Abstract Independent investors can install distributed generations (DGs) in power networks as long as they follow the systems’ rules and frameworks. Logically, they try to maximize their profits, and network… Click to show full abstract
Abstract Independent investors can install distributed generations (DGs) in power networks as long as they follow the systems’ rules and frameworks. Logically, they try to maximize their profits, and network owners/operators usually cannot directly control their decisions regarding the DG location and size. However, there are inherent interactions between their decisions and the systems’ technical and economic characteristics. In this paper, a new approach is presented for optimal DG placement and sizing from the standpoint of independent investors, with specific consideration given to interactions with pool-based electricity markets. The proposed approach is founded on the innovative combination of the meta-heuristic optimization model and the reinforcement learning-based market simulation strategy. This approach is implemented using the particle swarm optimization algorithm and the Q-learning technique, and it is comprehensively examined in the IEEE 30-bus system with consideration for different pricing rules and DG types. The results confirm that there are significant interdependencies between the optimal decision of DG investors and the strategic bidding behavior of market players. Also, they indicate that the proposed approach is useful for independent investors in identifying the most valuable DG location and size as well as for the systems’ policy-makers in investigating the long-term effects of specific rules.
               
Click one of the above tabs to view related content.