-
公开(公告)号：US20220124543A1
公开(公告)日：2022-04-21
申请号：US17561563
申请日：2021-12-23
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.
-
公开(公告)号：US20240064716A1
公开(公告)日：2024-02-22
申请号：US18498701
申请日：2023-10-31
申请人： Minyoung PARK , Wei MAO , Laurent CARIOU , Ehud RESHEF , Danny ALEXANDER , Daniel BRAVO , Chen KOJOKARO , Hosein NIKOPOUR
发明人： Minyoung PARK , Wei MAO , Laurent CARIOU , Ehud RESHEF , Danny ALEXANDER , Daniel BRAVO , Chen KOJOKARO , Hosein NIKOPOUR
IPC分类号： H04W72/0446 , H04L5/00 , H04W74/08
CPC分类号： H04W72/0446 , H04L5/0053 , H04W74/0816
摘要： This disclosure describes systems, methods, and devices related to enhanced transmission. A device may generate an aggregated medium access control protocol data unit (A-MPDU) frame, wherein the A-MPDU is associated with transmission of n Network Coding (NC) encoded frames. The device may divide the A-MPDU frame into k data frames and (n−k) parity frames within the A-MPDU frame. The device may transmit the k data frames. The device may transmit to a station device (STA) at least one of the (n−k) parity frames separately after the data frames in response to packet drops in the k data frames.
-
搜索结果
2 条记录 (耗时 0.02 秒)
