A Low-Carbon Economic Operation Optimization Method for Existing Park Integrated Energy Systems Based on Deep Learning and Grey Wolf Algorithm

Achieving optimal economic operation in park integrated energy systems relies crucially on the technology of multi-energy complementary and coordinated operation. However, in addressing the low-carbon economic dispatch problem of these systems, current technical methods fall short of fully accounting for the nonlinear factors present in the energy input, transformation, and output processes during the actual energy conversion within park integrated energy systems. As a result, these methods are insufficient for accurately optimizing and dispatching the low-carbon economic operation of existing park integrated energy systems. To address this deficiency, this paper proposes a low-carbon operation optimization method for park integrated energy systems based on deep learning and grey wolf optimization. This method uses a deep convolutional neural network to establish a deep regression model between the control strategies of various energy conversion devices in the park integrated energy system and the overall available power, heat, and cooling capacities. It then employs the grey wolf algorithm to optimize the control strategies of each device under the constraint of user load, with the goal of minimizing the sum of operation cost and carbon trading cost, thereby achieving low-carbon economic operation and optimization dispatch of existing park integrated energy systems.