Graph Convolutional Neural Network Assisted Genetic Algorithm for PDN Decap Optimization

• Main Authors: Manoharan, Haran, Juang, Jack, Zhang, Ling, Wang, Hanfeng, Pan, Jingnan, Qiu, Kelvin, Gao, Xu, Hwang, Chulsoon
• Format: Conference Proceeding
• Language: English
• Subjects: Convolutional neural networks; decap optimization; genetic algorithm; Genetic algorithms; graph convolutional neural network; Graph neural networks; Impedance; Libraries; Optimization; Prediction algorithms; Reinforcement learning; Training; Transfer learning
• ISSN: 2158-1118
• DOI: 10.1109/EMCSIPI49824.2024.10705608

This paper proposes a hybrid algorithm combining reinforcement learning (RL) and a genetic algorithm (GA) for PDN decap optimization. The trained RL agent uses a graph convolutional neural network as a policy network and predicts the decap solution for a given PDN impedance and target impedance, which is seeded as an initial population to the GA. The trained RL agent is scalable regarding the number of decap ports. The main goal is to save computation time and find the near global minimum or global minimum. Generalization of the algorithm to different decap libraries is achieved through transfer learning, eventually reducing the training time of the RL agent. The proposed algorithm finds a decap solution satisfying target impedance twice as fast compared with genetic algorithms.