Optimal integration of distributed generation (DG) resources inrnunbalanced distribution system considering uncertainty modelling

摘要

The advancements in distributed generation (DG) technologies and growing concern for environmentalrnfriendly sources of energy necessitate an accurate analysis of distribution system with DG sources. The photovoltaicrn(PV) source is one of the most promising DG types that can be used for power generation at therndistribution level because of its abundance. The efficient operation of the distribution system after the interconnectionrnof DG sources is highly dependent on its integration to the distribution network. The uncertaintyrnassociated with the generation from the DG sources should also be considered while planning the integration.rnThis paper presents the optimal sizing of the PV sources in the unbalanced distribution network byrnReinforcement Learning, which is an efficient strategy for handling the stochastic data in practical situations.rnThe uncertainty associated with the power output from the PV source is included in the power flowrnas a variable with multiple states. Here, the beta probability density function is used to model the randomnessrnof the PV source. The seasonal variation in the power loss reduction obtained shows the effectivenessrnof the uncertainty model. The proposed algorithm is validated and tested for the Institute of Electrical andrnElectronics Engineers (IEEE) 13-bus and 37-bus distribution feeders, which shows its suitability forrnimplementation in a real system. Copyright © 2016 John Wiley & Sons, Ltd.