Application of Least Square Support Vector Machine in Electronic Engineering Based on Principal Component Analysis

摘要

Electronic engineering can be further broken down into electrical measuring, adjusting and electronic technology. This paper starts from the electrical measurement technique and presents a least square support vector machine model in electronic engineering based on principal component analysis. Principal component analysis can extract main components of the input variables data which have impact on the power load, and to a certain extent, it reduces the dimension of the input variables while eliminates the original input variables redundant information, making the extracted integrated factor represent the original variables better. At the same time selecting least squares support vector machine as load forecasting model that can better achieve the nonlinear curve fitting to improve the forecast accuracy, and improve generalization performance. Use the model as a grid short-term load forecasting model, and make a case analysis compared to other methods. The experimental result shows that the model has good predictive results, and it can be applied to electronic engineering of other regions and power price forecasting field.