Adaptive energy consumption scheduling with load uncertainty for the smart grid

In this paper, we propose a novel real-time energy consumption scheduling algorithm that takes into account load uncertainty to minimize the energy payment for each user. We formulate the problem of load scheduling as an optimization problem. To reduce the computational complexity, we devise an approximate dynamic programming approach to schedule the operation of appliances. In our problem formulation, we consider different sets of appliances including must-run and controllable. Unlike most of the existing demand side management algorithms that assume perfect knowledge of users´ energy needs, our design only requires knowledge of some estimates of the future demand. Simulation results confirm that the proposed energy scheduling algorithm can benefit both the users by reducing their energy expenses and the utility companies by improving the peak-to-average ratio in load demand.