Benchmarking of CPU-intensive Stream Data Processing in The Edge Computing Systems

TL;DR

The paper tackles energy-efficient streaming on edge nodes by examining how CPU frequency scaling interacts with workload to affect power and performance. It formulates an energy-per-delivered-data objective $P_c(s)$ and empirically profiles a Raspberry Pi 4 using stress-ng and cpufreq controls to map performance and energy across workloads. Key findings show an optimal frequency around 1.5 GHz where efficiency peaks, while higher frequencies incur diminishing returns due to heat and power; power consumption increases with frequency, illustrating a clear trade-off. The work informs practical energy-aware edge scheduling and suggests future directions toward integrating the energy model with lightweight Kubernetes distributions and accelerators for ML/video workloads.

Abstract

Edge computing has emerged as a pivotal technology, offering significant advantages such as low latency, enhanced data security, and reduced reliance on centralized cloud infrastructure. These benefits are crucial for applications requiring real-time data processing or strict security measures. Despite these advantages, edge devices operating within edge clusters are often underutilized. This inefficiency is mainly due to the absence of a holistic performance profiling mechanism which can help dynamically adjust the desired system configuration for a given workload. Since edge computing environments involve a complex interplay between CPU frequency, power consumption, and application performance, a deeper understanding of these correlations is essential. By uncovering these relationships, it becomes possible to make informed decisions that enhance both computational efficiency and energy savings. To address this gap, this paper evaluates the power consumption and performance characteristics of a single processing node within an edge cluster using a synthetic microbenchmark by varying the workload size and CPU frequency. The results show how an optimal measure can lead to optimized usage of edge resources, given both performance and power consumption.

Figures (6)

• Figure 1: Stream data processing in the edge
• Figure 2: Stream data processing for various speed devices.
• Figure 3: Testbed components
• Figure 4: Result showing the variation of CPU efficiency by with varying CPU Frequency and CPU load for the SUT.
• Figure 5: Result showing the CPU efficiency v/s CPU Frequency for the SUT.