Time sequence prediction method and system based on period-trend-residual decomposition

By explicitly extracting the periodic, trend, and residual components of power load through a period-trend-residual decomposition architecture, the problem of high computational complexity in existing models is solved, achieving lightweight and high-precision time series forecasting, which is suitable for edge devices and ultra-long sequence scenarios.

CN121502220APending Publication Date: 2026-02-10QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
0 Cites 1 Cited by

Patent Information

Application Number
CN202511684278.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-17
Publication Date
2026-02-10

AI Technical Summary

Technical Problem

Existing time series forecasting models have high computational complexity and a large number of parameters in power load forecasting, making them difficult to deploy on edge devices. Furthermore, their practicality is limited in ultra-long series forecasting scenarios. They also lack explicit modeling of the internal structure of power load, making it difficult to balance forecasting accuracy and computational efficiency.

Method used

The system adopts a period-trend-residual decomposition architecture. Through a cyclic period generation module, an adaptive weighted multi-scale moving average module, and a residual perception module, it explicitly extracts the period, trend, and residual components of the time series and performs collaborative modeling and summation reconstruction.

Benefits of technology

It achieves lightweight time series forecasting, reduces the number of model parameters and computational complexity, improves forecast accuracy and robustness, is suitable for deployment on edge devices, and maintains high efficiency and scalability in ultra-long sequence scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a time series prediction method and system based on period-trend-residual decomposition, and relates to the technical field of time series data processing, and the method comprises the steps: obtaining time series data, inputting the time series data to a cycle period generation module for processing, and explicitly extracting and outputting a periodic component corresponding to a global periodic mode; inputting the time sequence data into an adaptive weighted multi-scale moving average module in parallel for processing so as to extract and output trend components corresponding to a sequence evolution trend under different time granularities; calculating and outputting a residual component representing high-frequency fluctuation and random disturbance through a residual sensing module based on the time sequence data, the periodic component and the trend component; and performing addition reconstruction on the periodic component, the trend component and the residual component to obtain a prediction result in a specific time range in the future. According to the invention, through the explicit decomposition and lightweight module, high prediction precision is ensured, the calculation complexity of the model is significantly reduced, and the lightweight of the model is realized.
Need to check novelty before this filing date? Find Prior Art