Search for: All records

Cloud platforms’ rapid growth raises significant concerns about their electricity consumption and resulting carbon emissions. Power capping is a known technique for limiting the power consumption of data centers where workloads are hosted. Today’s data center computer clusters co-locate latency-sensitive web and throughput-oriented batch workloads. When power capping is necessary, throttling only the batch tasks without restricting latency-sensitive web workloads is ideal because guaranteeing low response time for latency-sensitive workloads is a must due to Service-Level Objectives (SLOs) requirements. This paper proposes PADS, a hardware-agnostic workload-aware power capping system. Due to not relying on any hardware mechanism such as RAPL and DVFS, it can keep the power consumption of clusters equipped with heterogeneous architectures such as x86 and ARM below the enforced power limit while minimizing the impact on latency-sensitive tasks. It uses an application-performance model of both latency-sensitive and batch workloads to ensure power safety with controllable performance. Our power capping technique uses diagonal scaling and relies on using the control group feature of the Linux kernel. Our results indicate that PADS is highly effective in reducing power while respecting the tail latency requirement of the latency-sensitive workload. Furthermore, compared to state-of-the-art solutions, PADS demonstrates lower P95 latency, accompanied by a 90% higher effectiveness in respecting power limits. 

Reducing tail latency has become a crucial issue for optimizing the performance of online cloud services and distributed applications. In distributed applications, there are many causes of high end-to-end tail latency, including operating system delays, request re-ordering due to fan-out/fanin, and network congestion. Although recent research has focused on reducing tail latency for individual application components, such as by replicating requests and scheduling, in this paper, we argue for a holistic approach for reducing the end-to-end tail latency across application components. We propose TailClipper, a distributed scheduler that tags each arriving request with an arrival timestamp, and propagates it across the microservices' call chain. TailClipper then uses arrival timestamps to implement an oldest request first scheduler that combines global first-come first serve with a limited form of processor sharing to reduce end-to-end tail latency. In doing so, TailClipper can counter the performance degradation caused by request reordering in multi-tiered and microservices-based applications. We implement TailClipper as a userspace Linux scheduler and evaluate it using cloud workload traces and a real-world microservices application. Compared to state-of-the-art schedulers, our experiments reveal that TailClipper improves the 99th percentile response time by up to 81%, while also improving the mean response time and the system throughput by up to 54% and 29% respectively under high loads. 

As edge computing and sensing devices continue to proliferate, distributed machine learning (ML) inference pipelines are becoming popular for enabling low-latency, real-time decision-making at scale. However, the geographically dispersed and often resource-constrained nature of edge devices makes them susceptible to various failures, such as hardware malfunctions, network disruptions, and device overloading. These edge failures can significantly affect the performance and availability of inference pipelines and the sensing-to-decision-making loops they enable. In addition, the complexity of task dependencies amplifies the difficulty of maintaining performant and reliable ML operations. To address these challenges and minimize the impact of edge failures on inference pipelines, this paper presents several fault-tolerant approaches, including sensing redundancy, structural resilience, failover replication, and pipeline reconfiguration. For each approach, we explain the key techniques and highlight their effectiveness and tradeoffs. Finally, we discuss the challenges associated with these approaches and outline future directions. 

The impact of mobility decisions not only shapes urban traffic patterns and planning, but also its associated effects, such as greenhouse gas (GHG) emissions. Although e-bike sharing is not a new concept, it has shown significant strides in technological progress in recent years due to the ongoing process of digitalization, specifically towards decarbonization effects. Past studies have shown that e-bike sharing shows a potential as a fast, mobile, and environmentally friendly alternative to cars and public transport. Although e-bikes represent a viable alternative to traditional means of transportation, there is a lack of quantification in understanding the impact and acceptance of e-bikes towards social contexts as well as its adoption as a type of sharing concept. In this paper, we employ the Unified Theory of Acceptance and Use of Technology (UTAUT) model as an analytical framework to discern the use and acceptance of e-bike sharing as an emerging technological concept across different cities and social contexts. Our findings reveal that the e-bike sharing system's utilization is skewed towards a small percentage of "frequent users", and overall usage is biased towards younger, more-educated, and higher-income populations who live in bike-friendly areas. Our work contributes to the feasibility of embedding the e-bike sharing concept in the scope of the energy transition. 

Many IoT applications have increasingly adopted machine learning (ML) techniques, such as classification and detection, to enhance automation and decision-making processes. With advances in hardware accelerators such as Nvidia’s Jetson embedded GPUs, the computational capabilities of end devices, particularly for ML inference workloads, have significantly improved in recent years. These advances have opened opportunities for distributing computation across the edge network, enabling optimal resource utilization and reducing request latency. Previous research has demonstrated promising results in collaborative inference, where processing units in the edge network, such as end devices and edge servers, collaboratively execute an inference request to minimize latency.This paper explores approaches for implementing collaborative inference on a single model in resource-constrained edge networks, including on-device, device-edge, and edge-edge collaboration. We present preliminary results from proof-of-concept experiments to support each case. We discuss dynamic factors that can impact the performance of these inference execution strategies, such as network variability, thermal constraints, and workload fluctuations. Finally, we outline potential directions for future research.