Clustering and trend index-based power distribution network line load prediction method and device

Abstract

The invention discloses a clustering and trend index-based power distribution network line load prediction method and device. The method comprises the steps of obtaining and cleaning load historical time sequence data of each transformer area in a power distribution network; dividing all courts into a plurality of clustering clusters through clustering according to the load historical data set, summing and reconstructing the load historical data set of each clustering cluster, and obtaining a plurality of load samples day by day; acquiring holiday information corresponding to each load sample,and calculating a load change trend index in the same period of the last year; training a corresponding long-term and short-term memory neural network load prediction model by using the load sample,holiday information and load change trend index of each clustering cluster; and predicting corresponding load data by using each type of trained load prediction model, and finally superposing prediction results of each type of load to obtain a prediction result of the total load of the power distribution network line. The method and device can improve the short-term load prediction precision of the power distribution network, so as to achieve the purpose of guiding the dispatching operation of the power distribution network.

Description

technical field [0001] The invention relates to the technical field of distribution network load analysis and prediction, in particular to a long-short-term memory neural network distribution network line load prediction method based on clustering and trend indicators. Background technique [0002] The short-term load forecasting of the distribution network is an important technology for the economical and efficient operation of the distribution network. The short-term load forecasting is mainly based on the historical operation data of the distribution network, external weather, time and other holidays, etc., to mine the law and influencing factors of the load change of the distribution network. Infer the change trend of load in a short period of time in the future. Accurately predicting the short-term load of the distribution network is of great significance for reducing the cost of power generation and improving the level of refined operation and management of the distrib...

AI Technical Summary

Problems solved by technology

[0005] However, the current research on short-term load forecasting still has deficiencies in the following aspects: 1) Because the main users of different station areas will affect the load characteristics of the station area, the load characteristics of the special transformer and public transformer stations are quite different, and have their own characteristics. Therefore, the direct load forecasting of distribution lines is to directly forecast the mixed load data, and it is impossible to mine the power consumption characteristics of different station areas, resulting in insufficient accuracy of line load forecasting; 2) The power load has obvious differences in different seasons. In addition, holidays and production and life plan arrangements will also affect the variation of load in different periods to varying degrees

Usually, short-term load forecasting mainly considers the influence of temperature and holiday factors. It is usually forecasted by feature extraction or only by inputting the historical data of the latest period. It does not make full use of the historical data of the same period of load, and lacks in-depth analysis on the trend of load changes. It cannot be fully explored. The changing law of load in different time periods; 3) With the deepening of intelligent distribution network, equipment can collect and store massive distribution network data. Load data is a kind of time series data, and ordinary machine learning algorithms do not consider it in the regression prediction process. The time series characteristics of the load cannot transmit the effective information of the time series, which affects the load prediction effect and generalization performance of the model to a certain extent. It is necessary to use a prediction model suitable for load time series data to further improve the prediction accuracy

Images