{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T10:35:45Z","timestamp":1772102145530,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Project of State Grid Sichuan Electric Power Company","award":["52199723002T"],"award-info":[{"award-number":["52199723002T"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>To predict the output power of integrated energy systems (IES) under zero-carbon conditions, this research presents a Multi Data Fusion-based iTransformer prediction network (MDF-iTransformer). The network uses Multivariate Singular Spectrum Analysis (MSSA) to identify nonlinear relationships among variables and extract dynamic features from multi-modal data. It integrates an embedding block and multivariate attention module into the iTransformer network to capture complex patterns and long-term temporal dependencies in multi-dimensional data, thereby extracting dynamic features across different time scales and spatial dimensions. Subsequently, to address the issue of imbalanced datasets, the improved K-means-SMOTE (KS) algorithm is adopted to augment the number of small-class samples, effectively reducing model bias. Experimental results indicate that the proposed MDF-iTransformer achieves a root-mean-square error (RMSE) of 7.2 kW, mean absolute error (MAE) of 5.6 kW, mean absolute percentage error (MAPE) of 2.7%, and an R-squared value (R2) of 0.92 for a 1 h prediction horizon. It still maintains an RMSE of 14.4 kW, MAE of 11.9 kW, MAPE of 3.68%, and R2 of 0.74 at the 10 h horizon, with cross-season load forecasting errors consistently below 4%. Compared with other algorithms, MDF-iTransformer demonstrates higher accuracy and stronger robustness, playing a crucial role in the optimal operation of integrated energy systems.<\/jats:p>","DOI":"10.3390\/a19020164","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T08:58:21Z","timestamp":1771837101000},"page":"164","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MDF-iTransformer: Multi Data Fusion-Based iTransformer for Load Prediction of Zero-Carbon Emission Integrated Energy System in Urban Park"],"prefix":"10.3390","volume":"19","author":[{"given":"Yang","family":"Wei","sequence":"first","affiliation":[{"name":"Electric Power Science Research Institute, State Grid Sichuan Electric Power Company, Chengdu 610041, China"},{"name":"Sichuan Provincial Key Laboratory of Safety and Operation of New Power System, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengwei","family":"Chang","sequence":"additional","affiliation":[{"name":"State Grid Sichuan Electric Power Company, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Yang","sequence":"additional","affiliation":[{"name":"China National Institute of Standardization, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"Electric Power Science Research Institute, State Grid Sichuan Electric Power Company, Chengdu 610041, China"},{"name":"Sichuan Provincial Key Laboratory of Safety and Operation of New Power System, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Grid Sichuan Electric Power Company, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumin","family":"Chen","sequence":"additional","affiliation":[{"name":"Electric Power Science Research Institute, State Grid Sichuan Electric Power Company, Chengdu 610041, China"},{"name":"Sichuan Provincial Key Laboratory of Safety and Operation of New Power System, Chengdu 610041, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maomao","family":"Yan","sequence":"additional","affiliation":[{"name":"China National Institute of Standardization, Beijing 100191, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, J., Xie, B., Chen, Y., and Zhao, W. (2025, January 16\u201318). Low-Carbon Optimal Dispatch of Multi-Energy Complementary Integrated Energy System Considering Green Certificate and Carbon Emission Trading. Proceedings of the 2025 IEEE 3rd International Conference on Power Science and Technology (ICPST), Kunming, China.","DOI":"10.1109\/ICPST65050.2025.11089315"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"108955","DOI":"10.1016\/j.mineng.2024.108955","article-title":"Research on Carbon Emission Accounting and Carbon Emission Reduction Path of Coal Preparation Plant","volume":"217","author":"Xu","year":"2024","journal-title":"Miner. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"25211","DOI":"10.1007\/s10668-024-04752-w","article-title":"Forecasting China\u2019s Carbon Emission Intensity and Total Carbon Emissions Based on the WOA-Stacking Integrated Model","volume":"27","author":"Guo","year":"2025","journal-title":"Environ. Dev. Sustain."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"101471","DOI":"10.1016\/j.esd.2024.101471","article-title":"Characteristics of Residents\u2019 Carbon Emission and Driving Factors for Carbon Peaking: A Case Study in Wuhan, China","volume":"81","author":"Bei","year":"2024","journal-title":"Energy Sustain. Dev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"135314","DOI":"10.1016\/j.energy.2025.135314","article-title":"Carbon Emission Accounting Method for Coal-fired Power Units of Different Coal Types under Peak Shaving Conditions","volume":"320","author":"Chen","year":"2025","journal-title":"Energy"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108163","DOI":"10.1016\/j.ecolecon.2024.108163","article-title":"Can Carbon Tariffs Based on Domestic Embedded Carbon Emissions Reduce More Carbon Leakages?","volume":"220","author":"Jia","year":"2024","journal-title":"Ecol. Econ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4791","DOI":"10.15244\/pjoes\/177464","article-title":"Agricultural Carbon Emissions in China: Estimation, Influencing Factors, and Projection of Peak Emissions","volume":"33","author":"Wu","year":"2024","journal-title":"Pol. J. Environ. Stud."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"849","DOI":"10.18280\/ijdne.190315","article-title":"Forecasting CO2 Emissions in Malaysia Through ARIMA Modelling: Implications for Environmental Policy","volume":"19","author":"Segar","year":"2024","journal-title":"Int. J. Des. Nat. Ecodynamics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8322590","DOI":"10.1155\/2021\/8322590","article-title":"A Comparative Study of CO2 Emission Forecasting in the Gulf Countries Using Autoregressive Integrated Moving Average, Artificial Neural Network, and Holt-Winters Exponential Smoothing Models","volume":"2021","author":"Alam","year":"2021","journal-title":"Adv. Meteorol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107493","DOI":"10.1016\/j.buildenv.2020.107493","article-title":"Dynamic Measurement of the Airflow Rate in a Two-zones Dwelling, from the CO2 Tracer Gas-decay Method Using the Kalman Filter","volume":"188","author":"Remion","year":"2021","journal-title":"Build. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"12037","DOI":"10.1002\/2015JD023901","article-title":"Fast and slow climate responses to CO2 and solar forcing: A linear multivariate regression model characterizing transient climate change","volume":"120","author":"Cao","year":"2015","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hrithik, P.M., Rehman, M.Z., Dar, A.A., and Wangmo, A.T. (2024). Forecasting CO2 Emissions in India: A Time Series Analysis Using ARIMA. Processes, 12.","DOI":"10.3390\/pr12122699"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"129657","DOI":"10.1016\/j.jclepro.2021.129657","article-title":"A Random Forest-based Model for the Prediction of Construction-stage Carbon Emissions at the Early Design Stage","volume":"328","author":"Fang","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Cai, Y.H., Feng, J.X., Wang, Y.Q., Ding, Y., Hu, Y., and Fang, H. (2024). The Optuna-LightGBM-XGBoost Model: A Novel Approach for Estimating Carbon Emissions Based on the Electricity-Carbon Nexus. Appl. Sci., 14.","DOI":"10.3390\/app14114632"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2301139","DOI":"10.1002\/ente.202301139","article-title":"Improved Least Squares Support Vector Machine Model Based on Grey Wolf Optimizer Algorithm for Predicting CO2-Crude Oil Minimum Miscibility Pressure","volume":"12","author":"Li","year":"2024","journal-title":"Energy Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"120584","DOI":"10.1016\/j.ces.2024.120584","article-title":"Pyrolysis Conversion of Multi-layer Packaging Waste under a CO2 Atmosphere: Thermo-kinetic Study, Evolved Products Analysis and Artificial Neural Networks Modeling","volume":"300","author":"Wang","year":"2024","journal-title":"Chem. Eng. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wei, X.Y., and Xu, Y. (2023). Research on Carbon Emission Prediction and Economic Policy Based on TCN-LSTM Combined with Attention Mechanism. Front. Ecol. Evol., 11.","DOI":"10.3389\/fevo.2023.1270248"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Fahim, A., Fadil, H., and Bhatti, U.A. (2023, January 18\u201320). Forecasting the Carbon Emissions in African Countries Using EMD-GCN. Proceedings of the 2023 IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Chengdu, China.","DOI":"10.1109\/PRAI59366.2023.10332019"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yu, X.T., Cheng, J.H., and Li, L.Q. (2023). Prediction of CO2 Emissions Related to Energy Consumption for Rural Governance. Sustainability, 15.","DOI":"10.3390\/su152416750"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8046","DOI":"10.1016\/j.egyr.2022.06.025","article-title":"A Comparative Analysis to Forecast Carbon Dioxide Emissions","volume":"8","author":"Faruque","year":"2022","journal-title":"Energy Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e13755","DOI":"10.1111\/exsy.13755","article-title":"Temporal Evolution Pathway and Forecasting of Non-Fossil Energy Consumption and Carbon Emission Under China\u2019s Carbon Peak Target: A Markov Switching AR and RNN Approach","volume":"42","author":"Liu","year":"2025","journal-title":"Expert Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Han, Z.H., Cui, B.W., Xu, L.W., Wang, J., and Guo, Z. (2023). Coupling LSTM and CNN Neural Networks for Accurate Carbon Emission Prediction in 30 Chinese Provinces. Sustainability, 15.","DOI":"10.3390\/su151813934"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Keerthana, K.B., Wu, S.W., Wu, M.E., and Kokulnathan, T. (2023). The United States Energy Consumption and Carbon Dioxide Emissions: A Comprehensive Forecast Using a Regression Model. Sustainability, 15.","DOI":"10.3390\/su15107932"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4629","DOI":"10.5194\/amt-17-4629-2024","article-title":"Multi-decadal Atmospheric Carbon Dioxide Measurements in Hungary, Central Europe","volume":"17","author":"Haszpra","year":"2024","journal-title":"Atmos. Meas. Technol."},{"key":"ref_25","first-page":"146","article-title":"AI Driven Carbon Emission Estimation and Forecasting with Recommended Solution","volume":"2381","author":"Tesfai","year":"2025","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wu, X.H., Chen, L., Zhao, J.N., He, M., and Han, X. (2024). CNN-GRU-Attention Neural Networks for Carbon Emission Prediction of Transportation in Jiangsu Province. Sustainability, 16.","DOI":"10.3390\/su16198553"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Matushkin, D., Zaporozhets, A., Babak, V., Kulyk, M., and Denysov, V. (2025). Hourly Photovoltaic Power Forecasting Using Exponential Smoothing: A Comparative Study Based on Operational Data. Solar, 5.","DOI":"10.20944\/preprints202508.0603.v1"},{"key":"ref_28","first-page":"283","article-title":"Long-Term Photovoltaic Power Generation Forecasting Using Long Short-Term Memory Network: Insights into Stochastic Dynamics","volume":"627","author":"Matushkin","year":"2026","journal-title":"Nexus Sustain."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e2025GL116707","DOI":"10.1029\/2025GL116707","article-title":"Novel Deep Learning Transformer Model for Short to Sub-Seasonal Streamflow Forecast","volume":"52","author":"Ambika","year":"2025","journal-title":"Geophys. Res. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3095","DOI":"10.1007\/s12145-024-01330-6","article-title":"Evaluation of a Transformer-based Model for the Temporal Forecast of Coarse Particulate Matter (PMCO) Concentrations","volume":"17","year":"2024","journal-title":"Earth Sci. Inform."},{"key":"ref_31","first-page":"92","article-title":"Short-term Power Load Forecasting Based on Spatial-temporal Dynamic Graph and Multi-scale Transformer","volume":"12","author":"Zhu","year":"2025","journal-title":"J. Comput. Des. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1109\/TSG.2025.3535407","article-title":"A Hybrid LSTM-Transformer Model for Power Load Forecasting","volume":"16","author":"Pentsos","year":"2025","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"73671","DOI":"10.1109\/ACCESS.2025.3563070","article-title":"DiffTST: Diff Transformer for Multivariate Time Series Forecast","volume":"13","author":"Yang","year":"2025","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"114479","DOI":"10.1016\/j.rser.2024.114479","article-title":"Multi-step Photovoltaic Power Forecasting Using Transformer and Recurrent Neural Networks","volume":"200","author":"Kim","year":"2024","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e3001","DOI":"10.7717\/peerj-cs.3001","article-title":"Deep Learning in Time Series Forecasting with Transformer Models and RNNs","volume":"11","author":"Santos","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"33935","DOI":"10.1109\/ACCESS.2025.3543594","article-title":"A Deep Learning Model Using Transformer Network and Expert Optimizer for an Hour Ahead Wind Power Forecasting","volume":"13","author":"Thiyagarajan","year":"2025","journal-title":"IEEE Access"},{"key":"ref_37","first-page":"126150","article-title":"A differential geometric approach to time series forecasting","volume":"402","author":"Emami","year":"2021","journal-title":"Appl. Math. Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TNN.2010.2096824","article-title":"Lower upper bound estimation method for construction of neural network-based prediction intervals","volume":"22","author":"Khosravi","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_39","first-page":"123","article-title":"Computer age statistical inference: Confidence intervals and significance tests","volume":"1","author":"Efron","year":"2016","journal-title":"Camb. Univ. Press"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"119442","DOI":"10.1016\/j.enconman.2024.119442","article-title":"Tackling the Duck Curve in Renewable Power System: A Multi-task Learning Model with iTransformer for Net-load Forecasting","volume":"326","author":"Pei","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e70057","DOI":"10.1002\/we.70057","article-title":"Inverted Transformers for Effective Post-Calibration in Multisite Wind Power Forecasting","volume":"28","author":"Cohen","year":"2025","journal-title":"Wind Energy"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, F.H., Wang, Y.Q., Chen, W.B., and Zhao, C. (2025). An Improved iTransformer with RevIN and SSA for Greenhouse Soil Temperature Prediction. Agronomy, 15.","DOI":"10.3390\/agronomy15010223"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3405","DOI":"10.1016\/j.egyr.2024.09.023","article-title":"A Method for Short-term Electric Load Forecasting Based on the FMLP-iTransformer Model","volume":"12","author":"Fang","year":"2024","journal-title":"Energy Rep."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10489-025-07055-3","article-title":"MSLP-Gruformer: A Hybrid Model Based on iTransformer for Day-ahead Photovoltaic Power Forecasting","volume":"56","author":"Mo","year":"2026","journal-title":"Appl. Intell."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"130745","DOI":"10.1016\/j.energy.2024.130745","article-title":"Energy Management System Based on Economic Flexi-reliable Operation for the Smart Distribution Network Including Integrated Energy System of Hydrogen Storage and Renewable Sources","volume":"293","author":"Liang","year":"2024","journal-title":"Energy"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"12676","DOI":"10.1109\/JSEN.2025.3544242","article-title":"Multivariate Multiscale Variations Dispersion Entropy and Multivariate Multiscale Variations Fuzzy Dispersion Entropy for Time-Series Analysis","volume":"25","author":"Ding","year":"2025","journal-title":"IEEE Sens. J."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1795","DOI":"10.1007\/s41060-024-00561-6","article-title":"Multilayer Quantile Graph for Multivariate Time Series Analysis and Dimensionality Reduction","volume":"20","author":"Silva","year":"2025","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.isatra.2021.01.058","article-title":"Online Cement Clinker Quality Monitoring: A Soft Sensor Model Based on Multivariate Time Series Analysis and CNN","volume":"117","author":"Zhao","year":"2021","journal-title":"ISA Trans."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"126302","DOI":"10.1016\/j.eswa.2024.126302","article-title":"Multivariate Time Series Prediction with Multi-feature Analysis","volume":"268","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"110113","DOI":"10.1016\/j.sigpro.2025.110113","article-title":"Tensor-based Higher-order Multivariate Singular Spectrum Analysis and Applications to Multichannel Biomedical Signal Analysis","volume":"238","author":"Le","year":"2026","journal-title":"Signal Process."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1080\/10618600.2024.2362222","article-title":"Multivariate Singular Spectrum Analysis by Robust Diagonal wise Low-Rank Approximation","volume":"34","author":"Centofanti","year":"2025","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_52","unstructured":"Liu, Y., Hu, T.G., Zhang, H.R., Wu, H., Wang, S., Ma, L., and Long, M. (2024, January 7\u201311). ITransformer: Inverted Transformers Are Effective for Time Series Forecasting. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1186\/s40537-025-01150-5","article-title":"A Novel ST-iTransformer Model for Spatio-temporal Ambient Air Pollution Forecasting","volume":"12","author":"Zhang","year":"2025","journal-title":"J. Big Data"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/164\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T09:46:20Z","timestamp":1772099180000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["a19020164"],"URL":"https:\/\/doi.org\/10.3390\/a19020164","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,21]]}}}