A Perspective of Matching Theory for Distributed Offloading of Splittable Tasks in Fog Networks

Hoa Tran-Dang,Dong-Seong Kim 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.6

DISCO: Distributed Computation Offloading Framework for Fog Computing Networks

Tran, Hoa Dang,Kim, Dong-Seong 한국통신학회 2023 Journal of communications and networks Vol.25 No.1

Fog computing networks have been widely inte-grated in IoT-based systems to improve the quality of services(QoS) such as low response service delay through efficientoffloading algorithms. However, designing an efficient offloadingsolution is still facing many challenges including the complicatedheterogeneity of fog computing devices and complex computationtasks. In addition, the need for a scalable and distributed algo-rithm with low computational complexity can be unachievableby global optimization approaches with centralized informationmanagement in the dense fog networks. In these regards, thispaper proposes a distributed computation offloading framework(DISCO) for offloading the splittable tasks using matchingtheory. Through the extensive simulation analysis, the proposedapproaches show potential advantages in reducing the averagedelay significantly in the systems compared to some relatedworks.

Channel-Aware Cooperative Routing in Underwater Acoustic Sensor Networks

Hoa Tran-Dang,김동성 한국통신학회 2019 Journal of communications and networks Vol.21 No.1

This paper proposes cooperative routing algorithms toimprove the performance of underwater acoustic sensor networks(UW-ASNs). With the consideration of the poor acoustic link quality,a cross-layer design of physical layer and network layer is describedfor selecting simultaneously routing relays (RR) for forwardingdata on routing paths and cooperative relays (CR) forone-hop cooperative communications. In the networks, sourcesthat have data to transmit independently selects their own relays(i.e., both RR and CR) among their neighbors based on their linkquality indicators (i.e., signal-to-noise ratio (SNR), time of arrival(ToA)) and their physical distances represented by hop count (HC)to the destination. Exploiting packet receiving or overhearing in thenetworks, these parameters are averaged and updated frequentlyto adapt to the unreliable and varying characteristics of acousticchannel over the time. By this way, the “best” relays with the “best”estimated measurements are selected reliably. Our simulation resultsshow that the proposed algorithms improve the network performancein terms of end-to-end delay, energy consumption andpacket delivery ratio.

Dynamic Collaborative Task Offloading for Delay Minimization in the Heterogeneous Fog Computing Systems

Tran, Hoa Dang,Kim, Dong-Seong 한국통신학회 2023 Journal of communications and networks Vol.25 No.2

Fog computing systems have been widely integratedin IoT-based applications to improve quality of services (QoS)such as low response service delays. This improvement is enabledby task offloading schemes, which perform task computation nearthe task generation sources (i.e., IoT devices) on behalf of remotecloud servers. However, reducing delay remains challenging foroffloading strategies owing to the resource limitations of fogdevices. In addition, a high rate of task requests combined withheavy tasks (i.e., large task size) may cause a high imbalance ofthe workload distribution among the heterogeneous fog devices,which severely impacts the offloading performance in terms ofdelay. To address these issues, this paper proposes a dynamiccollaborative task offloading (DCTO) approach, which is basedon the resource states of fog devices, to dynamically derive thetask offloading policy. Accordingly, a task can be executed byeither a single fog or multiple fog devices through the parallelcomputation of subtasks to reduce the task execution delay. Through extensive simulation analysis, the proposed offloadingsolution showed potential advantages in reducing the averagedelay significantly in systems with a high rate of service requestsand heterogeneous fog environment compared with the existingsolutions. In addition, the proposed scheme can be implementedonline owing to its low computational complexity compared withthe algorithms proposed in related works

Reinforcement Learning based Resource Management for Fog Computing Environment: Literature Review, Challenges, and Open Issues

Hoa Tran-Dang,Sanjay Bhardwaj,Tariq Rahim,Arslan Musaddiq,Dong-Seong Kim 한국통신학회 2022 Journal of communications and networks Vol.24 No.1

In the IoT-based systems, the fog computing allowsthe fog nodes to offload and process tasks requested from IoTenableddevices in a distributed manner instead of the centralizedcloud servers to reduce the response delay. However, achievingsuch a benefit is still challenging in the systems with high rate ofrequests, which imply long queues of tasks in the fog nodes, thusexposing probably an inefficiency in terms of latency to offloadthe tasks. In addition, a complicated heterogeneous degree inthe fog environment introduces an additional issue that many ofsingle fogs can not process heavy tasks due to lack of availableresources or limited computing capabilities. Reinforcement learningis a rising component of machine learning, which providesintelligent decision making for agents to response effectively tothe dynamics of environment. This vision implies a great potentialof application of RL in the concept of fog computing regardingresource allocation for task offloading and execution to achievethe improved performance. This work presents an overview of RLapplications to solve the resource allocation related problems inthe fog computing environment. The open issues and challengesare explored and discussed for further study.

Towards Implementation of AI-enhanced Predictive Digital Twin on AI Chips

Hoa Tran-Dang,Dong-Seong Kim 한국통신학회 2023 한국통신학회 학술대회논문집 Vol.2023 No.6

Driven by 6G networking, Edge Intelligence (EI) makes the most of the widespread edge resources to gain Artificial Intelligence (AI) insight. Future time-critical and data-intensive applications need distributed AI (DAI) and analytics solutions on the Edge computing platforms to enable EI from small devices to whole industrial factories. To deal with critical challenges of DAI implementation such as communication reliability, resource constrains and heterogeneity of edge devices, and dynamic nature of edge computing environment, the integration of digital twin (DT) technology is important to form an efficient framework. With this framework, efficient DT models are developed for edge devices, edge servers, and edge networks to predict the states of physical entities using probabilistic graphical models (PGMs) and machine learning (ML) algorithms. In particularly, to implement DAI solutions efficiently, the developed DT models must predict and estimate the states of physical entities accurately enabled by the power of AI. This document introduces the perspective for develop a framework to implement AI algorithms on AI chips to create the predictive DT models.

Bandit Learning based Stable Matching for Decentralized Task Offloading in Dynamic Fog Computing Networks

Hoa Tran-Dang,김동성 한국통신학회 2024 Journal of communications and networks Vol.26 No.3

This paper deals with the task offloading problem in the dynamic fog computing networks (FCNs) that involves the task and resource allocations between a set of task nodes (TNs) having task computation needs and a set of helper nodes (HNs) having available computing resources. The problem is associated with the presence of selfishness and rational nodes of these nodes, in which the objective of TNs is to minimize the task completion time by offloading the tasks to the HNs while the HNs tend to maximize their monetization of task offloading resources. To tackle this problem, we use the fairness and stability principle of matching theory to assign the tasks of TNs to the resources of HNs based on their mutual preferences in a decentralized manner. However, the uncertainty of computing resource availability of HNs as well as dynamics of QoS requirements of tasks result in the lack of preferences of TN side that mainly poses a critical challenge to obtain a stable and reliable matching outcome. To address this challenge, we develop the first, to our knowledge, Thompson sampling based multi-armed bandit (MAB) learning to acquire better exploitation and exploration trade-off, therefore allowing TNs to achieve the informed preference relations of HNs quickly. Motivated by the above considerations, this paper aims at design a bandit learning based matching model (BLM) to realize the efficient decentralized task offloading algorithms in the dynamic FCNs. Extensive simulation results demonstrate the potential advantages of the TS based learning over the ε-greedy and UCB based baselines

Digital Twin-Assisted Efficient Offloading Model for NFV-enabled Mobile Edge Computing

Hoa Tran-Dang,Dong-Seong Kim 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.11

Data Forwarding Algorithm in Lossy Wireless Sensor Networks

Tran Dang Hoa(트란 당 호아),Dong-Sung Kim(김동성) 대한전자공학회 2011 대한전자공학회 학술대회 Vol.2011 No.12

This paper proposes a novel forwarding algorithm for lossy wireless sensor networks (WSNs), which increases network performance in terms of received traffic at the sink (R0 pcakets/s) and network lifeline. Due to lossy wireless links, each sensor node forms around itself three different communication regions, each characterized by different packet reception rate (PRRs). An optimal forwarding algorithm is derived by solving a linear programming problem (LPP) with the objective of maximizing R0 while satisfyung the essential constraint of balancing energy consumption. From the results of the LPP, a new metric combining hop distance (HD) and PRR was developed to formulate a novel forwarding algorithm called direct and multi-hop data forwarding with lossy awareness (DMFLLA) algorithm. The results of simulation indicate that the Proposed DMFLLA algorithm outperforms the conventional algorithms with respect to R0 and network lifetime.

Energy-Efficient Dual-Hop Cooperative Routing in Underwater Acoustic Sensor Networks

Hoa Tran-Dang,Toha Hasnat,Jae Min Lee,Dong-Seong Kim 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.1