Dynamic Voltage and Frequency Scaling in NoCs With Supervised and Reinforcement Learning Techniques

Fettes, Quintin; Clark, Mark A.; Bunescu, Răzvan; Kodi, Avinash; Louri, Ahmed

doi:10.1109/mc.2019.2923827

Computer

2019

DOI: 10.1109/mc.2019.2923827

|View full text |Cite

Dynamic Voltage and Frequency Scaling in NoCs With Supervised and Reinforcement Learning Techniques

Quintin Fettes

Mark A. Clark²,

Răzvan Bunescu

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

2024

Publication Types

Select...

Article4

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, some research papers have included a methodology in which the system monitors and acts on energy consumption, allowing it to improve several aspects. For example, through learning policies, the system can better respond to dynamic changes in applications [186] and to NoC processes that impact energy consumption the most [52]. Another way is by monitoring the strategies of other techniques, such as task replication, which, while improving system reliability, can also increase energy consumption too much [184].…”

mentioning

confidence: 99%

A Survey of MPSoC Management toward Self-Awareness

Gonzalez-Martinez,

Sandoval-Arechiga,

Solis-Sanchez

et al. 2024

Micromachines

View full text Add to dashboard Cite

Managing Multi-Processor Systems-on-Chip (MPSoCs) is becoming increasingly complex as demands for advanced capabilities rise. This complexity is due to the involvement of more processing elements and resources, leading to a higher degree of heterogeneity throughout the system. Over time, management schemes have evolved from simple to autonomous systems with continuous control and monitoring of various parameters such as power distribution, thermal events, fault tolerance, and system security. Autonomous management integrates self-awareness into the system, making it aware of its environment, behavior, and objectives. Self-Aware Cyber-Physical Systems-on-Chip (SA-CPSoCs) have emerged as a concept to achieve highly autonomous management. Communication infrastructure is also vital to SoCs, and Software-Defined Networks-on-Chip (SDNoCs) can serve as a base structure for self-aware systems-on-chip. This paper presents a survey of the evolution of MPSoC management over the last two decades, categorizing research works according to their objectives and improvements. It also discusses the characteristics and properties of SA-CPSoCs and explains why SDNoCs are crucial for these systems.

show abstract

mentioning

confidence: 99%

A Survey of MPSoC Management toward Self-Awareness

Gonzalez-Martinez,

Sandoval-Arechiga,

Solis-Sanchez

et al. 2024

Micromachines

View full text Add to dashboard Cite

show abstract

DeepNR: An adaptive deep reinforcement learning based NoC routing algorithm

R.S.

Rawat

Shahreyar

et al. 2022

Microprocessors and Microsystems

View full text Add to dashboard Cite

A Task Offloading Solution for Internet of Vehicles Using Combination Auction Matching Model Based on Mobile Edge Computing

Shi

2020

IEEE Access

View full text Add to dashboard Cite

From a global perspective, an Internet of Vehicles task offloading solution based on mobile edge computing is proposed, which satisfies the application requirements (high reliability) strictly. The average time for completing a task can be minimized with the reasonable task offloading solution. Firstly, we model the wireless network, the transmission time and the movement of vehicles. Besides, heterogeneous wireless network architecture is adopted, data centers are deployed at Small-cell Base Stations, Macro-cell Base Stations and Internet. Then considering the limitedness, heterogeneity and task diversity of resources, we utilize matching model based on combination auction to design the offloading model. Furthermore, the multi-round sequential combination auction mechanism is proposed, which equals the matching problem to the multi-dimensional grouping knapsack problem and uses dynamic programming to get the optimal match. This solution is based on virtual machine technology and voltage scaling technology in the task execution time model. Moreover, the computing resources can be measured by CPU frequency. We propose an optimization problem for the shortest average task completion time with limited resources. Finally, the effects of these parameters (such as the number of tasks per unit time, the amount of data offloaded and the number of CPU cycles) on the task execution efficiency are analyzed and compared with other algorithms by simulation experiments. Compared to existing schemes, simulation results show that the proposed algorithm can reduce system overhead and shorten task execution time effectively. INDEX TERMS Internet of Vehicles, task offloading, heterogeneous wireless network architecture, mobile edge computing, combination auction, channel gain.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Dynamic Voltage and Frequency Scaling in NoCs With Supervised and Reinforcement Learning Techniques

Cited by 4 publications

References 0 publications

A Survey of MPSoC Management toward Self-Awareness

A Survey of MPSoC Management toward Self-Awareness

DeepNR: An adaptive deep reinforcement learning based NoC routing algorithm

A Task Offloading Solution for Internet of Vehicles Using Combination Auction Matching Model Based on Mobile Edge Computing

Contact Info

Product

Resources

About