14,769 Hits in 6.3 sec

Energy-Efficient Routing and Rate Allocation for Delay Tolerant Networks

Yuanyuan Zeng, Jie Wu, Naixue Xiong, Deshi Li
2012 2012 32nd International Conference on Distributed Computing Systems Workshops  
Routing for Delay Tolerant Networks (DTNs) are challengeable for the continuously varied network environment.  ...  In this paper, we present an Energy-efficient Routing and Rate Allocation (ERRA) scheme based on Q-learning that can optimize the energy efficiency with the constraints of congestion, buffer and delay.  ...  Nash Q-learning approach For on-line multi-commodity cases, Q-learning approach is extended for multi-agent decision making.  ... 
doi:10.1109/icdcsw.2012.69 dblp:conf/icdcsw/ZengWXL12 fatcat:6mnq3n5brvefxavt3r4jq6jwpi

Inductive Approaches Based on Trial/Error Paradigm for Communications Network [chapter]

Abdelhamid Mellouk
2008 Reinforcement Learning  
For this purpose, other algorithms have been proposed like Confidence based Q-Routing (CQ-Routing) or Confidence based Dual Reinforcement Q-Routing (DRQ-Routing).  ...  In order to design adaptive algorithms for dynamic networks routing problems, many of works are largely oriented and based on the Reinforcement Learning (RL) notion (Sutton & Barto, 1997) .  ...  As Machine learning techniques, we use reinforcement learning to compute a good policy in a multi-agent system Hoceini et al., 2005) .  ... 
doi:10.5772/5289 fatcat:bpfxwalnp5grxpywql5363gqae

Multi-Agent Path Planning Using Deep Reinforcement Learning [article]

Mert Çetinkaya
2021 arXiv   pre-print
The produced problems are actually similar to a vehicle routing problem and they are solved using multi-agent deep reinforcement learning.  ...  Always the same simulation environment is used and only the location of target points for the agents to visit is changed.  ...  The tabular Q-learning can only work with finite or less number of states. Here, the solution becomes Deep Q-Learning (Deep Q-Networks) (DQN) [15] .  ... 
arXiv:2110.01460v1 fatcat:pm5hgh5agfdexkn35pjyhafsem

Toward Packet Routing with Fully-distributed Multi-agent Deep Reinforcement Learning [article]

Xinyu You, Xuanjie Li, Yuedong Xu, Hui Feng, Jin Zhao, Huaicheng Yan
2019 arXiv   pre-print
In this paper, we propose a novel packet routing framework based on multi-agent deep reinforcement learning (DRL) in which each router possess an independent LSTM recurrent neural network for training  ...  Packet routing is one of the fundamental problems in computer networks in which a router determines the next-hop of each packet in the queue to get it as quickly as possible to its destination.  ...  INTRODUCTION P ACKET routing is a very challenging problem in distributed and autonomous computer networks, especially in wireless networks in the absence of centralized or coordinated service providers  ... 
arXiv:1905.03494v2 fatcat:5vvgnwuh6jc57bos67h4gwgely

Sparse Distributed Memory Approach for Reinforcement Learning Driven Efficient Routing in Mobile Wireless Network System

Varshini Vidyadhar, Nagaraj R, G Sudha
2021 International Journal of Advanced Computer Science and Applications  
In addition, the time required for agent learning in the training phase is too long, which makes it difficult for the agent to generalize the observation state efficiently.  ...  To this end, this paper attempts to overcome the overhead memory problems encountered in Q-learning-based routing techniques.  ...  In this study, a modified Q-learning is adopted to formula tea location-based routing technique considering the mobility factor of the sensor nodes. The work of Zeng et al.  ... 
doi:10.14569/ijacsa.2021.0121117 fatcat:hh6siqah6jemlmoidxtia756ce

Autonomous Network Management Using Cooperative Learning for Network-Wide Load Balancing in Heterogeneous Networks

Minsoo Lee, Xiaohui Ye, Dan Marconett, Samuel Johnson, Rao Vemuri, S. J. Ben Yoo
2008 IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference  
To maintain network-wide load balancing, we propose Autonomous Network management with Team learning based Self-configuration (ANTS) which attempts to manage a feasible route for traffic flow with QoS  ...  To enable cognitive intelligence for network-wide load balancing, we implement a cross-layer mechanism in which learning agents in middleware layer can monitor the queue sizes of MAC layer, thereby allowing  ...  A cognitive agent manages a Q-value for each route path and uses it to make decisions to form a routing path for a traffic demand.  ... 
doi:10.1109/glocom.2008.ecp.489 dblp:conf/globecom/LeeYMJVY08 fatcat:sd57c56zinflvcxze55zsulsfu

Learning to Solve Vehicle Routing Problems: A Survey [article]

Aigerim Bogyrbayeva, Meraryslan Meraliyev, Taukekhan Mustakhov, Bissenbay Dauletbayev
2022 arXiv   pre-print
This paper provides a systematic overview of machine learning methods applied to solve NP-hard Vehicle Routing Problems (VRPs).  ...  We present the taxonomy of the studies for learning paradigms, solution structures, underlying models, and algorithms.  ...  They train the neural networks using supervised learning for the insertion operation inside LNS. [76] further enhances the idea of [77] using multi-agent systems to learn which meta-heuristic to apply  ... 
arXiv:2205.02453v1 fatcat:oe56znjda5heldqkbjpr5im2de

The Strategic Control of an Ant-Based Routing System Using Neural Net Q-Learning Agents [chapter]

David Legge
2005 Lecture Notes in Computer Science  
A solution has been sought that utilises a software Tesauro, G., “Pricing in Agent Economies using Neur- agent to adapt to these changing conditions by manip- al Networks and Multi-Agent Q-Learning”  ...  In this paper, it is intended to use Q-learning to link, except for when an extra threshold is applied – modify the parameters used by the ants.  ... 
doi:10.1007/978-3-540-32274-0_10 fatcat:u3diqxo2wve3dioiopu6r5eh64

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey [article]

Tianxu Li, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Qihui Wu, Yang Zhang, Bing Chen
2022 arXiv   pre-print
The issues consist of network access, transmit power control, computation offloading, content caching, packet routing, trajectory design for UAV-aided networks, and network security issues.  ...  Multi-agent Reinforcement Learning (MARL) allows each network entity to learn its optimal policy by observing not only the environments, but also other entities' policies.  ...  Thus, it is not suitable for solving multi-hop routing. To solve the problem, the Modified-QLAODV uses the DVF to employ all the neighbors' Q-tables to update the current node's Qvalue.  ... 
arXiv:2110.13484v2 fatcat:u2o5uxms65gmnp3q7xbh35l5oi

Traffic Engineering in Software-defined Networks using Reinforcement Learning: A Review

Delali Kwasi Dake, James Dzisi Gadze, Griffith Selorm Klogo, Henry Nunoo-Mensah
2021 International Journal of Advanced Computer Science and Applications  
The separation of the control and the forwarding plane in SDN has enabled the integration of RL agents in the networking architecture to enforce changes in traffic patterns during network congestions.  ...  The SDN architecture empowers network operators to monitor network traffic with agility, flexibility, robustness and centralized control.  ...  Multi-agent systems are seen in domain applications including: network resource management, computer games, distributed networking, cloud computing and intrusion detection systems.  ... 
doi:10.14569/ijacsa.2021.0120541 fatcat:3osugiglqrhwlegcc4x2mdsrxe

A Multi-Agent Learning Approach to Online Distributed Resource Allocation

Chongjie Zhang, Victor R. Lesser, Prashant J. Shenoy
2009 International Joint Conference on Artificial Intelligence  
Effective resource allocation in a network of computing clusters may enable building larger computing infrastructures. We consider this problem as a novel application for multiagent learning (MAL).  ...  We propose a MAL algorithm and apply it for optimizing online resource allocation in cluster networks.  ...  With modified Q-value function, the FAL algorithm updates the task routing policy π 2i .  ... 
dblp:conf/ijcai/ZhangLS09 fatcat:vgyyvaygafcfbjdhhbv4hdmg7q

Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem [article]

Fabio Sanches, Sean Weinberg, Takanori Ide, Kazumitsu Kamiya
2021 arXiv   pre-print
Quantum computing and machine learning have potential for symbiosis.  ...  Our method modifies the networks used in [1] by replacing key and query vectors for every node with quantum states that are entangled before being measured.  ...  learning agent.  ... 
arXiv:2109.07498v1 fatcat:rxfzucczyjektd6m4p55usf67m


Y. Han, A. Yilmaz
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
of the reinforcement learning approach and develop a dynamic routing ability for our agent.  ...  In this work, we propose an approach for an autonomous agent that learns to navigate in an unknown map in a real-world environment.  ...  INTRODUCTION With the introduction of deep reinforcement learning (DRL) in recent years, robotics field has started to widely use it.  ... 
doi:10.5194/isprs-annals-v-1-2021-145-2021 fatcat:ur3qavm25bfklfqpcdaeed5gme

A Cross-Layer Routing Protocol Based on Quasi-Cooperative Multi-Agent Learning for Multi-Hop Cognitive Radio Networks

Yihang Du, Chun Chen, Pengfei Ma, Lei Xue
2019 Sensors  
For this reason, a cross-layer routing protocol based on quasi-cooperative multi-agent learning is proposed in this study.  ...  Then the joint design problem is modeled as a Stochastic Game (SG), and a quasi-cooperative multi-agent learning scheme is presented to solve the SG, which only needs information exchange with previous  ...  Joint Routing and Resource Management with Conjecture Based Multi-Agent Q-Learning In order to introduce the quasi-cooperative multi-agent learning scheme, a brief introduction to multi-agent Q-learning  ... 
doi:10.3390/s19010151 fatcat:ifqa3o2lvjfbxadebyqdpcpj6m

Study of Group Route Optimization for IoT Enabled Urban Transportation Network

Koh Song Sang, Bo Zhou, Po Yang, Zaili Yang
2017 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)  
Instead of optimizing the routing path for individual drivers, this paper studies how to develop a new method to provide new routing method based on vehicles' similarities in a specific urban's transportation  ...  However, with the development of technologies in Internet of Things (IoT), vehicle to vehicle (V2V) or Vehicle to Infrastructure (V2I) communications, group based routing becomes achievable.  ...  It is difficult to manage a large, massive and complex urban transportation network. Besides, a multi-agent evacuation model was introduced by Zong et al.  ... 
doi:10.1109/ithings-greencom-cpscom-smartdata.2017.137 dblp:conf/ithings/SangZYY17 fatcat:r6ef2tbn2jbkvih3shqqsxcjl4
« Previous Showing results 1 — 15 out of 14,769 results