Emerging Edge Computing (EC) technology has shown promise for many delay-sensitive Deep Learning (DL) based applications of smart cities in terms of improved Quality-of-Service (QoS). EC requires judicious decisions which jointly consider the limited capacity of the edge servers and provided QoS of DL-dependent services. In a smart city environment, tasks may have varying priorities in terms of when and how to serve them; thus, priorities of the tasks have to be considered when making resource management decisions. In this paper, we focus on finding optimal offloading decisions in a three-tier user-edge-cloud architecture while considering different priority classes for the DL-based services and making a trade-off between a task’s completion time and the provided accuracy by the DL-based service. We cast the optimization problem as an Integer Linear Program (ILP) where the objective is to maximize a function called gain of system (GoS) defined based on provided QoS and priority of the tasks. We prove the problem is NP-hard. We then propose an efficient offloading algorithm, called PGUS, that is shown to achieve near-optimal results in terms of the provided GoS. Finally, we compare our proposed algorithm, PGUS, with heuristics and a state-of-the-art algorithm, called GUS, using both numerical analysis and real-world implementation. Our results show that PGUS outperforms GUS by a factor of 45% in average in terms of serving the top 25% higher priority classes of the tasks while still keeping the overall percentage of the dropped tasks minimal and the overall gain of system maximized.
more »
« less
QoS-Aware Placement of Deep Learning Services on the Edge with Multiple Service Implementations
Mobile edge computing pushes computationally-intensive services closer to the user to provide reduced delay due to physical proximity. This has led many to consider deploying deep learning models on the edge – commonly known as edge intelligence (EI). EI services can have many model implementations that provide different QoS. For instance, one model can perform inference faster than another (thus reducing latency) while achieving less accuracy when evaluated. In this paper, we study joint service placement and model scheduling of EI services with the goal to maximize Quality-of-Servcice (QoS) for end users where EI services have multiple implementations to serve user requests, each with varying costs and QoS benefits. We cast the problem as an integer linear program and prove that it is NP-hard. We then prove the objective is equivalent to maximizing a monotone increasing, submodular set function and thus can be solved greedily while maintaining a (1 – 1/e)-approximation guarantee. We then propose two greedy algorithms: one that theoretically guarantees this approximation and another that empirically matches its performance with greater efficiency. Finally, we thoroughly evaluate the proposed algorithm for making placement and scheduling decisions in both synthetic and real-world scenarios against the optimal solution and some baselines. In the real-world case, we consider real machine learning models using the ImageNet 2012 data-set for requests. Our numerical experiments empirically show that our more efficient greedy algorithm is able to approximate the optimal solution with a 0.904 approximation on average, while the next closest baseline achieves a 0.607 approximation on average.
more »
« less
- Award ID(s):
- 1948387
- NSF-PAR ID:
- 10317528
- Date Published:
- Journal Name:
- IEEE ICCCN Big Data and Machine Learning for Networking (BDMLN) Workshop • 2021
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
With the increasing demand for computationally intensive services like deep learning tasks, emerging distributed computing platforms such as edge computing (EC) systems are becoming more popular. Edge computing systems have shown promising results in terms of latency reduction compared to the traditional cloud systems. However, their limited processing capacity imposes a trade-off between the potential latency reduction and the achieved accuracy in computationally-intensive services such as deep learning-based services. In this paper, we focus on finding the optimal accuracy-time trade-off for running deep learning services in a three-tier EC platform where several deep learning models with different accuracy levels are available. Specifically, we cast the problem as an Integer Linear Program, where optimal task scheduling decisions are made to maximize overall user satisfaction in terms of accuracy-time trade-off. We prove that our problem is NP-hard and then provide a polynomial constant-time greedy algorithm, called GUS, that is shown to attain near-optimal results. Finally, upon vetting our algorithmic solution through numerical experiments and comparison with a set of heuristics, we deploy it on a testbed implemented to measure for real-world results. The results of both numerical analysis and real-world implementation show that GUS can outperform the baseline heuristics in terms of the average percentage of satisfied users by a factor of at least 50%.more » « less
-
Task offloading in edge computing infrastructure remains a challenge for dynamic and complex environments, such as Industrial Internet-of-Things. The hardware resource constraints of edge servers must be explicitly considered to ensure that system resources are not overloaded. Many works have studied task offloading while focusing primarily on ensuring system resilience. However, in the face of deep learning-based services, model performance with respect to loss/accuracy must also be considered. Deep learning services with different implementations may provide varying amounts of loss/accuracy while also being more complex to run inference on. That said, communication latency can be reduced to improve overall Quality-of-Service by employing compression techniques. However, such techniques can also have the side-effect of reducing the loss/accuracy provided by deep learning-based service. As such, this work studies a joint optimization problem for task offloading decisions in 3-tier edge computing platforms where decisions regarding task offloading are made in tandem with compression decisions. The objective is to optimally offload requests with compression such that the trade-off between latency-accuracy is not greatly jeopardized. We cast this problem as a mixed integer nonlinear program. Due to its nonlinear nature, we then decompose it into separate subproblems for offloading and compression. An efficient algorithm is proposed to solve the problem. Empirically, we show that our algorithm attains roughly a 0.958-approximation of the optimal solution provided by a block coordinate descent method for solving the two sub-problems back-to-back.more » « less
-
null (Ed.)Age of information has been proposed recently to measure information freshness, especially for a class of real-time video applications. These applications often demand timely updates with edge cloud computing to guarantee the user experience. However, the edge cloud is usually equipped with limited computation and network resources and therefore, resource contention among different video streams can contribute to making the updates stale. Aiming to minimize a penalty function of the weighted sum of the average age over multiple end users, this paper presents a greedy traffic scheduling policy for the processor to choose the next processing request with the maximum immediate penalty reduction. In this work, we formulate the service process when requests from multiple users arrive at edge cloud servers asynchronously and show that the proposed greedy scheduling algorithm is the optimal work-conserving policy for a class of age penalty functions.more » « less
-
Age of information has been proposed recently to measure information freshness, especially for a class of real-time video applications. These applications often demand timely updates with edge cloud computing to guarantee the user experience. However, the edge cloud is usually equipped with limited computation and network resources and therefore, resource contention among different video streams can contribute to making the updates stale. Aiming to minimize a penalty function of the weighted sum of the average age over multiple end users, this paper presents a greedy traffic scheduling policy for the processor to choose the next processing request with the maximum immediate penalty reduction. In this work, we formulate the service process when requests from multiple users arrive at edge cloud servers asynchronously and show that the proposed greedy scheduling algorithm is the optimal work- conserving policy for a class of age penalty functions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICCCN52240.2021.9522156
