Short-term generalized load prediction method based on transfer learning

Abstract

The invention discloses a short-term generalized load prediction method based on transfer learning, and the method comprises the following steps: constructing a short-term load prediction integrated model, and carrying out the analysis of a prediction error of the short-term load prediction model; solving the weight by using an algorithm based on iteration and cross validation; constructing a short-term load prediction model based on load time series decomposition and instance migration; based on the hidden variable model, constructing a public model for the target problem and the source problem; and designing a hidden variable extraction module based on the load affine curve. According to the method, the target of transfer learning is introduced into the short-term load prediction problem, the similarity between the source problem and the target problem is ingeniously utilized, the source problem data set is introduced to assist the training process of the target problem, and the target of improving the prediction effect of the target problem can be achieved; the prediction precision can be improved by utilizing the hidden variable model; through a hidden variable extraction module designed based on a load affine curve and based on the hypothesis, the calculation complexity can be reduced.

Description

technical field [0001] The invention relates to the technical field of power grids, in particular to a short-term generalized load forecasting method based on transfer learning. Background technique [0002] Power system short-term load forecasting is an important daily work of the power system dispatching operation department. The level of forecasting accuracy directly affects the safety, economy and power supply quality of power system operation. According to the theory of statistics, the accuracy of model prediction and the amount of data satisfy the relationship of -1 / 2 power, which means that the amount of data plays an important role in improving the accuracy of the load forecasting model and is an important driving force for improving the accuracy of load forecasting; [0003] However, in actual situations, lack of data is a very common phenomenon, which limits the improvement of load forecasting accuracy. For example: (1) When the power consumption scene changes (suc...

AI Technical Summary

Problems solved by technology

[0003] However, in actual situations, lack of data is a very common phenomenon, which limits the improvement of load forecasting accuracy. For example: (1) When the power consumption scene changes (such as electricity price adjustment), the load characteristics may change Big change

At this time, the load forecasting problem in the new scenario has not yet accumulated enough training data, and the load data in the original scenario contains a lot of useful information; (2) When a new user appears, there is a lack of historical load data of the new user in the power system , directly using a small amount of data to train the prediction model will lead to poor prediction results; (3) In addition, generalized new loads such as renewable energy, electric vehicles, and active loads are in the stage of rapid development, and it is difficult to obtain sufficient historical data. How to solve the problem of data The problem of high-precision generalized load forecasting under the lack of conditions is the key point, therefore, the present invention proposes a short-term generalized load forecasting method based on transfer learning to solve the deficiencies in the prior art

Images