mlsanityData to 14 Oct 2026

PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting

arXiv 2605.21550 ↗First posted 20 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Electricity load peak forecasting (ELPF), simultaneously predicting peak timing and intensity, is a prerequisite for effective grid scheduling and risk management. However, existing methods face three limitations. First, they adopt a two-stage predict-then-locate paradigm, which severs the link between temporal localization and intensity regression. Second, they still struggle with the multi-scale representation conflict, leading to peak misjudgment and timing misalignment. Third, the lack of explicit peak timing context during intensity regression causes intensity smoothing because predictions are dominated by global smoothing trends. To address these limitations, we propose PeakFocus, a unified framework for ELPF. (i) A Unified Peak-Aware Pipeline (UPAP) utilizes a triple hybrid loss to jointly supervise temporal localization and intensity regression, alongside a tolerance-based evaluation protocol. (ii) A Multi-Scale Mixing Peak Locator (MSM-PL) exploits coarse-grained features to mitigate peak misjudgment caused by local fluctuations, and injects them into fine-grained features via a cascade mechanism to resolve timing misalignment. (iii) A Location-Aware Decoder (LAD) injects peak timing context into the intensity regression process, providing explicit guidance to counteract intensity smoothing and improve peak intensity estimation. Extensive experiments on the public Electricity (ELC) dataset and our industrial-scale World Large-scale Electricity Load (WLEL) dataset show that PeakFocus outperforms baselines in both timing precision and intensity estimation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

31 of 42 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  11. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  12. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
19 more
  1. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  2. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  3. 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
  4. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  5. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 106
  6. 2025TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecastingcited by 64
  7. 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
  8. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 55
  9. 2024On the Role of Attention Masks and LayerNorm in Transformerscited by 48
  10. 2022Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecastingcited by 42
  11. 2024A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Datacited by 39
  12. 2024Adaptive Multi-Scale Decomposition Framework for Time Series Forecastingcited by 34
  13. 2024Unlocking the Power of LSTM for Long Term Time Series Forecastingcited by 29
  14. 2025Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillationcited by 20
  15. 2022Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Versioncited by 19
  16. 2021Daily peak electrical load forecasting with a multi-resolution approachcited by 4
  17. 2021Electrical peak demand forecasting- A reviewcited by 3
  18. 2023Unlocking the Potential of Deep Learning in Peak-Hour Series Forecastingcited by 3
  19. 2025MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecastingcited by 2

Built on by

Not cited yet.