Service Function Chain Deployment Algorithm Based on Multi-Agent Deep Reinforcement Learning

Aiming at the rapid growth of network services,which leads to the problems of long service request processing time and high deployment cost in the deployment of network function virtualization service function chain(SFC)under 5G networks,this paper proposes a multi-agent deep deterministic policy gradient optimization algorithm for SFC deployment(MADDPG-SD).Initially,an optimization model is devised to enhance the request acceptance rate,minimizing the latency and deploying the cost SFC is constructed for the network resource-constrained case.Subsequently,we model the dynamic problem as a Markov decision process(MDP),facilitating adaptation to the evolving states of network resources.Finally,by allocating SFCs to different agents and adopting a collaborative deployment strategy,each agent aims to maximize the request acceptance rate or minimize latency and costs.These agents learn strategies from historical data of virtual network functions in SFCs to guide server node selection,and achieve approximately optimal SFC deployment strategies through a cooperative framework of centralized training and distributed execution.Experimental simulation results indicate that the proposed method,while simultaneously meeting performance requirements and resource capacity constraints,has effectively increased the acceptance rate of requests compared to the comparative algorithms,reducing the end-to-end latency by 4.942%and the deployment cost by 8.045%.

Service Function Chain Migration in LEO Satellite Networks

With the advancements of software defined network(SDN)and network function virtualization(NFV),service function chain(SFC)placement becomes a crucial enabler for flexible resource scheduling in low earth orbit(LEO)satellite networks.While due to the scarcity of bandwidth resources and dynamic topology of LEO satellites,the static SFC placement schemes may cause performance degradation,resource waste and even service failure.In this paper,we consider migration and establish an online migration model,especially considering the dynamic topology.Given the scarcity of bandwidth resources,the model aims to maximize the total number of accepted SFCs while incurring as little bandwidth cost of SFC transmission and migration as possible.Due to its NP-hardness,we propose a heuristic minimized dynamic SFC migration(MDSM)algorithm that only triggers the migration procedure when new SFCs are rejected.Simulation results demonstrate that MDSM achieves a performance close to the upper bound with lower complexity.

A Hierarchical Framework for Visualising and Simulating Supply Chains in Virtual Environments

This paper presents research into applying virtual environment (VE) technology to supply chain management (SCM). Our research work has employed virtual manufacturing environments to represent supply chain nodes to simulate processes and activities in supply chain management. This will enable those who are involved in these processes and activities to gain an intuitive understanding of them, so as to design robust supply chains and make correct decisions at the right time. A framework system and its hierarchical structure for visualising and simulating supply chains in virtual environments are reported and detailed in this paper.

Research on Multi-stage Optimum Design Technology for Virtual Supply Chain Based on Cybermediary in Manufacturing Industry

Virtual supply chain based on cybermediary (VSC-CM) is an innovative VSC pattern meeting informationization development requirements in the manufacturing industry. Methods and features of customer-demand-oriented optimum VSC design adopted by CM are discussed. A customer demand goal system applying to VSC-CM design and quantifying methods of these goals are accordingly given. Then a three-stage optimum VSC design scheme based on dynamic goals is designed, which considers both the holistic optimization of VSC and individuation demands of member enterprises. To implement the scheme, an optimum algorithm synthesizing fuzzy c-means clustering algorithm and topsis comprehensive evaluation algorithm is presented. Feasibility and rapidity of this scheme is proved through a case analysis finally.

Research on The Factors Affecting Profit Allocation Based on Virtual Supply Chain

Traditional profit allocation solutions cannot be effectively applied to the practice for the limitations in their premises and principles. This paper based on the practical processes of virtual supply chain performs analysis on major factors relative to cost and risk which effect the profit allocation among the partners, and then proposes the quantitative relations between the factors and profit allocation. The relations can serve as a base for further research on extensive profit allocation model.

The Architecture and Operation Mode of Virtual Supply Chain

Virtual supply chain, as a modern collaborative mode of enterprises, is important to decrease the cost and improve the efficiency and the quality of supply chains, and to satisfy customers. Based on the analysis of the conception and characteristics of the virtual supply chain, the architecture of virtual supply chain is built, and corresponding objects, tasks, information and technologies are described. Three operation modes-Order-driven, manufacturer-centered, and retailer-centered are researched. As a case, virtual supply chain is applied in the electronic commerce and networked customization system of ceramic products.

CT VIRTUAL ENDOSCOPY IN ASSESSING OSSICULAR CHAIN DISRUPTION CSUSED BY TEMPORAL BONE FRACTURE AND EAR TRAUMA

Objective To explore the value of computed tomography virtual endoscopy(VE) in assessing ossicular chain disruption in temporal bone fracture and ear trauma with intact tympanum. Methods High resolution spiral computerized tomography(CT) was completed in 35 cases of temporal bone fracture and 5 cases of tympanum trauma, all with intact or healed tympanum. Three-dimensional reconstruction was completed using a virtual endoscopy software. Audiological tests were conducted in all patients and evaluation of facial nerve injury in patients with facial paralysis. Patients with mild conductive deafness, ossicular chain subluxation on VE, and no facial paralysis were treated conservatively for 4-12 weeks with repeated hearing evaluation; those with facial paralysis underwent surgery if no recovery after 4- 8 weeks of conservative treatment. Patients with moderate to severe conductive hearing loss or mixed hearing loss, incus long process fracture or dislocation on VE and facial paralysis, underwent ossicular chain reconstruction and facial nerve decompression after conservative treatment for 4-8 weeks, or exploratory tympanotomy only if no facial paralysis. VE, audiological tests and facial nerve function tests were repeated in 3-6 months after surgery. Results Of the 6 cases with mild conductive hearing loss, ossicular chain subluxation and no facial paralysis, 3recovered to normal hearing spontaneously and 3 showed no significant improvement, after 4-12 weeks of conservative treatment. After conservative treatment for 4-8 weeks, 3 of the 12 cases with mild conductive deafness, ossicular chain dislocation on VE and facial paralysis recovered to normal hearing and HouseBrackmann(HB) grade I facial function from HB grade II,4 showed facial function recovery to HB grade I(n=2) or II(n=2) from HB grade III but no hearing recovery, and 5 gained no recovery and went on to receive exploratory tympanotomy and facial nerve decompression. The 11 cases with moderate to severe conductive deafness, incus long process fracture or dislocation on VE and facial paralysis all received ossicular chain reconstruction and facial nerve decompression after 4-8 weeks of conservative treatment. The 7 cases with moderate to severe conductive deafness, dislocated or fallen incus on VE but no facial paralysis received ossicular chain reconstruction after conservative treatment. The 4 cases with mixed hearing loss, dislocated or fallen incus on VE and no facial paralysis received ossicular chain repair via the intact canal wall epitympanum approach after conservative treatment. Pharmacological therapies continued postoperatively in these patients to treat sensorineural deafness. Although temporal bone CT scans displayed the fracture line and malleus/incus abnormalities, VE provided additional detailed information on dislocation of incudomalleal and incudostapedial joints, incus dislocation or fracture, separation between crus longum incudis and stapes, and incus shifting. These were all confirmed during surgery. VE results and surgery findings were 100% consistent in patients with ossicular chain disruption. Conclusion VE can provide reliable visual evidence for accurate assessment of traumatic ossicular chain disruption, timing of surgery and individualizing surgical strategies and postoperative follow-up.

Supply Chain Management System Model of Virtual Enterprises Based on Multi-Agent

Based on the analysis of a virtual enterprise and the development of supply chain management, their integration is proposed. Then, the difference between multi-agent system modeling method and the traditional modeling method is analyzed, and a method based on Java agent framework for multi-agent systems（ JAFMAS） is proposed. By using this method the virtual enterprise＇ s supply chain management system model is established.

AdaptNF: Adaptive service chain scheduling with stateless migration and NF consolidation

The combination of network function virtualization and software-defined networking allows various network functions to process flows according to their characteristics and requirements.Due to the highly dynamic nature of the workload,the network infrastructure needs to properly schedule the underlying resources in order to respond to workload changes in a timely manner.However,the existing NFV platform lacks a comprehensive solution for how to scale under workload variation,which may seriously hurt the overall system performance.To improve the scalability of the NFV platform and ensure consistent high performance under dynamic workloads,we propose AdaptNF,a novel NFV platform designed to support a combination of course-grained and fine-grained resource scheduling strategies.To deal with resource imbalance,which is the essential scheduling problem that leads to insufficient NFV performance,AdaptNF adopts a novel algorithm that can efficiently balance the workload among multiple network function instances through stateless flow migration.Our controlled experiments show that the AdaptNF scheme can optimize resource allocation and ensure outstanding performance after scaling.In terms of network throughput and latency,AdaptNF significantly improves the performance of the underlying NFV platform.

元宇宙:概念、技术及应用研究综述

网络技术、人机交互和人工智能等技术的飞速发展催生了元宇宙,并进一步促进人们物质生活各个方面的数字化转型.2021年是元宇宙元年,元宇宙作为一个新兴的概念受到产业界、学术界、媒体界及公众的广泛关注.本文尝试从技术维度和应用角度深度剖析元宇宙.首先,从定义、起源与发展、特征和关键技术(网络及运算技术、物联网技术、人机交互技术、电子游戏技术、区块链技术、数字孪生技术和其他技术)等多方面对元宇宙的概念及内涵进行论述;然后,讨论了当下布局元宇宙的企业和应用实例;最后,剖析了目前元宇宙发展存在的问题和机遇,并对未来研究与应用进行了展望.通过对元宇宙当前的发展状况、研究趋势进行归纳分析以及科学地评估元宇宙的落地应用,为元宇宙研究人员提供有益的参考和借鉴.

分子水平上的虚拟仿真实验之思政元素的挖掘与提炼——以“高分子的构象、形态及尺寸的模拟与计算”项目为例

高分子的构象、形态及尺寸的模拟与计算,是分子水平上的虚拟仿真实验项目,结合诺贝尔奖获得者de Gennes和P.J.Flory的理论工作、由项目组自身教研成果转化、师生合作研发而成。与小分子化合物相比,高分子的研究方法有很大的不同,特别是需要采用统计方法来描述高分子链的构象、形态,计算高分子链的平均尺寸,这是经典的物理化学方法所不能完成的。本项目从研发到教学实践、再经改进,教学内容的更新优化中,自然融入了诺贝尔奖成果、哲学思想、科学思维、学科发展史、教研成果等多个维度的思政元素。

基于资源感知的多域服务功能链编排成本优化

网络功能虚拟化技术的兴起使得实例化为服务功能链(SFC)的网络服务能够共享基底网络,缓解了传统网络体系结构僵化的问题.然而,网络中大量服务请求给多域SFC编排带来了新的挑战.首先由于域内网络资源信息及内部策略的保密性,使得多域SFC的编排更为复杂.其次多域SFC编排要确定最佳候选编排域集,先前的研究较少考虑域间负载的均衡性,对服务接受率造成了消极影响.此外跨网络域编排服务请求对服务的成本和响应时间提出了更严格的要求.为解决上述挑战,在本文中,我们首先针对多域网络隐私性需求,提出了域级图的构造方法;然后基于域间负载均衡提出了域权重的计算方法进行SFC编排域的选择;最后,针对多域网络成本和响应时间需求,提出编排算法.实验结果表明,提出的算法有效地权衡了平均服务成本和接受率,并且在服务平均响应时间方面也得到了优化.

亚文化视域下虚拟主播的受众需求、互动机制和优化路径研究

近年来,虚拟主播作为一种网络主播新类型,深受青少年亚文化群体的喜爱。研究发现,受众喜欢虚拟主播的原因主要有虚拟主播独具魅力的亚文化风格、虚实交错的神奇体验、在线陪伴弥补现实孤独、构建完美形象和身份认同等。受众与虚拟主播的互动类型多样,直播互动具有仪式化特点,亲密关系的构建基于商业逻辑基础上。作为新兴的媒介和产业形态,虚拟主播目前还存在过度消费导致虚拟主播和粉丝的双向功能异化、虚拟主播的圈层构建的狂热与无序、受众的过度介入导致互动边界模糊行为等问题。因此,政府与社会、网络平台、主播运营公司、受众、虚拟主播等各方应各负其责,共同促进虚拟主播行业规范发展。

虚拟农业供应链模式的Repast仿真分析

通过Repast仿真技术,对比分析了传统农业供应链与大数据云服务平台支持下的农业供应链运营表现,并深入探讨了供应链中的竞争合作关系及其对决策过程和效率的影响.研究结果显示:大数据云服务平台显著提高了农业供应链的信息流通速度和协作效率,进而增强了协同效应和整体绩效.这为农业供应链的现代化转型提供了坚实的实证基础,并为供应链各参与主体提供了宝贵的参考依据.

基于虚拟集聚视角下农业产业链融合发展对策研究

农业虚拟产业集聚是数字经济创新驱动下农业产业链融合发展的新型模式,具有打破传统地理空间束缚,实现产业集群之间的跨区域合作,促进创新要素的高效流动等优势,是提升农业新质生产力的核心要素。基于农业虚拟产业集聚视角,对贵州省农业产业链融合发展现状进行分析,发现存在各主体协同创新不足、集聚水平不高、数字技术融合度不强及高层次农业人才短缺等问题。解决这些问题,相关部门要统筹规划,加强引导产业主体协同创新发展;夯实基础,打造农业产业链虚拟集聚共享平台;畅通通道,促进数字技术与农业产业链深度融合;层层把关,完善农业产业链高层次人才培养体系。

全球供应链空间重构下的中国外贸“三新”:新格局、新动能与新质生产力

习近平总书记创造性地提出“新质生产力”这一全新概念。在当前国际经济环境复杂多变、全球经贸形势日趋严峻的现实中,“加快形成新质生产力,增强发展新动能”应成为中国外贸工作的根本原则和行动指南。文章描绘了当前中国外贸的空间新格局,分析了全球供应链空间重构下呈现出的中国外贸新动能,定义和阐释了促进外贸高质量发展的“外贸新质生产力”,最后提出了政策性思考及建议。文章认为,当前,受贸易保护主义、地缘政治冲突、制造业回流等多种因素的影响,全球产业链供应链加速重构,从以成本管控、生产效能、科学技术为导向转为以供应安全、产业稳健和地缘政治为目标,并呈现出区域化、多元化、本土化、数字化、集聚化等多种形式并存的发展特征,逐渐趋向于碎片化的发展格局。在新的空间格局下,中国外贸面临着前所未有的风险和挑战,对欧美发达经济体的出口贸易大幅下降,出口企业举步维艰。面对这一复杂严峻的外部环境,中国凭借全球第一制造大国的雄厚实力,利用数字技术赋能制造业,大力推进产业结构转型升级,产品结构推陈出新,积极应对“脱钩断链”、产业链外迁导致的订单转移、出口下降这一不利局势,以电动载人汽车、锂离子蓄电池和太阳能电池为代表的“新三样”产品出口取代传统劳动密集型“旧三样”产品出口,实现了稳规模优结构、提质增效的阶段性目标,为外贸高质量发展注入了新动能。文章针对新质生产力在中国外贸领域内的具体表现进行了深入细致的分析,认为数据、信息与流量是外贸新质生产力的关键要素;新一轮科技革命与产业变革的交融是外贸新质生产力的动力源;数实融合、虚实融合是外贸新质生产力的坚实基础。外贸新质生产力具有双轮驱动的独特优势与韧性,灯塔工厂是外贸新质生产力的中流砥柱,独角兽是外贸新质生产力的生力军,建立在虚拟集聚平台上的跨境电商新模式、海外仓、全托管等新业态,形成了当前中国外贸新质生产力。要以先进制造业、新兴产业、未来产业支撑和提升外贸新质生产力,以规模巨大的国内消费市场扩大和提振外贸新质生产力。

基于技术驱动与服务创新的虚拟现实产业发展研究

虚拟现实(VR)技术以高度沉浸感为用户带来全新的多感官交互体验,推动产生新兴服务业态并以新服务模式促进传统行业转型升级,推动高附加值、高层次和多元化服务产业体系建设。本文梳理了VR产业链结构和关键技术发展现状,剖析了VR与服务业融合应用的前景、方法与场景分类,分析了VR产业的发展趋势以及我国VR产业在产业链供给、应用落地、行业规范和专业人才培育等方面面临的主要问题。研究建议:加强基础研发投入,突破核心技术难点;培育领头试点项目,打造示范应用平台;构建配套服务体系,营造良好的产业发展环境;健全高技能人才队伍建设,提升我国在全球VR产业布局中的竞争优势,加速服务业的智能化、交互性、定制化发展。

面向冷链智能立体仓库的数字孪生系统构建

目的当前冷链物流行业立体仓库存在货品损耗率高、失温严重、信息化水平低等问题,确保冷链智能立体仓库的食品质量安全,并实现降本增效。方法面向冷链智能立体仓库的运行场景,设计全映射与多维仿真的数字孪生五维模型,通过对多源异构数据的融合,实现立体仓库全要素的状态实时可视化与监测预警,并提出一种支持系统联动决策的模型优化策略,对立体库负载与温控区热力分布进行智能调节,最大限度提高运行效率和降低运营成本。结果构建了一套冷链智能立体仓库数字孪生系统,通过对优化前后仓库运行数据进行对比,同等仓储环境条件下生鲜蔬菜的食品保鲜度损耗率同比下降了25%~30%,实现了冷链智能立体仓库实时数据与动态虚拟模型的精准映射与联动运转。结论以广东某供应链管理有限公司佛山智能冷链仓储物流中心的冷链立体仓库为实践对象,形成了冷链智能立体仓库一体化管控新模式。为冷链智能立体仓库运营管理、调度联动决策与协同作业提供了数字孪生技术的应用参考,为建立更完善的保鲜产品包装与冷链食品质量安全提供了新路径。

适用于多虚拟电厂交易的改进拜占庭容错算法共识机制

分布式能源投资主体的多样性,使各资源在互动过程中的信任构建更加困难,因此需要探究多虚拟电厂交互模式并构建相应信任体系。基于主侧区块链技术构建了多虚拟电厂交易模型总体架构,明确了多虚拟电厂交易流程。通过主侧锚定技术构建跨链通道,实现多虚拟电厂链上协同运行模式。针对节点维护区块链网络环境积极性不高导致的信任环境缺失和区块链性能下降的问题,基于节点功能不同提出了一种差异化信用评价指标来规范节点行为,同时利用该指标对拜占庭容错算法(practical byzantine fault tolerance,PBFT)进行改进。实验结果表明使用差异化信用评价指标改进的共识算法在所提多虚拟电厂架构下能构建信任环境并提升共识效率。

GAT-IL:一种基于图注意力网络与模仿学习的服务功能链部署方法

网络功能虚拟化通过将网络功能从专用硬件设备迁移到商用服务器上运行的软件中间盒中,简化了网络服务的配置和管理.在网络功能虚拟化的环境下,由一系列有序的虚拟网络功能组成的服务功能链正在成为承载网络服务的主流形式.将底层物理网络资源分配给服务功能链的需求称为服务功能链部署问题.对于基础设施提供商来说,在有限的资源条件下获得长期高回报是一个重要的挑战.本文形式化定义了服务功能链部署问题,提出了一种基于图注意力网络与模仿学习的服务功能链部署方法(Graph Attention Network and Imitation Learning,GAT-IL).该方法使用图注意力网络评估每个物理服务器的放置潜力,通过蒙特卡洛树搜索方法给出专家示范,并采用模仿学习方法进行智能体的训练,融入集束搜索策略优化解空间.大量的实验结果表明,本文提出的GAT-IL方法在平均收益代价比和接受率的性能指标上均优于现有代表性算法.