Research On Least Squares Support Vector Machine Power System Short-Term Load Forecasting |
Posted on:2007-01-27 | Degree:Master | Type:Thesis |
Country:China | Candidate:Y Q Yang | Full Text:PDF |
GTID:2132360185993116 | Subject:Power system and its automation |
Abstract/Summary: | PDF Full Text Request |
Short-term load forecasting is a very important task of power system. Accurate short-term load forecasting is meaningful for the economical, safe and credible operation of power system. With the development of power system, especially the development of electricity market, high accuracy forecasting method must be researched.This paper first researched the BP artificial neural network load forecasting model. The network is trained with Levenberg-Marquardt algorithm. Levenberg-Marquardt algorithm is a fast training algorithm for neural network. It is the best algorithm for the small and medium size network. But the weight is optimized by grads descend and the problem of local minima cannot be solved. The local minima problem is the main difficulty of accurate forecasting. And the problem makes the training result changes as the training process repeats. This makes it is hard to select the input vector and model with validating.The local minima problem is solved in support vector machine. So support vector machine is more robust and accurate for forecasting and it is considered to be the substitution of artificial neural network. In this paper least squares support vector machines is applied to forecast the load. Least squares support vector machine is an expansion of standard support vector machine. It is faster and easier to use. The...
|
Keywords/Search Tags: | Power System, Short Term Load Forecasting, Artificial Neural Network(ANN), Least Squares Support Vector Machine (LS-SVM), Bayesian Evidence Framework, Particle Swarm Optimization |
PDF Full Text Request |
Related items |