[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3583133.3596429acmconferencesArticle/Chapter ViewAbstractPublication PagesgeccoConference Proceedingsconference-collections
abstract

Evolutionary configuration of the Temporal Convolutional Network for the electricity price prediction

Published: 24 July 2023 Publication History

Abstract

Using a case study of forecasting the recent, volatile electricity price from the Polish day-ahead market, the paper compares two different approaches to finding Temporal Convolutional Network configurations of high performance. First, the CMA-ES[1] was evaluated, and later, the MoTPE[4] was examined. For the same 24-h price forecast task and using the same training and test sets, the first, evolutionary approach resulted in both better prediction performance and, more importantly, significantly shorter computation time. The search through 103 different hyperparameter combinations was completed in less than an hour, and the short-period evaluation resulted in sMAPE of 12.9 and rMAE of 0.31.

References

[1]
Y Akimoto and N Hansen. 2022. CMA-ES and Advanced Adaptation Mechanisms (GECCO '22). ACM.
[2]
Yitian C et al. 2020. Probabilistic forecasting with temporal convolutional neural network. Neurocomputing (2020).
[3]
K Olivares et al. 2023. Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx. Int. J. of Forec. 39 (2023).
[4]
Y Ozaki et al. 2020. Multiobjective Tree-Structured Parzen Estimator for Computationally Expensive Optimization Problems (GECCO '20). ACM.

Cited By

View all
  • (2024)Coupling Temporal Convolutional Networks with Anomaly Detection and CMA-ES for the Electricity Price ForecastingProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3664098(105-106)Online publication date: 14-Jul-2024

Index Terms

  1. Evolutionary configuration of the Temporal Convolutional Network for the electricity price prediction

    Recommendations

    Comments

    Please enable JavaScript to view thecomments powered by Disqus.

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation
    July 2023
    2519 pages
    ISBN:9798400701207
    DOI:10.1145/3583133
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 24 July 2023

    Check for updates

    Author Tags

    1. hyper-parameter optimization
    2. deep learning
    3. temporal convolutional network
    4. CMA-ES
    5. electricity price forecasting

    Qualifiers

    • Abstract

    Conference

    GECCO '23 Companion
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)11
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 01 Jan 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Coupling Temporal Convolutional Networks with Anomaly Detection and CMA-ES for the Electricity Price ForecastingProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3638530.3664098(105-106)Online publication date: 14-Jul-2024

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media