Real-time power load forecasting method based on integrated network of incremental transfinite vector regression machine

Abstract

The present invention discloses a real-time power load forecasting method based on an integrated network of an incremental transfinite vector regression machine, comprising an online learning stage and an online load forecasting stage. The online learning stage comprises the following steps: acquiring a first batch of power load data and influence factor data in real time, and normalizing the data; initializing an II-ESVR model; and acquiring a (k+1)th (k is not less than 1) batch of power load data and influence factor data in real time, normalizing the data, and performing incremental learning and training. The online load forecasting stage comprises the following steps: acquiring data of a batch of related influence factors in real time, normalizing the data and using the data as an input of the model; and calculating forecasting results based on the II-ESVR model and parameters of the learning stage in real time. According to the present invention, the real-time power load forecasting method based on the integrated network of the incremental transfinite vector regression machine solves the problem of instability caused by the diversity of the data, has the characteristics of "fastness, stability and accuracy", and can meet the requirements of future development of power load forecasting.

Description

Technical field: [0001] The invention relates to the technical field of power load forecasting, in particular to a real-time power load forecasting method based on an incremental overlimit vector regression machine integrated network. Background technique: [0002] Most of the existing power load forecasting systems are batch offline forecasting systems. The main method is that the system collects historical data within a certain period of time, and predicts the law of power load generation by modeling the static historical data. This batch offline forecasting method requires the system to be able to store a large amount of historical load data, which will put a huge pressure on the computing overhead and storage space of the system. [0003] With the development of the power market, power load forecasting plays a vital role in power system dispatching, power consumption planning, and planning. The importance of power load forecasting is becoming increasingly apparent, and t...

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is that when dealing with large-scale power system load data, on the basis of the existing over-limit vector regression machine method, combined with incremental learning and integrated learning ideas, a method based on incremental over-limit vector regression is proposed. The real-time power load forecasting model of the regression machine IncrementalESVR (IESVR), by further constructing an integrated network model IntegratedIncrementalESVR (II-ESVR) to solve the problem of instability of a single IESVR model caused by the diversity of power load data

Images