The Forecasting Research Of Electric Power Load For Changzhi Power Marketing

Electricity is very important for the national economy with the marketing of the electrical enterprises becomes faster and faster. Electrical business is running into a high speed development stage. The electric power is changing from seller to buyer .In this situation, the traditional management system and the traditional management can't meet the current needs. Therefore, power load forecastiong is an important part of power sales decision support system and it plays an important role in power sales decision making.Electric load has both regularity and randomicity. Load of next period has close relation to historical load, current operation status, meteorologic factor of forecasting period and date type, in which there are a lot of linear and non-linear relations. This paper analyzes the factor of the changes , and studies the existing methods of load forecasting. Sudied on the BP neural network model of the structure, algorithm and BP neural network for electric load forecasting problems. Established the model for the electricity load forecasting in Changzhi BP neural network model with the power load this area's CharacteristicsIntroduced the concept of fuzzy sets in the Changzhi BP neural network model, and established the model for the electricity load forecasting in Changzhi fuzzy neural network model which is appropriate for Changzhi. At the same time, we get the parameters of the network model. Then test the daily load forecast simulation of the BP neural network model and fuzzy neural network model.The Changzhi area data is used to simulate electric load data validation, and analysis of the absolute prediction error and relative error. The results showed that the two models can be good short-term forecasting of electric load. The relative error is smaller and high accuracy. We can see the fuzzy neural network prediction results were better than BP neural network, this model can be used to power load Short-term forecast data.