Bi-level energy management model for the smart grid considering customer behavior in the wireless sensor network platform

Today, smart grids (SG) and its relationship to wireless sensor network (WSN) provides a suitable platform for establishing the two-way communication of the energy management system and network users. This issue can accurately plan the smart grid in real time with minimum cost. This paper proposes a bi-level energy manage-ment model for smart grids in uncertainty and demand-side management (DSM) in the Internet of things (IoT) platform based on WSN. In the upper level, for accurate planning in real-time and relationship with energy management system, the customers are modelled in wireless sensor network platform and clustered by fuzzy C -Means algorithm. Then, the energy consumption of the network sensors in the IoT platform is optimized by the genetic algorithm (GA). Moreover, the customer behavior optimization was performed utilizing the price-based demand response (PBDR) model and transferring demand load from the peak to the valley load times. The objective functions in the lower layer minimized the emission pollution, operation costs and energy not supplied (ENS) index using the multi-objective Moth-Flame optimization (MOMFO) algorithm. The Monte Carlo tech-nique is used for modeling renewable energy sources (RES)'s uncertain output. Finally, the suggested approach is confirmed through the analysis of a case study. The proposed model's capability in planning a uniform smart grid operation is demonstrated by simulation study and comparison with multi-objective particle swarm optimization (MOPSO), epsilon-constraint and benders techniques.