With the deepening of electric power market reform and the extension of direct power purchase for large consumers in China, more and more attention is paid to the credit risk in direct power purchasing. Combined with the characteristic of direct power purchase for large consumers, an operation environment and transaction behavior based trust evaluation model in direct power purchase for large consumers is designed in this paper. The model classifies the trust into operation environment trust and transaction trust, and the SVM (support vector machine) algorithm and feedback evaluation method are adopted respectively to evaluate them. Thus the evaluation result which is obtained from two parts by different methods is more objective and exact. In addition, the trust evaluation is applied to the selection of negotiation partner in this paper. And then a trust and game theory based negotiation flow for direct power purchasing is designed. In the flow the bidding strategy based on game theory is adopted. So it can be applied in automated negotiation system to provide assistant decision-making and technology supporting for users who take part in electric power direct purchasing. |