Application of multi-agent in power term load forecasting

The mid-long term electric load forecasting provide essential data for the grid planning, it is helpful to optimize the planning of the power system. Solving the problem by the way of some agents´ cooperation is the focus of multi-agent systems theory and technology. It is more useful to do the forecasting by the multi-agent collaboration than individual agent do it independently. So that, in this paper introduces a multi-agent system diagnosis model. This model include three diagnosis-agents, a management-agent and fusion-agent. In this model the Diagnosis-agent are established according to the growth trend prediction technology, regression model and Grey forecasting techniques, which are three different kinds of load forecasting algorithm. Those diagnosis-agents are regulated and controlled by the Management-agent, which purpose to achieve the fault diagnosis in consultation under all diagnosis-agents. The fusion-agent will give the final load under the control situation which is from the Management-agent´s message, forecasting result which should be from all the Diagnosis-agents´ forecast result and numbers of different diagnosis-agent.