Smart City Gnosys
Smart city article details
| Title | Xai-Based Photovoltaic Energy Management Framework For Smart Cities |
|---|---|
| ID_Doc | 62095 |
| Authors | Alagarsamy M.; Rajasekaran U.; Ganesan S.; Palanivel R. |
| Year | 2025 |
| Published | IEEE Access, 13 |
| DOI | http://dx.doi.org/10.1109/ACCESS.2025.3572492 |
| Abstract | The demand for explainable energy forecasting models has been emphasized in recent studies to enhance decision-making transparency. The efficient conversion of solar energy is stochastic and depends on environmental conditions. To address this, we propose a model-chain framework named XPEMM (XAI-based Photovoltaic Energy Management Model chain) for Solar Energy Production and Management in Smart Cities, ensuring explainability using LIME. Our model chain consists of three stages: Long-term forecasting of Global Horizontal Irradiance (GHI) as the first stage, Regression Modeling of GHI with power as the second stage, and Model-Agnostic explanation generation as the third stage. A recursive forecasting strategy was employed, leveraging Recurrent Neural Networks (RNN) to reduce error accumulation over a 5-year forecast horizon. The output of the proposed model chain assists grid cell operators in real-time monitoring, resulting in optimized performance by predicting the causes of high and low performance in advance, allowing for necessary adjustments. It also aids in site selection for high-budget PV-plant installations. We used two different datasets for training and benchmarking the Recursive Multistep GHI Forecasting Model (RMGFM). The proposed recursive forecasting strategy has been evaluated using RMSE and MAE error metrics which are 91.40 and 47.32 respectively, which are 2.9% 29.39%, and 7.9% less than the previously established approach using LSTM, PCR, and SVR based on RMSE measure and 15.9%, 49.9%, 34.8% less based on MAE metric. This study concludes that a recursive approach is best for long-term forecasting of GHI in regions with cyclic climatic patterns based on RMSE and MAE values. The interpretation of the LIME output establishes the fitness of model agnosticity in the Photovoltaic model chain. © 2013 IEEE. |
| Author Keywords | LIME; photovoltaics; recurrent neural network; time series forecasting; XAI |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
52236  | 0.902 | Petrosian O.; Zhang Y. | Solar Power Generation Forecasting In Smart Cities And Explanation Based On Explainable Ai | Smart Cities, 7, 6 (2024) |
| 36015 | 0.892 | Suanpang P.; Jamjuntr P. | Machine Learning Models For Solar Power Generation Forecasting In Microgrid Application Implications For Smart Cities | Sustainability (Switzerland), 16, 14 (2024) |
| 36023 | 0.89 | Kumari P.; Toshniwal D. | Machine Learning Techniques For Hourly Global Horizontal Irradiance Prediction: A Case Study For Smart Cities Of India | Energy Proceedings, 18 (2021) |
| 32373 | 0.884 | Mithul Raaj A.T.; Balaji B.; R R S.A.P.; Naidu R.C.; Rajesh Kumar M.; Ramachandran P.; Rajkumar S.; Kumar V.N.; Aggarwal G.; Siddiqui A.M. | Intelligent Energy Management Across Smart Grids Deploying 6G Iot, Ai, And Blockchain In Sustainable Smart Cities | IoT, 5, 3 (2024) |
| 52237 | 0.884 | Almadhor A.; Mallikarjuna K.; Rahul R.; Chandra Shekara G.; Bhatia R.; Shishah W.; Mohanavel V.; Suresh Kumar S.; Thimothy S.P. | Solar Power Generation In Smart Cities Using An Integrated Machine Learning And Statistical Analysis Methods | International Journal of Photoenergy, 2022 (2022) |
| 11704 | 0.876 | Madhiarasan M. | Bayesian Optimisation Algorithm Based Optimised Deep Bidirectional Long Short Term Memory For Global Horizontal Irradiance Prediction In Long-Term Horizon | Frontiers in Energy Research, 13 (2025) |
| 6687 | 0.875 | Rao B.S.; Aparna M.; Raju M.S.N. | Advancing Smart City Energy Management: Very Short-Term Photovoltaic Power Generation Forecasting Using Multi-Scale Long Short-Term Memory Deep Learning | Biomass and Solar-Powered Sustainable Digital Cities (2024) |
| 22945 | 0.874 | Dhanwanth B.; Dhanasakkaravarthi B.; Belshi J.V.G.; Mohanaprakash T.A.; Saranya S.; Naveen P. | Empowering Solar Energy With Advanced Iot-Based Forecasting: A Hybrid Deep Learning Model For Enhanced Efficiency With Big Data | International Conference on Sustainable Communication Networks and Application, ICSCNA 2023 - Proceedings (2023) |
| 17813 | 0.866 | Sharma P.K.; Kumar M.V.K.; Ahmad M.W.; Radhika M. | Deep Learning And Multi-Horizontal Solar Energy Forecasting Of Different Weather Conditions In Smart Cities | Sustainable Smart Homes and Buildings with Internet of Things (2024) |
| 52235 | 0.864 | Sankari S.S.; Kumar P.S. | Solar Power Forecasting In Smart Cities Using Deep Learning Approaches: A Review | International Research Journal of Multidisciplinary Technovation, 6, 6 (2024) |