基于补偿式CSI的分布式跨层联合资源分配算法

Distributed cross layer joint resource allocation algorithm based on compensation CSI

为消除过时信道状态信息(CSI)对分布式无线多跳网络环境下跨层资源分配效率的影响,提高跨层联合资源分配的准确性,基于信道相关性提出了一种补偿式跨层联合资源分配算法.利用瞬时和过时信道状态信息之间的条件概率密度函数,基于瑞利衰落信道模型求得输出信号对干扰加噪声之比(SINR)模型下条件容量的闭式解。为补偿部分网络性能的损失,提出了一种考虑过时信道状态信息的联合拥塞控制、信道分配和功率控制的算法,在此过程中网络被建模成一个网络效用最优化(NUM)问题,可变的链路数据率和功率等资源限制作为约束条件。运用拉格朗日对偶分解技术,分布式求解NUM问题。实验对比分析表明:在确保较低复杂度的前提下,该算法有效改善了分布式多跳网络资源分配的合理性,使其网络总体效用得到提升,降低了能耗。

In order to eliminate the effect of outdated channel state information（CSI） on cross layer resource allocation efficiency in distributed wireless multi-hop network environment, and improve the accuracy of cross layer joint resource allocation, a compensation cross layer joint resource allocation algorithm based on channel correlation is proposed. The conditional probability density function between the instantaneous and outdated channel state information is adopted, and the closed solution of the conditional capacity under the condition of signal to interference plus Noise Ratio（SINR） is obtained based on Rayleigh fading channel model. In order to compensate for the partial network performance loss, a joint congestion control, channel allocation and power control algorithm considering the outdated state information is proposed. In the process the network is modeled as a Networkunility Maximization （NUM） problem, and the variable link data rate and power resource constraints are used as constraints. By using Lagrange dual decomposition technique, the NUM problem is solved by distributed solution. Experimental comparison analysis show that under the promise of ensuring lower complexity, the algorithm can effectively improve the reasonable allocation of resources in distributed multi-hop network, so that the overall utility of the network is improved, and the energy consumption is reduced.