MétaCan
Menu
Back to cohort
Record W3084179282 · doi:10.1109/jiot.2020.3022572

Multiagent Deep-Reinforcement-Learning-Based Virtual Resource Allocation Through Network Function Virtualization in Internet of Things

2020· article· en· W3084179282 on OpenAlexafffund
Hurmat Ali Shah, Lian Zhao

Bibliographic record

VenueIEEE Internet of Things Journal · 2020
Typearticle
Languageen
FieldComputer Science
TopicSoftware-Defined Networks and 5G
Canadian institutionsToronto Metropolitan University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceReinforcement learningResource allocationVirtual networkNetwork virtualizationDistributed computingVirtualizationComputer networkOptimization problemResource management (computing)Artificial intelligenceCloud computingAlgorithm

Abstract

fetched live from OpenAlex

Resource allocation is a significant task in the emerging area of Internet of Things (IoT). IoT devices are usually low-cost devices with limited computational power and capabilities for long term communication. In this article, the network function virtualization (NFV) technique is used to access resources of the network and a reinforcement learning (RL) algorithm is used to solve the problem of resource allocation in IoT networks. The traffic of the IoT network uses the substrate network which is available through NFV for its data transmission. The data transmission needs of the IoT network are translated to virtual requests and service function chain (SFC) are mapped to the substrate network to serve the requests. The problem of SFC placement while meeting the system constraints of the IoT network is a nonconvex problem. In the proposed deep RL (DRL)-based resource allocation, the virtual layer acts as a common repository of the network resources. The optimization problem of SFC placement under the system constraints of IoT networks can be formulated as a Markovian decision process (MDP). The MDP problem is solved through a multiagent DRL algorithm where each agent serves an SFC. Two Q-networks are considered, where one Q-network solves the SFC placement problem while the other updates weights of the Q-network through keeping track of long-term policy changes. The virtual agents serving SFCs interact with the environment, receive reward collectively and update the policy by using the learned experiences. We show that the proposed scheme can solve the optimization problem of SFC placement through adequate reward design, state, and action space formulation. Simulation results demonstrate that the multiagent DRL scheme outperforms the reference schemes in terms of utility gained as measured through different network parameters.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.008
Threshold uncertainty score0.015

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.234
Teacher spread0.215 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations63
Published2020
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Internet of Things JournalSame topicSoftware-Defined Networks and 5GFrench-language works237,207