Data-driven demand-side energy market management model based on the optimal closed loop dynamic energy price control

The increasing share of intermittent renewable energy resources makes maintaining supply–demand balance a critical challenge in modern electricity markets. To address this issue, this study proposes a data-driven demand-side market management framework that integrates an artificial neural network (ANN)-based price–demand model with a closed-loop dynamic energy price controller. The ANN model predicts market demand using electricity price and meteorological indicators, while a PID controller, whose parameters are tuned by the Marine Predators Algorithm (MPA), regulates the dynamic price to minimize energy imbalance. A multi-objective optimization function is formulated to simultaneously reduce supply–demand mismatch and prevent negative price occurrences, which can destabilize liberalized energy markets. The proposed scheme is tested on the Australian electricity market, and simulation results demonstrate that the integrated ANN–PID–MPA framework can govern demand variations and achieve optimal energy balancing. The findings confirm the potential of data-driven closed-loop price control as an effective demand-side management strategy for future smart grid environments.