中文摘要：

提出一种基于动态指数平滑模型对网络流量负载进行预测的负载均衡协议DES-LBPTP（a Dynamic Exponential Smoothing Model-Based Load Balancing Protocol for Traffic Prediction in Ad Hoc Networks）.该协议以MAC层接口队列中分组长度为流量负载的衡量依据,利用动态指数平滑预测模型对节点的流量负载进行预测,根据预测到的下一时刻流量负载状况,在节点出现拥塞丢包之前,提前实施路由更新机制,避免中间节点拥塞,以此提高网络性能.此外,该协议在中间节点根据流量负载状况有选择地转发RREQ、在目的节点采用延时应答也在一定程度上改善了网络性能.仿真结果与AODV协议相比,端到端时延降低约50%,归一化开销改善28%,分组投递率最大增长10.4%.

英文摘要：

This paper propose a Dynamic Exponential Smoothing Model-Based Load Balancing Protocol for Traffic Prediction in Ad Hoc Networks.DES-LBPTP.By predicting the traffic load with dynamic exponential smoothing model according to the number of data packets in the interface queue of MAC layer,the nodes′ load state in the future can be determined earlier.Then the route-discovery mechanism prevent the forthcoming congestion,and the transfer reliability can be improved.In addition,the selectively transfer of RREQ on the basis of the load status and the delay response of destination node also improve the network performance to some extent.Simulation results proved that,in comparison with the traditional protocol,DES-LBPTP protocol can reduce the end-to-end delay by approximately 50% and the normalized routing overhead by 28%,while raising the delivery ratio by 10.4%.