Clustering-based Energy-aware Scheduling of Smart Residential Area

Abstract

Updating power system networks without changing the existing network facilities is done by modifying the consumer's energy demand curve using the Demand Response (DR) program. The increase in energy consumption, its environmental impact and limits in generation illustrates the importance of energy savings and alternate usage as Demand side management (DSM). Clustering methods provide proper planning and management of loads during the DR program. DR congestion of residential electrical loads scheduling is effectively managed by clustering of all the load curves in the smart residential area. The purpose of clustering the consumers is to understand the different energy behaviour better and identify the typical seasonal consumption patterns for the residential consumers, thereby creating a smart control strategy for the DR program. This work mainly focuses on applying load clustering method to reshape the load curve in the residential area during summer. The optimal scheduling of loads using this proposed method provide peak load management, Peak to Average Ratio (PAR) reduction, and the minimization of electricity cost of the consumer. The proposed seasonal clustering-based scheduling framework is solved using CPLEX solver.

Keywords

• clustering algorithms
• energy management
• load management
• meter reading
• smart grids