A Demand-driven, Proactive Tasks Management Model at the Edge

Karanika, Anna; Oikonomou, Panagiotis; Kolomvatsos, Kostas; Loukopoulos, Thanasis

doi:10.1109/fuzz48607.2020.9177653

Cited by 29 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest realization of ∆ is 44% (approximately) with the mean and median being around 23-25%. Moreover, the lowest value for ∆ in [12] is around 84%, depending on the experimental scenario. The proposed model exhibits worse performance than the scheme in [12] only when EC nodes should evict too many tasks (like in the scenario when k = 150, E = 500 and W = 50).…”

Section: Performance Assessmentmentioning

confidence: 99%

“…For the description of the problem under consideration, we borrow the notation provided in [12], that deals with the same problem; however, it proposes a different solution compared to the current effort. We consider a set of N EC nodes, N = {n 1 , n 2 , .…”

Section: Preliminaries and Problem Formulationmentioning

confidence: 99%

“…Nodes are ranked based on the collected cost, and the node with the lowest ranking is selected for the final allocation. We additionally compare our scheme with the model presented in [12]. There, a fuzzy logic model is adopted to decide which tasks will be offloaded to peers.…”

Section: Performance Assessmentmentioning

confidence: 99%

“…The "where" question has already been answered by the research community (e.g., in [11]). For responding to the former ("which") question, we go beyond the state of the art compared to our previous effort in the domain [12]. Instead of using an uncertainty management methodology (in [12], we propose a model built upon the principles of Fuzzy Logic), we investigate the adoption of Deep Machine Learning (DML) technologies [13].…”

Section: Introductionmentioning

confidence: 99%

“…For responding to the former ("which") question, we go beyond the state of the art compared to our previous effort in the domain [12]. Instead of using an uncertainty management methodology (in [12], we propose a model built upon the principles of Fuzzy Logic), we investigate the adoption of Deep Machine Learning (DML) technologies [13]. More specifically, we build upon a Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) and expose a decision making mechanism for selecting the appropriate tasks to be offloaded by an EC node.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Deep Learning Model for Demand-Driven, Proactive Tasks Management in Pervasive Computing

Kolomvatsos

Anagnostopoulos

2020

IoT

Self Cite

View full text Add to dashboard Cite

Pervasive computing applications deal with the intelligence surrounding users that can facilitate their activities. This intelligence is provided in the form of software components incorporated in embedded systems or devices in close distance with end users. One example of infrastructure that can host intelligent pervasive services is the Edge Computing (EC) ecosystem. EC nodes can execute a number of tasks for data collected by devices present in the Internet of Things (IoT). In this paper, we propose an intelligent, proactive tasks management model based on demand. Demand depicts the number of users or applications interested in using the available tasks in EC nodes, thus characterizing their popularity. We rely on a Deep Machine Learning (DML) model and more specifically on a Long Short Term Memory (LSTM) network to learn the distribution of demand indicators for each task and estimate the future interest in them. This information is combined with historical observations of and support for a decision making scheme to conclude which tasks that are offloaded due to limited interest in them. We have to recognise that, in our decision making, we also take into consideration the load that every task may add to the processing node where it will be allocated. The description of our model is accompanied by a large set of experimental simulations for evaluating the proposed mechanism. We provide numerical results and reveal that the proposed scheme is capable of deciding on the fly, while concluding the most efficient decisions.

show abstract

Section: Performance Assessmentmentioning

confidence: 99%

Section: Preliminaries and Problem Formulationmentioning

confidence: 99%

Section: Performance Assessmentmentioning

confidence: 99%