Modeling of Deep Neural Network (DNN) Placement and Inference in Edge Computing

Bensalem, Mounir; Dizdarevć, Jasenka; Jukan, Admela

doi:10.1109/iccworkshops49005.2020.9145449

Cited by 11 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bensalem et al [63] laid out an edge server based on a deep neural network and proposed the best layout model. Different kinds of deep neural networks have the ability to extract various features from data because they have their own distinct structures, which can help with model optimization [64] .…”

Section: Ai For Edge Server Placementmentioning

confidence: 99%

“…Different kinds of deep neural networks have the ability to extract various features from data because they have their own distinct structures, which can help with model optimization [64] . In the process of designing the optimal layout model, the authors [63] put forward the formula of deep neural network parameter selection after comprehensively considering the communication delay between nodes and the cost of EC nodes. They then determined the most suitable parameters of the deep neural network model through this formula.…”

Section: Ai For Edge Server Placementmentioning

confidence: 99%

“…The high [62] Distributed deep learning In the distributed deep learning algorithm, the edge server placement model is continuously updated through the model transmission of centralized and edge nodes. [63] Deep neural network According to the communication delay between nodes and the calculation cost, the edge server placement model of the deep neural network is obtained and the model is trained in the actual network environment to improve its performance. [66] Edge convolutional neural network-G The EdgeCNN-G model is different from the EdgeCNN model as it uses a group computer to place the edge server.…”

Section: Offloading Requirementmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence for edge service optimization in Internet of Vehicles: A survey

et al. 2022

Tsinghua Sci. Technol.

137

View full text Add to dashboard Cite

The Internet of Vehicles (IoV) plays a crucial role in providing diversified services because of its powerful capability of collecting real-time information. Generally, collected information is transmitted to a centralized resourceintensive cloud platform for service implementation. Edge Computing (EC) that deploys physical resources near road-side units is involved in IoV to support real-time services for vehicular users. Additionally, many measures are adopted to optimize the performance of EC-enabled IoV, but they hardly help make dynamic decisions according to real-time requests. Artificial Intelligence (AI) is capable of enhancing the learning capacity of edge devices and thus assists in allocating resources dynamically. Although extensive research has employed AI to optimize EC performance, summaries with relative concepts or prospects are quite few. To address this gap, we conduct an exhaustive survey about utilizing AI in edge service optimization in IoV. Firstly, we establish the general condition and relative concepts about IoV, EC, and AI. Secondly, we review the edge service frameworks for IoV and explore the use of AI in edge server placement and service offloading. Finally, we discuss a number of open issues in optimizing edge services with AI.

show abstract

Section: Ai For Edge Server Placementmentioning

confidence: 99%

Section: Ai For Edge Server Placementmentioning

confidence: 99%

Section: Offloading Requirementmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence for edge service optimization in Internet of Vehicles: A survey

et al. 2022

Tsinghua Sci. Technol.

137

View full text Add to dashboard Cite

show abstract

“…This dichotomy determines the need for multiple design re-spins (before a successful integration), potentially leading to long tuning phases, overloading the designers and producing results highly depending on their skills. Despite the variety of resources available, optimizing these heterogeneous computing architectures for performing low-latency and energy-efficient DL inference tasks without compromising performance is still a challenge [5].…”

Section: Ai System Engineering Challengesmentioning

confidence: 99%

Applying AI in Practice: Key Challenges and Lessons Learned

Fischer¹,

Ehrlinger²,

Geist³

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The main challenges along with lessons learned from ongoing research in the application of machine learning systems in practice are discussed, taking into account aspects of theoretical foundations, systems engineering, and human-centered AI postulates. The analysis outlines a fundamental theory-practice gap which superimposes the challenges of AI system engineering at the level of data quality assurance, model building, software engineering and deployment.

show abstract