Load2Load: Day-ahead load forecasting at aggregated level

Yılmaz, Mustafa Berkay

doi:10.55730/1300-0632.3960

Load2Load: Day-ahead load forecasting at aggregated level

Mustafa Berkay YILMAZ (Akdeniz Üniversitesi, Mühendislik Fakültesi, Bilgisayar Bölümü, Antalya, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

2 0

Yıl: 2022 Cilt: 30 Sayı: 7 Sayfa Aralığı: 2636 - 2653 Metin Dili: İngilizce DOI: 10.55730/1300-0632.3960 İndeks Tarihi: 14-12-2022

Load2Load: Day-ahead load forecasting at aggregated level

Öz:

A reliable and accurate short-term load forecasting (STLF) helps utilities and energy providers deal with the challenges posed by supply and demand balance, higher penetration of renewable energies and the development of electricity markets with increasingly complex pricing strategies in future smart grids. Recent advances in deep learning have been successively utilized to STLF. However, there is no certain study that evaluates the performances of different STLF methods at an aggregated level on different datasets with different numbers of daily measurements. In this study, a deep learning STLF architecture called Load2Load is proposed for day-ahead forecasting. Different forecasting methods have been evaluated and compared on two datasets with different temporal resolutions and features. An additive ensemble method as well as a selective ensemble method that selects the outputs of different forecasters in an hourly manner are proposed. Moreover; a modified sequential forward feature selection algorithm is proposed, resulting in better performance with a much smaller number of features. Numerical results show that the proposed Load2Load architecture has a competing performance compared to other advanced forecasters. When used together with the proposed ensemble methods, Load2Load can significantly improve the forecasting performance. The proposed feature selection algorithm results in better performance for the majority of the cases while reducing the dimensionality. According to the results with two different datasets; the proposed methods are shown to be robust to temporal resolutions, feature types and sequence lengths.

Anahtar Kelime: Day-ahead electrical load forecasting aggregated-level forecasting deep learning forecaster ensemble generative adversarial network feature selection

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Bhattacharyya S, Thanh L. Short-term electric load forecasting using an artificial neural network: Case of Northern Vietnam. International Journal of Energy Research 2004; 28 (4): 463 – 472.
[2] Santos P, Martins A, Pires AJ, Martins J, Vilela-Mendes R. Short term load forecast using trend information and process reconstruction. International Journal of Energy Research 2006; 30 (8): 811 – 822.
[3] Sousa JC, Jorge HM, Neves LP. Short-term load forecasting based on support vector regression and load profiling. International Journal of Energy Research 2014; 38 (3): 350–362.
[4] Srivastava AK, Pandey AS, Singh D. Short-term load forecasting methods: A review. 2016 International Conference on Emerging Trends in Electrical Electronics Sustainable Energy Systems (ICETEESES), pp. 130–138.
[5] Baliyan A, Gaurav K, Mishra SK. A review of short term load forecasting using artificial neural network models. Procedia Computer Science 2015; 48: 121 – 125. International Conference on Computer, Communication and Convergence (ICCC 2015).
[6] Yildiz B, Bilbao J, Sproul A. A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renewable and Sustainable Energy Reviews 2017; 73: 1104 – 1122.
[7] Liu X, Zhang Z, Song Z. A comparative study of the data-driven day-ahead hourly provincial load forecasting methods: From classical data mining to deep learning. Renewable and Sustainable Energy Reviews 2020; 119: 109632.
[8] Hsu CC, Chen XT, Chen YS, Chang A. Short-term load forecasting by machine learning. 2020 International Symposium on Community-centric Systems (CcS), pp. 1–6.
[9] Lee YS, Tong LI. Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowledge-Based Systems 2011; 24 (1): 66 – 72.
[10] Ahmed T, Vu D, Muttaqi K, Agalgaonkar A. Load forecasting under changing climatic conditions for the city of Sydney, Australia. Energy 2018; 142: 911 – 919.
[11] Amjady N. Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Transactions on Power Systems 2001; 16 (4): 798–805.
[12] Harun MHH, Othman MM, Musirin I. Short term load forecasting (stlf) using artificial neural network based multiple lags and stationary time series. 2010 4th International Power Engineering and Optimization Conference (PEOCO), pp. 363–370.
[13] Kumar Srivastava A, Singh D, Pandey AS. Short term load forecasting using regression trees: Random forest, bagging and m5p. International Journal of Advanced Trends in Computer Science and Engineering 2020; 9 (2): 1898 – 1902.
[14] Li Y, Che J, Yang Y. Subsampled support vector regression ensemble for short term electric load forecasting. Energy 2018; 164: 160 – 170.
[15] Fan GF, Guo YH, Zheng JM, Hong WC. Application of the weighted k-nearest neighbor algorithm for short-term load forecasting. Energies 2019; 12 (5): 916.
[16] Jian Z, Cencen X, Ziang Z, Xiaohua L. Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. 2017 51st Annual Conference on Information Sciences and Systems (CISS), pp. 1–6.
[17] Li L, Ota K, Dong M. Everything is image: CNN-based short-term electrical load forecasting for smart grid. 2017 14th International Symposium on Pervasive Systems, Algorithms and Networks 2017 11th International Conference on Frontier of Computer Science and Technology 2017 Third International Symposium of Creative Computing (ISPAN-FCST-ISCC), pp. 344–351.
[18] Zhang N, Li Z, Zou X, Quiring SM. Comparison of three short-term load forecast models in southern California. Energy 2019; 189: 116358.
[19] Chen H, Wang S, Wang S, Li Y. Day-ahead aggregated load forecasting based on two-terminal sparse coding and deep neural network fusion. Electric Power Systems Research 2019; 177: 105987.
[20] Guo Z, Zhou K, Zhang X, Yang S. A deep learning model for short-term power load and probability density forecasting. Energy 2018; 160: 1186 – 1200.
[21] Mele E. A review of machine learning algorithms used for load forecasting at microgrid level. Sinteza 2019 - International Scientific Conference on Information Technology and Data Related Research, pp. 452–458.
[22] Solyali D. A comparative analysis of machine learning approaches for short-/long-term electricity load forecasting in cyprus. Sustainability 2020; 12 (9): 3612.
[23] Bouktif S, Fiaz A, Ouni A, Serhani M. Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches †. Energies 2018; 11 (7): 1636.
[24] Choi H, Ryu S, Kim H. Short-term load forecasting based on Resnet and LSTM. In 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) 2018: 1–6.
[25] Uher V, Burget R, Dutta MK, Mlynek P. Forecasting electricity consumption in Czech Republic. In 2015 38th International Conference on Telecommunications and Signal Processing (TSP) 2015: 262–265.
[26] Mahdavi N. Probabilistic forecasting of operational demand in Australia. In 2020 International Conference on Smart Grids and Energy Systems (SGES) (2020), pp. 139–144.
[27] Laouafi A, Laouafi F, Boukelia TE. An adaptive hybrid ensemble with pattern similarity analysis and error correction for short-term load forecasting. Applied Energy 2022; 322: 119525.
[28] Yang Y, Wang Z, Gao Y, Wu J, Zhao S et al. An effective dimensionality reduction approach for short-term load forecasting. Electric Power Systems Research 2022; 210: 108150.
[29] Esener II, Yüksel T, Kurban M. Short-term load forecasting without meteorological data using AI-based structures. Turkish Journal of Electrical Engineering and Computer Sciences 2015; 23 (2): 370 - 380.
[30] Akinola SA, Thakur P, Sharma MS, Kumar K, Singh G. Deep learning approach to load forecasting: A survey. In Communication, Networks and Computing (Singapore, 2021), Springer Singapore, pp. 250–262.
[31] Chelabi H, Khadir MT, Chikhaoui B, Telmoudi AJ. Comparison of deep learning architectures for short-term electrical load forecasting based on multi-modal data. Cybernetics and Systems 2022; 53 (1): 186–207.
[32] Gasparin A, Lukovic S, Alippi C. Deep learning for time series forecasting: The electric load case. CAAI Transactions on Intelligence Technology 2021; 7 (1): 1–25.
[33] Liu Y, Dutta S, Kong AWK, Yeo CK. An image inpainting approach to short-term load forecasting. IEEE Transactions on Power Systems 2022: 1–1.
[34] Bendaoud NMM, Farah N, Ahmed SB. Comparing generative adversarial networks architectures for electricity demand forecasting. Energy and Buildings 2021; 247: 111152.
[35] Dumas J, Wehenkel A, Lanaspeze D, Cornélusse B, Sutera A. A deep generative model for probabilistic energy forecasting in power systems: normalizing flows. Applied Energy 2022; 305: 117871.
[36] Tian C, Ye Y, Lou Y, Zuo W, Zhang G et al. Daily power demand prediction for buildings at a large scale using a hybrid of physics-based model and generative adversarial network. Building Simulation 2022; 15: 1685–1701.
[37] Zhu L, Huang Y. Research on deep generative model application for shortterm load forecasting of enterprise electricity. IOP Conference Series: Earth and Environmental Science 2021; 687 (1): 012113.
[38] Huang N, He Q, Qi J, Hu Q, Wang R et al. Multinodes interval electric vehicle day-ahead charging load forecasting based on joint adversarial generation. International Journal of Electrical Power & Energy Systems 2022; 143: 108404.
[39] Zhou Y, Ding Z, Wen Q, Wang Y. Robust load forecasting towards adversarial attacks via Bayesian learning. IEEE Transactions on Power Systems 2022: 1–1.
[40] Yaprakdal F, Yılmaz MB, Baysal M, Anvari-Moghaddam A. A deep neural network-assisted approach to enhance short-term optimal operational scheduling of a microgrid. Sustainability 2020; 12 (4): 1653.
[41] Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D et al. Generative adversarial nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2 (Cambridge, MA, USA, 2014), NIPS’14, MIT Press, p. 2672–2680.
[42] Chang CC, Lin CJ. Training v-support vector regression: Theory and algorithms. Neural Computation 2002; 14 (8): 1959–1977.
[43] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016: 770–778.

APA	Yılmaz M (2022). Load2Load: Day-ahead load forecasting at aggregated level. , 2636 - 2653. 10.55730/1300-0632.3960
Chicago	Yılmaz Mustafa Berkay Load2Load: Day-ahead load forecasting at aggregated level. (2022): 2636 - 2653. 10.55730/1300-0632.3960
MLA	Yılmaz Mustafa Berkay Load2Load: Day-ahead load forecasting at aggregated level. , 2022, ss.2636 - 2653. 10.55730/1300-0632.3960
AMA	Yılmaz M Load2Load: Day-ahead load forecasting at aggregated level. . 2022; 2636 - 2653. 10.55730/1300-0632.3960
Vancouver	Yılmaz M Load2Load: Day-ahead load forecasting at aggregated level. . 2022; 2636 - 2653. 10.55730/1300-0632.3960
IEEE	Yılmaz M "Load2Load: Day-ahead load forecasting at aggregated level." , ss.2636 - 2653, 2022. 10.55730/1300-0632.3960
ISNAD	Yılmaz, Mustafa Berkay. "Load2Load: Day-ahead load forecasting at aggregated level". (2022), 2636-2653. https://doi.org/10.55730/1300-0632.3960

APA	Yılmaz M (2022). Load2Load: Day-ahead load forecasting at aggregated level. Turkish Journal of Electrical Engineering and Computer Sciences, 30(7), 2636 - 2653. 10.55730/1300-0632.3960
Chicago	Yılmaz Mustafa Berkay Load2Load: Day-ahead load forecasting at aggregated level. Turkish Journal of Electrical Engineering and Computer Sciences 30, no.7 (2022): 2636 - 2653. 10.55730/1300-0632.3960
MLA	Yılmaz Mustafa Berkay Load2Load: Day-ahead load forecasting at aggregated level. Turkish Journal of Electrical Engineering and Computer Sciences, vol.30, no.7, 2022, ss.2636 - 2653. 10.55730/1300-0632.3960
AMA	Yılmaz M Load2Load: Day-ahead load forecasting at aggregated level. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(7): 2636 - 2653. 10.55730/1300-0632.3960
Vancouver	Yılmaz M Load2Load: Day-ahead load forecasting at aggregated level. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(7): 2636 - 2653. 10.55730/1300-0632.3960
IEEE	Yılmaz M "Load2Load: Day-ahead load forecasting at aggregated level." Turkish Journal of Electrical Engineering and Computer Sciences, 30, ss.2636 - 2653, 2022. 10.55730/1300-0632.3960
ISNAD	Yılmaz, Mustafa Berkay. "Load2Load: Day-ahead load forecasting at aggregated level". Turkish Journal of Electrical Engineering and Computer Sciences 30/7 (2022), 2636-2653. https://doi.org/10.55730/1300-0632.3960