{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T17:42:57Z","timestamp":1767634977483,"version":"3.48.0"},"reference-count":49,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Nature Science Foundation Committee","award":["62473115"],"award-info":[{"award-number":["62473115"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Accurate prediction of sensor network data in critical domains such as electric power systems and traffic planning is a core task for ensuring grid stability and enhancing urban operational efficiency. Although deep learning models have achieved significant architectural advancements, their training strategy implicitly assumes that all future events are equally predictable, ignoring that the future evolution of sensor signals intertwines deterministic patterns with stochastic events and that prediction difficulty increases with temporal distance. Forcing a model to fit inherently unpredictable events with a uniform supervision may impair its ability to learn generalizable patterns. To address this, we introduce an Unpredictability Perception loss that dynamically computes a supervision weight. The computation of this weight unifies two assessment dimensions of the intrinsic unpredictability of the forecasting task. The first originates from a posterior analysis of the signal content\u2019s randomness, while the second stems from an a priori consideration of temporal distance. The first dimension, through a complexity-aware weight derived from local spectral entropy, reduces supervision on random segments of the signal. The second dimension, through a temporal decay weight based on exponential decay, lessens supervision for distant future points. Applied to the advanced TimeMixer model, experimental results show that our approach achieves performance improvements across multiple public benchmark datasets. By matching the supervision strength to the intrinsic predictability of the signals, our proposed Unpredictability Perception loss function enhances the forecasting accuracy for sensor network data, providing a more reliable technical foundation for ensuring the stability of critical infrastructures like power grids and optimizing urban traffic systems.<\/jats:p>","DOI":"10.3390\/e28010064","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T13:35:47Z","timestamp":1767620147000},"page":"64","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Perceiving Unpredictability for New Energy Power and Electricity Consumption Forecasting"],"prefix":"10.3390","volume":"28","author":[{"given":"Lin","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Economics and Technology of State Grid Liaoning Electric Power Co., Ltd., Shenyang 110006, China"}]},{"given":"Jian","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Economics and Technology of State Grid Liaoning Electric Power Co., Ltd., Shenyang 110006, China"}]},{"given":"Ruojing","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Economics and Technology of State Grid Liaoning Electric Power Co., Ltd., Shenyang 110006, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8317-8434","authenticated-orcid":false,"given":"Yifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Harbin Institute of Technology, Shenzhen 518055, China"}]},{"given":"Yichen","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Science, Harbin Institute of Technology, Shenzhen 518055, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1664-8613","authenticated-orcid":false,"given":"Yi","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Science, Harbin Institute of Technology, Shenzhen 518055, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, M., Yang, M., Chen, S., Li, H., Xing, G., and Li, S. (2025). FCP-Former: Enhancing Long-Term Multivariate Time Series Forecasting with Frequency Compensation. Sensors, 25.","DOI":"10.20944\/preprints202507.1980.v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"7050","DOI":"10.1109\/TII.2021.3056867","article-title":"A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation","volume":"17","author":"Xia","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1766","DOI":"10.1002\/er.7293","article-title":"Fastest-growing source prediction of US electricity production based on a novel hybrid model using wavelet transform","volume":"46","author":"Qiao","year":"2022","journal-title":"Int. J. Energy Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5726","DOI":"10.1109\/TIA.2021.3114129","article-title":"Forecasting Electricity Price in Different Time Horizons: An Application to the Italian Electricity Market","volume":"57","author":"Imani","year":"2021","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, H., Wang, H., Yu, M., Wang, Y., and Luo, Y. (2025). Long Short-Term Memory\u2013Model Predictive Control Speed Prediction-Based Double Deep Q-Network Energy Management for Hybrid Electric Vehicle to Enhanced Fuel Economy. Sensors, 25.","DOI":"10.3390\/s25092784"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Park, M.J., and Yang, H.S. (2024). Comparative Study of Time Series Analysis Algorithms Suitable for Short-Term Forecasting in Implementing Demand Response Based on AMI. Sensors, 24.","DOI":"10.20944\/preprints202409.1615.v1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1109\/TPWRS.2023.3301442","article-title":"An Interval Prediction Method for Day-Ahead Electricity Price in Wholesale Market Considering Weather Factors","volume":"39","author":"Lu","year":"2024","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Li, F., Wang, X., Bao, X., Wang, Z., and Li, R. (2024). Energy Management Strategy for Fuel Cell Vehicles Based on Online Driving Condition Recognition Using Dual-Model Predictive Control. Sensors, 24.","DOI":"10.3390\/s24237647"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pourbunthidkul, S., Pahaisuk, N., Laon, P., Houngkamhang, N., and Phasukkit, P. (2025). An Enhanced Cascaded Deep Learning Framework for Multi-Cell Voltage Forecasting and State of Charge Estimation in Electric Vehicle Batteries Using LSTM Networks. Sensors, 25.","DOI":"10.3390\/s25123788"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2822","DOI":"10.1109\/TSG.2022.3166791","article-title":"Electricity Price Prediction for Energy Storage System Arbitrage: A Decision-Focused Approach","volume":"13","author":"Sang","year":"2022","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kiouvrekis, Y., Givisis, I., Panagiotakopoulos, T., Tsilikas, I., Ploussi, A., Spyratou, E., and Efstathopoulos, E.P. (2025). A Comparative Analysis of Explainable Artificial Intelligence Models for Electric Field Strength Prediction over Eight European Cities. Sensors, 25.","DOI":"10.3390\/s25010053"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yan, J., Li, H., Bai, Y., Liu, J., Lv, H., and Bai, Y. (2025). Timestamp-Guided Knowledge Distillation for Robust Sensor-Based Time-Series Forecasting. Sensors, 25.","DOI":"10.3390\/s25154590"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1109\/TPWRS.2023.3235193","article-title":"Probabilistic Electricity Price Forecast with Optimal Prediction Interval","volume":"39","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Song, N., Chang-Silva, R., Lee, K., and Park, S. (2025). Dynamic Model Selection in a Hybrid Ensemble Framework for Robust Photovoltaic Power Forecasting. Sensors, 25.","DOI":"10.20944\/preprints202507.0775.v1"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2703","DOI":"10.1109\/TSG.2022.3166600","article-title":"A Transformer-Based Method of Multienergy Load Forecasting in Integrated Energy System","volume":"13","author":"Wang","year":"2022","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7023","DOI":"10.1109\/TII.2025.3574403","article-title":"Optimal Transport with Mamba for Multimodal Inertial Signal Enhancement","volume":"21","author":"Wang","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_17","unstructured":"Nie, Y., H. Nguyen, N., Sinthong, P., and Kalagnanam, J. (2023, January 1\u20135). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_18","unstructured":"Liu, Y., Hu, T., Zhang, H., 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 Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_19","unstructured":"Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J.Y., and Zhou, J. (2024, January 7\u201311). TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"12924","DOI":"10.1109\/TII.2024.3431018","article-title":"Wavelet Encoding Network for Inertial Signal Enhancement via Feature Supervision","volume":"20","author":"Wang","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2546","DOI":"10.1109\/TPWRS.2015.2468586","article-title":"ARIMA-Based Frequency-Decomposed Modeling of Wind Speed Time Series","volume":"31","author":"Yunus","year":"2016","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/TPWRS.2009.2033277","article-title":"ARIMA-Based Time Series Model of Stochastic Wind Power Generation","volume":"25","author":"Chen","year":"2010","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1109\/TPWRS.2011.2161780","article-title":"Short-Term Load Forecasting with Exponentially Weighted Methods","volume":"27","author":"Taylor","year":"2012","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/72.279188","article-title":"Recurrent neural networks and robust time series prediction","volume":"5","author":"Connor","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3409","DOI":"10.1109\/TSP.2004.837418","article-title":"Prediction of chaotic time series based on the recurrent predictor neural network","volume":"52","author":"Han","year":"2004","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1109\/TNNLS.2012.2198074","article-title":"Toward Automatic Time-Series Forecasting Using Neural Networks","volume":"23","author":"Yan","year":"2012","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.1109\/TASE.2021.3077537","article-title":"A Hybrid Prediction Method for Realistic Network Traffic with Temporal Convolutional Network and LSTM","volume":"19","author":"Bi","year":"2022","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2879","DOI":"10.1109\/TNNLS.2019.2934110","article-title":"Nonpooling Convolutional Neural Network Forecasting for Seasonal Time Series with Trends","volume":"31","author":"Liu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, H., Dong, Z., Jiang, R., Deng, J., Deng, J., Chen, Q., and Song, X. (2023, January 21\u201325). Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, New York, NY, USA. CIKM\u201923.","DOI":"10.1145\/3583780.3615160"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"110188","DOI":"10.1016\/j.ress.2024.110188","article-title":"A Bayesian adversarial probsparse Transformer model for long-term remaining useful life prediction","volume":"248","author":"Cheng","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_31","first-page":"22419","article-title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","volume":"Volume 34","author":"Ranzato","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_32","first-page":"27268","article-title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","volume":"Volume 162","author":"Chaudhuri","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"ref_33","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January May). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Vienna, Austria (Virtual)."},{"key":"ref_34","unstructured":"Zhang, Y., and Yan, J. (2023, January 1\u20135). Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhou, N., Zeng, H., and Zhou, J. (2024, January 12\u201314). DLinear-Based Prediction of the RUL of PEMFC. Proceedings of the 2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China.","DOI":"10.1109\/ICCECE61317.2024.10504160"},{"key":"ref_36","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., and Long, M. (2023, January 1\u20135). TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_37","unstructured":"Wang, H., Peng, J., Huang, F., Wang, J., Chen, J., and Xiao, Y. (2023, January 1\u20135). MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_38","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017, January 4\u20139). What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1016\/j.ijforecast.2019.07.001","article-title":"DeepAR: Probabilistic forecasting with autoregressive recurrent networks","volume":"36","author":"Salinas","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_40","first-page":"1050","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","volume":"Volume 48","author":"Balcan","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1038\/s41467-019-10105-3","article-title":"Inferring causation from time series in Earth system sciences","volume":"10","author":"Runge","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"126343","DOI":"10.1016\/j.apenergy.2025.126343","article-title":"Causal neural network for carbon prices probabilistic forecasting","volume":"397","author":"Han","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_43","unstructured":"Wang, Y., and Zhao, Y. (March, January 25). HEROS-GAN: Honed-Energy Regularized and Optimal Supervised GAN for Enhancing Accuracy and Range of Low-Cost Accelerometers. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_44","first-page":"021029","article-title":"Wave-Function Network Description and Kolmogorov Complexity of Quantum Many-Body Systems","volume":"14","author":"Schmitt","year":"2024","journal-title":"Phys. Rev. X"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"10309","DOI":"10.1007\/s11071-023-08392-z","article-title":"Multiscale three-dimensional Holo\u2013Hilbert spectral entropy: A novel complexity-based early fault feature representation method for rotating machinery","volume":"111","author":"Zheng","year":"2023","journal-title":"Nonlinear Dyn."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"103274","DOI":"10.1016\/j.inffus.2025.103274","article-title":"General pre-trained inertial signal feature extraction based on temporal memory fusion","volume":"123","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1038\/s41592-021-01331-z","article-title":"Spectral entropy outperforms MS\/MS dot product similarity for small-molecule compound identification","volume":"18","author":"Li","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. (2021, January 19\u201321). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Lai, G., Chang, W.C., Yang, Y., and Liu, H. (2018, January 8\u201312). Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks. Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA.","DOI":"10.1145\/3209978.3210006"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/64\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T13:43:30Z","timestamp":1767620610000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["e28010064"],"URL":"https:\/\/doi.org\/10.3390\/e28010064","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]}}}