Meta learning-based combined prediction method for time-varying nonlinear load of electrical power system

Abstract

The invention discloses a meta learning-based combined prediction method for a time-varying nonlinear load of an electrical power system. The method has the beneficial effects that (1) meta learning is a final result obtained by learning for a plurality of times on the basis of the learning result, and an output result of the previous layer of model and a characteristic attribute of a prediction sequence are utilized as input information of the next layer of learning, so that the previous learning can be fully applied to the later conclusion process, so that system deviation in the used learning algorithm can be found out and corrected and the learning accuracy is improved; (2) the optimal weight is obtained by setting the mean square error to the minimum and adjusting a gating network parameter through a decision condition in meta learning. Thus, important reference basis is provided for optimization and determination of the weight of the load combined prediction model.

Description

technical field [0001] The invention relates to a load forecasting method for an electric power system, and belongs to the technical field of electric power systems and automatic load forecasting thereof. Background technique [0002] Electric power is an important foundation of the national economy and a key and leading industry in the national economic development strategy. Load forecasting, as one of the key tasks of the power production sector, provides conditions for the normal operation of the power system. It plays a vital role in economically and rationally arranging the start and stop of the unit, reducing the spinning reserve capacity, optimizing the maintenance plan of the unit, reducing the cost of power generation, and improving economic benefits. Improving the prediction accuracy is the precondition for giving full play to the role of power system load forecasting, which has important practical significance. [0003] At present, the commonly used load forecast...

AI Technical Summary

Problems solved by technology

The above forecasting methods all use a single forecasting model, resulting in large forecast deviations in certain time periods

[0004] Due to the nonlinear, time-varying and uncertain characteristics of electric load, the mathematical models adopted by these single forecasting methods have limited applicability, and cannot estimate and adjust the parameters of the forecasting model in a timely and accurate manner, and it is not easy to describe the load. Sudden changes, so it has certain limitations, and it is difficult to obtain high prediction accuracy

Images