Reputation-based electricity scheduling scheme for complex network of user electricity consumption

Abstract

With the emergence of various high-powered electrical equipment, the demand for electric energy has increased rapidly. Subsequently, it has highlighted some issues of electricity consumption, such as the adjustment of electricity consumption peak. Although many electricity scheduling schemes have been proposed to adjust and control user load of electricity consumption, the current regulation of user load is not accurate and effective because the load regulation of different regional grid users is a complex network system. In this paper, we propose a reputation-based user electricity scheduling scheme for the complex network of user electricity consumption, whose purpose is to accurately adjust the electricity consumption of related users to further improve the adjustment of electricity consumption peak. In our scheme, we first model a complex network of user electricity consumption. Then we construct a reputation calculation method for electricity users, where the calculated reputation of users is one of the basis for assigning scheduling tasks to users and calculating the price subsidy received by users who complete the scheduling tasks. Further, we use the machine learning method to train a computation model to calculate the adjustment coefficients of electricity load, and then the electricity scheduling tasks are adjusted based on the calculated adjustment coefficients. Finally, the corresponding electricity scheduling tasks are assigned to the selected electricity users respectively for adjusting the electricity consumption of these users. Experiment results show the effectiveness of our proposed scheme. Our scheme can effectively calculate the reputation values of users based on their historical data, and the corresponding electricity scheduling tasks are effectively assigned to related users to accurately adjust the electricity consumption of these users according to their reputation values and the real-time adjustment coefficients, so as to efficiently improve the adjustment of electricity consumption peak.