Profit-Maximized Collaborative Computation Offloading and Resource Allocation in Distributed Cloud and Edge Computing Systems

Yuan, Haitao; Zhou, MengChu

doi:10.1109/tase.2020.3000946

Cited by 147 publications

(42 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to its better performance, it can be seen that Algorithm 1 is more stable and converges faster than FedAvg and Per- FedAvg. This further confirms the effectiveness of weightbased proximal term in (6) in dealing with the negative effects of the random sampling strategy to select user participation in the heterogeneous setting.…”

Section: A Numerical Results For the Proposed Fl Algorithmsupporting

confidence: 70%

“…In addition, it is predicted that there will be over 10 billion smart objects in the IoT connected to the Internet and the overall mobile data will reach 49 exabytes per month by 2021 (an increase of about 188% compared to 2018) [5]. Computation and data storage services can be provided by a cloud and edge computing system [6], [7], in which users' tasks are intelligently uploaded to a cloud data center layer and an edge computing layer. Many IoT applications require pre-processing and classifying data and then are used to predict future events using machine learning (ML) techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks

Nguyen

Sharma

et al. 2021

IEEE Internet Things J.

110

View full text Add to dashboard Cite

Federated learning (FL) allows multiple edge computing nodes to jointly build a shared learning model without having to transfer their raw data to a centralized server, thus reducing communication overhead. However, FL still faces a number of challenges such as non-iid distributed data and heterogeneity of user equipments (UEs). Enabling a large number of UEs to join the training process in every round raises a potential issue of the heavy global communication burden. To address these issues, we generalize the current state-of-the-art Federated Averaging (FedAvg) by adding a weight-based proximal term to the local loss function. The proposed FL algorithm runs stochastic gradient descent in parallel on a sampled subset of the total UEs with replacement during each global round. We provide a convergence upper bound characterizing the trade-off between convergence rate and global rounds, showing that a small number of active UEs per round still guarantees convergence. Next, we employ the proposed FL algorithm in wireless Internet-of-Things (IoT) networks to minimize either total energy consumption or completion time of FL, where a simple yet efficient path-following algorithm is developed for its solutions. Finally, numerical results on unbalanced datasets are provided to demonstrate the performance improvement and robustness on the convergence rate of the proposed FL algorithm over FedAvg. They also reveal that the proposed algorithm requires much less training time and energy consumption than the FL algorithm with full user participation. These observations advocate the proposed FL algorithm for a paradigm shift in bandwidth-constrained learning wireless IoT networks.

show abstract

Section: A Numerical Results For the Proposed Fl Algorithmsupporting

confidence: 70%

Section: Introductionmentioning

confidence: 99%

Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks

Nguyen

Sharma

et al. 2021

IEEE Internet Things J.

110

View full text Add to dashboard Cite

show abstract

“…An effective conservative heterogeneous earliest completion time algorithm is designed to solve it. Yuan et al [ 41 ] jointly consider CPU, memory, and bandwidth resources, load balance of all heterogeneous nodes in the edge layer, the maximum amount of energy, the maximum number of servers, and task queue stability in the cloud data centers layer. It designs a profit-maximized collaborative computation offloading and resource allocation algorithm to maximize the profit of the system while ensuring that response time limits of tasks are strictly met.…”

Section: Computing Task Scheduling Schemementioning

confidence: 99%

Recent Advances in Collaborative Scheduling of Computing Tasks in an Edge Computing Paradigm

Chen

Zhou

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

In edge computing, edge devices can offload their overloaded computing tasks to an edge server. This can give full play to an edge server’s advantages in computing and storage, and efficiently execute computing tasks. However, if they together offload all the overloaded computing tasks to an edge server, it can be overloaded, thereby resulting in the high processing delay of many computing tasks and unexpectedly high energy consumption. On the other hand, the resources in idle edge devices may be wasted and resource-rich cloud centers may be underutilized. Therefore, it is essential to explore a computing task collaborative scheduling mechanism with an edge server, a cloud center and edge devices according to task characteristics, optimization objectives and system status. It can help one realize efficient collaborative scheduling and precise execution of all computing tasks. This work analyzes and summarizes the edge computing scenarios in an edge computing paradigm. It then classifies the computing tasks in edge computing scenarios. Next, it formulates the optimization problem of computation offloading for an edge computing system. According to the problem formulation, the collaborative scheduling methods of computing tasks are then reviewed. Finally, future research issues for advanced collaborative scheduling in the context of edge computing are indicated.

show abstract

“…A very few works concern the QoE as a metric directly. energy Gao et al [49] independent full cost Chen et al [50] independent full cost Chen et al [51] independent full profit Yuan et al [52] independent full profit Lin et al [53] independent full performance, energy Du et al [54] independent full performance, energy Duan et al [55] independent full performance, energy Mahmud et al [56] independent full performance, profit Li et al [57] independent full Performance, cost Sun et al [58] independent full performance, cost Adhikari et al [59] independent full performance, utilization Ma et al [60] independent full QoE, cost Miao et al [61] independent partial performance Kai et al [62] independent partial performance Guo et al [63] independent partial performance Meng et al [64], [65] independent partial performance hop-e Cui et al [66], [67] independent partial performance hop-d, hop-e Sarkar et al [68] independent partial performance hop-e Ouyang et al [69] independent partial performance Y Cheng et al [70] independent partial energy Xia et al [71] independent partial energy Zhang et al [72] independent partial cost Chabbouh et al [73] independent partial performance, balance Y Wang et al [74] independent partial performance, cost Zhao et al [75] independent partial performance, cost Khayyat et al [76] independent partial performance, energy Alshahrani et al [77] independent partial performance, energy Chen et al [78] independent partial performance, cost, energy Hong et al [16] independent partial performance, energy hop-d Sun et al [79] independent partial performance, energy Long et al [80] independent partial performance, energy Nguyen et al…”

Section: Optimization Objectivementioning

confidence: 99%

“…Yuan et al [52] work on the optimization of the profit for edge-cloud providers. They formulate the profit optimization with considerations of the maximum response time constraint for all tasks and the load balance for edge nodes, where the revenue and the penalty cost for each task is specified by SLAs and the cost includes the execution costs of tasks offloaded to edge nodes and the energy cost of task executions in cloud servers.…”

Section: ) All Offloading A: Response Time Optimizationmentioning

confidence: 99%

A Survey and Taxonomy on Task Offloading for Edge-Cloud Computing

et al. 2020

View full text Add to dashboard Cite

Edge-cloud computing, combining the benefits of both edge computing and cloud computing, is one of the most promising ways to address the resource insufficiency of smart devices. Task offloading is an important challenge must be addressed for edge-cloud computing in practice, which decides the place and the time for performing each task. Even though there is existing research focusing on the task offloading in edge-cloud computing, a lot of problems should be solved before the application of these offloading technologies. Thus, in this article, we first propose a taxonomy of task offloading in edge-cloud environments to investigate and classify related research articles, and then summarize several challenges which have not been addressed for future research directions on this area to promote the development of edge-cloud market.

show abstract

Profit-Maximized Collaborative Computation Offloading and Resource Allocation in Distributed Cloud and Edge Computing Systems

Cited by 147 publications

References 35 publications

Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks

Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks

Recent Advances in Collaborative Scheduling of Computing Tasks in an Edge Computing Paradigm

A Survey and Taxonomy on Task Offloading for Edge-Cloud Computing

Contact Info

Product

Resources

About