{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:58:30Z","timestamp":1777694310909,"version":"3.51.4"},"reference-count":47,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICA"],"published-print":{"date-parts":[[2024,4,26]]},"abstract":"<jats:p>Short-term residential load forecasting plays a crucial role in smart grids, ensuring an optimal match between energy demands and generation. With the inherent volatility of residential load patterns, deep learning has gained attention due to its ability to capture complex nonlinear relationships within hidden layers. However, most existing studies have relied on default loss functions such as mean squared error (MSE) or mean absolute error (MAE) for neural networks. These loss functions, while effective in overall prediction accuracy, lack specialized focus on accurately predicting load peaks. This article presents a comparative analysis of soft-DTW loss function, a smoothed formulation of Dynamic Time Wrapping (DTW), compared to other commonly used loss functions, in order to assess its effectiveness in improving peak prediction accuracy. To evaluate peak performance, we introduce a novel evaluation methodology using confusion matrix and propose new errors for peak position and peak load, tailored specifically for assessing peak performance in short-term load forecasting. Our results demonstrate the superiority of soft-DTW in capturing and predicting load peaks, surpassing other commonly used loss functions. Furthermore, the combination of soft-DTW with other loss functions, such as soft-DTW + MSE, soft-DTW + MAE, and soft-DTW + TDI (Time Distortion Index), also enhances peak prediction. However, the differences between these combined soft-DTW loss functions are not substantial. These findings highlight the significance of utilizing specialized loss functions, like soft-DTW, to improve peak prediction accuracy in short-term load forecasting.<\/jats:p>","DOI":"10.3233\/ica-230731","type":"journal-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T10:34:15Z","timestamp":1707474855000},"page":"327-340","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing peak prediction in residential load forecasting with soft dynamic time wrapping loss functions"],"prefix":"10.1177","volume":"31","author":[{"given":"Yuyao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Christian","family":"Obrecht","sequence":"additional","affiliation":[]},{"given":"Fr\u00e9d\u00e9ric","family":"Kuznik","sequence":"additional","affiliation":[]}],"member":"179","reference":[{"key":"10.3233\/ICA-230731_ref1","doi-asserted-by":"crossref","first-page":"112094","DOI":"10.1016\/j.enpol.2020.112094","article-title":"Microgrids and the transition toward decentralized energy systems in the United States: A Multi-Level Perspective","volume":"149","author":"Ajaz","year":"2021","journal-title":"Energy Policy"},{"key":"10.3233\/ICA-230731_ref2","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.rser.2017.01.064","article-title":"Enhancing smart grid with microgrids: Challenges and opportunities","volume":"72","author":"Yolda\u015f","year":"2017","journal-title":"Renewable and Sustainable Energy Reviews"},{"issue":"6","key":"10.3233\/ICA-230731_ref3","doi-asserted-by":"crossref","first-page":"3586","DOI":"10.1016\/j.rser.2012.02.049","article-title":"A review on the prediction of building energy consumption","volume":"16","author":"Magoul\u00e8s","year":"2012","journal-title":"Renewable and Sustainable Energy Reviews"},{"issue":"17","key":"10.3233\/ICA-230731_ref4","doi-asserted-by":"crossref","first-page":"3254","DOI":"10.3390\/en12173254","article-title":"Forecasting energy use in buildings using artificial neural networks: A review","volume":"12","author":"Runge","year":"2019","journal-title":"Energies"},{"key":"10.3233\/ICA-230731_ref5","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1016\/j.apenergy.2018.12.004","article-title":"Assessment of deep recurrent neural network-based strategies for short-term building energy predictions","volume":"236","author":"Fan","year":"2019","journal-title":"Applied Energy"},{"issue":"1","key":"10.3233\/ICA-230731_ref6","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/59.910780","article-title":"Neural networks for short-term load forecasting: A review and evaluation","volume":"16","author":"Hippert","year":"2001","journal-title":"IEEE Transactions on Power Systems"},{"key":"10.3233\/ICA-230731_ref7","doi-asserted-by":"crossref","unstructured":"Almalaq A, Edwards G. A review of deep learning methods applied on load forecasting. In 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE. 2017. pp. 511\u2013516.","DOI":"10.1109\/ICMLA.2017.0-110"},{"issue":"03","key":"10.3233\/ICA-230731_ref8","doi-asserted-by":"crossref","first-page":"2130001","DOI":"10.1142\/S0129065721300011","article-title":"An experimental review on deep learning architectures for time series forecasting","volume":"31","author":"Lara-Ben\u00edtez","year":"2021","journal-title":"International Journal of Neural Systems"},{"key":"10.3233\/ICA-230731_ref9","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.procs.2017.11.374","article-title":"Load forecasting via deep neural networks","volume":"122","author":"He","year":"2017","journal-title":"Procedia Computer Science"},{"issue":"4","key":"10.3233\/ICA-230731_ref10","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1007\/s10489-020-01932-9","article-title":"Convolutional residual network to short-term load forecasting","volume":"51","author":"Sheng","year":"2021","journal-title":"Applied Intelligence"},{"issue":"5","key":"10.3233\/ICA-230731_ref11","doi-asserted-by":"crossref","first-page":"5271","DOI":"10.1109\/TSG.2017.2686012","article-title":"Deep learning for household load forecasting \u2013 A novel pooling deep RNN","volume":"9","author":"Shi","year":"2017","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"5","key":"10.3233\/ICA-230731_ref12","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.3390\/en11051138","article-title":"Short-term load forecasting with multi-source data using gated recurrent unit neural networks","volume":"11","author":"Wang","year":"2018","journal-title":"Energies"},{"issue":"18","key":"10.3233\/ICA-230731_ref13","doi-asserted-by":"crossref","first-page":"3560","DOI":"10.3390\/en12183560","article-title":"Short-term load forecasting for a single household based on convolution neural networks using data augmentation","volume":"12","author":"Acharya","year":"2019","journal-title":"Energies"},{"issue":"9","key":"10.3233\/ICA-230731_ref14","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.3390\/en14092524","article-title":"Short-term load forecasting using encoder-decoder wavenet: Application to the french grid","volume":"14","author":"Dorado\u00a0Rueda","year":"2021","journal-title":"Energies"},{"key":"10.3233\/ICA-230731_ref15","doi-asserted-by":"crossref","unstructured":"Marino DL, Amarasinghe K, Manic M. Building energy load forecasting using deep neural networks. In IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society. IEEE. 2016. pp. 7046\u20137051.","DOI":"10.1109\/IECON.2016.7793413"},{"key":"10.3233\/ICA-230731_ref16","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.apenergy.2017.07.114","article-title":"Short-term residential load forecasting: Impact of calendar effects and forecast granularity","volume":"205","author":"Lusis","year":"2017","journal-title":"Applied Energy"},{"issue":"7","key":"10.3233\/ICA-230731_ref17","doi-asserted-by":"crossref","first-page":"5595","DOI":"10.1002\/cpe.5595","article-title":"An effective deep learning neural network model for short-term load forecasting","volume":"32","author":"Li","year":"2020","journal-title":"Concurrency and Computation: Practice and Experience"},{"issue":"11","key":"10.3233\/ICA-230731_ref18","doi-asserted-by":"crossref","first-page":"3224","DOI":"10.3390\/en14113224","article-title":"Short-term load forecasting using neural networks with pattern similarity-based error weights","volume":"14","author":"Dudek","year":"2021","journal-title":"Energies"},{"issue":"1","key":"10.3233\/ICA-230731_ref19","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","article-title":"Dynamic programming algorithm optimization for spoken word recognition","volume":"26","author":"Sakoe","year":"1978","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"10.3233\/ICA-230731_ref20","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.is.2015.04.007","article-title":"Time-series clustering \u2013 a decade review","volume":"53","author":"Aghabozorgi","year":"2015","journal-title":"Information Systems"},{"key":"10.3233\/ICA-230731_ref21","unstructured":"Cuturi M, Blondel M. Soft-dtw: a differentiable loss function for time-series. In International Conference on Machine Learning. PMLR. 2017. pp. 894\u2013903."},{"key":"10.3233\/ICA-230731_ref22","doi-asserted-by":"crossref","unstructured":"Wolf P, Chin A, Baker B. Unsupervised data-driven automotive diagnostics with improved deep temporal clustering. In 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall). IEEE. 2019. pp. 1\u20136.","DOI":"10.1109\/VTCFall.2019.8891120"},{"key":"10.3233\/ICA-230731_ref23","doi-asserted-by":"crossref","unstructured":"Liang J, Tang W. Fuzzy Clustering Based Scenario Reduction for Stochastic Day-Ahead Scheduling in Power Systems. In 2020 IEEE Power & Energy Society General Meeting (PESGM). IEEE. 2020. pp. 1\u20135.","DOI":"10.1109\/PESGM41954.2020.9281916"},{"key":"10.3233\/ICA-230731_ref24","doi-asserted-by":"crossref","unstructured":"Hu H, Tang M, Bai C. Datsing: Data augmented time series forecasting with adversarial domain adaptation. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2020. pp. 2061\u20132064.","DOI":"10.1145\/3340531.3412155"},{"issue":"19","key":"10.3233\/ICA-230731_ref25","doi-asserted-by":"crossref","first-page":"6088","DOI":"10.3390\/en14196088","article-title":"A meta-modeling power consumption forecasting approach combining client similarity and causality","volume":"14","author":"Kontogiannis","year":"2021","journal-title":"Energies"},{"issue":"20","key":"10.3233\/ICA-230731_ref26","doi-asserted-by":"crossref","first-page":"6565","DOI":"10.3390\/en14206565","article-title":"Definition of Residential Power Load Profiles Clusters Using Machine Learning and Spatial Analysis","volume":"14","author":"Flor\u00a0Ambrosi","year":"2021","journal-title":"Energies"},{"key":"10.3233\/ICA-230731_ref27","doi-asserted-by":"crossref","unstructured":"Ho K-H, Huang P-S, Wu I-C, Wang F-J. Prediction of Time Series Data Based on Transformer with Soft Dynamic Time Wrapping. In 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan). IEEE. 2020. pp.\u00a01\u20132.","DOI":"10.1109\/ICCE-Taiwan49838.2020.9258155"},{"key":"10.3233\/ICA-230731_ref28","unstructured":"Le\u00a0Guen V, Thome N. Shape and time distortion loss for training deep time series forecasting models. Advances in Neural Information Processing Systems. 2019; 32."},{"key":"10.3233\/ICA-230731_ref29","doi-asserted-by":"crossref","first-page":"106377","DOI":"10.1016\/j.compag.2021.106377","article-title":"A dual-head attention model for time series data imputation","volume":"189","author":"Zhang","year":"2021","journal-title":"Computers and Electronics in Agriculture"},{"issue":"9","key":"10.3233\/ICA-230731_ref30","doi-asserted-by":"crossref","first-page":"4001","DOI":"10.3390\/app11094001","article-title":"An Improved attention-based integrated deep neural network for PM2.5 concentration prediction","volume":"11","author":"Shi","year":"2021","journal-title":"Applied Sciences"},{"key":"10.3233\/ICA-230731_ref31","doi-asserted-by":"crossref","unstructured":"Singh RP, Gao PX, Lizotte DJ. On hourly home peak load prediction. In 2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm). IEEE. 2012. pp. 163\u2013168.","DOI":"10.1109\/SmartGridComm.2012.6485977"},{"key":"10.3233\/ICA-230731_ref32","doi-asserted-by":"crossref","unstructured":"Milojkovi\u0107 J, Litovski I, Litovski V. ANN application for the next day peak electricity load prediction. In 11th Symposium on Neural Network Applications in Electrical Engineering. IEEE. 2012. pp. 237\u2013241.","DOI":"10.1109\/NEUREL.2012.6420024"},{"issue":"7","key":"10.3233\/ICA-230731_ref33","doi-asserted-by":"crossref","first-page":"3984","DOI":"10.3390\/su14073984","article-title":"Regression-Based Methods for Daily Peak Load Forecasting in South Korea","volume":"14","author":"Lee","year":"2022","journal-title":"Sustainability"},{"issue":"2","key":"10.3233\/ICA-230731_ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TAC.1959.1104847","article-title":"On adaptive control processes","volume":"4","author":"Bellman","year":"1959","journal-title":"IRE Transactions on Automatic Control"},{"issue":"3","key":"10.3233\/ICA-230731_ref35","doi-asserted-by":"crossref","first-page":"237","DOI":"10.3233\/ICA-210650","article-title":"Pattern discovery in time series using autoencoder in comparison to nonlearning approaches","volume":"28","author":"Noering","year":"2021","journal-title":"Integrated Computer-Aided Engineering"},{"key":"10.3233\/ICA-230731_ref37","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.3233\/ICA-230731_ref38","unstructured":"Li H, Xu Z, Taylor G, Studer C, Goldstein T. Visualizing the loss landscape of neural nets. Advances in Neural Information Processing Systems. 2018; 31."},{"issue":"10","key":"10.3233\/ICA-230731_ref39","doi-asserted-by":"crossref","first-page":"2672","DOI":"10.3390\/en13102672","article-title":"Houseec: Day-ahead household electrical energy consumption forecasting using deep learning","volume":"13","author":"Kiprijanovska","year":"2020","journal-title":"Energies"},{"issue":"16","key":"10.3233\/ICA-230731_ref40","doi-asserted-by":"crossref","first-page":"3199","DOI":"10.3390\/en12163199","article-title":"Research on short-term load prediction based on Seq2seq model","volume":"12","author":"Gong","year":"2019","journal-title":"Energies"},{"issue":"3","key":"10.3233\/ICA-230731_ref41","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1109\/TPWRS.2020.3028133","article-title":"Short-term load forecasting for industrial customers based on TCN-LightGBM","volume":"36","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Power Systems"},{"key":"10.3233\/ICA-230731_ref42","doi-asserted-by":"crossref","unstructured":"Cheng Y, Xu C, Mashima D, Thing VL, Wu Y. PowerLSTM: power demand forecasting using long short-term memory neural network. In International Conference on Advanced Data Mining and Applications. Springer. 2017. pp. 727\u2013740.","DOI":"10.1007\/978-3-319-69179-4_51"},{"key":"10.3233\/ICA-230731_ref43","doi-asserted-by":"crossref","first-page":"106073","DOI":"10.1016\/j.epsr.2019.106073","article-title":"Load demand forecasting of residential buildings using a deep learning model","volume":"179","author":"Wen","year":"2020","journal-title":"Electric Power Systems Research"},{"issue":"1","key":"10.3233\/ICA-230731_ref44","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TSG.2017.2753802","article-title":"Short-term residential load forecasting based on LSTM recurrent neural network","volume":"10","author":"Kong","year":"2017","journal-title":"IEEE Transactions on Smart Grid"},{"key":"10.3233\/ICA-230731_ref45","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.segan.2016.02.005","article-title":"Deep learning for estimating building energy consumption","volume":"6","author":"Mocanu","year":"2016","journal-title":"Sustainable Energy, Grids and Networks"},{"issue":"3","key":"10.3233\/ICA-230731_ref48","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1016\/j.patcog.2010.09.013","article-title":"A global averaging method for dynamic time warping, with applications to clustering","volume":"44","author":"Petitjean","year":"2011","journal-title":"Pattern Recognition"},{"issue":"8","key":"10.3233\/ICA-230731_ref49","doi-asserted-by":"crossref","first-page":"4773","DOI":"10.1016\/j.asoc.2011.07.005","article-title":"A computational intelligence scheme for the prediction of the daily peak load","volume":"11","author":"Nagi","year":"2011","journal-title":"Applied Soft Computing"},{"key":"10.3233\/ICA-230731_ref50","doi-asserted-by":"crossref","first-page":"107860","DOI":"10.1016\/j.epsr.2022.107860","article-title":"LSTM enhanced by dual-attention-based encoder-decoder for daily peak load forecasting","volume":"208","author":"Zhu","year":"2022","journal-title":"Electric Power Systems Research"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICA-230731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:14:52Z","timestamp":1777454092000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICA-230731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":47,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/ica-230731","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]}}}