Taming Wireless Fluctuations by Predictive Queuing Using a Sparse-Coding Link-State Model

Abstract

We introduce State-Informed Link-Layer Queuing (SILQ), a system that models, predicts, and avoids packet delivery failures caused by temporary wireless outages in everyday scenarios. By stabilizing connections in adverse link conditions, SILQ boosts throughput and reduces performance variation for network applications, for example by preventing unnecessary TCP timeouts due to dead zones, elevators, and subway tunnels. SILQ makes predictions in real-time by actively probing links, matching measurements to an overcomplete dictionary of patterns learned offline, and classifying the resulting sparse feature vectors to identify those that precede outages. We use a clustering method called sparse coding to build our data-driven link model, and show that it produces more variation-tolerant predictions than traditional loss-rate, location-based, or Markov chain techniques.We present extensive data collection and field-validation of SILQ in airborne, indoor, and urban scenarios of practical interest. We show how offline unsupervised learning discovers link-state patterns that are stable across diverse networks and signal-propagation environments. Using these canonical primitives, we train outage predictors for 802.11 (Wi-Fi) and 3G cellular networks to demonstrate TCP throughput gains of 4x with off-the-shelf mobile devices. SILQ addresses delivery failures solely at the link layer, requires no new hardware, and upholds the end-to-end design principle to enable easy integration across applications, devices, and networks.

A Survey of Anticipatory Mobile Networking: Context-Based Classification, Prediction Methodologies, and Optimization Techniques

“…As an example, the inter-download times of video segments are predicted in [102], where the output sequences are the interdownload times of the already downloaded segments and the states are the instants of the next download request. ARIMA: [13], [38], [40], [46], [47], [54], [58], [59], [63], [100], [119] Kalman: [32], [ CF: [16], [134], [149] Cluster: [15], [34], [51], [117], [122], [123], [148], [156] Decision trees: [35], [98], [ Functional: [28], [29], [38], [64], [99], [104], [105] SVM: [51], [114], [139] ANN: [14], [48], [106], [ 2) Bayesian inference: This approach allows to make statements about what is unknown, by conditioning on what is known. Bayesian prediction can be summarized in the following steps: 1) define a model that expresses qualitative aspects of our knowledge but has unknown parameters, 2) specify a prior probability distribution for the unknown parameters, 3) compute the posterior probability distribution for the parameters, given the observed data, and 4) make predictions by averaging ove...…”

“…As an example, the inter-download times of video segments are predicted in [102], where the output sequences are the interdownload times of the already downloaded segments and the states are the instants of the next download request. ARIMA: [13], [38], [40], [46], [47], [54], [58], [59], [63], [100], [119] Kalman: [32], [49] Classification CF: [16], [134], [149] Cluster: [15], [34], [51], [117], [122], [123], [148], [156] Decision trees: [35], [98], [ Functional: [28], [29], [38], [64], [99], [104], [105] SVM: [51], [114], [139] ANN: [14], [48], [106], […”

“…No entry can be associated to multiple centroids ( K j=1 c ij = 1, ∀i ∈ M). Clustering is applied in anticipatory networking to build a data-driven link model [51], to find similarities within vehicular paths [34], to identify social events [99] that might impact network performance, and to identify device types [93].…”

“…In particular, the predicted channel availability is used to maximize the throughput and to reduce the time overhead of channel sensing. Predictors robust to channel variations are investigated also in [51]. A clustering method with supervised SVM classification is proposed.…”

A Structured Deep Neural Network for Data Driven Localization in High Frequency Wireless Networks

“…As a result, any localization procedure must be sufficiently fast to meet these conditions. When the alignment latency between end points is too long, the system initialization overhead will be high, while intermittent latency (e.g., MAC ARQ) resulting from packet loss due to misaligned beams can potentially disrupt higher layer protocols, causing loss of throughput from, for example, TCP timeouts [12]. Further, as many new applications have stringent latency budgets, such as Virtual Reality (VR) and Augmented Reality (AR), it is important that deployments requiring localization are cognizant of the latency cost of the localization method used.…”