An autonomous computation offloading strategy in Mobile Edge Computing: A deep learning-based hybrid approach

Shakarami, Ali; Shahidinejad, Ali; Ghobaei‐Arani, Mostafa

doi:10.1016/j.jnca.2021.102974

Cited by 95 publications

(31 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mobile IDS consists of handheld wireless devices (smartphones or mobile devices) with intrusion detection capabilities [59][60][61][62][63][64][65]. It has a self-configurable network in which, without the help of any party, the system automatically deployed very quickly.…”

Section: Ids Overview and Limitationsmentioning

confidence: 99%

An edge based hybrid intrusion detection framework for mobile edge computing

Singh

Chatterjee

Satapathy

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

The Mobile Edge Computing (MEC) model attracts more users to its services due to its characteristics and rapid delivery approach. This network architecture capability enables users to access the information from the edge of the network. But, the security of this edge network architecture is a big challenge. All the MEC services are available in a shared manner and accessed by users via the Internet. Attacks like the user to root, remote login, Denial of Service (DoS), snooping, port scanning, etc., can be possible in this computing environment due to Internet-based remote service. Intrusion detection is an approach to protect the network by detecting attacks. Existing detection models can detect only the known attacks and the efficiency for monitoring the real-time network traffic is low. The existing intrusion detection solutions cannot identify new unknown attacks. Hence, there is a need of an Edge-based Hybrid Intrusion Detection Framework (EHIDF) that not only detects known attacks but also capable of detecting unknown attacks in real time with low False Alarm Rate (FAR). This paper aims to propose an EHIDF which is mainly considered the Machine Learning (ML) approach for detecting intrusive traffics in the MEC environment. The proposed framework consists of three intrusion detection modules with three different classifiers. The Signature Detection Module (SDM) uses a C4.5 classifier, Anomaly Detection Module (ADM) uses Naive-based classifier, and Hybrid Detection Module (HDM) uses the Meta-AdaboostM1 algorithm. The developed EHIDF can solve the present detection problems by detecting new unknown attacks with low FAR. The implementation results illustrate that EHIDF accuracy is 90.25% and FAR is 1.1%. These results are compared with previous works and found improved performance. The accuracy is improved up to 10.78% and FAR is reduced up to 93%. A game-theoretical approach is also discussed to analyze the security strength of the proposed framework.

show abstract

Section: Ids Overview and Limitationsmentioning

confidence: 99%

An edge based hybrid intrusion detection framework for mobile edge computing

Singh

Chatterjee

Satapathy

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…In the past few years, we can find a plethora of work towards offloading problems from mobile devices to the remote server or cloud. Similar to other domains, in cloud computing, Deep Learning (DL) has been widely applied [8][9][10][11][12][13]. At the same time, a tremendous amount of efforts have been made towards reducing the overload of DL tasks to make it feasible on smartphones [14].…”

Section: Related Workmentioning

confidence: 99%

Computation offloading technique for energy efficiency of smart devices

Choi

Paul

2021

J Cloud Comp

View full text Add to dashboard Cite

The substantial number of wearable devices in the healthcare industry and the continuous growth of the market procreates the demand for computational offloading. Despite major development of wearable devices and offloading techniques, there are several concerns such as latency, battery power, and computation capability that requires significant development. In this paper, we focus on the fact that most smart wearable devices have Bluetooth pairing with smartphones, and Bluetooth communication is significantly energy-efficient compare to 3G/LTE or Wi-Fi. We propose a computation offloading technique that offloads from the smartphone to the cloud server considering the decision model of both wearable devices and smartphones. Mobile cloud computing can elevate the capacity of smartphones considering the battery state and efficient communications with the cloud. In our model, we increase the energy efficiency of smart devices. To accomplish this, a Dhrystone Millions of Instructions per Second (DMIPS)-based workload measurement model along with a computation offloading decision model were created. According to the performance evaluation, offloading from wearable devices to smartphones and offloading once to cloud server can reduce energy consumption significantly.

show abstract

“…The MAPE‐K (monitor, analyze, plan, execute, knowledge) loop is a control methodology for self‐control systems introduced by IBM in 2003. This concept has been utilized as a reference control model in different environments and computation paradigms such as cloud computing, fog computing, and edge computing 18‐20 . The four mentioned components of MAPE‐K would be discussed later in more detail.…”

Section: Introductionmentioning

confidence: 99%

“…The four mentioned components of MAPE‐K would be discussed later in more detail. However, despite its comprehensive utilization in various computation environments such as the cloud, the MAPE‐K loop has not yet been exploited in the service placement process, applied in the present study 20 .…”

Section: Introductionmentioning

confidence: 99%

Toward an autonomic approach for Internet of Things service placement using gray wolf optimization in the fog computing environment

2021

Self Cite

View full text Add to dashboard Cite

Divers and the huge amount of data produced by the Internet of Things (IoT) applications on the one hand, and inherent limitations of local equipment to handle these data, on the other hand, leads to present emerging closer technologies to the end‐users such as fog computing environment. Nevertheless, despite the numerous advantages of such an environment, it still needs state‐of‐the‐art approaches to cope with some inherent limitations. In the literature, resource placement strategies are generally proposed to address such problems, in which the IoT applications are mapped to fog nodes. However, despite its importance, different approaches attempt to enhance the overall system's performance and users' expectations: none of such approaches is satisfactory. In this article, to deploy IoT applications on fog nodes, an autonomic IoT service placement approach based on the gray wolf optimization scheme is proposed, enhancing the system's performance while considering execution costs. Besides, the autonomic concepts help make an appropriate automanagement system that fits better the fog environment's dynamic behavior. Simulation results demonstrate that the proposed approach outperforms the other approaches and converges to the solution in near‐optimal application deployment on fog nodes in respect of the performance of performing services that are 93.7%, the performance of the average waiting time for performed services that are 100%, the remaining services sent to an extra provisioned period that is zero.

show abstract

An autonomous computation offloading strategy in Mobile Edge Computing: A deep learning-based hybrid approach

Cited by 95 publications

References 32 publications

An edge based hybrid intrusion detection framework for mobile edge computing

An edge based hybrid intrusion detection framework for mobile edge computing

Computation offloading technique for energy efficiency of smart devices

Toward an autonomic approach for Internet of Things service placement using gray wolf optimization in the fog computing environment

Contact Info

Product

Resources

About