Partitional Clustering-Hybridized Neuro-Fuzzy Classification Evolved through Parallel Evolutionary Computing and Applied to Energy Decomposition for Demand-Side Management in a Smart Home

The key advantage of smart meters over rotating-disc is their ability to transmit electric energy consumption data power utilities’ remote centers. Besides enabling the automated collection consumers’ for billing purposes, gathered by and analyzed through Artificial Intelligence (AI) make realization consumer-centric use cases possible. A meter installed in a domestic sector an electrical grid used located at entry point household/building’s connection can gather composite/circuit-level data. However, it not able decompose its measured circuit-level into appliance-level consumption. In this research, we present AI model, neuro-fuzzy classifier integrated with partitional clustering metaheuristically optimized parallel-computing-accelerated evolutionary computing, that performs decomposition on residential demand-side management, where publicly available UK-DALE (UK Domestic Appliance-Level Electricity) dataset experimentally test presented model classify On/Off status monitored appliances. As shown effective providing consumers. Further, be provided industrial as well commercial