Simulation of Solar Phase Change Thermal Storage Distributed Energy System Based on Offshore Oil Platform

This study explores the design of a distributed energy system integrated with solar phase change thermal storage. Using MATLAB and Simulink, a mathematical model of the system was developed. Load demand was simulated using DeST software for a North Sea Oil Platform. A convolutional neural network (CNN) was employed for load forecasting, leveraging its effectiveness in analyzing time series data patterns. Suitable unit equipment was selected based on load simulations, and operations were conducted to evaluate load outputs and energy consumption changes across different seasons. The CNN demonstrated success in predicting cooling, heating, and power loads, aiding the platform in anticipating load fluctuations. Additionally, the solar phase change thermal storage system stores thermal energy during transitional seasons and poor weather, providing backup energy output. It also alleviates winter heat load pressure on the distributed energy system. Optimization strategies, including energy utilization rate evaluation and genetic algorithm applications, were employed to enhance system efficiency and maintain stable operation. The results improved energy management during typical daily operations across all seasons.