Risk Based Day-ahead Energy Resource Management with Renewables via Computational Intelligence

An indeterminate and variable nature of renewable energy sources like solar photovoltaic, wind power, load consumption, electric vehicles trips and market spot prices, make the operation and control of energy management system quite complex. Also, it is expected that the system should be consistent and resilient in case of extreme events like faults, hurricanes etc. This paper has used the risk based optimization strategies considering uncertainty of aforementioned parameters to minimize the operational cost of the aggregator. A 13-bus practical distribution system with 15-scenarios (03-scenarios as extreme events with high impact) are considered as a test system. WCCI-2018 award winning, Enhanced Velocity Differential Evolutionary Particle Swarm Optimization (EVDEPSO) computational intelligence method has been used to solve this problem.