QFloor: Queue Delay Reduction in Dynamic Backpressure Networks

QFloor addresses the high queuing delays inherent in backpressure forwarding, including in dynamic or oscillatory networks. QFloor is purely local and reactionary: it adds placeholder bytes to the advertised queue values with the explicit goal of keeping the minimum queue depth at a static pre-configured number of bytes. QFloor deals with queue depth dynamics by looking at the queue depth over a dynamically-sized observation window of time, adding placeholder bytes if that minimum depth is too high, and removing placeholder bytes whenever the backpressure algorithm dictates a dequeue from a queue with only placeholder bytes. Experimentation in a fully-implemented backpressure forwarding system shows that QFloor can reduce the end-to-end latency by more than 90% even in a network with only one and two-hop paths.

[1]  A. Robert Calderbank,et al.  Layering as Optimization Decomposition: A Mathematical Theory of Network Architectures , 2007, Proceedings of the IEEE.

[2]  Franziska Wulf,et al.  Minimization Methods For Non Differentiable Functions , 2016 .

[3]  Gregory Lauer,et al.  ASAP: Preventing Starvation in Backpressure Forwarding , 2018, MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM).

[4]  Leandros Tassiulas,et al.  Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks , 1992 .

[5]  Ness B. Shroff,et al.  Utility maximization for communication networks with multipath routing , 2006, IEEE Transactions on Automatic Control.

[6]  Longbo Huang,et al.  Delay reduction via Lagrange multipliers in stochastic network optimization , 2009, IEEE Transactions on Automatic Control.

[7]  Alexander L. Stolyar,et al.  Maximizing Queueing Network Utility Subject to Stability: Greedy Primal-Dual Algorithm , 2005, Queueing Syst. Theory Appl..

[8]  Michael J. Neely,et al.  Super-Fast Delay Tradeoffs for Utility Optimal Fair Scheduling in Wireless Networks , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[9]  Atilla Eryilmaz,et al.  Heavy-ball: A new approach to tame delay and convergence in wireless network optimization , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[10]  Jia Liu,et al.  Achieving Low-Delay and Fast-Convergence in Stochastic Network Optimization: A Nesterovian Approach , 2016, SIGMETRICS.

[11]  Gregory Lauer,et al.  Latency-Aware Forwarding for IRON: Latency Support for Back-Pressure Forwarding , 2018, MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM).

[12]  R. Srikant,et al.  Fair Resource Allocation in Wireless Networks Using Queue-Length-Based Scheduling and Congestion Control , 2005, IEEE/ACM Transactions on Networking.

[13]  Leandros Tassiulas,et al.  Resource Allocation and Cross-Layer Control in Wireless Networks , 2006, Found. Trends Netw..

[14]  J. G. Dai,et al.  Maximum Pressure Policies in Stochastic Processing Networks , 2005, Oper. Res..

[15]  Eytan Modiano,et al.  Fairness and Optimal Stochastic Control for Heterogeneous Networks , 2005, IEEE/ACM Transactions on Networking.

[16]  Longbo Huang,et al.  The power of online learning in stochastic network optimization , 2014, SIGMETRICS '14.