Optimal Control of a Virtual Power Plant by Maximizing Conditional Value-at-Risk

This research acquired data from the Central Weather Bureau Observation Data Inquiry System (CODIS) for historical weather information, such as observation time, temperature, humidity, wind speed, global radiation, etc., and constructed a database by using Excel software. Least square support vector machine (LSSVM) was used to forecast speed solar radiation; then, power output of derived. Considering factors demand response load electricity pricing, maximized risk income model virtual plant (VPP) is established based on conditional value-at-risk (CVAR). An enhanced bacterial foraging algorithm (EBFA) proposed solve dispatch problem VPP in this paper. In an EBFA, stochastic weight trade-off embedded improve behavior pattern individual bacteria enhance their sorting efficiency accuracy high-dimension solution space. Various moving patterns EBFA were considered improvement, which demonstrated system Penghu island, Taiwan. Many scenarios created, including various seasons, rebate pricings, confidence levels, so maximal return could be simulated analyzed. Simulation tests show positive result perform maximizing income. paper also provides guideline handle management.