Least Squares Support Vector Machine Power Forecasting Method Based on Maximum Correlation Entropy Criterion

Abstract

The invention discloses a least squares support vector machine power prediction method based on the maximum correlation entropy criterion. The steps include: Step 1. Construct an input data set based on the power consumption in the same period of three years in history and the corresponding monthly average temperature, and use Least squares support vector machine method to build a forecasting model of electricity sales in the month to be tested; step 2, data preprocessing; step 3, normalize the input data set; step 4, for historical electricity consumption, small temperature samples Data, select the least squares support vector machine model to predict electricity sales; step 5, the key parameter σ of the model 0 and σ are optimized to determine the optimal parameters; step 6, the key parameter σ 0 Optimize with σ; step 7, select monthly relative error and annual average relative error as the evaluation index of the prediction result, and calculate the prediction accuracy at this time; step 8, make at least 3-5 predictions, and take the average value. The method of the invention can effectively predict electricity sales for users.

Description

technical field [0001] The invention belongs to the technical field of power system electricity sales forecasting, and relates to a least squares support vector machine power forecasting method based on the maximum correlation entropy criterion. [0002] technical background [0003] Since the long-term transaction contract power of the power system is the planned value, and the supply and demand of power are affected by many random factors, it is difficult to predict accurately. Therefore, the high-precision power sales forecasting method has very critical theoretical significance and engineering value. [0004] In the actual electricity sales forecasting scheme, the current electricity sales companies generally use the historical electricity consumption data collected on the user side as the forecast basis. However, due to the generally low reliability of these data, the structure of historical electricity consumption data on the user side is not neat enough, coupled with t...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a least squares support vector machine electricity forecasting method based on the maximum correlation entropy criterion, which solves the problem that the accuracy of the electricity sales forecast model is not high under the existing technical conditions, and it is difficult to meet the requirements of electricity sales transactions

Images