摘要
为了提高智能电网中家域网的传输控制协议(TCP)性能,提出一种自适应速率控制方法,利用无线局域网(WLAN)技术的通信机制提高电力线通信(PLC)的链路利用率,采用启发式动态规划,通过神经网络训练估计瓶颈链路的容量,根据应用的长期服务质量调整TCP数据包的发送速率.仿真结果表明,该方法可以有效滤除PLC信道中冲击噪声的负面影响,其性能优于现有TCP的拥塞控制.
An adaptive rate control is proposed to improve Transmission Control Protocol(TCP) performance in the Home Area Networks(HANs) in smart grid. The proposed method exploits the communications mechanism of Wireless Local Area Network(WLAN) to improve the Power Line Communications(PLC) link utilization. The Heuristic Dynamic Programming(HDP) technique is employed to obtain the optimal rate control policy. The bottleneck link capacity is estimated by neural network training. The sending rate of TCP data packet is adapted according to the long-term quality of service(QOS) of applications. Simulation results illustrate that the proposed method effectively filters out the negative impact from the impulse noise in PLC channel and outperforms the existing TCP.
出处
《华南师范大学学报(自然科学版)》
CAS
北大核心
2017年第5期29-34,共6页
Journal of South China Normal University(Natural Science Edition)
基金
国家自然科学基金项目(61501127
61422201
61370159
U1201253)
广东省自然科学基金项目(2016A030313705
2014A030310347)
广东省应用型科技研发专项(2015B010129001)
广东省优秀青年教师培养计划项目(YQ2013057)
广州市珠江科技新星专项项目(2014J2200097)
关键词
智能电网
电力线通信
无线局域网
传输控制协议
速率控制
启发式动态规划
smart grid
power line communications
wireless local area network
transmission control protocol
rate control
heuristic dynamic programming