- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Learning-based Computation Offloading for IoT Devices with Energy Harvesting
摘要： Internet of Things (IoT) devices can apply mobile edge computing (MEC) and energy harvesting (EH) to provide high level experiences for computational intensive applications and concurrently to prolong the lifetime of the battery. In this paper, we propose a reinforcement learning (RL) based offloading scheme for an IoT device with EH to select the edge device and the offloading rate according to the current battery level, the previous radio transmission rate to each edge device and the predicted amount of the harvested energy. This scheme enables the IoT device to optimize the offloading policy without knowledge of the MEC model, the energy consumption model and the computation latency model. Further, we present a deep RL based offloading scheme to further accelerate the learning speed. Their performance bounds in terms of the energy consumption, computation latency and utility are provided for three typical offloading scenarios and verified via simulations for an IoT device that uses wireless power transfer for energy harvesting. Simulation results show that the proposed RL based offloading scheme reduces the energy consumption, computation latency and task drop rate and thus increases the utility of the IoT device in the dynamic MEC in comparison with the benchmark offloading schemes.
关键词： Mobile edge computing,energy harvesting,reinforcement learning,computation offloading,Internet of Things
更新于2025-09-23 15:22:29
-
[IEEE 2018 Asia Communications and Photonics Conference (ACP) - Hangzhou, China (2018.10.26-2018.10.29)] 2018 Asia Communications and Photonics Conference (ACP) - Energy efficient Placement of Baseband Functions and Mobile Edge Computing in 5G Networks
摘要： We propose and compare different potential placement schemes for baseband functions and mobile edge computing on their energy efficiency. Simulation results show that NFV enabled flexible placement reduces more than 20% power than traditional solutions.
关键词： Mobile edge computing placement,5G optical transport,Baseband functions placement,energy efficiency
更新于2025-09-23 15:22:29
-
[IEEE 2018 28th International Telecommunication Networks and Applications Conference (ITNAC) - Sydney, Australia (2018.11.21-2018.11.23)] 2018 28th International Telecommunication Networks and Applications Conference (ITNAC) - CamThings: IoT Camera with Energy-Efficient Communication by Edge Computing based on Deep Learning
摘要： In recent years, the demand for IoT cameras has increased due to the high demand for image data. However, the image sensor is unsuitable as an energy-constrained edge device for IoT due to its high-power consumption. Therefore, periodic on–off scheduling of IoT cameras is a promising approach since video recording using image sensors is energy-intensive. Due to the constrained computing performance of edge devices, IoT is still based on cloud computing with energy leaks by transmitting all the data of edge devices to cloud. In this paper, we proposed energy-efficient communication via edge computing based on deep learning, which reduces power consumption by transmitting only images of interest classified using edge computing. We also designed and implemented CamThings, which is an energy-efficient IoT camera with periodic on–off scheduling and the proposed energy-efficient communication. To analyze and evaluate the efficiency of the proposed communication scheme, we implemented a power consumption model for CamThings. In an environment with a low interest ratio, the proposed CamThings is superior to the baseline method with only periodic on–off scheduling in terms of power consumption and lifetime. When the scheduling period T is 5s and the interest ratio is 0.1, the proposed method consumed 41% less power than the baseline method. As a result, CamThings has a lifetime of more than one month.
关键词： Wireless Communication,Energy Efficiency,Edge Computing,IoT Camera,Deep Learning
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE 5G World Forum (5GWF) - Silicon Valley, CA, USA (2018.7.9-2018.7.11)] 2018 IEEE 5G World Forum (5GWF) - Local Area Data Network for 5G System Architecture
摘要： We introduce a noble concept and design of Local Area Data Network (LADN) that geographically isolates the operator network resources to provide high data rate, low latency, and service localization for 5G System Architecture. In addition, we compare two alternative solutions of handling the LADN session with considerations of UE power consumptions and human mobility patterns. The proposed LADN technology enables the edge computing.
关键词： Edge Computing,Local Area Data Network,5G System Architecture
更新于2025-09-23 15:21:01
-
A framework involving MEC: imaging satellites mission planning
摘要： Satellite will play an important role in many important industries and exist as a carrier of information transmission in the era of Internet of Things. Massive data can be used in planning and scheduling processes A general data-driven framework- imaging satellite mission planning framework (ISMPF) for solving imaging mission planning problems is proposed. ISMPF mainly includes three parts: task assignment, planning and scheduling and task execution. The framework gives a general solution to the problem of satellite mission planning. The two core parts of the planning and scheduling module are machine learning algorithms and planning and scheduling algorithms, which greatly affect the quality of the results. Machine learning algorithm is mainly used to quickly obtain feasible initial solution. This idea can be used to quickly analyze and model the imaging satellite observation mission planning, imaging satellite measurement and control, data downlink mission planning problems. It has a strong generality and is suitable for most situations of imaging satellites. In order to verify the validity of ISMPF, we designed test examples for measurement and control, data downlink missions. Experimental verification demonstrates the effectiveness of our proposed framework.
关键词： Framework,Imaging satellite,Mission planning,Mobile edge computing
更新于2025-09-19 17:15:36
-
[IEEE 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Huangshan, China (2019.8.5-2019.8.8)] 2019 18th International Conference on Optical Communications and Networks (ICOCN) - An Incentive Auction-based Cooperative Resource Provisioning Scheme for Edge Computing over Passive Optical Networks
摘要： Edge computing integrated passive optical networks have been gained more and more attention recently due to the high bandwidth and low latency for cloud services. In this paper, we study cooperative resource provisioning (CRP) among multiple cloudlets for one service because the resource capacity of each cloudlet is relatively limited comparing with the ever-increasing computation. We first formulate the CRP problem by ILP based on auction; then we design an auction-based scheme to motivate cloudlets to share their resources, which can be divided into two algorithms: CRP and TPD; finally, we demonstrate the effectiveness of our work by simulations.
关键词： Edge Computing (EC),Passive Optical Networks (PON),Cooperative Resource Provisioning (CRP)
更新于2025-09-16 10:30:52
-
Disaggregated edge-enabled C+L-band filterless metro networks
摘要： The recent interest in the upgrade and enhancements of metro transport networks and the availability of transponder cards with coherent receivers is opening the way to filterless solutions employing only passive splitters/couplers and optical amplifiers, potentially achieving significant capital expeditures and operating expenditures savings. However, the filterless option suffers from inefficiencies, mainly due to the broadcasting constraint and the reduced optical reach. To overcome such limitations, this paper proposes three complementary strategies to upgrade optical filterless metro networks (FMN). First, the number of supported channels is incremented by exploiting the full C+L-band. To this end, two design architectures (i.e., Single and Dual Region) are proposed and evaluated, targeting double capacity with respect to the standard C-band and an upgrade to cost reduction. Second, we investigate a dual-architecture solution, extending metro deployments with a low-cost filterless and unamplified L-band system. Its design trade-offs are evaluated to determine its suitability in providing direct low-latency connectivity between metro-access nodes with the aim of supporting edge-computing platforms. Finally, the flexibility of the FMN is extended by introducing disaggregated transponders with different bitrates (i.e., 100 Gbps and 400 Gbps) and configurable transmission parameters, such as the modulation format and the forward error correction). Such flexibility is exploited through the extension of the OpenConfig YANG model of the optical line system, thus enabling automatic spectrum and transmission parameter assignment by means of a centralized software-defined-network controller and achieving better resource utilization. Simulation and experimental results are provided, showing the effectiveness and the potential impact of filterless metro solutions in future deployments and low-cost network upgrades supporting edge/fog clusters and 5G.
关键词： edge computing,C+L-band,5G,disaggregated transponders,filterless metro networks
更新于2025-09-16 10:30:52
-
[IEEE OCEANS 2019 - Marseille - Marseille, France (2019.6.17-2019.6.20)] OCEANS 2019 - Marseille - Experiments of Recreating the Frequency Domain Properties of Seawater Channel for Underwater Optical Communication
摘要： Mobile Edge Computing (MEC) has recently emerged as a promising technology to push the cloud frontier to the network edge, provisioning network services in close proximity of mobile users. Serving users at edge clouds has many advantages, such as reducing service delay, lower operational cost, and improved network resource availability. Furthermore, providing virtualized network service in MEC can improve user service experience, simplify network service deployments, and ease network resource management. However, provisioning reliable and seamless virtualized network services for mobile users while meeting their individual stringent delay requirements is of signi?cant importance and challenging. In this paper, we study mobile users requesting for virtualized network function services in MEC. We ?rst formulate two novel user request admission problems that take into account user mobility and service delay requirements. One is to minimize the admission cost of all user requests, assuming that there are suf?cient resources in MEC to meet user resource demands; the other is to maximize the accumulative network utility, subject to resource capacities of cloudlets, where the utility gain by admitting a request is determined by its resource demand and delay requirement, and the requested resource utilization in MEC. We then devise ef?cient approximation algorithms for the two problems. We ?nally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are promising.
关键词： Network Function Virtualization,MEC,delay-sensitive,NFV,user mobility,Mobile Edge Computing,VNF service replication
更新于2025-09-11 14:15:04
-
Towards converged, collaborative and co-automatic (3C) optical networks
摘要： The interconnection of all things is developing a new diagram of future information networks. However, it is di?cult to realize future applications with only one single technique. Collaboration between multiple advanced techniques is leading the way for the development of future information networks. Optical communication is an enabling technique to achieve high speed, long reach, and low latency communication, which plays an important role on the transformation of information networks. To achieve these advantages that caters to the characteristics of future information networks, collaboration of multiple advanced techniques with optical, which is called “optical plus X”, could realize the vision of “all things connected with networks”. In this paper, we focus on the collaboration between optical networks with other techniques, mainly discuss four representative aspects, which are “optical plus IP”, “optical plus radio”, “optical plus computing”, and “optical plus AI”. We discuss the challenges, timely works, and developing trends. Finally, we give the future visions for optical network towards a collaborative, converged and co-automatic optical network.
关键词： 5G optical transport networks,AI-assisted optical networks,edge computing optical networks,3C optical networks,IP over optical networks
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Guangzhou, China (2018.10.8-2018.10.12)] 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Smart Office System with Face Detection at the Edge
摘要： The rapid increase in the number of Internet connected devices has placed a high level of demand on both the network bandwidth and the processing power currently available to the centralized physical datacentres that embody the ‘Cloud’. To alleviate such a demand and relieve the network capacity, the Edge Computing paradigm was recently proposed. Such a paradigm evangelizes the processing of data locally, closer to users and so avoiding the slow communication of data to centralized datacentres. The realization of such a paradigm requires the evaluation of smart applications on various potential energy efficient devices by understanding their processing and storage limits, while also looking for efficient methods to improve their capabilities. In this paper, we develop and evaluate an end to end smart office application on a representative Edge device, the latest Raspberry-Pi, while utilizing existing Cloud on Demand services connected through an Android application and Amazon Alexa Skill. The developed solution monitors various environmental conditions and is able to recognize users using facial recognition. We will evaluate the requirements of such an application on an Edge device and explore methods to reduce the data stored and processed, while evaluating the impact this has on the detection rate. In particular, we evaluate the effectiveness of increasing the image compression levels by measuring the level of compression used versus the time to create trained data and the face detection rate it produces. Our experimentation shows favourable results for the Edge system implementation, while also supporting the possibility of the hybridisation of Cloud and local processing to achieve complex tasks while minimising network use.
关键词： Edge Computing,Smart Environment,IoT,Facial Recognition
更新于2025-09-04 15:30:14