Load day-ahead prediction correction method and device based on error correction and storage medium

Abstract

The invention discloses a load day-ahead prediction correction method and device based on error correction and a storage medium, and the method comprises the following steps: 1, building a day-ahead prediction model based on historical load and historical meteorological data; 2, obtaining a prediction result of a to-be-predicted day based on the day-ahead prediction model, storing the prediction result of the to-be-predicted day and the actual load data of the to-be-predicted day, and accumulating multiple groups of prediction results of the to-be-predicted day and the corresponding actual load data; 3, setting key parameters of a correction algorithm by using the prediction results of the multiple groups of days to be predicted and the corresponding actual load data and adopting a particle swarm algorithm; and 4, in a correction time period of the day to be predicted, regularly checking whether a correction condition is satisfied based on a day-ahead predicted load value, an actual load value and a correction starting deviation threshold value Door, starting correction when the correction condition is satisfied, and correcting a day-ahead predicted result of the day through a correction algorithm to realize optimal economic operation of the microgrid.

Description

technical field [0001] The invention belongs to the field of power load forecasting, and in particular relates to a method, device and storage medium for a day-ahead load forecasting correction based on error correction. Background technique [0002] Power load forecasting is an important basis for ensuring the stable and economical operation of the power system. Load forecasting in different time spans has different application purposes to the power grid. Among them, accurate short-term load forecasting results can help power system staff to formulate reasonable production plans, maintain supply and demand balance and ensure grid security, while reducing resource waste and electricity costs. Load levels are affected by day type, weather, climate, special events, etc. Load forecasting techniques can be divided into statistical methods and artificial intelligence methods. Artificial neural network is a soft computing technology that does not require forecasters to explicitl...

AI Technical Summary

Problems solved by technology

Some work has focused on the day-ahead prediction of microgrid building load consumption, and there is no corrective algorithm that can make timely feedback and adjustments based on the actual load on the day

This leads to the fact that the previously proposed day-ahead load forecasting algorithm either requires a large amount of information input and is difficult to obtain, and is not practical; or the forecasting accuracy is not good and cannot cope with sudden load increases.

Images