Supply Chain Scheduling Using Double Deep Time-Series Differential Neural Network

The purpose of supply chain scheduling is to be able find an optimized plan and strategy so as optimize the benefits entire chain. This paper proposes a method for processing tightly coordinated task problems based on improved Double Deep Timing Differential Neural Network (DDTDN) algorithm. Semi-Markov Decision Process (SMDP) modeling state characteristics action problem realized, transform into multi-stage decision problem. deep neural network model can help fit value function, unique reinforcement learning online evaluation mechanism realize selection best combination, it under condition only stator time. Finally, optimal group obtained.