Real-Time Efficient Short-Term Peak Load and Day-Ahead Electricity Load Forecasting System Using Machine Learning Approach
Keywords:
Short-Term Peak Load, Real-Time System, Zero-Mean Normalization, Principal Component Analysis Network, Electricity Load Forecasting System, Sampling and Self Attention, Improved Moth Flame OptimizationAbstract
Short-term load forecasting is crucial for efficiently managing electricity usage, spanning from weekly down to sub-hourly intervals. This practice not only saves resources but also ensures customer needs are met promptly. Day-ahead peak demand forecasting plays a vital role in load management, aiding in power system planning and operation. Yet, due to its complex non-linear nature, accurately predicting peak loads presents significant challenges. Therefore, this research proposed a hybrid predictive deep learning with an optimization algorithm to forecast precise electricity for 30-minute intervals. First, the maximum and minimum ranges of various parameters are determined by looking at historical data. The real-time datasets from January 1 to December 31st 2021 were used to derive hourly real-time system demand load data. The original dataset undergoes preprocessing to reconstruct its electrical characteristics. Zero-mean normalization is applied to both load and temperature data to standardize them. In intricate electric load systems, redundant information can hinder accurate pattern extraction for load forecasting. Principal Component Analysis Network (PCANet) identifies relevant features while eliminating redundancy. A DeepWalk Gated Recurrent Unit Model (DWGRU) framework is then constructed to capture temporal dependencies from historical sequences, integrating spatial, temporal, and semantic features for load forecasting. These extracted features are dynamically combined using an attention mechanism. Subsequently, a Hybrid Sampling and Self Attention with Deep Neural Network (HSSA-DNN) is employed to forecast 30-minute peak loads efficiently, utilizing Improved Moth Flame Optimization (IMFO). The proposed methodology is implemented using Matlab Simulink software. Forecasting accuracy is assessed using statistical error metrics such as Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) to identify optimal models. Experimental results showcase the superior accuracy of the proposed approach, evidenced by precise direction, equality, stability, correlation, comprehensive accuracy, and statistical performance analysis. Comparisons with existing methods reveal a reduction in Mean Absolute Scaled Error of up to 0.2088. Achieving a high day-ahead net load forecasting accuracy of 99.15% underscores the effectiveness of load forecasting. This highlights the critical role of input data structure and quality in further enhancing forecasting accuracy and reliability.
Downloads
References
Huang, N., Wang, S., Wang, R., Cai, G., Liu, Y., and Dai, Q., “Gated spatial-temporal graph neural network based short-term load forecasting for wide-area multiple buses”. International Journal of Electrical Power & Energy Systems, 145, pp.108651, (2023). https://doi.org/10.1016/j.ijepes.2022.108651
Yang, Y., Wang, Z., Zhao, S., and Wu, J., “An integrated federated learning algorithm for short-term load forecasting”. Electric Power Systems Research, 214, pp.108830, (2023). https://doi.org/10.1016/j.epsr.2022.108830
Hua, H., Liu, M., Li, Y., Deng, S., and Wang, Q., “An ensemble framework for short-term load forecasting based on parallel CNN and GRU with improved ResNet”. Electric Power Systems Research, 216, pp.109057, (2023). https://doi.org/10.1016/j.epsr.2022.109057
Zhang, T., Zhang, X., Chau, T.K., Chow, Y., Fernando, T., and Iu, H.H.C., “Highly accurate peak and valley prediction short-term net load forecasting approach based on decomposition for power systems with high PV penetration”. Applied Energy, 333, pp.120641, (2023). https://doi.org/10.1016/j.apenergy.2023.120641
Sekhar, C., and Dahiya, R., “Robust framework based on hybrid deep learning approach for short-term load forecasting of building electricity demand”. Energy, pp.126660, (2023). https://doi.org/10.1016/j.energy.2023.126660
Ribeiro, M.H.D.M., da Silva, R.G., Ribeiro, G.T., Mariani, V.C. and dos Santos Coelho, L., “Cooperative ensemble learning model improves electric short-term load forecasting”. Chaos, Solitons & Fractals, 166, pp.112982, (2023). https://doi.org/10.1016/j.chaos.2022.112982
Ran, P., Dong, K., Liu, X., and Wang, J., “Short-term load forecasting based on ceemdan and transformer”. Electric Power Systems Research, 214, pp.108885, (2023). https://doi.org/10.1016/j.epsr.2022.108885
Li, S., Kong, X., Yue, L., Liu, C., Khan, M.A., Yang, Z., and Zhang, H., “Short-term electrical load forecasting using hybrid model of manta ray foraging optimization and support vector regression”. Journal of Cleaner Production, pp.135856, (2023). https://doi.org/10.1016/j.jclepro.2023.135856
Shahare, K., Mitra, A., Naware, D., Keshri, R., and Suryawanshi, H.M., “Performance analysis and comparison of various techniques for short-term load forecasting”. Energy Reports, 9, pp.799-808, (2023). https://doi.org/10.1016/j.egyr.2022.11.086
Srivastava, A.K., Pandey, A.S., Houran, M.A., Kumar, V., Kumar, D., Tripathi, S.M., Gangatharan, S. and Elavarasan, R.M., “A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection”. Energies, 16(2), pp.867, (2023). https://doi.org/10.3390/en16020867
Heidarpanah, M., Hooshyaripor, F., and Fazeli, M., “Daily electricity price forecasting using artificial intelligence models in the Iranian electricity market”. Energy, 263, pp.126011, (2023). https://doi.org/10.1016/j.energy.2022.126011
Zambrano-Asanza, S., Morales, R.E., Montalvan, J.A., and Franco, J.F., “Integrating artificial neural networks and cellular automata model for spatial-temporal load forecasting”. International Journal of Electrical Power & Energy Systems, 148, pp.108906, (2023). https://doi.org/10.1016/j.ijepes.2022.108906
Panagiotou, D.K., and Dounis, A.I., “Comparison of Hospital Building’s Energy Consumption Prediction Using Artificial Neural Networks, ANFIS, and LSTM Network”. Energies, 15(17), pp.6453, (2022). https://doi.org/10.3390/en15176453
Hu, Y., Li, J., Hong, M., Ren, J., and Man, Y., “Industrial artificial intelligence-based energy management system: Integrated framework for electricity load forecasting and fault prediction”. Energy, 244, pp.123195, (2022). https://doi.org/10.1016/j.energy.2022.123195
Rao, S.N.V.B., Yellapragada, V.P.K., Padma, K., Pradeep, D.J., Reddy, C.P., Amir, M., and Refaat, S.S., “Day-ahead load demand forecasting in urban community cluster microgrids using machine learning methods”. Energies, 15(17), pp.6124, (2022). https://doi.org/10.3390/en15176124
Bashir, T., Haoyong, C., Tahir, M.F., and Liqiang, Z., “Short-term electricity load forecasting using a hybrid prophet-LSTM model optimized by BPNN”. Energy Reports, 8, pp.1678-1686, (2022). https://doi.org/10.1016/j.egyr.2021.12.067
Tang, X., Chen, H., Xiang, W., Yang, J., and Zou, M., “Short-term load forecasting using channel and temporal attention based temporal convolutional network”. Electric Power Systems Research, 205, pp.107761, (2022). https://doi.org/10.1016/j.epsr.2021.107761
Liu, R., Chen, T., Sun, G., Muyeen, S.M., Lin, S., and Mi, Y., “Short-term probabilistic building load forecasting based on feature-integrated artificial intelligent approach”. Electric Power Systems Research, 206, pp.107802, (2022). https://doi.org/10.1016/j.epsr.2022.107802
Ghenai, C., Al-Mufti, O.A.A., Al-Isawi, O.A.M., Amirah, L.H.L., and Merabet, A., “Short-term building electrical load forecasting using adaptive neuro-fuzzy inference system (ANFIS)”. Journal of Building Engineering, 52, pp.104323, (2022). https://doi.org/10.1016/j.jobe.2022.104323
Meng, Z., Xie, Y., and Sun, J., “Short-term load forecasting using neural attention model based on EMD”. Electrical Engineering, pp.1-10, (2022). https://doi.org/10.1007/s00202-021-01420-4
Matrenin, P., Safaraliev, M., Dmitriev, S., Kokin, S., Ghulomzoda, A., and Mitrofanov, S., “Medium-term load forecasting in isolated power systems based on ensemble machine learning models”. Energy Reports, 8, pp.612-618, (2022). https://doi.org/10.1016/j.egyr.2021.11.175
Alrasheedi, A., and Almalaq, A., “Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting”. Mathematics, 10(15), pp.2666, (2022). https://doi.org/10.3390/math10152666
Sayed, H.A., William, A., and Said, A.M., “Smart Electricity Meter Load Prediction in Dubai Using MLR, ANN, RF, and ARIMA”. Electronics, 12(2), pp.389, (2023). https://doi.org/10.3390/electronics12020389
ZulfiqAr, M., Kamran, M., Rasheed, M.B., Alquthami, T., and Milyani, A.H., “A Short-Term Load Forecasting Model Based on Self-Adaptive Momentum Factor and Wavelet Neural Network in Smart Grid”. IEEE Access, 10, pp.77587-77602, (2022). DOI: 10.1109/ACCESS.2022.3192433
Bacanin, N., Stoean, C., Zivkovic, M., Rakic, M., Strulak-Wójcikiewicz, R., and Stoean, R., “On the benefits of using metaheuristics in the hyperparameter tuning of deep learning models for energy load forecasting”. Energies, 16(3), pp.1434, (2023). https://doi.org/10.3390/en16031434
Li, L., Guo, L., Wang, J., and Peng, H., “Short-Term Load Forecasting Based on Spiking Neural P Systems”. Applied Sciences, 13(2), pp.792. (2023). https://doi.org/10.3390/app13020792
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
