Abstract:

According to the problem that public buildings baseline load was hard to forecast effectively, a kind of artificial neutral network forecasting method based on Fuzzy C-Means (FCM) optimization preprocesses was proposed. The complicated historical data were   divided into a mixture of multiple populations, and each population was represented by a single forecasting model. This method could reduce ANN training data and overcame the disadvantage of very large data and slow processing speed. The forecasting result can have greater forecasting accuracy and effectively forecast  the public buildings baseline load compared with the standard BP neutral network.

Key words:  baseline load forecasting, demand response, FCM algorithm, artificial neutral network