发明申请
- 专利标题: GRAPH NEURAL NETWORK AND REINFORCEMENT LEARNING TECHNIQUES FOR CONNECTION MANAGEMENT
-
申请号: US17561563申请日: 2021-12-23
-
公开(公告)号: US20220124543A1公开(公告)日: 2022-04-21
- 发明人: Oner ORHAN , Vasuki NARASIMHA SWAMY , Marcel NASSAR , Hosein NIKOPOUR , Shilpa TALWAR
- 申请人: Oner ORHAN , Vasuki NARASIMHA SWAMY , Marcel NASSAR , Hosein NIKOPOUR , Shilpa TALWAR
- 申请人地址: US CA San Jose; US CA San Francisco; US CA San Diego; US CA San Jose; US CA Santa Clara
- 专利权人: Oner ORHAN,Vasuki NARASIMHA SWAMY,Marcel NASSAR,Hosein NIKOPOUR,Shilpa TALWAR
- 当前专利权人: Oner ORHAN,Vasuki NARASIMHA SWAMY,Marcel NASSAR,Hosein NIKOPOUR,Shilpa TALWAR
- 当前专利权人地址: US CA San Jose; US CA San Francisco; US CA San Diego; US CA San Jose; US CA Santa Clara
- 主分类号: H04W28/02
- IPC分类号: H04W28/02 ; H04W24/02 ; H04W28/08 ; G06N3/08
摘要:
The present disclosure provides connection management techniques based on graph neural networks (GNN) and deep reinforcement learning (DRL) to optimize user association and load balancing. A graph structure of a communication network is considered for the GNN architecture and DRL is used to learn parameters of the GNN algorithm/model. Connection management is defined as a combinatorial graph optimization problem, and the DRL mechanism uses the underlying graph to learn weights of the GNN for an optimal user connections or associations. The connection management techniques can consider local network features to make better decisions to balance network traffic load while network throughput is also maximized. Implementations are provided based on edge computing frameworks include the Open RAN (O-RAN) architecture. Other embodiments may be described and/or claimed.