Bus-level ultra-short-term net load interval prediction method and device

By employing the quantile regression method of convolutional long short-term memory deep neural networks, the accuracy problem of ultra-short-term interval prediction of bus-level net load was solved, enabling precise power grid dispatching and supporting risk early warning.

CN115983107BActive Publication Date: 2026-06-09GUANGDONG POWER GRID CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GUANGDONG POWER GRID CO LTD
Filing Date
2022-12-14
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately predict ultra-short-term periods of bus-level net load with a high proportion of renewable energy, leading to increased complexity in grid dispatching and insufficient risk warnings.

Method used

A convolutional long short-term memory deep neural network quantile regression method is adopted. By combining historical data of electrical load, photovoltaic power and wind power, a prediction feature set is constructed through preprocessing and downscaling. A quantile regression layer is added and an overall loss function is established to perform ultra-short-term interval prediction of bus-level net load.

Benefits of technology

It achieves accurate prediction of the net load probability range at the bus level, providing important data support for real-time risk warning and auxiliary decision-making in the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115983107B_ABST
    Figure CN115983107B_ABST
Patent Text Reader

Abstract

The application provides a bus-level ultra-short-term net load interval prediction method, device, equipment and storage medium, the method comprises the following steps: obtaining electric load historical data, photovoltaic power historical data and wind power historical data, and preprocessing the data; obtaining numerical weather prediction data, and performing downscaling processing on the time resolution thereof; constructing a prediction feature set based on the preprocessed historical data and the downscaling-processed numerical weather prediction data; constructing a deep neural network prediction model for electric load, photovoltaic power and wind power respectively; and calculating bus-level net load ultra-short-term interval prediction results according to obtained load ultra-short-term interval prediction results, photovoltaic power ultra-short-term interval prediction results and wind power ultra-short-term interval prediction results. The application can accurately predict the probability interval of bus-level net load, and can provide data support and important reference basis for real-time risk early warning and auxiliary decision-making of the power system.
Need to check novelty before this filing date? Find Prior Art