Title :
Load forecasting model based on multi-agents cooperation
Author :
Pan, Guanyu ; Dou, Quansheng
Author_Institution :
Inst. of Math., Jilin Univ., Changchun, China
Abstract :
This paper proposed the electricity load Load Forecasting based on the multi-agent (Multi-Agents System MAS)coordination, and encapsulated different forecasting models into different Agents, by using communication between the Agents and the corporation mechanism , the forecasting problem can be solved, and cooperatively forecast based on the approximate day model, regression model, neural network model and rules revision model. The experiments showed that the cooperative forecasting model can get better forecasting precision, and the forecasting results are relatively stable, which is significant for the improvement of real load forecasting precision.
Keywords :
load distribution; load forecasting; multi-agent systems; neural nets; regression analysis; MAS; approximate day model; cooperative forecasting model; corporation mechanism; electricity load; load forecasting model; load forecasting precision; multiagent cooperation; multiagent coordination; multiagent system; neural network model; regression model; rules revision model; Accuracy; Data models; Forecasting; Load forecasting; Load modeling; Neural networks; Predictive models; Cooperation; MAS; load forecasting;
Conference_Titel :
Natural Computation (ICNC), 2012 Eighth International Conference on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4577-2130-4
DOI :
10.1109/ICNC.2012.6234721