Self consumption and user comfort are two important metrics to evaluate efficiency and quality-of-service (QoS) of an energy management technique in stand-alone distributed photovoltaic (PV) systems. Prior work focuses on a joint problem of maximizing the two metrics, however, every user demand is variable and uncertain, and PV output power is highly vulnerable to weather variations. In consequence, the joint problem has non linearities at a given instant, on a given day and in a given weather condition. The extent of these non linearities increases with the consideration of high temporal resolution. If these non linearities are well addressed, would lead to significant improvement in system efficiency and user QoS. In this paper, we propose an artificial neural network (ANN) based technique to solve the joint optimization problem with inherent non linearities. Our proposed technique is scalable to user tasks, and adaptable to temporal resolution and the non linearities. Simulation results validate effectiveness of the proposed technique in terms of the selected performance metrics.
|Title of host publication||2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)|
|Publication status||Published - Oct 2018|