Research on an Optimization and Dispatch Decision-Making Model for Electricity Market Operation Based on Big Data

With the global energy transition and the development of smart grid technologies, electricity markets face multiple challenges including balancing supply and demand, optimal resource allocation, and economic dispatch. Simultaneously, the widespread deployment of smart meters, SCADA systems, and IoT devices has resulted in massive, heterogeneous, and high-frequency data that provide unprecedented information for real-time monitoring and dispatch decision-making in power systems. In this paper, we propose a multi-period economic dispatch optimization model based on big data analytics and solve the resulting convex quadratic programming problem using efficient convex optimization techniques. First, we analyze the characteristics of electricity market data and employ data cleaning, normalization, and principal component analysis (PCA) to extract key features. Then, by incorporating quadratic cost functions and operational constraints for each generating unit, we formulate an optimization problem aimed at minimizing the total generation cost while ensuring supply-demand balance over a 24-hour period. Simulation experiments on dispatch data from a regional power market demonstrate that the proposed method effectively accommodates demand fluctuations and allocates generation output optimally, thereby reducing overall operating costs. This research offers a novel approach for real-time dispatch decision-making in electricity markets and lays the foundation for further studies that incorporate uncertainties from renewable energy and energy storage systems.