Electricity price prediction method and device, nonvolatile storage medium and electronic equipment

CN122175624APending Publication Date: 2026-06-09HUANENG CLEAN ENERGY RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUANENG CLEAN ENERGY RES INST
Filing Date
2024-12-09
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing electricity price forecasting methods consume a lot of computing resources, have long training times, and are difficult to scale up quickly and update forecast results rapidly.

Method used

A lightweight, low-parameter time-mixing-feature-mixing neural network model is adopted. By acquiring and preprocessing historical electricity price, meteorological, and boundary condition data, the temporal dependencies and interrelationships of the data are determined using the time-mixing module and the feature-mixing module, and electricity price prediction is performed.

Benefits of technology

Without sacrificing prediction accuracy, it significantly shortens model training time, improves prediction speed and efficiency, reduces resource consumption, and provides real-time electricity price prediction reference.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122175624A_ABST
    Figure CN122175624A_ABST
Patent Text Reader

Abstract

This application discloses an electricity price prediction method, apparatus, non-volatile storage medium, and electronic device. The method includes: acquiring an input dataset, which includes historical electricity price data, meteorological data, boundary condition data of the target power system, and time-series feature data; preprocessing the data in the input dataset; and processing the preprocessed input dataset using a prediction model to obtain the predicted electricity price for the target time period. The prediction model includes multiple mixing layers, each including a time mixing module and a feature mixing module. The time mixing module determines the temporal dependencies of the data input into the prediction model, and the feature mixing module determines the relationships between the data input into the prediction model. This application solves the technical problems of low prediction efficiency and slow result updates caused by the large amount of computational resources and long prediction training time required by existing prediction techniques.
Need to check novelty before this filing date? Find Prior Art