EAPS: Edge-Assisted Predictive Sleep Scheduling for 802.11 IoT Stations

TL;DR

This work addresses the energy-delay trade-off in 802.11 IoT deployments by introducing edge-assisted predictive sleep scheduling (EAPS). It leverages a Linux-based AP with a dedicated Collector/Scheduler to gather cross-layer features and uses ML (notably LSTM with history) to predict the downlink delivery delay $oldsymbol{ abla_c}$, announcing sleep schedules via a high-priority control path. Empirical results in cloud and edge scenarios show that EAPS can reduce energy consumption close to PSM while keeping delivery delays near the always-awake baseline, with significant improvements over traditional PSM/APSM/CAM schemes. The approach demonstrates the viability of edge computing for real-time sleep scheduling in WiFi IoT and points to future work on wake-up-radio integration and SDN-enabled wake strategies.

Abstract

The broad deployment of 802.11 (a.k.a., WiFi) access points and significant enhancement of the energy efficiency of these wireless transceivers has resulted in increasing interest in building 802.11-based IoT systems. Unfortunately, the main energy efficiency mechanisms of 802.11, namely PSM and APSD, fall short when used in IoT applications. PSM increases latency and intensifies channel access contention after each beacon instance, and APSD does not inform stations about when they need to wake up to receive their downlink packets. In this paper, we present a new mechanism---edge-assisted predictive sleep scheduling (EAPS)---to adjust the sleep duration of stations while they expect downlink packets. We first implement a Linux-based access point that enables us to collect parameters affecting communication latency. Using this access point, we build a testbed that, in addition to offering traffic pattern customization, replicates the characteristics of real-world environments. We then use multiple machine learning algorithms to predict downlink packet delivery. Our empirical evaluations confirm that when using EAPS the energy consumption of IoT stations is as low as PSM, whereas the delay of packet delivery is close to the case where the station is always awake.

Figures (13)

• Figure 1: The end-to-end delay components between a station and a server. The prediction of $\delta_{c}$ is particularly challenging because it is affected by several factors such as traffic rate, channel utilization, and buffering mechanisms employed by the Linux kernel's network layer and wireless NIC's driver.
• Figure 2: The architecture developed and used in this paper. The Collector module communicates with various kernel and user-space components to collect a set of features required for delay prediction. The Scheduler estimates the sleep duration and conveys it to the station. This figure primarily focuses on the wired-to-wireless interfaces path to compute $\delta_{c}$. Some of the modules required to collect other delay components ($\delta_{a}$ and $\delta_{b}$) are not included in this figure.
• Figure 3: Traffic characterisation.
• Figure 4: (a) Standard deviation of burst size, (b) standard deviation of burst interval, (c) burstiness ($\mathcal{B}$), and (d) dynamicity ($\mathcal{D}$) of traffic generated by our testbed compared to traffic captured in real-world environments. ND and HD refer to normal and high dynamicity, respectively.
• Figure 5: of machine-learning algorithms versus the number of samples (transactions) in training dataset for (a) Normal Dynamicity (ND), and (b) High Dynamicity (HD) scenarios. Results are averaged over all s. converges the fastest, and requires up to 3x more datapoints.