Towards Application-Driven Task Offloading in Edge Computing Based on Deep Reinforcement Learning

Sun, Ming; Bao, Tie; Xie, Dan; Lv, Hengyi; Si, Guoliang

doi:10.3390/mi12091011

Cited by 8 publications

(7 citation statements)

References 18 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fourth measurement object is a circuit board [ 20 ] having uneven surface. Especially, the circuit board has many reflections because there are many electronic components on the surface.…”

Section: Resultsmentioning

confidence: 99%

Development of a Three-Dimensional Optical Verification Technology without Environmental Pollution for Metal Components with Different Surface Properties

Kuo

Lee³

2022

Materials

View full text Add to dashboard Cite

Nowadays, the optical measuring approach is widely used in the precision machining industry due to high measurement efficiency. In the industry, measuring devices play a crucial role in the field of quality assurance. In practical engineering, the green measurement approach indeed plays an important role in the industry currently. In this study, a state-of-the-art green technique for three-dimensional (3D) optical measurements without environmental pollution is demonstrated, which is an environmentally friendly optical measurement method. This method can perform precise optical measurement without matte coatings. This work dealt with the possibility of measuring four metal components that were not sprayed with anything. The differences in the optical measurement results between with and without matte coatings were investigated and analyzed. It was found that the research result has practical value in the precision machining industry because average size errors of the four measurement objects with different surface properties can be controlled at about 3 µm, 0.1 µm, 0.5 µm, and 9 µm. A technical database with industrial value was established for optical measurements of metal components with different surface properties without matte coatings, which can serve as an alternative to the conventional 3D optical measurement.

show abstract

Section: Resultsmentioning

confidence: 99%

Development of a Three-Dimensional Optical Verification Technology without Environmental Pollution for Metal Components with Different Surface Properties

Kuo

Lee³

2022

Materials

View full text Add to dashboard Cite

show abstract

“…In the case of HedgeRank with a low-power (LP) and a high-performance (HP) edge device configuration (LP + HP), it provides lower execution time (12.1%~26.7%), with lower energy consumption (0.1%~15.2%) compared to the state-of-the-art PPR technique, MeLoPPR. Our HedgeRank could be orthogonally applied to many applications with PPR, such as various algorithms based on graph processing [ 6 ] as well as graph neural networks (GNNs) [ 5 ]. We expect that HedgeRank will be applied for a wider range of applications for edge environments for better energy efficiency without sacrificing performance.…”

Section: Discussionmentioning

confidence: 99%

“…Personalized PageRank (PPR) is a variant of PageRank that is widely used in graph-based neural networks, recommendation systems, social network analysis, image processing, bioinformatics, etc. [ 1 , 2 , 3 , 4 , 5 , 6 ]. PageRank calculates the importance of each node for all nodes in a graph, whereas PPR calculates the importance and relevance of each node for the source node.…”

Section: Introductionmentioning

confidence: 99%

HedgeRank: Heterogeneity-Aware, Energy-Efficient Partitioning of Personalized PageRank at the Edge

Gong

2023

Micromachines

View full text Add to dashboard Cite

Personalized PageRank (PPR) is a widely used graph processing algorithm used to calculate the importance of source nodes in a graph. Generally, PPR is executed by using a high-performance microprocessor of a server, but it needs to be executed on edge devices to guarantee data privacy and network latency. However, since PPR has a variety of computation/memory characteristics that vary depending on the graph datasets, it causes performance/energy inefficiency when it is executed on edge devices with limited hardware resources. In this paper, we propose HedgeRank, a heterogeneity-aware, energy-efficient, partitioning technique of personalized PageRank at the edge. HedgeRank partitions the PPR subprocesses and allocates them to appropriate edge devices by considering their computation capability and energy efficiency. When combining low-power and high-performance edge devices, HedgeRank improves the execution time and energy consumption of PPR execution by up to 26.7% and 15.2% compared to the state-of-the-art PPR technique.

show abstract

“…Figure 3 shows the 3D digitizing instruments used in this study, namely GOM ATOS Triple Scan II optical 3D scanner (ATOS, GOM Inc., Essen, Germany). We used a 3D optical scanner with blue light source to quantify the dimensions of the measurement objects [ 12 , 16 , 17 ]. We mixed the TiO 2 powder [ 13 , 18 ] with 95% ethanol in a weight ratio of 1:4 to create the mixture.…”

Section: Methodsmentioning

confidence: 99%

An Environmentally-Friendly Three-Dimensional Computer-Aided Verification Technique for Plastic Parts

Kuo

Lee³

2022

Polymers

View full text Add to dashboard Cite

Plastic components play a significant role in conserving and saving energy. Plastic products provide some advantages over metal, including reducing part weight, manufacturing costs, and waste, and increasing corrosion resistance. Environmental sustainability is one of the sustainable development goals (SDGs). Currently, the non-contact computer-aided verification method is frequently employed in the plastic industry due to its high measurement efficiency compared with the conventional contact measuring method. In this study, we proposed an innovative, green three-dimensional (3D) optical inspection technology, which can perform precise 3D optical inspection without spraying anything on the component surface. We carried out the feasibility experiments using two plastic parts with complex geometric shapes under eight different proposed measurement strategies that can be adjusted according to the software interface. We studied and analyzed the differences in 3D optical inspection for building an empirical technical database. Our aim in this study is to propose a technical database for 3D optical measurements of an object without spraying anything to the component’s surface. We found that the research results fulfilled the requirements of the SDGs. Our research results have industrial applicability and practical value because the dimensional average error of the two plastic parts has been controlled at approximately 3 µm and 4.7 µm.

show abstract

Towards Application-Driven Task Offloading in Edge Computing Based on Deep Reinforcement Learning

Cited by 8 publications

References 18 publications

Development of a Three-Dimensional Optical Verification Technology without Environmental Pollution for Metal Components with Different Surface Properties

Development of a Three-Dimensional Optical Verification Technology without Environmental Pollution for Metal Components with Different Surface Properties

HedgeRank: Heterogeneity-Aware, Energy-Efficient Partitioning of Personalized PageRank at the Edge

An Environmentally-Friendly Three-Dimensional Computer-Aided Verification Technique for Plastic Parts

Contact Info

Product

Resources

About