RNN based Energy Demand Prediction for Smart-Home in Smart-Grid Framework

in Smart-Grid Framework Md. Shirajum Munir, Sarder Fakhrul Abedin, Md. Golam Rabiul Alam, Do Hyeon Kim, Choong Seon Hong Department of Computer Science and Engineering, Kyung Hee University, South Korea. { munir, saab0015, robi, doma, cshong }@khu.ac.kr Abstract In modern development arena, smart grid and smart home are indispensable for intelligent technology toward the sustainable expansion of green technology and social progress. Therefore, smart home appliances, automated vehicles as well as the renewable energy sources e.g. solar, wind etc. are the key components of the smart home, which guarantees the quality life and well-being. To empower those appliances, smart home needs to provide seamless energy management through the smart grid. In such case, it becomes more challenging for managing energy demand response in the smart home through the smart grid. Therefore, in this research, we have focused on solving this problem by introducing intelligent energy predictor for smart home users. More precisely, we have modeled intelligent energy predictor using recurrent neuron network for smart home IoT network. Finally, we have simulated the result of the proposed intelligent predictor model which shows higher performance gain of the proposed approach with respect to prediction accuracy and convergence.