Intelligent Price Optimization in Smart Distribution Networks: A Risk-Sensitive Cheetah Hunter Optimization Algorithm for Distribution Locational Marginal Price Assessment

Distribution locational marginal pricing (DLMP) is an efficient approach to optimize the pricing of distribution systems. This paper focuses on DLMP to minimize losses within the distribution network. This approach can be strategically manipulated to adjust the profits for distributed generation (DG) owners and the distribution company. Furthermore, the paper employs the information gap decision theory (IGDT) method scenarios to model the uncertainty surrounding electricity market prices. By incorporating the risk-averse (RA) scenario, network operators can discern RA solutions and optimal outcomes derived from the algorithm. On the other hand, the risk-tolerance (RT) scenario helps identify riskier solutions, enabling appropriate decision-making based on whether the solutions are RA or risky in nature. To further enhance the quality of outcomes, this paper combines IGDT scenarios with the cheetah hunter optimization (CHO) algorithm to ensure the obtained results are both optimal and accurate. The proposed method’s performance is evaluated through simulations conducted on a 69-bus IEEE power network using the MATLAB software environment. The results obtained from this approach demonstrate its superior accuracy when compared to previous methodologies.