Enhanced Load Forecasting Using CNN-BiLSTM Models in University Buildings with Solar PV

International Journal of Electrical and Electronics Engineering

© 2024 by SSRG - IJEEE Journal

Volume 11 Issue 10

Year of Publication : 2024

Authors : Muhammad Zulhamizan Ahmad, Nofri Yenita Dahlan, Zuhaila Mat Yasin

10.14445/23488379/IJEEE-V11I10P107

How to Cite?

Muhammad Zulhamizan Ahmad, Nofri Yenita Dahlan, Zuhaila Mat Yasin, "Enhanced Load Forecasting Using CNN-BiLSTM Models in University Buildings with Solar PV," SSRG International Journal of Electrical and Electronics Engineering, vol. 11,  no. 10, pp. 61-70, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I10P107

Abstract:

Energy management is an imperative practice involving the detailed monitoring, regulation, and optimization of energy consumption within various domains aimed at conserving resources and controlling energy costs. The escalating demand for electricity and integrating renewable energy sources has brought forth an array of complexities that challenge energy management efforts. As a result, the need to enhance the precision of load forecasting has surged in importance, attracting significant attention from researchers and organizations alike. Traditional time series models have their own limitations. These models rely on the assumption of linear relationships and stationary time series data, thereby potentially falling short of capturing the intricate, non-linear variations often present in energy consumption patterns. This limitation necessitates the exploration of more advanced and adaptable forecasting techniques. Campus buildings present some challenges for load forecasting. These challenges arise from the dynamic and ever-changing load patterns within educational institutions, which can fluctuate significantly based on various factors such as lecture schedules, semester breaks, and special occasions. This study introduces an innovative hybrid model called CNN-BiLSTM, which integrates Convolutional Neural Networks (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) models to address the complexities of load patterns to produce accurate forecasts. The proposed model is thoroughly benchmarked against traditional Artificial Neural Networks (ANN) and BiLSTM models. Load data from the UiTM Permatang Pauh campus building, which encompasses 343 days of data collected at 30-minute intervals, a total of 16,464 data points for analysis. Leveraging this load data, comprehensive feature engineering was conducted, leading to the generation of categorical data such as hour, calendar attributes, and semester status. The CNN-BiLSTM model outperforms its counterparts, achieving a remarkable Mean Absolute Percentage Error (MAPE) of 6.9%. Therefore, as demonstrated through rigorous benchmarking, the model's superior performance highlights its potential significance for improving energy management in educational institutions and other domains with similar load complexity.

Keywords:

Load forecasting, Artificial Neural Network, Bidirectional, Long Short-Term Memory. Convolutional Neural Network, CNN-LSTM, Campus building.

References:

[1] Minan Tang et al., “Short-Term Load Forecasting of Electric Vehicle Charging Stations Accounting for Multifactor IDBO Hybrid Models,” Energies, vol. 17, no. 12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Zulfiqar Ahmad Khan et al., “Efficient Short-Term Electricity Load Forecasting for Effective Energy Management,” Sustainable Energy Technologies and Assessments, vol. 53, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Altaf Hussain et al., “A Hybrid Deep Learning-Based Network for Photovoltaic Power Forecasting,” Complexity, vol. 2022, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mosbah Aouad et al., “A CNN-Sequence-to-Sequence Network with Attention for Residential Short-Term Load Forecasting,” Electric Power Systems Research, vol. 211, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] J.S. Hassan et al., “Building Energy Consumption in Malaysia: An Overview,” Jurnal Teknologi (Sciences & Engineering), vol. 70, no. 7, pp. 33-38, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[6] K.P.M Kementerian Pelajaran Malaysia, Malaysia Educational Statistic 2020, 2020.
[7] Yisheng Cao et al., “PSO-Stacking Improved Ensemble Model for Campus Building Energy Consumption Forecasting Based on Priority Feature Selection,” Journal of Building Engineering, vol. 72, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Rijalul Fahmi Mustapa et al., “Non-Linear and Linear Baseline Energy Modelling Comparative Studies in Educational Buildings,” International Journal of Engineering & Technology, vol. 7, no. 4.22, pp. 61-66, 2018.
[Publisher Link]
[9] Neelam Mughees et al., “Deep Sequence to Sequence Bi-LSTM Neural Networks for Day-Ahead Peak Load Forecasting,” Expert Systems with Applications, vol. 175, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Gokcen Ozdemir et al., “The Role of eXplainable Artificial Intelligence (XAI) in Smart Grids,” Big Data Application in Power Systems, pp. 349-370, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Serge Guefano et al., “Forecast of Electricity Consumption in the Cameroonian Residential Sector by Grey and Vector Autoregressive Models,” Energy, vol. 214, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Bobo Wang et al., “Ss5:A Neural Network-Based Energy Consumption Prediction Model for Feature Selection and Paremeter Optimization of Winders,” 2020 IEEE International Conference on Networking, Sensing and Control (ICNSC), Nanjing, China, pp. 1-5, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Tahreem Anwar et al., “Introduction to Load Forecasting,” International Journal of Pure and Applied Mathematics, vol. 119, no. 15c, pp. 1527-1538, 2018.
[Google Scholar] [Publisher Link]
[14] Yousuf M.S. Khara, Asad Mahmood, and Kafait Ullah, “Load Forecasting of an Educational Institution Using Machine Learning: The Case of Nust, Islamabad,” Pakistan Journal of Science, vol. 71, no. 4, pp. 252-257, 2019.
[Google Scholar]
[15] Y. Wang, “Short-Term Power Load Forecasting Based on Machine Learning,” 2020.
[Google Scholar]
[16] Wang Hao, Hayinaer Tueraili, and Song Bin, “Refined Load Forecasting of Distribution Network Based on ARIMA Model with Multi-Factor Combination Analysis,” 2021 IEEE 4th International Electrical and Energy Conference (CIEEC), Wuhan, China, pp. 1-4, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] A.A. Komyakov, V.V. Erbes, and V.I. Ivanchenko, “Application of Artificial Neural Networks for Electric Load Forecasting on Railway Transport,” 2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), Rome, Italy, pp. 43-46, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Lingling Tang, Yulin Yi, and Yuexing Peng, “An Ensemble Deep Learning Model for Short-Term Load Forecasting Based on ARIMA and LSTM,” 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Beijing, China, pp. 1-6, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Innocent Mpawenimana et al., “A Comparative Study of LSTM and ARIMA for Energy Load Prediction with Enhanced Data Preprocessing,” 2020 IEEE Sensors Applications Symposium (SAS), Lumpur, Malaysia, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Chafak Tarmanini et al., “Short Term Load Forecasting Based on ARIMA and ANN Approaches,” Energy Reports, vol. 9, pp. 550-557, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jean Calvin Nsangou et al., “Explaining Household Electricity Consumption Using Quantile Regression, Decision Tree and Artificial Neural Network,” Energy, vol. 250, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Moon Keun Kim, Yang-Seon Kim, and Jelena Srebric, “Predictions of Electricity Consumption in a Campus Building Using Occupant Rates and Weather Elements with Sensitivity Analysis: Artificial Neural Network vs. Linear Regression,” Sustainable Cities and Society, vol. 62, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Jihoon Moon, Seungmin Rho, and Sung Wook Baik, “Toward Explainable Electrical Load Forecasting of Buildings: A Comparative Study of Tree-Based Ensemble Methods with Shapley Values,” Sustainable Energy Technologies and Assessments, vol. 54, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Lakhmi C. Jain, and Larry R. Medsker, Recurrent Neural Networks (Design and Applications), CRC Press, Inc., 1999.
[Google Scholar] [Publisher Link]
[25] Sepp Hochreiter, and Jürgen Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Ge Zhang, Xiaoqing Bai, and Yuxuan Wang, “Short-Time Multi-Energy Load Forecasting Method Based on CNN-Seq2Seq Model with Attention Mechanism,” Machine Learning with Applications, vol. 5, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[27] First Ali Agga et al., “Short-Term Load Forecasting Based on CNN and LSTM Deep Neural Networks,” IFAC-PapersOnLine, vol. 55, no. 12, pp. 777-781, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Liu Wenya, “Cooling, Heating and Electric Load Forecasting for Integrated Energy Systems Based on CNN-LSTM,” 2021 6th International Conference on Power and Renewable Energy (ICPRE), Shanghai, China, pp. 808-812, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Shafiul Hasan Rafi et al., “A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network,” IEEE Access, vol. 9, pp. 32436-32448, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Xifeng Guo et al., “A Short-Term Load Forecasting Model of Multi-Scale CNN-LSTM Hybrid Neural Network Considering the Real-Time Electricity Price,” Energy Reports, vol. 6, no. 9, pp. 1046-1053, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Phornnara Nop, and Zhijun Qin, “Transmission System Load Forecasting Using Neural Network Approach, Case Study: Electricité du Cambodge (EDC),” 2020 IEEE Student Conference on Electric Machines and Systems (SCEMS), Jinan, China, pp. 329-333, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Lemuel Clark P. Velasco, Karl Anthony S. Arnejo, and Justine Shane S. Macarat, “Performance Analysis of Artificial Neural Network Models for Hourahead Electric Load Forecasting,” Procedia Computer Science, vol. 197, pp. 16-24, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Tasarruf Bashir et al., “Short Term Electricity Load Forecasting Using Hybrid Prophet-LSTM Model Optimized by BPNN,” Energy Reports, vol. 8, pp. 1678-1686, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Nirmala C.R. et al., “Forecasting Price of the Crude Oil Using LSTM Based on RNN,” International Journal for Research in Applied Science & Engineering Technology, vol. 10, no. 7, pp. 196-206, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Maged Mamdouh, Mostafa Ezzat, and Hesham Hefny, “Improving Flight Delays Prediction by Developing Attention-Based Bidirectional LSTM Network,” Expert Systems with Applications, vol. 238, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Umar Javed et al., “A Novel Short Receptive Field Based Dilated Causal Convolutional Network Integrated with Bidirectional LSTM for Short-Term Load Forecasting,” Expert Systems with Applications, vol. 205, 2022.
[CrossRef] [Google Scholar] [Publisher Link]