Method and system for short-term load forecasting based on big data technology

Abstract

The invention discloses a short-term load forecasting method and system based on big data technology, comprising the following steps: acquiring historical data of electricity consumption of each user in the system; load level and load curve shape of each user; determining the electricity consumption mode of the user; According to the electricity consumption pattern of each user, the prediction model of each user's load is selected; a set of influencing factors of each user's load is constructed; a number of dominant influencing factors are screened out and given weights, and then a subset of influencing factors is constructed through each dominant influencing factor; The leading influencing factors and their weights are used to select and optimize the parameters of the prediction model of each user's load, and then predict the predicted value of each user's electricity load at the time to be predicted; And the system network loss, the predicted value of the total electricity load of the system at the time to be predicted is obtained, the method and the system can realize short-term load prediction, and the prediction accuracy is high.

Description

technical field [0001] The invention belongs to the field of electric power technology, and relates to a short-term load forecasting method and system, in particular to a short-term load forecasting method and system based on big data technology. Background technique [0002] For a long time, due to the low coverage of user information collection devices, the object of short-term load prediction is usually limited to the system load of the entire network. Scholars at home and abroad have done a lot of theoretical and method research work on this, and proposed a variety of different characteristics. Prediction methods such as time series method, artificial neural network method, expert system method and fuzzy neural network method, etc., the accuracy is continuously improved. [0003] However, because the system load is composed of multiple electricity loads, the changes of electricity loads vary widely. Different types of electricity loads have their own load characteristics...

AI Technical Summary

Problems solved by technology

[0003] However, since the system load is composed of multiple power loads, the changes of power loads vary greatly. Different types of power loads have their own load characteristics and load development rules. When superimposed, power loads will weaken or even offset some power loads. The regularity of system load changes becomes blurred, and it is difficult to accurately locate the real cause of load fluctuations; at the same time, due to the many factors affecting the load, and the characteristics of nonlinearity, complexity and hysteresis between them, in practical applications It is very difficult to establish a relationship model between system load and many influencing factors

Therefore, the accuracy of existing load forecasting is not high

Images