Uncertainty aware optimal battery sizing for cloud energy storage in community microgrid.

Cloud energy storage systems (CES) are a new paradigm for the application of consumer-side energy storage in residential community microgrids. By transforming traditional consumers into self-sustaining and utility consumers, CES facilitates interaction between consumers and utilities as well as between consumers. Residential CES development is complicated by the flexible capacity of CES batteries and the uncertainty of supply. This paper recommends the CES system for residential prosumers. A machine learning-based uncertainty quantization and an artificial ecosystem optimization (AEO) method are used to determine optimal battery capacity considering PV, load, and price uncertainty. Compare this algorithm to the other four optimization algorithms to find out how well it works. The feasibility and profitability of deploying CES with residential PV are assessed. This problem minimizes the user's cost and maximizes the profit of the CES operator. The sensitivity analysis of CES is analyzed for various storage capacity penetrations. Further, optimal battery capacity determines the use of an AEO algorithm. Based on a PJM dataset of residential PV, load, and electricity price, simulation results demonstrate that the suggested framework integrated with a distributed PV system is more economical to DES. • Modeling of cloud energy storage. • Artificial intelligence based learning uncertainty quantification mechanism. • Proposed an optimization algorithm for optimal battery capacity for CES. • Dynamic price mechanism used to obtain optimal charging and discharging profile for better the utilization of CES. [ABSTRACT FROM AUTHOR]