Research on intelligent scheduling optimization and prediction model of wharf coal yard based on deep learning

As a key link of coal supply chain, the efficiency of dispatching management of wharf coal yard directly affects the operating cost and service level of the whole supply chain. The traditional scheduling method relies on manual experience, which has some problems such as low efficiency and waste of resources. In this study, an intelligent scheduling optimization and prediction model based on deep learning is proposed to solve the above problems. The model comprehensively considers factors such as time, cost and energy consumption through a multi-objective optimization model, and dynamically adjusts equipment allocation and operation sequence by using reinforcement learning (RL). At the same time, Long Short-Term Memory (LSTM) combined with attention mechanism is used to accurately predict coal inventory and equipment energy consumption, which provides data support for dispatching decision. The graph neural network (GNN) is used to model the complex dependence among equipment, operation and inventory in the coal yard, so as to realize the optimal allocation of global resources. The simulation analysis shows that the model is superior to the traditional methods in scheduling efficiency, inventory forecasting accuracy and energy cost control, and has obvious dynamic adaptability and robustness, which provides a new solution for intelligent management of wharf coal yard.