A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf
.
Filters
Edge Offloading in Smart Grid
[article]
2024
arXiv
pre-print
Moreover, edge offloading can play a pivotal role for the next-generation smart grid AI applications because it enables the efficient utilization of computing resources and addresses the challenges of ...
variables and optimization algorithms to assess the efficiency of edge offloading. ...
Edge AI is emerging as a new paradigm for the efficient management of smart grids due to machine and deep learning model improvements [8] . ...
arXiv:2402.01664v1
fatcat:xvq4v5t6hrgrbpeupvh2j3ikly
Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency
[article]
2024
arXiv
pre-print
The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. ...
Lastly, we show that the 'prune' method can reduce the training time for certain models by up to 6x without affecting the accuracy when compared against a compression-aware split-learning approach. ...
ACKNOWLEDGMENTS This research was in part supported by the Academy of Finland (grant number 345008), and the National Science Foundation CNS AI Institute (grant number 2112562), as well as the NSF-AoF ...
arXiv:2311.05739v4
fatcat:upvpraqetbderhmbvwfxm5cy7i
Computation offloading through mobile vehicles in IoT-edge-cloud network
2020
EURASIP Journal on Wireless Communications and Networking
Thus, it is a challenging problem to find a way to offload tasks for sensing devices. ...
In this paper, we propose a computation offloading scheme through mobile vehicles in IoT-edge-cloud network. ...
The mobile edge computing is proposed to provide computation services for edge devices. ...
doi:10.1186/s13638-020-01848-5
fatcat:nhrmrgzw6vejvfljuagyqm24ii
Ready Player One: UAV Clustering based Multi-Task Offloading for Vehicular VR/AR Gaming
[article]
2019
arXiv
pre-print
With rapid development of unmanned aerial vehicle (UAV) technology, application of the UAVs for task offloading has received increasing interest in the academia. ...
To tackle this problem, in this article, we propose a new architecture for UAV clustering to enable efficient multi-modal multi-task task offloading. ...
[7] propose a deep learning algorithm for applying a UAV to identify wildfire. ...
arXiv:1904.03861v1
fatcat:robkqzggufge7ixrlqxkbyoqnq
Edge Intelligence in Smart Grids: A Survey on Architectures, Offloading Models, Cyber Security Measures, and Challenges
2022
Journal of Sensor and Actuator Networks
Additionally, we discuss how the use of AI has aided in optimizing the performance of edge computing. ...
In addition, substantial work has been expended in the literature to incorporate artificial intelligence (AI) techniques into edge computing, resulting in the promising concept of edge intelligence (EI ...
In general, AI for edge computing can be viewed in four essential aspects: edge caching, edge training, edge inference, and edge offloading. ...
doi:10.3390/jsan11030047
fatcat:rgsocn6zj5ewbms5dqrgz25ewq
Blockchain-Enhanced Offloading in Mobile Edge Computing: A Systematic Review and Survey of Current Trends and Future Directions
[article]
2024
arXiv
pre-print
Mobile Edge Computing (MEC) looks promising for enhancing performance and reducing costs by offloading the computing work of IoT to MEC servers. ...
This paper reviews these Blockchain-based offloading methods for different MEC settings. ...
Offloading in Edge AI Applications: Investigating offloading's role in edge AI applications, including federated learning, can expand the horizon for intelligent edge computing solutions. ...
arXiv:2403.05961v1
fatcat:o6btohbd65hbldhz74vx46hkym
Intelligent Rapid Adaptive Offloading Algorithm for Computational Services in Dynamic Internet of Things System
2019
Sensors
As an innovative technology, multi-access edge computing can provide cloudlet capabilities by offloading computation-intensive services from devices to a nearby edge server. ...
In particular, the offloading policy can be rapidly derived from an estimation algorithm based on a deep neural network, which uses an experience replay training method to improve model accuracy and adopts ...
Acknowledgments: The authors appreciate all the reviewers and editors for their precious comments and work on this article.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/s19153423
fatcat:bdm46rr44zfsppv2ecysnvnzbm
DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
[article]
2021
arXiv
pre-print
We propose DeepWear, a deep learning (DL) framework for wearable devices to improve the performance and reduce the energy footprint. ...
Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks. ...
For cases such as running WaveNet on LG Urbane with Nexus GPU 6 available, DeepWear can even speed up the processing for more than 20 times (23.0X) compared to the wearable-only strategy. ...
arXiv:1712.03073v3
fatcat:6zgkveypofeuvblm6oj5g32tni
Delay-Optimal Task Offloading for UAV-Enabled Edge-Cloud Computing Systems
2022
IEEE Access
, vol. 20, no. 22, p.
multiplication operations in model solving and speed up the 6441, 2020.
convergence process ...
pabilities, while the service time for edge and the proposed
5. ...
doi:10.1109/access.2022.3174127
fatcat:byuk6yfw75erhf2wqvlo7all5y
Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression and Challenge
[article]
2019
arXiv
pre-print
On the algorithm level, compression approaches are introduced for both deep neural networks and the underlying Markov Decision Processes, enabling accurate low-dimensional representations of challenges ...
On the one hand, deep reinforcement learning (DRL) provides a powerful tool for scalable optimization for high dimensional RRM problems in a dynamic environment. ...
In Section IV, to reduce the computation and energy consumption in DRL algorithms, several algorithm compression approaches are introduced, including deep neural network compression, MDP model compression ...
arXiv:1910.05054v1
fatcat:6xgjbxuexvfptjtmocsmf5haty
Privacy-Preserving Compressive Model for Enhanced Deep-Learning-based Service Provision System in Edge Computing
2019
IEEE Access
In this paper, we design a deep-learning-based service provision system for protecting the privacy and enhancing services in edge computing. ...
INDEX TERMS Compressive model, differential privacy, deep learning, edge computing. ...
Thus, the edge nodes provide enhanced services for the near IoT devices. Unfortunately, edge nodes are limited by their power, speed of processor, data storage, and communication resources. ...
doi:10.1109/access.2019.2927163
fatcat:xixgtt6565betn7urr47qvboy4
Physical Layer Security Assisted Computation Offloading in Intelligently Connected Vehicle Networks
[article]
2022
arXiv
pre-print
To address these issues, we utilize an ergodic secrecy rate to determine how many tasks are offloaded to the edge, where ergodic secrecy rate represents the average secrecy rate over all realizations in ...
In this paper, we propose a secure computation offloading scheme (SCOS) in intelligently connected vehicle (ICV) networks, aiming to minimize overall latency of computing via offloading part of computational ...
The issue of high mobility in vehicular networks should not be ignored for improving the performance of computation offloading schemes for vehicles. ...
arXiv:2203.13536v1
fatcat:uau75vkvqjdqppjpafsryobauu
Optimization-Based Offloading and Routing Strategies for Sensor-Enabled Video Surveillance Networks
2020
IEEE Access
INDEX TERMS Edge Computing, Offloading, Quality of Service, Routing, Video Surveillance.
I. ...
Yu, “Distributed Deep Learning
Model for Intelligent Video Surveillance Systems with Edge ...
doi:10.1109/access.2020.3029421
fatcat:rpxsfgjnwvgprmepypsuw2uuoq
DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices
[article]
2022
arXiv
pre-print
., with different network conditions, various device types) using deep reinforcement learning technology. ...
neural network (CNN) inference on more than one edge device. ...
Deep Reinforcement Learning in CNN Model Compression To tackle the complex configurations and performance of CNN architecture, DRL has been used in CNN model compression and is proven to be effective in ...
arXiv:2202.01699v2
fatcat:jtleqcvgsrfcpguu72xreoot3q
DeepBrain: Experimental Evaluation of Cloud-Based Computation Offloadingand Edge Computing in the Internet-of-Drones for Deep Learning Applications
2020
Sensors
In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. ...
This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. ...
Acknowledgments: The authors would like to thank Prince Sultan University, Riyadh, Saudi Arabia for supporting this work. ...
doi:10.3390/s20185240
pmid:32937865
pmcid:PMC7570899
fatcat:rn72ff2dlbb7jldqb46uawz4xe
« Previous
Showing results 1 — 15 out of 947 results