Renewable energy management in smart home environment via forecast embedded scheduling based on Recurrent Trend Predictive Neural Network

Smart home energy management systems help the distribution grid operate more efficiently and reliably, enable effective penetration of distributed renewable sources. These rely on robust forecasting, optimization, control/scheduling algorithms that can handle uncertain nature demand generation. This paper proposes an advanced ML algorithm, called Recurrent Trend Predictive Neural Network based Forecast Embedded Scheduling (rTPNN-FES), to provide efficient residential control. rTPNN-FES is a novel neural network architecture simultaneously forecasts generation schedules household appliances. By its embedded structure, eliminates utilization separate for forecasting scheduling generates schedule against errors. also evaluates performance proposed algorithm IoT-enabled smart home. The evaluation results reveal provides near-optimal $37.5$ times faster than optimization while outperforming state-of-the-art techniques.