密集异构网络中基于多目标优化的资源分配策略

密集异构网络(Dense Heterogeneous Network, DHN)通过部署小基站可以提升网络容量和用户速率,但小基站的密集部署会产生巨大的能耗和严重的干扰,进而影响系统的能量效率(Energy Efficiency, EE)和频谱效率(Spectral Efficiency, SE)。在保证用户服务质量(Quality of Service, QoS)需求的前提下,为了联合优化系统的能量效率和频谱效率,研究了密集异构网络中下行链路的资源分配(Resource Allocation, RA)问题。首先,将频谱和小基站发射功率分配问题建模为联合优化系统能量效率和频谱效率的多目标优化问题;其次,提出了基于单策略多目标强化学习(Single-strategy Multi-objective Reinforcement Learning, SMRL)的资源分配算法求解所建立的多目标优化问题。仿真结果表明,与基于单目标强化学习的资源分配算法相比,所提算法可以实现系统能量效率和频谱效率的联合优化,与基于群体智能算法的资源分配算法相比,所提算法的系统能量效率提高了1%～1.5%,频谱效率...     

Discrete particle swarm optimization based multi-objective service path constructing algorithm

Aiming at previous research primarily focused on constructing service paths with a single objective,for exam-ple,latency minimization,cost minimization or load balance,which ignored the overall performance of constructed ser-vice paths,a multi-objective service path constructing algorithm based on discrete particle swarm optimization (MOPSO) was proposed.To promote the convergence rate and improve constructing performance,the criterions for selecting can-didate physical nodes and paths were explored,and a particle position initialization and update strategy (PIFC) was de-signed.Simulation experiments show that the proposed algorithms can improve the overall quality of service paths and increase the success rate and long-term average revenue.     

基于多目标效用优化的分布式数据交易算法

传统的集中式数据交易模式不能很好地适用于当前万物互联、数据实时产生的智能时代,为了使产生的数据发挥更大的价值,设计一种有效的数据交易框架至关重要.为此,提出了一种基于联盟区块链的分布式数据交易框架,在不依赖第三方的情况下实现了P2P的数据交易.针对已有数据交易模型仅考虑数据本身的因素,而忽略用户任务相关因素的问题,基于...     

融合面积估算和多目标优化的硬件任务划分算法

针对可重构计算机系统配置次数(划分块数)的最小化问题,提出了一种融合面积估算和多目标优化的硬件任务划分算法。该算法每次划分均进行硬件资源面积的估算,并且通过充分考虑可重构资源的使用、一个数据流图所有划分块执行延迟总和、划分模块间边数等因素构造了新的探测函数prior_assigned(),该函数能够计算每个就绪节点的优先权值,新算法通过该值能动态调整就绪列表任务节点的调度次序。实验结果表明,与现有的层划分、簇划分、增强静态列表、多目标时域划分、簇层次敏感等5种划分算法相比,该算法能获得最少的模块数,并且随着可重构处理单元面积的增大,除层划分算法之外,其执行延迟的均值也是最小的。     

一种基于地理信息系统的异构网络多目标算法

地理信息系统（Geographic Information System,GIS）和多目标算法为异构网络基站部署问题带来新的突破。ArcGIS系列是GIS专业化的管理软件,采用ArcGIS软件对包含学校、医院等场景的中国某市密集城区进行建模分析,并且提出基于目标权重因子的多目标离散粒子群算法（Multi-objective Discrete Particle Swarm Optimization algorithm based on Target Weight Factor,MDPSO/TWF）,基于多个目标函数整体最优研究异构网络基站部署问题。仿真结果表明,所提的MDPSO/TWF算法具有可行性和先进性,可以综合考虑网络负载和网络能效多个优化目标,将业务需求与实际基站选址相结合,在满足业务需求的基础上尽可能达到节能的目的。     

Task-oriented resource prediction and adjustment algorithm for space-based information network

The tasks of a space-based information network are complex and diverse, but the resources of a space-based environment are minimal. The existing methods are challenging to match task demand to resource supply accurately. Aiming at the problem of accurate prediction from task to resource, we propose a resource prediction adjustment strategy. First, we propose a multidimensional resource prediction algorithm based on improved particle swarm optimization and back propagation (IPSO-BP) neural network. The improved PSO is used to optimize the weight and threshold of BP neural network to make up for the defects that BP neural network is easy to fall into local minimum and the predicted output value is not unique. Second, to meet the quality of service (QoS) of tasks, we propose a density-based performance evaluation algorithm (DPEA) to adjust resources. This method uses the idea of local sensitive hash to select the evaluation subset for the configuration task, then dynamically selects the $k$ nearest neighbors of the configuration task, and uses the idea of weighted average to evaluate the QoS performance index of the configuration task. Simulation results show that the proposed resource prediction and adjustment strategy effectively reduces the scheduling time overhead and improves resource utilization.     

Multi mobile agent itinerary planning based on network coverage and multi-objective discrete social spider optimization algorithm

The multi mobile agent collaboration planning model was constructed based on the mobile agent load balancing and total network energy consumption index.In order to prolong the network lifetime,the network node dormancy mechanism based on WSN network coverage was put forward,using fewer worked nodes to meet the requirements of network coverage.According to the multi mobile agent collaborative planning technical features,the multi-objective discrete social spider optimization algorithm (MDSSO) with Pareto optimal solutions was designed.The interpolation learning and exchange variations particle updating strategy was redefined,and the optimal set size was adjusted dynamically,which helps to improve the accuracy of MDSSO.Simulation results show that the proposed algorithm can quickly give the WSN multi mobile agent path planning scheme,and compared with other schemes,the network total energy consumption has reduced by 15%,and the network lifetime has increased by 23%.     

基于蚁群优化的移动P2P网络路由选择算法

因为移动P2P网络具有动态性而且移动节点能量受限,提升移动P2P数据传输效率至关重要.利用蚁群优化算法,将蚂蚁的信息素与节点的能量和通信带宽结合起来,在蚁群选择路径时,减少其寻优路径上的信息素浓度,根据概率路由表中信息素的浓度对路由选择策略进行调整,避免网络拥塞和个别节点能量消耗过快,提出了一种移动P2P网络的多路径路由选择算法.实验结果表明,与EDSR路由协议相比,提出的算法能够降低节点的分组丢失率和端到端的平均时延,提高了网络的生存周期.     

Wakeup strategy based on multi-objective optimization for fixed relay nodes

In order to deal with the “tidal effect” when people move in the city and solve the problem of high energy consumption of fixed relay nodes in opportunistic networks,a wakeup strategy of multi-objective optimization was proposed,which made use of the message forward ability and energy consumption of fixed relay nodes.This strategy used energy efficiency as the indicator to make the nodes awake,and deployed a network revenue-energy consumption model to resolve the contradiction between energy consumption and message forward ability.As the selection problem of awake relay nodes was a NP-hard problem,genetic algorithm was used to select proper fixed relay nodes to keep awake.In this process,selection operator was improved to make the algorithm converge to solution space quickly.Experiments show that the proposed wakeup strategy can guarantee the successful rate of message transmission and improve the average message forwarding capabilities of fixed relay nodes by consuming a unit energy.     

基于遗传算法的Pareto多目标配电网重构

配电网重构一般采用对单一目标优化,而配电网重构却是一个多目标优化问题。因此,在此提出了基于小生境思想的遗传算法,以配电网的经济性、安全性和供电可靠性为目标,并采用Pareto寻优方式,得出Pareto最优解集,实现了和以往不同的另一种寻优方式,即先寻优后决策。在寻优过程中,通过小生境环境和交叉率和变异率的自适应机制,提高了遗传算法的全局收敛能力和收敛速度,并通过算例验证了方法的有效性。     

Switch competing migration algorithm based on process optimization in SDN

In the distributed software defined network,switch se1ects rigid migration object and has coordinating migration prob1ems.The prime switch migration scheme into two processes inc1uded se1ecting migration object and dep1oying switches dynamica11y was optimized,a switch competing migration a1gorithm was proposed based on process optimization.First1y,it synthesized de1ay,traffic and fai1ure cost,and se1ected migration object.Then,according to surviva1 time,migration time and dynamic 1oad thresho1d of contro11er,switches were migrated into object contro11er through iterative competition.Resu1ts show that compared with the existed migration a1gorithms the proposed a1gorithm se1ects more reasonab1e migration objects,avoiding migration conf1ict between switches,and contro11er 1oad ba1ancing rate has been promoted to 25.6% average1y.     

基于SDN框架的网络资源定价策略

针对网络中用户集中提出资源请求所造成资源负载过重和网络拥塞的问题,提出一种基于SDN架构的网络资源定价策略。首先,分析用户的需求和消费模式,确定资源交易模型。其次,结合现货消费模式和计划消费确定预约机制下资源动态定价策略模型。最后,根据所提出的资源定价策略,对资源价格进行实例仿真,结果表明,通过价格刺激用户提前预约资源,结合每个用户的信任度与消费习惯给出相应的优惠价格,可以有效地避免用户集中获取网络资源。     

基于多目标的MIMO无线mesh网络信道优化策略

MIMO是一种可有效提高无线网络信道带宽的技术。将MIMO技术应用在无线mesh网络中会遇到信道干扰和无线节点之间无协同策略等问题,导致网络效率降低。基于无线mesh网络中节点的多属性特征,以节点属性和内容分发为约束,提出了基于多目标优化算法与多层分发联合的调度和优化策略。实验结果表明,该算法能有效降低无线mesh网络分发数据过程中的时延,提高网络的吞吐表现和服务质量。     

基于动态交换策略的快速多目标粒子群优化算法研究

本文提出了一种基于动态交换策略的快速多目标粒子群优化算法,通过把初始种群分割成Pareto和Non_Pareto集合,并在迭代过程中对Pareto解集进行动态调整,从而较好地完成了多目标优化算法对Pareto解集的搜索和逼近.实验和应用实例均表明了该算法的有效性和快速性,并通过性能指标ER的计算验证了本算法优于某些同类的多目标优化算法.     

特征选择算法综述

自20世纪90年代以来,特征选择成为模式识别和机器学习领域的重要研究方向,研究成果十分显著,但是也存在许多问题需要进一步研究。本文首先将特征选择视为特征集合空间中的启发式搜索问题,对特征选择涉及的四个要素进行了阐述,然后从各个角度对特征选择算法进行了分类,概述了其各个分支的发展态势,最后探讨了基于多目标免疫优化的特征选择方法的研究思路。     

自由空间光网络路由与资源优化的研究和仿真

针对卫星光网络提出了一种k值约束优化方法,针对地面光网络提出了一种启发式资源优化方法.搭建了基于OPNET的自由空间光网络仿真平台,对优化前后的网络整体性能进行分析,结果表明该方法能提高网络资源利用率和网络吞吐量.     

Improved satellite resource allocation algorithm based on DRL and MOP

In view of the multi-objective optimization (MOP) problem of sequential decision-making for resource allocations in multi-beam satellite systems,a deep reinforcement learning(DRL) based DRL-MOP algorithm was proposed to improve the system performance and user satisfaction degree.With considering the normalized weighted sum of spectrum efficiency,energy efficiency,and satisfaction index as the optimization goal,the dynamically changing system environments and user arrival model were built by the proposed algorithm,and the optimization of the accumulative performance in satellite systems based on DRL and MOP was realized.Simulation results show that the proposed algorithm can solve the MOP problem with rapid convergence ability and low complexity,and it is obviously superior to other algorithms in terms of system performance and user satisfaction optimization.     

基于蚁群算法的P2P网络资源发现算法

Gossip协议是P2P网络的一种流行的资源发现算法,但它没有考虑寻找最低成本的资源。论文提出了基于蚁群算法的新的资源发现算法,在查找资源的同时,综合考虑路径载荷、延时等因素,找到综合费用最低的路径。仿真实验表明,该算法比Dijkstra算法解集的平均综合费用低10%左右,从而能更有效地利用网络资源。     

基于改进灰狼优化算法的服务功能链映射算法

随着工业互联网、车联网、元宇宙等新型互联网应用的兴起,网络的低时延、可靠性、安全性、确定性等方面的需求正面临严峻挑战。采用网络功能虚拟化技术在虚拟网络部署过程中,存在服务功能链映射效率低与部署资源开销大等问题,联合考虑节点激活成本、实例化开销,以最小化平均部署网络成本为优化目标建立了整数线性规划模型,提出基于改进灰狼优化算法的服务功能链映射(improved grey wolf optimization based service function chain mapping,IMGWO-SFCM)算法。该算法在标准灰狼优化算法基础上添加了基于无环K最短路径(K shortest path,KSP)问题算法的映射方案搜索、映射方案编码以及基于反向学习与非线性收敛改进三大策略,较好地平衡了其全局搜索及局部搜索能力,实现服务功能链映射方案的快速确定。仿真结果显示,该算法在保证更高的服务功能链请求接受率下,相较于对比算法降低了11.86%的平均部署网络成本。     

WCDMA无线网络码资源优化

中国联通WCDMA网络经过两年多的大规模建设与发展,用户数量不断增加,网络负荷也逐渐增高,与用户感知密切相关的码资源也开始不足的现象,导致网络性出现波动甚至恶化,比如无线接通率降低,单用户速率下降等。通过对长沙WCDMA无线网络码资源利用情况的分析研究,从覆盖控制、双载波方案、参数优化等方面来优化解决。