, 2016, doi: 10.1109/TSG.2016.2580575.

[16] Y. Ji, J. Wang, J. Xu, X. Fang, and H. Zhang, "Real-Time Energy Management of a Microgrid Using Deep Reinforcement Learning," Energies, vol. 12, no. 12, p. 2291, 2019, doi: 10.3390/en12122291.

[17] J. Schmidhuber, "Deep Learning in Neural Networks: An Overview," Neural Networks, vol. 61, pp. 85-117, 2015, doi: 10.1016/j.neunet.2014.09.003.

[18] L. P. Dinesh, N. Al Khafaf, and B. McGrath, "A Short Term Multistep Forecasting Model for Photovoltaic Generation Using Deep Learning Model," Sustainable Operations and Computers, vol. 6, pp. 34-46, 2025, doi: 10.1016/j.susoc.2024.11.003.

[19] R. L. Winkler, "A Decision-Theoretic Approach to Interval Estimation," Journal of the American Statistical Association, vol. 67, no. 337, pp. 187-191, 1972, doi: 10.1080/01621459.1972.10481224.

[20] W. Amnuaypongsa, W. Wangdee, and J. Songsiri, "Neural Network-Based Prediction Interval Estimation with Large Width Penalization for Renewable Energy Forecasting and System Applications," Energy Conversion and Management: X, vol. 27, p. 101119, 2025, doi: 10.1016/j.ecmx.2025.101119.

[21] V. R. S. Mahala, A. K. Yadav, D. Saxena, and R. Kumar, "Bi-Level Optimization Framework for Networked Microgrids With Forecasting and Uncertainty Analysis in an Edge-Fog-Cloud Architecture," IEEE Transactions on Industry Applications, 2026, doi: 10.1109/TIA.2026.3675195.

[22] A. Saoud and A. Recioui, "Hybrid Algorithm for Cloud-Fog System Based Load Balancing in Smart Grids," Bulletin of Electrical Engineering and Informatics, vol. 11, no. 1, pp. 477-487, 2022, doi: 10.11591/eei.v11i1.3450.

[23] D. Yu, Z. Ma, and R. Wang, "Efficient Smart Grid Load Balancing via Fog and Cloud Computing," Mathematical Problems in Engineering, vol. 2022, no. 1, p. 3151249, 2022, doi: 10.1155/2022/3151249.

[24] A. Hemmati and A. M. Rahmani, "ClusFC-IoT: A Clustering-Based Approach for Data Reduction in Fog-Cloud-Enabled IoT," Concurrency and Computation: Practice and Experience, vol. 36, no. 27, p. e8284, 2024, doi: 10.1002/cpe.8284.

[25] P. Periasamy et al., "ERAM-EE: Efficient Resource Allocation and Management Strategies with Energy Efficiency under Fog-Internet of Things Environments," Connection Science, vol. 36, no. 1, p. 2350755, 2024, doi: 10.1080/09540091.2024.2350755.

[26] R. Krishnan and S. Durairaj, "Reliability and Performance of Resource Efficiency in Dynamic Optimization Scheduling Using Multi-Agent Microservice Cloud-Fog on IoT Applications," Computing, vol. 106, no. 12, pp. 3837-3878, 2024, doi: 10.1007/s00607-024-01301-1.

[27] A. Khan, F. Ullah, D. Shah, M. H. Khan, S. Ali, and M. Tahir, "EcoTaskSched: A Hybrid Machine Learning Approach for Energy-Efficient Task Scheduling in IoT-Based Fog-Cloud Environments," Scientific Reports, vol. 15, no. 1, p. 12296, 2025, doi: 10.1038/s41598-025-96974-9.

[28] A. A. Mohamed et al., "Energy Aware Task Scheduling of IoT Application Using a Hybrid Metaheuristic Algorithm in Cloud Computing," Computers, Materials & Continua, vol. 86, no. 3, 2026.

[29] A. Zia et al., "Multi-Objective Enhanced Cheetah Optimizer for Joint Optimization of Computation Offloading and Task Scheduling in Fog Computing," Computers, Materials & Continua, vol. 86, no. 3, 2026.

[30] O. Laayati, H. El Hadraoui, A. El Maghraoui, N. Guennouni, M. Mekhfioui, and A. Chebak, "Metaheuristic-Optimized Forecasting in a Smart Edge-Fog-Cloud Energy Management Framework: An Industrial Mining Case Study," Results in Engineering, p. 107303, 2025, doi: 10.1016/j.rineng.2025.107303.

[31] M. Rashad, M. S. Abdellatif, and A. H. Rabie, "An Improved Human Evolutionary Optimization Algorithm for Maximizing Green Hydrogen Generation in Intelligent Energy Management System (IEMS)," Results in Engineering, vol. 27, p. 105998, 2025, doi: 10.1016/j.rineng.2025.105998.

[32] M. Mansouri, M. Eskandari, Y. Asadi, and A. Savkin, "A Cloud-Fog Computing Framework for Real-Time Energy Management in Multi-Microgrid System Utilizing Deep Reinforcement Learning," Journal of Energy Storage, vol. 97, p. 112912, 2024, doi: 10.1016/j.est.2024.112912.

[33] X. Liu et al., "Multi-Agent Primal Dual DDPG Based Reactive Power Optimization of Active Distribution Networks via Graph Reinforcement Learning," IEEE Internet of Things Journal, 2025, doi: 10.1109/JIOT.2025.3575445.

[34] C. Guo, X. Wang, Y. Zheng, and F. Zhang, "Real-Time Optimal Energy Management of Microgrid with Uncertainties Based on Deep Reinforcement Learning," Energy, vol. 238, p. 121873, 2022, doi: 10.1016/j.energy.2021.121873.

[35] C. Buratti, P. Ricciardi, and M. Vergoni, "HVAC Systems Testing and Check: A Simplified Model to Predict Thermal Comfort Conditions in Moderate Environments," Applied Energy, vol. 104, pp. 117-127, 2013, doi: 10.1016/j.apenergy.2012.11.015.

[36] T. Ahmed, P. Kumar, and L. Mottet, "Natural Ventilation in Warm Climates: The Challenges of Thermal Comfort, Heatwave Resilience and Indoor Air Quality," Renewable and Sustainable Energy Reviews, vol. 138, p. 110669, 2021, doi: 10.1016/j.rser.2020.110669.

[37] R. Yao, B. Li, and J. Liu, "A Theoretical Adaptive Model of Thermal Comfort-Adaptive Predicted Mean Vote (aPMV)," Building and Environment, vol. 44, no. 10, pp. 2089-2096, 2009, doi: 10.1016/j.buildenv.2009.02.014.

[38] C. Chellaswamy, R. Ganesh Babu, and A. Vanathi, "A Framework for Building Energy Management System with Residence Mounted Photovoltaic," Building Simulation, vol. 14, no. 4, pp. 1031-1046, 2021, doi: 10.1007/s12273-020-0735-x.

[39] F. Al-Quayed, "AI-Powered Anomaly Detection and Cybersecurity in Healthcare IoT with Fog-Edge," Computer Modeling in Engineering & Sciences (CMES), vol. 146, no. 1, p. 1, 2026, doi: 10.32604/cmes.2025.074799.

[40] R. Bhallamudi, S. Kumarasamy, and C. Sundarabalan, "Effect of Dust and Shadow on Performance of Solar Photovoltaic Modules: Experimental Analysis," Energy Engineering: Journal of the Association of Energy Engineers, vol. 118, no. 6, p. 1827, 2021, doi: 10.32604/EE.2021.016798.