IoT Edge Computing Research Articles

Study on cyber‐security for IoT edge utilizing pattern match accelerator

AbstractA malware detection algorithm that can be embedded in IoT edge computing is proposed in this study and validated using an emulator. This algorithm, with a pattern match accelerator, reduces the computing cost while maintaining a relatively high detection accuracy. For autonomous driving, complicated IoT edge computing must have a huge amount of embedded program codes. In such a situation, the invasion of malware can lead to compromised cybersecurity. In this study, a pattern match accelerator is implemented for such issues, thereby offering IoT edge computing that detects malware automatically. Edge computing is designed to apply simply structural level analysis algorithms using HLAC mask pattern. We developed a pseudo‐emulator system environment and conducted performance confirmation of the proposed technique using 641 chosen samples from six types of malware families. The algorithm's efficiencies demonstrated an identification performance of approximately 80%. In comparison to characteristic extraction using AI, the computing cost was reduced and these processes enable edge computing with high cybersecurity features.

Privacy-preserving incentive mechanism for multi-leader multi-follower IoT-edge computing market: A reinforcement learning approach

Abstract Computation offloading is a promising solution for resource-limited IoT devices to accomplish computation-intensive tasks. In order to promote the service trading between edge computing service providers and IoT devices, a series of works have explored incentive mechanisms for IoT-edge computing. However, most traditional incentive mechanisms (such as Stackelberg game-based approaches) expose privacy of participants. Moreover, the existing Reinforcement Learning (RL) based incentive mechanisms do not consider the competition among multiple providers, which is not in line with reality. In this paper, taking privacy concern and competition among providers into consideration, we utilize RL technique to design a privacy-preserving incentive mechanism for multiple providers and multiple IoT devices. Specifically, we model the pricing and demand problem of providers and IoT devices as a multi-leader multi-follower Stackelberg game, in which the providers work as leaders to determine their prices first, and then the IoT devices determine their demands as followers. We prove the existence and uniqueness of the Nash Equilibrium (NE) of this game. Due to privacy concern, providers and IoT devices are unwilling to disclose their own parameters, which makes the derivation of NE becoming a great challenge. To address this problem, a new RL-based Pricing Mechanism (RLPM) is proposed, which enables providers to learn their optimal pricing strategies without knowing private information of other participants. Finally, numerical simulations are conducted to illustrate the convergence and effectiveness of the RLPM compared with other existing algorithms.

An Edge-Based Social Distancing Detection Service to Mitigate COVID-19 Propagation

COVID-19 virus has strongly impacted our everyday life. Without the availability of a vaccine or a well-established and efficient treatment, we have to live with it. One way to mitigate the propagation of the virus is to respect social distancing between persons. Indeed, many governments have adopted it as one of the key solutions to reduce the propagation of the virus. However, it is difficult to enforce social distancing among the population. In this article, we propose to combine IoT and multi-access edge computing (MEC) technologies to build a service that checks and warns people in near real time if they are not practicing social distancing. The proposed service is composed of a client application side installed on the users' smartphone, which periodically sends GPS coordinates to remote servers sitting at the edge of the network (i.e., at MEC). The remote servers use a local algorithm to detect and warn users who are not practicing social distancing. The proposed service respects privacy and anonymity by hiding the user identity, and is capable of warning users in near real time thanks to the usage of MEC.

Parallel Recurrent Convolutional Neural Networks-Based Music Genre Classification Method for Mobile Devices

With the rapid development of the mobile internet of things (IoTs) and mobile sensing devices, a large amount of mobile computing-oriented applications have attracted attention both from industry and academia. Deep learning based methods have achieved great success in artificial intelligence (AI) oriented applications. To advance the development of AI-based IoT systems, effective and efficient algorithms are in urgent need for IoT Edge Computing. Time-series data classification is an ongoing problem in applications for mobile devices (e.g. music genre classification on mobile phones). However, the traditional methods require field expertise to extract handcrafted features from the time-series data. Deep learning has been demonstrated to be effective and efficient in this kind of data. Nevertheless, the existing works neglect some of the sequential relationships found in the time-series data, which are significant for time-series data classification. Considering the aforementioned limitations, we propose a hybrid architecture, named the parallel recurrent convolutional neural network (PRCNN). The PRCNN is an end-to-end training network that combines feature extraction and time-series data classification in one stage. The parallel CNN and Bi-RNN blocks focus on extracting the spatial features and temporal frame orders, respectively, and the outputs of two blocks are fused into one powerful representation of the time-series data. Then, the syncretic vector is fed into the softmax function for classification. The parallel network structure guarantees that the extracted features are robust enough to represent the time-series data. Moreover, the experimental results demonstrate that our proposed architecture outperforms the previous approaches applied to the same datasets. We also take the music data as an example to conduct contrastive experiments to verify that our additional parallel Bi-RNN block can improve the performance of time-series classification compared with utilizing CNNs alone.

Multiagent-Based Flexible Edge Computing Architecture for IoT

This article presents a proposal for FLEC architecture, which solves problems resulting from the rigidity of the traditional IoT architecture and edge computing. FLEC architecture is a flexible and advanced IoT system model characterized by environment adaptation ability and user orientation ability. We utilize COSAP, a system configuration platform based on a multiagent framework, as an implementation procedure for FLEC architecture. Furthermore, this article presents its application case study of a healthcare support system for a sports event with many participants. Finally, we demonstrate the contribution of this proposed architecture to problem solution in edge computing.

Consolidate IoT Edge Computing with Lightweight Virtualization

Lightweight virtualization (LV) technologies have refashioned the world of software development by introducing flexibility and new ways of managing and distributing software. Edge computing complements today's powerful centralized data centers with a large number of distributed nodes that provide virtualization close to the data source and end users. This emerging paradigm offers ubiquitous processing capabilities on a wide range of heterogeneous hardware characterized by different processing power and energy availability. The scope of this article is to present an in-depth analysis on the requirements of edge computing from the perspective of three selected use cases that are particularly interesting for harnessing the power of the Internet of Things. We discuss and compare the applicability of two LV technologies, containers and unikernels, as platforms for enabling the scalability, security, and manageability required by such pervasive applications that soon may be part of our everyday lives. To inspire further research, we identify open problems and highlight future directions to serve as a road map for both industry and academia.

Toward Architectural and Protocol-Level Foundation for End-to-End Trustworthiness in Cloud/Fog Computing

With Cloud/Fog Computing being a paradigm combination of IoT context and Edge Computing extended with Cloud/Fog, business process in it involves dataflows among multi-layers and multi-nodes, possibly provided by multi-organizations. Achieving end-to-end trustworthiness over the whole dataflow in such a Cloud/Fog Computing context is a challenging issue, nonetheless a necessary pre-condition for a successful business process on intra-/inter- organizational level. This paper investigates technical conundrums related to this target and proposes a policy-based approach for trustworthiness governance. An architectural layout is proposed with according modules, by carrying out two methodologies. One resides in tracing data derivation and maintaining security-level over the whole dataflow, handling data aggregation with several protocols. The other is to express data owner trustworthiness requirements with an enhanced attribute-based access control policy model and to evaluate data accessing nodes’ trustworthiness-related properties. Experiments show that processing time per attribute pair drops as the scales of policies increase, suggesting good scaling property of the system.