{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:30:16Z","timestamp":1769675416429,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry for Economic Affairs and Energy (BMWE) within the framework of the Research Program EnOB: ML-EBESR in Cooperation with Green Fusion GmbH","award":["03EN1076B"],"award-info":[{"award-number":["03EN1076B"]}]},{"name":"Open Access Publication Fund of TU Berlin"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3656258","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:40:48Z","timestamp":1768941648000},"page":"12297-12315","source":"Crossref","is-referenced-by-count":0,"title":["An Explainable Transformer-Based Mixture of Experts for Heat Load Forecasting"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9584-7519","authenticated-orcid":false,"given":"Pedram","family":"Babakhani","sequence":"first","affiliation":[{"name":"Hermann-Rietschel-Institut (HRI), Technische Universität Berlin (TU Berlin), Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2476-3681","authenticated-orcid":false,"given":"Alexander","family":"Neubauer","sequence":"additional","affiliation":[{"name":"Hermann-Rietschel-Institut (HRI), Technische Universität Berlin (TU Berlin), Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5243-2430","authenticated-orcid":false,"given":"Mengbo","family":"Yu","sequence":"additional","affiliation":[{"name":"Hermann-Rietschel-Institut (HRI), Technische Universität Berlin (TU Berlin), Berlin, Germany"}]},{"given":"Stefan","family":"Brandt","sequence":"additional","affiliation":[{"name":"Hermann-Rietschel-Institut (HRI), Technische Universität Berlin (TU Berlin), Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-6333","authenticated-orcid":false,"given":"Martin","family":"Kriegel","sequence":"additional","affiliation":[{"name":"Hermann-Rietschel-Institut (HRI), Technische Universität Berlin (TU Berlin), Berlin, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1016\/j.adapen.2024.100181","article-title":"Impact of forecasting on energy system optimization","volume":"15","author":"Peterssen","year":"2024","journal-title":"Adv. Appl. Energy"},{"key":"ref2","article-title":"A state-of-the-art comparative review of load forecasting methods: Characteristics, perspectives, and applications","volume":"26","author":"Hasan","year":"2025","journal-title":"Energy Convers. Manage., X"},{"issue":"3","key":"ref3","doi-asserted-by":"crossref","first-page":"679","DOI":"10.3390\/en18030679","article-title":"Forecasting heat power demand in retrofitted residential buildings","volume":"18","author":"Guz","year":"2025","journal-title":"Energies"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1016\/j.rineng.2025.106872","article-title":"Sustainable thermal load prediction in residential buildings using machine learning: A case study analysis","volume":"27","author":"Abdul-Zahra","year":"2025","journal-title":"Results Eng."},{"issue":"7","key":"ref5","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.3390\/en18071775","article-title":"Real implementation and testing of short-term building load forecasting: A comparison of SVR and NARX","volume":"18","author":"Hern\u00e1ndez","year":"2025","journal-title":"Energies"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2024.114290","article-title":"Building heating load forecasting based on the theory of transient heat transfer and deep learning","volume":"313","author":"Shi","year":"2024","journal-title":"Energy Buildings"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3600100.3623742"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM51994.2024.10689186"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2023.129866","article-title":"District heating load patterns and short-term forecasting for buildings and city level","volume":"289","author":"Hua","year":"2024","journal-title":"Energy"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2023.127637","article-title":"Load forecasting of district heating system based on improved FB-prophet model","volume":"278","author":"Shakeel","year":"2023","journal-title":"Energy"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2022.112630","article-title":"Day-ahead heat load forecasting during the off-season in the district heating system using generalized additive model","volume":"278","author":"Bujalski","year":"2023","journal-title":"Energy Buildings"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"17","key":"ref13","doi-asserted-by":"crossref","first-page":"6234","DOI":"10.3390\/en16176234","article-title":"Bayesian optimization-based LSTM for short-term heating load forecasting","volume":"16","author":"Li","year":"2023","journal-title":"Energies"},{"issue":"15","key":"ref14","doi-asserted-by":"crossref","first-page":"2406","DOI":"10.3390\/math13152406","article-title":"Seasonally adaptive VMD-SSA-LSTM: A hybrid deep learning framework for high-accuracy district heating load forecasting","volume":"13","author":"Zhang","year":"2025","journal-title":"Mathematics"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.133536","article-title":"A novel heat load prediction model of district heating system based on hybrid whale optimization algorithm (WOA) and CNN-LSTM with attention mechanism","volume":"312","author":"Cui","year":"2024","journal-title":"Energy"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.124179","article-title":"Load forecasting of district heating system based on informer","volume":"253","author":"Gong","year":"2022","journal-title":"Energy"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.130347","article-title":"Accuracy improvement of the load forecasting in the district heating system by the informer-based framework with the optimal step size selection","volume":"291","author":"Zhang","year":"2024","journal-title":"Energy"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.133535","article-title":"Short-term heating load forecasting model based on SVMD and improved informer","volume":"312","author":"Tan","year":"2024","journal-title":"Energy"},{"key":"ref20","first-page":"303","article-title":"Probabilistic load forecasting for integrated energy systems based on quantile regression patch time series transformer","volume-title":"Energy Rep.","volume":"13","author":"Zhang","year":"2025"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126446","article-title":"Integrated energy short-term multivariate load forecasting based on PatchTST secondary decoupling reconstruction for progressive layered extraction multi-task learning network","volume":"269","author":"Qu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref22","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2022","journal-title":"arXiv:2210.02186"},{"issue":"14","key":"ref23","doi-asserted-by":"crossref","first-page":"5330","DOI":"10.3390\/en16145330","article-title":"An ensemble framework for short-term load forecasting based on TimesNet and TCN","volume":"16","author":"Zuo","year":"2023","journal-title":"Energies"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-15777-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2298\/tsci241223048z"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2025.100480","article-title":"Explainable multi-step heating load forecasting: Using SHAP values and temporal attention mechanisms for enhanced interpretability","volume":"20","author":"Neubauer","year":"2025","journal-title":"Energy AI"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2025.134641","article-title":"Explainable district heating load forecasting by means of a reservoir computing deep learning architecture","volume":"318","author":"Serra","year":"2025","journal-title":"Energy"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-34146-3"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.121753","article-title":"Explainable district heat load forecasting with active deep learning","volume":"350","author":"Huang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2024.100358","article-title":"Explainability and interpretability in electric load forecasting using machine learning techniques\u2014A review","volume":"16","author":"Baur","year":"2024","journal-title":"Energy AI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s41601-022-00245-y"},{"key":"ref32","first-page":"152","article-title":"Explainable AI for cooling load prediction and heat flow estimation using SHAP values","volume-title":"Proc. BauSim Conf.","volume":"10","author":"Neubauer"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1016\/j.applthermaleng.2025.127552","article-title":"Building heat load forecasting with mechanism-based data fusion: A stacking ensemble approach for district heating systems","volume":"279","author":"Yang","year":"2025","journal-title":"Appl. Thermal Eng."},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1016\/j.jobe.2024.110199","article-title":"Enhancing residential heating load prediction with advanced machine learning and optimization techniques","volume":"95","author":"Mohebbi","year":"2024","journal-title":"J. Building Eng."},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2025.135947","article-title":"A multi-energy load forecasting method based on the mixture-of-experts model and dynamic multilevel attention mechanism","volume":"324","author":"Hu","year":"2025","journal-title":"Energy"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3661945"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3534419"},{"key":"ref38","article-title":"Time-MoE: Billion-scale time series foundation models with mixture of experts","author":"Shi","year":"2024","journal-title":"arXiv:2409.16040"},{"key":"ref39","article-title":"TriForecaster: A mixture of experts framework for multi-region electric load forecasting with tri-dimensional specialization","author":"Zhu","year":"2025","journal-title":"arXiv:2508.09753"},{"key":"ref40","volume-title":"OEMOF\/demandlib: v0.2.2","author":"Krien","year":"2025"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.126618","article-title":"TCN-BiLSTM-CE: An interdisciplinary approach for missing energy data imputation by contextual inference","volume":"401","author":"Yu","year":"2025","journal-title":"Appl. Energy"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/3140\/5\/052023"},{"key":"ref43","first-page":"5048","article-title":"Improving heat demand forecasting with feature reduction in an encoder\u2013decoder LSTM model","volume-title":"Energy Rep.","volume":"14","author":"Darbandi","year":"2025"},{"key":"ref44","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","author":"Nie","year":"2022","journal-title":"arXiv:2211.14730"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.2307\/4615733"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11359141.pdf?arnumber=11359141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:00:36Z","timestamp":1769634036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3656258","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}