The energy sector must achieve a delicate balance between energy supply and demand. Highly accurate energy consumption forecasts can help plant operators achieve this goal. In this study, various techniques from three artificial intelligence categories, namely convolutional neural networks (CNNs), machine learning (ML), and time-series deep learning (DL), were applied to predict short-term regional energy consumption from a power company. An image conversion process was proposed in which numerical matrices of input values created by the slidingwindow technique are encoded into two-dimensional grayscale images as input for CNN models. The proposed method outperformed conventional numerical input methods. The best ML and time-series DL models were combined into ensemble models with ImageNet-winning CNN architectures; the ensemble models had lower performance than did CNN alone. Moreover, various leading models performing single-step or multistep forecasting and models that use seasonal or annual data were constructed. The performance of all the constructed models was evaluated, and the most efficient models were determined as proposed models. Based on the analysis results, season-based EfficientNetV2B0 was the best model for hourahead forecast, while that for day-ahead forecast was year-based ResNet50V2. Finally, a nature-inspired optimization algorithm, namely jellyfish search (JS), was used to fine-tune the proposed models’ hyperparameters to minimize prediction error. Remarkable results after optimization were the improvement in accuracy and reduction in training time, indicating that JS is an amazing method to find out the optimal model hyperparameters. The proposed models can help utilities plan daily power allocation and match supply and demand to maintain a stable power system.

The energy sector must achieve a delicate balance between energy supply and demand. Highly accurate energy consumption forecasts can help plant operators achieve this goal. In this study, various techniques from three artificial intelligence categories, namely convolutional neural networks (CNNs), machine learning (ML), and time-series deep learning (DL), were applied to predict short-term regional energy consumption from a power company. An image conversion process was proposed in which numerical matrices of input values created by the slidingwindow technique are encoded into two-dimensional grayscale images as input for CNN models. The proposed method outperformed conventional numerical input methods. The best ML and time-series DL models were combined into ensemble models with ImageNet-winning CNN architectures; the ensemble models had lower performance than did CNN alone. Moreover, various leading models performing single-step or multistep forecasting and models that use seasonal or annual data were constructed. The performance of all the constructed models was evaluated, and the most efficient models were determined as proposed models. Based on the analysis results, season-based EfficientNetV2B0 was the best model for hourahead forecast, while that for day-ahead forecast was year-based ResNet50V2. Finally, a nature-inspired optimization algorithm, namely jellyfish search (JS), was used to fine-tune the proposed models’ hyperparameters to minimize prediction error. Remarkable results after optimization were the improvement in accuracy and reduction in training time, indicating that JS is an amazing method to find out the optimal model hyperparameters. The proposed models can help utilities plan daily power allocation and match supply and demand to maintain a stable power system.

[1] Chou JS, Truong NS. Cloud forecasting system for monitoring and alerting of energy use by home appliances. Appl Energ. 2019;249:166-77.
[2] Chou, Truong. Multistep energy consumption forecasting by metaheuristic optimization of time-series analysis and machine learning (vol 45, pg 4581, 2021). Int J Energ Res. 2022.
[3] Chou JS, Truong DN, Kuo CC. Imaging time-series with features to enable visual recognition of regional energy consumption by bio-inspired optimization of deep learning. Energy. 2021;224.
[4] Zhu JZ, Dong HJ, Zheng WY, Li SL, Huang YT, Xi L. Review and prospect of data-driven techniques for load forecasting in integrated energy systems. Appl Energ. 2022;321.
[5] Duan Y. A Novel Interval Energy-Forecasting Method for Sustainable Building Management Based on Deep Learning. Sustainability-Basel. 2022;14.
[6] Niu DX, Yu M, Sun LJ, Gao T, Wang KK. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism. Appl Energ. 2022;313.
[7] Pinheiro MG, Madeira SC, Francisco AP. Short-term electricity load forecasting—A systematic approach from system level to secondary substations. Appl Energ. 2023;332:120493.
[8] Lee YW, Gaik T, Yaan Yee C. Forecasting Electricity Consumption Using Time Series Model. International Journal of Engineering and Technology(UAE). 2018;7:218-23.
[9] Ma Z, Ye C, Ma W. Support vector regression for predicting building energy consumption in southern China. Energy Procedia. 2019;158:3433-8.
[10] Pham AD, Ngo NT, Truong TTH, Huynh NT, Truong NS. Predicting energy consumption in multiple buildings using machine learning for improving energy efficiency and sustainability. J Clean Prod. 2020;260.
[11] Barman M, Choudhury NBD, Sutradhar S. A regional hybrid GOA-SVM model based on similar day approach for short-term load forecasting in Assam, India. Energy. 2018;145:710-20.
[12] He Y, Wu PC, Li YF, Wang YL, Tao F, Wang Y. A generic energy prediction model of machine tools using deep learning algorithms. Appl Energ. 2020;275.
[13] Olu-Ajayi R, Alaka H, Sulaimon I, Sunmola F, Ajayi S. Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. Journal of Building Engineering. 2022;45:103406.
[14] Robinson C, Dilkina B, Hubbs J, Zhang WW, Guhathakurta S, Brown MA, et al. Machine learning approaches for estimating commercial building energy consumption. Appl Energ. 2017;208:889-904.
[15] Zheng SB, Zhong QW, Peng LL, Chai XD. A Simple Method of Residential Electricity Load Forecasting by Improved Bayesian Neural Networks. Math Probl Eng. 2018;2018.
[16] Lahouar A, Slama JH. Day-ahead load forecast using random forest and expert input selection. Energ Convers Manage. 2015;103:1040-51.
[17] Ngo NT, Truong TTH, Truong NS, Pham AD, Huynh NT, Pham TM, et al. Proposing a hybrid metaheuristic optimization algorithm and machine learning model for energy use forecast in non-residential buildings. Sci Rep-Uk. 2022;12.
[18] Baliyan A, Gaurav K, Mishra SK. A Review of Short Term Load Forecasting using Artificial Neural Network Models. Procedia Computer Science. 2015;48:121-5.
[19] Schaffer AL, Dobbins TA, Pearson SA. Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions. Bmc Med Res Methodol. 2021;21.
[20] Wang Z, Hong TZ, Piette MA. Building thermal load prediction through shallow machine learning and deep learning. Appl Energ. 2020;263.
[21] Khurana U, Turaga D, Samulowitz H, Parthasrathy S. Cognito: Automated Feature Engineering for Supervised Learning. 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)2016. p. 1304-7.
[22] Senjyu T, Yona A, Urasaki N, Funabashi T. Application of Recurrent Neural Network to Long-Term-Ahead Generating Power Forecasting for Wind Power Generator. 2006 IEEE PES Power Systems Conference and Exposition2006. p. 1260-5.
[23] Wan RZ, Mei SP, Wang J, Liu M, Yang F. Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting. Electronics-Switz. 2019;8.
[24] Bhoj N, Singh Bhadoria R. Time-series based prediction for energy consumption of smart home data using hybrid convolution-recurrent neural network. Telematics and Informatics. 2022;75:101907.
[25] Khalil M, McGough AS, Pourmirza Z, Pazhoohesh M, Walker S. Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption - A systematic review. Eng Appl Artif Intel. 2022;115.
[26] Zhu A, Li X, Mo Z, Wu R. Wind power prediction based on a convolutional neural network. 2017 International Conference on Circuits, Devices and Systems (ICCDS)2017. p. 131-5.
[27] Zang H, Cheng L, Ding T, Cheung KW, Wei Z, Sun G. Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning. International Journal of Electrical Power & Energy Systems. 2020;118:105790.
[28] Lee H, Song J. Introduction to convolutional neural network using Keras; an understanding from a statistician. Commun Stat Appl Met. 2019;26:591-610.
[29] Sadaei HJ, Silva PCDE, Guimaraes FG, Lee MH. Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series. Energy. 2019;175:365-77.
[30] Agga A, Abbou A, Labbadi M, Houm YE, Ou Ali IH. CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production. Electr Pow Syst Res. 2022;208:107908.
[31] Kim T-Y, Cho S-B. Predicting residential energy consumption using CNN-LSTM neural networks. Energy. 2019;182:72-81.
[32] Li Y, He YY, Zhang MZ. Prediction of Chinese energy structure based on Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM). Energy Sci Eng. 2020;8:2680-9.
[33] Ghimire S, Bhandari B, Casillas-Pérez D, Deo RC, Salcedo-Sanz S. Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia. Eng Appl Artif Intel. 2022;112:104860.
[34] Alhussein M, Aurangzeb K, Haider SI. Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting. IEEE Access. 2020;8:180544-57.
[35] Tran D-H, Luong D-L, Chou J-S. Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings. Energy. 2020;191:116552.
[36] Iwendi C, Maddikunta PKR, Gadekallu TR, Lakshmanna K, Bashir AK, Piran MJ. A metaheuristic optimization approach for energy efficiency in the IoT networks. Software Pract Exper. 2021;51:2558-71.
[37] Yao S, Xu Y-P, Ramezani E. Optimal long-term prediction of Taiwan’s transport energy by convolutional neural network and wildebeest herd optimizer. Energy Rep. 2021;7:218-27.
[38] Altan A, Karasu S, Zio E. A new hybrid model for wind speed forecasting combining long short-term memory neural network, decomposition methods and grey wolf optimizer. Applied Soft Computing. 2021;100:106996.
[39] Chou J-S, Truong D-N. A novel metaheuristic optimizer inspired by behavior of jellyfish in ocean. Applied Mathematics and Computation. 2021;389:125535.
[40] Chou JS, Truong DN. Multiobjective optimization inspired by behavior of jellyfish for solving structural design problems. Chaos Soliton Fract. 2020;135.
[41] Bhatt D, Patel C, Talsania H, Patel J, Vaghela R, Pandya S, et al. CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope. Electronics-Switz. 2021;10.
[42] Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks. Neural Information Processing Systems. 2012;25.
[43] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2014. p. arXiv:1409.556.
[44] He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016. p. 770-8.
[45] He K, Zhang X, Ren S, Sun J. Identity Mappings in Deep Residual Networks2016.
[46] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016. p. 2818-26.
[47] Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. AAAI Conference on Artificial Intelligence. 2016;31.
[48] Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2017. p. 1800-7.
[49] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. ArXiv. 2017;abs/1704.04861.
[50] Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition2018. p. 4510-20.
[51] Zoph B, Vasudevan V, Shlens J, Le QV. Learning Transferable Architectures for Scalable Image Recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition2018. p. 8697-710.
[52] Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In: Kamalika C, Ruslan S, editors. Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research: PMLR; 2019. p. 6105--14.
[53] Tan M, Le QV. EfficientNetV2: Smaller Models and Faster Training. ArXiv. 2021;abs/2104.00298.
[54] Stanton J. Galton, Pearson, and the Peas: A Brief History of Linear Regression for Statistics Instructors. Journal of Statistics Education. 2001;9.
[55] McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics. 1943;5:115-33.
[56] Drucker H, C C, Kaufman L, Smola A, Vapnik V. Support Vector Regression Machines. Advances in Neural Information Processing Systems. 2003;9.
[57] Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and Regression Trees. 1984.
[58] Han H-G, Chen Q, Qiao J. Research on an online self-organizing radial basis function neural network. Neural computing & applications. 2010;19:667-76.
[59] Chou J-S, Chen L-Y, Liu C-Y. FBI-Optimised XGBoost System for Predicting Compressive Strength of Ready-Mixed Concrete. Journal of Computational Design and Engineering. 2022.
[60] Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation. 1997;9:1735-80.
[61] Bedi J, Toshniwal D. Deep learning framework to forecast electricity demand. Appl Energ. 2019;238:1312-26.
[62] Cho K, Merrienboer B, Bahdanau D, Bengio Y. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. 2014.
[63] Hadjout D, Torres JF, Troncoso A, Sebaa A, Alvarez FM. Electricity consumption forecasting based on ensemble deep learning with application to the Algerian market. Energy. 2022;243.