Sub-sampling SVR integration-based short-term power load prediction method

Abstract

The invention belongs to the technical field of rapid analysis of computer data, and discloses a sub-sampling SVR integration-based short-term power load prediction method; a sub-sampling support vector regression integration method is adopted, and a sub-sampling strategy is executed for realizing parallel learning of a support vector machine, so that it is guaranteed that each single SVR has enough diversity, and the loss amount of information is reduced; and a new group optimization learning algorithm based on single SVR integration is selected, so that it is guaranteed that each SVR integration has enough strength to predict short-term load data. The small-size sub-sampling-based integration method has the classical U-statistical magnitude statistics reasoning property, and by virtue ofintroduction of a small-scale sub-sampling strategy, so that the complexity of an estimator is effectively reduced; and meanwhile, the calculation precision and efficiency are improved, and a relatively high confidence interval is returned. An SSVRE mode is easily transplanted into a parallel computing framework.

Description

technical field [0001] The invention belongs to the technical field of rapid analysis of computer data, in particular to a short-term power load forecasting method (SSVRE) based on sub-sampling SVR integration. Background technique [0002] Short-term power load forecasting (STLF) plays a vital role in power operation, and the problem of short-term load forecasting (such as half-hour power load) will generate a large amount of data in real time; therefore, it can quickly process data and give a reasonable point estimate forecast Estimating and confidence intervals is a major challenge for power companies. At present, the commonly used prior art in the industry is as follows: Existing art Che J, Wang J, Tang Y. Optimal training subset in a support vector regression electric load forecasting model. Applied Soft Computing 2012, 12(5):1523-1531 .Based on the VC dimension theory and "kernel" technology, the SVR model is indirectly transformed into a multiple linear regression pr...

AI Technical Summary

Problems solved by technology

[0003] To sum up, the problems existing in the prior art are: the connection between the parameter setting and the training subset method is not considered, the model with the U-statistic property is not established and its statistical properties are derived, and the point estimation cannot be returned. Confidence Intervals and Confidence Levels

However, the power forecasting system based on point estimation will be limited by its own uncertainty and low confidence level, and the establishment of the SVR model involves a relatively large amount of data, high computational complexity, and general accuracy

Images