scholarly journals An Intelligent Offloading System Based on Multiagent Reinforcement Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Yu Weng ◽  
Haozhen Chu ◽  
Zhaoyi Shi

Intelligent vehicles have provided a variety of services; there is still a great challenge to execute some computing-intensive applications. Edge computing can provide plenty of computing resources for intelligent vehicles, because it offloads complex services from the base station (BS) to the edge computing nodes. Before the selection of the computing node for services, it is necessary to clarify the resource requirement of vehicles, the user mobility, and the situation of the mobile core network; they will affect the users’ quality of experience (QoE). To maximize the QoE, we use multiagent reinforcement learning to build an intelligent offloading system; we divide this goal into two suboptimization problems; they include global node scheduling and independent exploration of agents. We apply the improved Kuhn–Munkres (KM) algorithm to node scheduling and make full use of existing edge computing nodes; meanwhile, we guide intelligent vehicles to the potential areas of idle computing nodes; it can encourage their autonomous exploration. Finally, we make some performance evaluations to illustrate the effectiveness of our constructed system on the simulated dataset.


2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Fitsum Debebe Tilahun ◽  
Chung G. Kang

Enhanced licensed-assisted access (eLAA) is an operational mode that allows the use of unlicensed band to support long-term evolution (LTE) service via carrier aggregation technology. The extension of additional bandwidth is beneficial to meet the demands of the growing mobile traffic. In the uplink eLAA, which is prone to unexpected interference from WiFi access points, resource scheduling by the base station, and then performing a listen before talk (LBT) mechanism by the users can seriously affect the resource utilization. In this paper, we present a decentralized deep reinforcement learning (DRL)-based approach in which each user independently learns dynamic band selection strategy that maximizes its own rate. Through extensive simulations, we show that the proposed DRL-based band selection scheme improves resource utilization while supporting certain minimum quality of service (QoS).



2021 ◽  
pp. 39-45
Author(s):  
Yabin Wang ◽  
◽  
Jing Yu

The emergence of edge computing makes up for the limited capacity of devices. By migrating intensive computing tasks from them to edge nodes (EN), we can save more energy while still maintaining the quality of service.Computing offload decision involves collaboration and complex resource management. It should be determined in real time according to dynamic workload and network environment. The simulation experiment method is used to maximize the long-term utility by deploying deep reinforcement learning agents on IOT devices and edge nodes, and the alliance learning is introduced to distribute the deep reinforcement learning agents. First, build the Internet of things system supporting edge computing, download the existing model from the edge node for training, and unload the intensive computing task to the edge node for training; upload the updated parameters to the edge node, and the edge node aggregates the parameters with the The model at the edge nodecan get a new model; the cloud can get a new model at the edge node and aggregate, and can also get updated parameters from the edge node to apply to the device.



2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Sungwon Moon ◽  
Jaesung Park ◽  
Yujin Lim

Multiaccess edge computing (MEC) has emerged as a promising technology for time-sensitive and computation-intensive tasks. With the high mobility of users, especially in a vehicular environment, computational task migration between vehicular edge computing servers (VECSs) has become one of the most critical challenges in guaranteeing quality of service (QoS) requirements. If the vehicle’s tasks unequally migrate to specific VECSs, the performance can degrade in terms of latency and quality of service. Therefore, in this study, we define a computational task migration problem for balancing the loads of VECSs and minimizing migration costs. To solve this problem, we adopt a reinforcement learning algorithm in a cooperative VECS group environment that can collaborate with VECSs in the group. The objective of this study is to optimize load balancing and migration cost while satisfying the delay constraints of the computation task of vehicles. Simulations are performed to evaluate the performance of the proposed algorithm. The results show that compared to other algorithms, the proposed algorithm achieves approximately 20–40% better load balancing and approximately 13–28% higher task completion rate within the delay constraints.



2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Ying Yu

With the popularization of mobile terminals and the rapid development of mobile communication technology, many PC-based services have placed high demands on data processing and storage functions. Cloud laptops that transfer data processing tasks to the cloud cannot meet the needs of users due to low latency and high-quality services. In view of this, some researchers have proposed the concept of mobile edge computing. Mobile edge computing (MEC) is based on the 5G evolution architecture. By deploying multiple service servers on the base station side near the edge of the user’s mobile core network, it provides nearby computing and processing services for user business. This article is aimed at studying the use of caching and MEC processing functions to design an effective caching and distribution mechanism across the network edge and apply it to civil aviation express marketing. This paper proposes to focus on mobile edge computing technology, combining it with data warehouse technology, clustering algorithm, and other methods to build an experimental model of MEC-based caching mechanism applied to civil aviation express marketing. The experimental results in this paper show that when the cache space and the number of service contents are constant, the LECC mechanism among the five cache mechanisms is more effective than LENC, LRU, and RR in cache hit rate, average content transmission delay, and transmission overhead. For example, with the same cache space, ATC under the LECC mechanism is about 4%~9%, 8%~13%, and 18%~22% lower than that of LENC, LRU, and RR, respectively.



2005 ◽  
Vol 173 (4S) ◽  
pp. 453-453
Author(s):  
Martin G. Sanda ◽  
Rodney L. Dunn ◽  
Christopher S. Saigal ◽  
Eric A. Klein ◽  
Louis L. Pisters ◽  
...  


2016 ◽  
Vol 15 ◽  
pp. 163-171
Author(s):  
M. G. Shcherbakovskiy

The article discusses the reasonsfor an expert to participate in legal proceedings. The gnoseological reason for that consists of the bad quality of materials subject to examination that renders the examination either completely impossible or compromises objective, reasoned and reliable assessment of the findings. The procedural reason consists ofa proscription for an expert to collect evidence himself or herself. The author investigates into the ways of how an expert can participate in legal proceedings. If the defense invites an expert to participate in the proceedings, then it is recommended that his or her involvement should be in the presence of attesting witnesses and recorded in the protocol. In the course of the legal proceedings an expert has the following tasks: adding initial data, acquiring new initial data, understanding the situation of the incident, acquiring new objects to be studied, including samples for examination. An expert’s participation in legal proceedings differs from the participation of a specialist or an examination on the scene of the incident. The author describes the tasks that an expert solves in the course of legal proceedings, the peculiarities ofan investigation experiment practices, the selection of samples for an examination, inspection, interrogation.



2019 ◽  
Vol 9 (01) ◽  
pp. 47-54
Author(s):  
Rabbai San Arif ◽  
Yuli Fitrisia ◽  
Agus Urip Ari Wibowo

Voice over Internet Protocol (VoIP) is a telecommunications technology that is able to pass the communication service in Internet Protocol networks so as to allow communicating between users in an IP network. However VoIP technology still has weakness in the Quality of Service (QoS). VOPI weaknesses is affected by the selection of the physical servers used. In this research, VoIP is configured on Linux operating system with Asterisk as VoIP application server and integrated on a Raspberry Pi by using wired and wireless network as the transmission medium. Because of depletion of IPv4 capacity that can be used on the network, it needs to be applied to VoIP system using the IPv6 network protocol with supports devices. The test results by using a wired transmission medium that has obtained are the average delay is 117.851 ms, jitter is 5.796 ms, packet loss is 0.38%, throughput is 962.861 kbps, 8.33% of CPU usage and 59.33% of memory usage. The analysis shows that the wired transmission media is better than the wireless transmission media and wireless-wired.



Author(s):  
Fahmi Yunistyawan ◽  
Yunistyawan J Berchmans ◽  
Gembong Baskoro

This study implements the auto start control system on an electric motor 3 phase C4Feeding pump when the discharge pressure is low-low (4.3 kg /cm²). The C4 feeding pumpmotor was initially manually operated from the local control station, this was very ineffectiveand inefficient because it still relied on the field operator to operate the pump motor and whenthe plant was in normal operating it is very risk if the field operator late to operate motor then itwill impact to quality of the product, and if the delay time to operate motor is too long then planthave to shut down, therefore improvement is needed in the C4 feeding pump motor controlsystem. In this paper, various types of 3-phase motor control are explained which allow it to beapplied to the C4 feeding pump motor that are on-off, inverter, and variable speed drive andefficient selection of the three systems control of the motor. Software and hardware used in thisthesis work are DCS CENTUM VP Yokogawa.



Moreana ◽  
2002 ◽  
Vol 39 (Number 149) (1) ◽  
pp. 41-60 ◽  
Author(s):  
Eugenio M. Olivares Merino
Keyword(s):  

The recent reprinting of Álvaro de Silva’s 1998 edition of a selection of More’s letters prompts the author to examine the subject of Spanish translations of More, and of de Silva’s general commentary on More’s correspondence and on his relationship to other humanists. The author reflects on aspects of More’s personality as exposed in his letters and uses what he finds as a corrective to several biographical misconceptions. He points out the strengths and weaknesses of de Silva’s work and compares it with that of other translators, particularly Elizabeth Rogers, and notes the particularly Spanish quality of de Silva’s edition.



Sign in / Sign up

Export Citation Format

Share Document