Distributed Job Dispatching in Edge Computing Networks with Random Transmission Latency: A Low-Complexity POMDP Approach

This paper studies mobile edge computing (MEC) networks where multiple wireless devices (WDs) offload their computation tasks to multiple edge servers and one cloud server. Considering different real-time computation tasks at different WDs, every task is decided to be processed locally at its WD or to be offloaded to and processed at one of the edge servers or the cloud server. In this paper, we investigate low-complexity computation offloading policies to guarantee quality of service of the MEC network and to minimize WDs’ energy consumption. Specifically, both a linear programing relaxation-based (LR-based) algorithm and a distributed deep learning-based offloading (DDLO) algorithm are independently studied for MEC networks. We further propose a heterogeneous DDLO to achieve better convergence performance than DDLO. Extensive numerical results show that the DDLO algorithms guarantee better performance than the LR-based algorithm. Furthermore, the DDLO algorithm generates an offloading decision in less than 1 millisecond, which is several orders faster than the LR-based algorithm.

Download Full-text

LocKedge: Low-Complexity Cyberattack Detection in IoT Edge Computing

IEEE Access ◽

10.1109/access.2021.3058528 ◽

2021 ◽

Vol 9 ◽

pp. 29696-29710

Author(s):

Truong Thu Huong ◽

Ta Phuong Bac ◽

Dao M. Long ◽

Bui D. Thang ◽

Nguyen T. Binh ◽

...

Keyword(s):

Low Complexity ◽

Edge Computing

Download Full-text

Two-Stage Computation Offloading Scheduling Algorithm for Energy-Harvesting Mobile Edge Computing

Energies ◽

10.3390/en12224367 ◽

2019 ◽

Vol 12 (22) ◽

pp. 4367

Author(s):

Laihyuk Park ◽

Cheol Lee ◽

Woongsoo Na ◽

Sungyun Choi ◽

Sungrae Cho

Keyword(s):

Energy Harvesting ◽

Scheduling Algorithm ◽

Low Complexity ◽

Edge Computing ◽

System Stability ◽

Computation Offloading ◽

Mobile Edge Computing ◽

Renewable Energy Resources ◽

Two Stage ◽

Second Stage

Recently, mobile edge computing (MEC) technology was developed to mitigate the overload problem in networks and cloud systems. An MEC system computes the offloading computation tasks from resource-constrained Internet of Things (IoT) devices. In addition, several convergence technologies with renewable energy resources (RERs) such as photovoltaics have been proposed to improve the survivability of IoT systems. This paper proposes an MEC integrated with RER system, which is referred to as energy-harvesting (EH) MEC. Since the energy supply of RERs is unstable due to various reasons, EH MEC needs to consider the state-of-charge (SoC) of the battery to ensure system stability. Therefore, in this paper, we propose an offloading scheduling algorithm considering the battery of EH MEC as well as the service quality of experience (QoE). The proposed scheduling algorithm consists of a two-stage operation, where the first stage consists of admission control of the offloading requests and the second stage consists of computation frequency scheduling of the MEC server. For the first stage, a non-convex optimization problem is designed considering the computation capability, SoC, and request deadline. To solve the non-convex problem, a greedy algorithm is proposed to obtain approximate optimal solutions. In the second stage, based on Lyapunov optimization, a low-complexity algorithm is proposed, which considers both the workload queue and battery stability. In addition, performance evaluations of the proposed algorithm were conducted via simulation. However, this paper has a limitation in terms of verifying in a real-world scenario.

Download Full-text

Smart Privacy Protection for Big Video Data Storage Based on Hierarchical Edge Computing

Sensors ◽

10.3390/s20051517 ◽

2020 ◽

Vol 20 (5) ◽

pp. 1517

Author(s):

Di Xiao ◽

Min Li ◽

Hongying Zheng

Keyword(s):

Data Storage ◽

Privacy Protection ◽

Rapid Development ◽

Fog Computing ◽

Low Complexity ◽

Video Data ◽

Edge Computing ◽

Scalar Data ◽

Key Frames ◽

Multi Access

Recently, the rapid development of the Internet of Things (IoT) has led to an increasing exponential growth of non-scalar data (e.g., images, videos). Local services are far from satisfying storage requirements, and the cloud computing fails to effectively support heterogeneous distributed IoT environments, such as wireless sensor network. To effectively provide smart privacy protection for video data storage, we take full advantage of three patterns (multi-access edge computing, cloudlets and fog computing) of edge computing to design the hierarchical edge computing architecture, and propose a low-complexity and high-secure scheme based on it. The video is divided into three parts and stored in completely different facilities. Specifically, the most significant bits of key frames are directly stored in local sensor devices while the least significant bits of key frames are encrypted and sent to the semi-trusted cloudlets. The non-key frame is compressed with the two-layer parallel compressive sensing and encrypted by the 2D logistic-skew tent map and then transmitted to the cloud. Simulation experiments and theoretical analysis demonstrate that our proposed scheme can not only provide smart privacy protection for big video data storage based on the hierarchical edge computing, but also avoid increasing additional computation burden and storage pressure.

Download Full-text

Intelligent Dynamic Data Offloading in a Competitive Mobile Edge Computing Market

Future Internet ◽

10.3390/fi11050118 ◽

2019 ◽

Vol 11 (5) ◽

pp. 118 ◽

Cited By ~ 10

Author(s):

Giorgos Mitsis ◽

Pavlos Athanasios Apostolopoulos ◽

Eirini Eleni Tsiropoulou ◽

Symeon Papavassiliou

Keyword(s):

Selection Process ◽

Learning Automata ◽

Low Complexity ◽

End Users ◽

Edge Computing ◽

Mobile Edge Computing ◽

Data Offloading ◽

Learning Framework ◽

Computing Services ◽

Key Enabling Technologies

Software Defined Networks (SDN) and Mobile Edge Computing (MEC), capable of dynamically managing and satisfying the end-users computing demands, have emerged as key enabling technologies of 5G networks. In this paper, the joint problem of MEC server selection by the end-users and their optimal data offloading, as well as the optimal price setting by the MEC servers is studied in a multiple MEC servers and multiple end-users environment. The flexibility and programmability offered by the SDN technology enables the realistic implementation of the proposed framework. Initially, an SDN controller executes a reinforcement learning framework based on the theory of stochastic learning automata towards enabling the end-users to select a MEC server to offload their data. The discount offered by the MEC server, its congestion and its penetration in terms of serving end-users’ computing tasks, and its announced pricing for its computing services are considered in the overall MEC selection process. To determine the end-users’ data offloading portion to the selected MEC server, a non-cooperative game among the end-users of each server is formulated and the existence and uniqueness of the corresponding Nash Equilibrium is shown. An optimization problem of maximizing the MEC servers’ profit is formulated and solved to determine the MEC servers’ optimal pricing with respect to their offered computing services and the received offloaded data. To realize the proposed framework, an iterative and low-complexity algorithm is introduced and designed. The performance of the proposed approach was evaluated through modeling and simulation under several scenarios, with both homogeneous and heterogeneous end-users.

Download Full-text