Analyzing the Impact of Environmental Factors on Solar Power Output Using Explainable Deep Learning Techniques

International Journal of Electronics and Communication Engineering

© 2024 by SSRG - IJECE Journal

Volume 11 Issue 10

Year of Publication : 2024

Authors : Diaa Salman, Yonis Khalif Elmi, Abdullahi Mohamed Isak, Abdulaziz Ahmed Siyad

10.14445/23488549/IJECE-V11I10P110

How to Cite?

Diaa Salman, Yonis Khalif Elmi, Abdullahi Mohamed Isak, Abdulaziz Ahmed Siyad, "Analyzing the Impact of Environmental Factors on Solar Power Output Using Explainable Deep Learning Techniques," SSRG International Journal of Electronics and Communication Engineering, vol. 11,  no. 10, pp. 119-134, 2024. Crossref, https://doi.org/10.14445/23488549/IJECE-V11I10P110

Abstract:

An advanced prediction of power generation is necessary for renewable systems to achieve optimal efficiency and output. This paper explores advanced deep learning models: Long Short-Term Memory (LSTM), 1D Convolutional Neural Network (1D-CNN), and a combined LSTM-1DCNN model to predict output solar power using historical time series climatic data. The feature consists of the main characteristics, namely temperature, air pressure, sun radiation, and humidity of the solar power. Several evaluation metrics were used to better assess each model's performance and the extent to which it has addressed research questions. The best model that showed high accuracy and good generalization of the output data was chosen as the LSTM-1DCNN hybrid model. Regarding the projections, each feature's contribution was evaluated using SHAP values with the "SHAP" package. The analysis carried out by the study revealed that models were influenced most by sun radiation. As the three models are analyzed, the call for multiple deep-learning techniques increases the forecast level. This paper focuses on the potential of using hybrid deep learning models to enhance the accuracy of the power output predictions while, by SHAP analysis, underlining the requirement for the model explainability. However, such work offers significant viewpoints and room for other developments that can use more prominent datasets and elaborate details. However, the results also highlight the areas to learn about the possibility of increasing the reliability and interpretability of the model's outcomes while underlining the necessity to apply advanced modelling approaches to optimize energy systems.

Keywords:

Deep learning, Explainability, Forecasting, Solar power, SHAP.

References:

[1] Javier López Gómez et al., “Photovoltaic Power Prediction Using Artificial Neural Networks and Numerical Weather Data,” Sustainability, vol. 12, no. 24, pp. 1-19, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ramadan J. Mustafa et al., “Environmental Impacts on the Performance of Solar Photovoltaic Systems,” Sustainability, vol. 12, no. 2, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Sheraz Aslam et al., “A Survey on Deep Learning Methods for Power Load and Renewable Energy Forecasting in Smart Microgrids,” Renewable and Sustainable Energy Reviews, vol. 144, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mouad Louhichi et al., “Shapley Values for Explaining the Black Box Nature of Machine Learning Model Clustering,” Procedia Computer Science, vol. 220, pp. 806-811, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Alejandro Barredo Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges Toward Responsible AI,” Information Fusion, vol. 58, pp. 82-115, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Vorhauer-Huget et al., “Computational Optimization of Porous Structures for Electrochemical Processes,” Processes, vol. 8, no. 10, pp. 1-21, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Mikhail K. Kaban et al., “Structure and Density of Sedimentary Basins in the Southern Part of the East-European Platform and Surrounding Area,” Applied Sciences, vol. 11, no. 2, pp. 1-16, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Carlos Toro et al., “Erratum: On the Detection of Spectral Emissions of Iron Oxides in Combustion Experiments of Pyrite Concentrates,” Sensors, vol. 20, no. 5, pp. 1-15, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Mohammad Abdul Baseer et al., “Electrical Power Generation Forecasting from Renewable Energy Systems Using Artificial Intelligence Techniques,” Energies, vol. 16, no. 18, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Natei Ermias Benti, Mesfin Diro Chaka, and Addisu Gezahegn Semie, “Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects,” Sustainablity, vol. 15, no. 9, pp. 1-33, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Francois Rozon, Craig McGregor, and Michael Owen, “Long-Term Forecasting Framework for Renewable Energy Technologies' Installed Capacity and Costs for 2050,” Energies, vol. 16, no. 19, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Georgios Tsoumanis et al., “Implementation of a Topology Independent MAC (TiMAC) Policy on a Low-Cost IoT System,” Future Internet, vol. 12, no. 5, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Xi Qin et al., “Exploring Driving Forces of Green Growth: Empirical Analysis on China's Iron and Steel Industry,” Sustainability, vol. 11, no. 4, pp. 1-11, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yaojian Xu et al., “A Complementary Fused Method using GRU and XGBoost Models for Long-Term Solar Energy Hourly Forecasting,” Expert Systems with Applications, vol. 254, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Jimin Kim et al., “Multi-Step Photovoltaic Power Forecasting using Transformer and Recurrent Neural Networks,” Renewable and Sustainable Energy Reviews, vol. 200, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mohamad Abou Houran et al., “COA-CNN-LSTM: Coati Optimization Algorithm-Based Hybrid Deep Learning Model for PV/Wind Power Forecasting in Smart Grid Applications,” Applied Energy, vol. 349, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Muhammad Muneeb Shaikh, Rizwan A. Butt, and Attaullah Khawaja, “Forecasting Total Electron Content (TEC) using CEEMDAN LSTM Model,” Advances in Space Research, vol. 71, no. 10, pp. 4361-4373, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Tingxin Wen et al., “Modeling and Forecasting CO2 Emissions in China and its Regions using a Novel ARIMA-LSTM Model,” Heliyon, vol. 9, no. 11, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Indrajeet Kumar, Bineet Kumar Tripathi, and Anugrah Singh, “Attention-based LSTM Network-Assisted Time Series Forecasting Models for Petroleum Production,” Engineering Applications of Artificial Intelligence, vol. 123, no. C, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Mustafa Wassef Hasan et al., “Building an IoT Temperature and Humidity Forecasting Model based on Long Short-Term Memory (LSTM) with Improved Whale Optimization Algorithm,” Memories - Materials, Devices, Circuits and Systems, vol. 6, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Behmard Sabzipour et al., “Comparing a Long Short-Term Memory (LSTM) Neural Network with a Physically-Based Hydrological Model for Streamflow Forecasting Over a Canadian Catchment,” Journal of Hydrology, vol. 627, no. A, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Huynh Duy Tran et al., “Forecasting Hourly PM2.5 Concentration with an Optimized LSTM Model,” Atmospheric Environment, vol. 315, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Tariq Limouni et al., “Accurate One Step and Multistep Forecasting of Very Short-Term PV Power using LSTM-TCN Model,” Renewable Energy, vol. 205, pp. 1010-1024, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Weifang Mao et al., “Forecasting and Trading Credit Default Swap Indices using a Deep Learning Model Integrating Merton and LSTMs,” Expert Systems with Applications, vol. 213, no. B, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Yisheng Cao et al., “Multi-Timescale Photovoltaic Power Forecasting using an Improved Stacking Ensemble Algorithm based LSTM-Informer Model,” Energy, vol. 283, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Sumriti Ranjan Patra, Hone-Jay Chu, and Tatas, “Regional Groundwater Sequential Forecasting using Global and Local LSTM Models,” Journal of Hydrology: Regional Studies, vol. 47, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Lang Zheng, Weisheng Lu, and Qianyun Zhou, “Weather Image-Based Short-Term Dense Wind Speed Forecast with a ConvLSTM-LSTM Deep Learning Model,” Building and Environment, vol. 239, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Mohammed Adel Djari, Lahouaria Benasla, and Walid Rahmouni, “Voltage Stability Assessment using the V-Q Sensitivity and Modal Analyses Methods,” 2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B), Boumerdes, Algeria, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Chao-Kai Wen, Wan-Ting Shih, and Shi Jin, “Deep Learning for Massive MIMO CSI Feedback,” IEEE Wireless Communications Letters, vol. 7, no. 5, pp. 748-751, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Ajay Shrestha, and Ausif Mahmood, “Review of Deep Learning Algorithms and Architectures,” IEEE Access, vol. 7, pp. 53040 53065, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Mahin Mohammadi et al., “Advanced Fusion of MTM-LSTM and MLP Models for Time Series Forecasting: An Application for Forecasting the Solar Radiation,” Measurement: Sensors, vol. 33, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Filipe D. Campo, Tiago C. Sousa, and Ramiro S. Barbosa, “Short-Term Forecast of Photovoltaic Solar Energy Production Using LSTM,” Energies, vol. 17, no. 11, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Pedro Lara-Benítez et al., “Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting,” Applied Sciences, vol. 10, no. 7, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Mansoor Khan et al., “Forecasting Renewable Energy for Environmental Resilience Through Computational Intelligence,” PLoS One, vol. 16, no. 8, pp. 1-28, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Tobias Clement et al., “Coping with Data Distribution Shifts: XAI-Based Adaptive Learning with SHAP Clustering for Energy Consumption Prediction,” AI 2023: Advances in Artificial Intelligence, Lecture Notes in Computer Science, pp. 147-159, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Md. Tanzib Hosain et al., “Explainable AI Approaches in Deep Learning: Advancements, Applications and Challenges,” Computers and Electrical Engineering, vol. 117, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Muhammad Naveed Akhter et al., “An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants,” Energies, vol. 15, no. 6, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Maria Konstantinou, Stefani Peratikou, and Alexandros G. Charalambides, “Solar Photovoltaic Forecasting of Power Output using LSTM Networks,” Atmosphere, vol. 12, no. 1, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Nur Liyana Mohd Jailani et al., “Investigating the Power of LSTM-Based Models in Solar Energy Forecasting,” Processes, vol. 11, no. 5, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[40] T. Sana Amreen, Radharani Panigrahi, N.R. Patne, “Solar Power Forecasting Using Hybrid Model,” 2023 5th International Conference on Energy, Power and Environment: Towards Flexible Green Energy Technologies (ICEPE), Shillong, India, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Wen-Chi Kuo et al., “Assessment of Different Deep Learning Methods of Power Generation Forecasting for Solar PV System,” Applied Sciences, vol. 12, no. 15, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Wei Li, Dataset, Figshare, 2018.
[CrossRef] [Publisher Link]