Vehicular edge networks involves edge servers that are close to mobile devices to provide extra computation resource to complete the computation tasks of mobile devices with low latency and high reliability. Considerable efforts on computation offloading in vehicular edge networks have been developed to reduce the energy consumption and computation latency, in which roadside units (RSUs) are usually considered as the fixed edge servers. Nonetheless, the computation offloading with considering mobile vehicles as mobile edge servers in vehicular edge networks still needs to be further investigated. To this end, in this paper, we propose a deep reinforcement learning based computation offloading with mobile vehicles in vehicular edge computing, namely DRL-COMV, in which some vehicles (such as autonomous vehicle) are deployed and considered as the mobile edge servers that move in vehicular edge networks and cooperate with fixed edge servers to provide extra computation resource for mobile devices, in order to assist in completing the computation tasks of these mobile devices with great QoE (i.e.,low latency) for mobile devices. Particularly, the computation offloading model with considering both mobile and fixed edge servers is conducted to achieve the computation tasks offloading through vehicle-to-vehicle (V2V) communications, and a collaborative route planning is considered for these mobile edge servers to move in vehicular edge networks with objective of improving efficiency of computation offloading. Then, a deep reinforcement learning approach with designing rational reward function is proposed to determine the effective computation offloading strategies for multiple mobile devices and multiple edge servers with objective of maximizing both QoE (i.e., low latency) for mobile devices. Through performance evaluations, our results show that our proposed DRL-COMV scheme can achieve a great convergence and stability. Additionally, our results also demonstrate that our DRL-COMV scheme also can achieve better both QoE and task offloading requests hit ratio for mobile devices in comparison with existing approaches (i.e., DDPG, IMOPSOQ and GABDOS). 

A Deep Reinforcement Learning based Computation Offloading with Mobile Vehicles in Vehicular Edge Computing

In the context of large-scale rural construction in China, scientific and effective cognition and evaluation of the visual quality of public space in traditional villages is very important for improving the spatial quality of traditional villages. This study builds a cognitive and evaluation mechanism about the visual quality of public space in traditional villages by focusing on eye tracking techniques in ergonomic analysis, combining the results of subjective questionnaires and empirical judgments about the spatial perception of traditional villages. Lixiang Village in Nanjing is selected as a case to explore a scientific analysis of the visual quality of public spaces in traditional villages by using eye tracking technology to collect the subjects’ observation of different types of public spaces in the village and combining the results of the subjective questionnaire. The results of the study showed that the correlations between subjects’ subjective ratings and eye movement data are not as strong, but only moderate for some of these indicators. Moreover, buildings and structures are the most important factors in shaping the richness of public space. Finally, relevant design suggestions and strategies are proposed: in traditional village public spaces, the visual quality of structures and surrounding enclosing buildings should be focused on enhancing, while the focus should be on optimizing the orientation of paths, and also on shaping the unique visual impression of each public space. 

https://www.tandfonline.com/doi/pdf/10.1080/13467581.2023.2229410?needAccess=true&role=button

Evaluation of Public Space in Traditional Villages Based on Eye Tracking Technology

The rapid proliferation of low-latency and high-bandwidth applications has brought edge computing to the forefront of mobile network architectures. However, the strategic placement of edge servers plays a vital role in balancing price-performance trade-offs significantly. Existing works addressing the Edge Server Placement Problem have assumed homogeneous computational capabilities across ESs, which is not a pragmatic assumption considering variations in user densities and workload fluctuations across typical cityscapes. This work proposes a solution to the Edge Server Placement Problem with heterogeneous ES capacities and introduces a novel scheme to evaluate the workload of ESs for 5G networks. Additionally, this paper also proposes a novel Knapsack-based Metaheuristic for allocating base stations to edge servers, turning the Edge Server Placement Problem into a 0-1 Knapsack problem. Experimental evaluation using popular 5G traffic demand datasets has found that the proposed approach improves workload balance by 40.79%, utilisation rates by 57.58%, and reduces energy consumption by 44.68% approximately vis-à-vis homogeneous counterparts. 

A Knapsack-based Metaheuristic for Edge Server Placement in 5G networks with heterogeneous edge capacities

A Survey of Edge Computing Resource Allocation and Task Scheduling Optimization

The evolution of communication technology has driven the demand for intelligent power grids and data analysis in power systems. However, obtaining and annotating electrical data from intelligent terminals is time-consuming and challenging. We propose Meta In-Context Learning (M-ICL), a new approach that harnesses large language models to classify time series electrical data, which largely alleviates the need for annotated data when adapting to new tasks. The proposed M-ICL consists of two stages: meta-training and meta-testing. In meta-training, the model is trained on various tasks that have an adequate amount of training data. The meta-training stage aims to learn the mapping between electrical data and the embedding space of large language models. In the meta-testing stage, the trained model makes predictions on new tasks. By utilizing the in-context learning ability of large language models, M-ICL adapts models to new tasks effectively with only a few annotated instances (e.g., 1–5 training instances per class). Our contributions lie in the new application of large language models to electrical data classification and the introduction of M-ICL to improve the classification performance with the strong in-context learning ability of large language models. Furthermore, we conduct extensive experiments on 13 real-world datasets, and the experimental results show that the proposed M-ICL improves the average accuracy over all datasets by 19.06%, 12.06%, and 6.63% when only one, two, and five training instances for each class are available, respectively. In summary, M-ICL offers a promising solution to the challenges of electrical data classification.

Meta In-Context Learning: Harnessing Large Language Models for Electrical Data Classification

With the rapid growth of mobile devices, more and more time sensitive tasks are emerging. This kind of task often has strict requirements on delay. Edge computing solves this problem to a great extent. However, the computing resources of the edge server are limited. When the number of tasks is too large, some tasks may not be completed within the specified time. In this paper, we aim to maximize the task completion rate. We propose a priority task scheduling scheme based on coherent beamforming(CB) technique and successive interference cancellation(SIC) technique. CB technique enables edge devices to transmit to distant edge servers, and SIC technique ensures that multiple tasks can be received simultaneously by edge servers. We first build the system model, and show that the model is a NP-hard problem. For solving the problem, in our algorithm, we first determine the transmission tasks in each time slot, and select a suitable server for each task. After tasks arrive at servers, we insert them into task queues according to their priorities. In simulations, we compare our schemes with other four schemes. Simulation results show that our scheme can improve the task completion rate and reduce completion delay. 

Task offloading strategy to maximize task completion rate in heterogeneous edge computing environment

NOMA-Based Task Offloading and Allocation in Vehicular Edge Computing Networks

AbstractFederated learning based on edge computing environment has great potential to facilitate the implementation of artificial intelligence at the edge of the network. However, because of the limited resource at the edge, place the complete Deep Neural Networks (DNN) model on the edge for training may not a good choice. In this paper, we study the time optimization for asynchronous federated learning based on model partition. That is, the DNN model is divided into two parts and deployed separately on the device and the edge server for the model training. First, we give the metric of the relationship between learning accuracy and iteration frequency, and then we build a mathematical model based on this. Because the solution space of mathematical model is too large to be solved directly, we propose an algorithm to minimize the total time by dynamically adjusting the model partition point and bandwidth allocation. Simulation results show that our algorithm can reduce the time by 32% to 60% compared with the other three methods.KeywordsFederated learningModel partitionEdge computing 

An Asynchronous Federated Learning Optimization Scheme Based on Model Partition

Most researches on the Internet of Vehicles (IoV) in the 5G era are focused on the low latency and the massive transmitted data. However, the 5G base station has relatively a small coverage and a high cost, which is the main reason to hinder the development of the 5G applications on the IoV. In this paper, we try to put forward some feasible solutions for this problem. We will use two physical layer communication techniques, the Coherent Beamforming (CB) technique and the Successive Interference Cancellation (SIC) technique, to jointly optimize the throughput of vehicles data transmission and the network infrastructure cost. We first establish the mathematical model based on CB and SIC technology and prove that it cannot be solved directly. Then, we design the Road and CB-nodes Assignment (RCA) algorithm and the Uninstalling Data Scheduling (UDS) algorithm to solve the problem. RCA is based on CB and SIC technology to reasonably arrange CB-nodes, so that CB-nodes set can send data from vehicles to the base station and the base station can receive multiple sets of data at the same time. UDS schedules vehicles based on various factors to optimize the total amount of data transferred by vehicles and improve throughput. In simulations, we conduct some comparative experiments, which are the not using Algorithm 3 scheme, the CB scheme, the SIC scheme, the common scheme and the Relay Task Offloading Scheme in Vehicular Edge Computing algorithm (RVEC Algorithm). Results show that our proposed method has the advantages of cost saving and throughput improvement.

Joint CB and SIC Technology to Optimize Throughput and Cost Under IoV

AbstractFederated Learning (FL) is a distributed machine learning approach which is suitable for edge computing environment. While in this environment, how to take full advantage of the computing resources on end devices and edge servers is still a difficult problem. Especially for the synchronous federated learning, computing resources among different participants will lead to extra time cost and cause resource waste. In this paper, we try to reduce the time cost and the computing resource waste by using model splitting and task scheduling. We first establish the mathematical model and find it can not be solved directly. Then we design our algorithm which we name as the Federated Learning Offloading Acceleration (FLOA) algorithm to obtain a sub-optimal solution. The FLOA algorithm first uses the Partition Points Selection method to reduce the size of the solution space, then proposes a task offloading method based on matching theory. Experiments and simulations show that compared to the other three calculation methods, the single iteration time is reduced by \(47\%\), \(28\%\), \(14\%\) under our algorithm in turn.KeywordsEdge computingFederated learningModel splitting 

Synchronous Federated Learning Latency Optimization Based on Model Splitting

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yi Shi

Author Tools

Chat about Author