摘要
Most of current wireless packet scheduling algorithms aim at resource allocation as fairly as possible or maximizing throughput. This paper proposed a new packet scheduling algorithm that aims at satisfying delay requirement and is the improvement of earliest due first (EDF) algorithm in wired networks. The main idea is to classify the packets based on their delay bound, scheduling the most "urgent" class of user and the users that have the best channel condition with higher priority. This algorithm can easily integrate with common buffer management algorithms, when buffer management algorithm cannot accept new arrival packets, try to modify scheduling policy. Packet scheduling algorithms in multiple bottleneck wireless networks were also discussed. A new variable multi-hop factor was defined to estimate the congestion situation (including channel condition) of future hops. Multi-hop factor can be integrated into packet scheduling algorithms as assistant and supplement to improve its performance in multi-bottleneck wireless networks.
Most of current Wireless packet scheduling algorithms aim at resource allocation as fairly as possible or maximizing throughput. This paper proposed a new packet scheduling algorithm that aims at satisfying delay re- quirement and is the improvement of earliest due first （EDF） algorithm in wired networks. The main idea is to classify the packets based on their delay bound, scheduling the most ＂urgent＂ class of user and the users that have the best channel condition with higher priority. This algorithm can easily integrate with common buffer management algorithms, when buffer management algorithm cannot accept new arrival packets, try to modify scheduling policy. Packet scheduling algorithms in multiple bottleneck wireless networks were also discussed. A new variable multi-hop factor was defined to estimate the congestion situation （including channel condition） of future hops. Multi-hop factor can be integrated into packet scheduling algorithms as assistant and supplement to improve its performance in multi-bottleneck wireless networks.
