An official website of the United States government
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud/edge servers may decrease the mobile device’s computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple “exits” earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the tradeoff between accuracy and delay can be tuned according to the current conditions or application demands. In this article, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the article by providing a set of compelling research challenges.
more »
« less
Distributed Threshold-based Offloading for Heterogeneous Mobile Edge Computing
In this paper, we consider a large-scale heterogeneous mobile edge computing system, where each device’s mean computing task arrival rate, mean service rate, mean energy consumption, and mean offloading latency are drawn from different bounded continuous probability distributions to reflect the diverse compute-intensive applications, mobile devices with different computing capabilities and battery efficiencies, and different types of wireless access networks (e.g., 4G/5G cellular networks, WiFi). We consider a class of distributed threshold-based randomized offloading policies and develop a threshold update algorithm based on its computational load, average offloading latency, average energy consumption, and edge server processing time, depending on the server utilization. We show that there always exists a unique Mean-Field Nash Equilibrium (MFNE) in the large-system limit when the task processing times of mobile devices follow an exponential distribution. This is achieved by carefully partitioning the space of mean arrival rates to account for the discrete structure of each device’s optimal threshold. Moreover, we show that our proposed threshold update algorithm converges to the MFNE. Finally, we perform simulations to corroborate our theoretical results and demonstrate that our proposed algorithm still performs well in more general setups based on the collected real-world data and outperforms the well-known probabilistic offloading policy.
more »
« less
- Award ID(s):
- 1955997
- PAR ID:
- 10435559
- Date Published:
- Journal Name:
- 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Wireless charging coupled with computation offloading in edge networks offers a promising solution for realizing power-hungry and computation intensive applications on user-devices. We consider a multi-access edge computing (MEC) system with collocated MEC server and base-station/access point (AP), each equipped with a massive MIMO antenna array, supporting multiple users requesting data computation and wireless charging. The goal is to minimize the energy consumption for computation offloading and maximize the received energy at the user from wireless charging. The proposed solution is a novel two-stage algorithm employing nested descent algorithm, primal-dual subgradient and linear programming techniques to perform data partitioning and time allocation for computation offloading and design the optimal energy beamforming for wireless charging, all within MEC-AP transmit power and latency constraints. Algorithm results show that optimal energy beamforming significantly outperforms other schemes such as isotropic or directed charging without beam power allocation. Compared to binary offloading, data partition in partial offloading leads to lower energy consumption and more charging time, leading to better wireless charging performance. The charged energy over an extended period of multiple time-slots both with and without computation offloading can be substantial. Wireless charging from MEC-AP thus offers a viable untethered approach for supplying energy to user-devices.more » « less
-
In the era of pervasive digital connectivity, intelligent surveillance systems (ISS) have become essential tools for ensuring public safety, protecting critical infrastructure, and deterring security threats in various environments. The current state of these systems heavily relies on the computational capabilities of mobile devices for tasks such as real-time video analysis, object detection, and tracking. However, the limited processing power and energy constraints of these devices hinder their ability to perform these tasks efficiently and effectively. The dynamic nature of the surveillance environment also adds complexity to the task-offloading process. To address this issue, mobile edge computing (MEC) comes into play by offering edge servers with higher computational capabilities and proximity to mobile devices. It enables ISS by offloading computationally intensive tasks from resource-constrained mobile devices to nearby MEC servers. Therefore, in this paper, we propose and implement an energy-efficient and cost-effective task-offloading framework in the MEC environment. The amalgamation of binary and partial task-offloading strategies is used to achieve a cost-effective and energy-efficient system. We also compare the proposed framework in MEC with mobile cloud computing (MCC) environments. The proposed framework addresses the challenge of achieving energy-efficient and cost-effective solutions in the context of MEC for ISS. The iFogSim simulator is used for implementation and simulation purposes. The simulation results show that the proposed framework reduces latency, cost, execution time, network usage, and energy consumption.more » « less
-
Edge computing allows end-user devices to offload heavy computation to nearby edge servers for reduced latency, maximized profit, and/or minimized energy consumption. Data-dependent tasks that analyze locally-acquired sensing data are one of the most common candidates for task offloading in edge computing. As a result, the total latency and network load are affected by the total amount of data transferred from end-user devices to the selected edge servers. Most existing solutions for task allocation in edge computing do not take into consideration that some user tasks may actually operate on the same data items. Making the task allocation algorithm aware of the existing data sharing characteristics of tasks can help reduce network load at a negligible profit loss by allocating more tasks sharing data on the same server. In this paper, we formulate the data sharing-aware task allocation problem that make decisions on task allocation for maximized profit and minimized network load by taking into account the data-sharing characteristics of tasks. In addition, because the problem is NP-hard, we design the DSTA algorithm, which finds a solution to the problem in polynomial time. We analyze the performance of the proposed algorithm against a state-of-the-art baseline that only maximizes profit. Our extensive analysis shows that DSTA leads to about 8 times lower data load on the network while being within 1.03 times of the total profit on average compared to the state-of-the-art.more » « less
-
With the explosion of intelligent and latency-sensitive applications such as AR/VR, remote health and autonomous driving, mobile edge computing (MEC) has emerged as a promising solution to mitigate the high end-to-end latency of mobile cloud computing (MCC). However, the edge servers have significantly less computing capability compared to the resourceful central cloud. Therefore, a collaborative cloud-edge-local offloading scheme is necessary to accommodate both computationally intensive and latency-sensitive mobile applications. The coexistence of central cloud, edge servers and the mobile device (MD), forming a multi-tiered heterogeneous architecture, makes the optimal application deployment very challenging especially for multi-component applications with component dependencies. This paper addresses the problem of energy and latency efficient application offloading in a collaborative cloud-edgelocal environment. We formulate a multi-objective mixed integer linear program (MILP) with the goal of minimizing the systemwide energy consumption and application end-to-end latency. An approximation algorithm based on LP relaxation and rounding is proposed to address the time complexity. We demonstrate that our approach outperforms existing strategies in terms of application request acceptance ratio, latency and system energy consumption.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
