移动边缘计算中基于联邦学习的视频请求预测和协作缓存策略

随着互联网社交平台的崛起和移动智能终端设备的普及,自媒体短视频、直播等视频业务蓬勃发展,人们对高质量视频服务的需求也急剧上升。与此同时,连接到核心网络的大量智能设备增加了回程链路的负载,传统的云计算难以满足用户对视频服务的低延迟要求。移动边缘计算(MEC)通过在网络边缘部署具有计算和存储能力的边缘节点,通过在更靠近用户的边缘侧提高计算和存储服务,降低了数据传输时延进而缓解了网络阻塞。因此,基于MEC架构,该文充分利用网络边缘资源,提出了基于联邦学习的视频请求预测和视频协作缓存策略。通过利用多个边缘节点对提出的深度请求预测模型(DRPN)视频请求预测模型进行联邦训练,预测视频未来的请求情况,然后量化缓存内容所带来的时延收益并协作地以最大化该时延收益为目的进行缓存决策。该文分析了真实数据集MovieLens,模拟了视频请求缓存场景并进行实验。仿真结果表明,相比于其他策略,所提策略不仅能有效降低用户等待时延,在有限的缓存空间中提高内容多样性,从而提高缓存命中率,降低缓存成本,还能降低整个系统的通信成本。

计及充电请求预测补偿的电动汽车有序充电策略

针对现有有序充电策略未能充分考虑和应用后续时段内新增充电请求的问题,提出了一种计及充电请求预测补偿的住宅区电动汽车有序充电控制策略。在均分出的每个控制时段末,该策略依据实际新增充电请求数据修正了先前控制时段对当前控制时段新增充电请求的预测结果,并采用预测结果对后续各控制时间段内的新增待充电请求作了补偿,提高了充电请求预测结果的应用效果。在此基础上,构建了使系统负荷波动最小的有序充电控制模型。大量的算例分析及结果表明,该策略实施效果上佳,应用前景可观。

基于带宽请求预测和云资源预留的视频移植策略

提出云辅助P2P-VoD架构下的视频移植策略。首先根据P2P特性预测每视频频道的用户带宽请求数,为视频移植提供依据。而后设计了最小预留带宽的云带宽资源申请算法,利用较小的开销代价满足VoD服务实时性要求。最后设计了移植策略,决定如何进行视频移植。实验结果表明,提出的策略能够在费用开销和用户满意度之间取得较好的平衡。

C-V2X边缘缓存中文件请求预测机制

在基于蜂窝通信演进形成的车用无线通信技术(Cellular-Vehicle to everything,C-V2X)场景下,基站作为多接入边缘计算(Multi-access Edge Computing,MEC)边缘缓存节点可提高用户获取数据的效率,但其缓存容量有限.因此,C-V2X中如何准确预测缓存请求内容成为待解决的重要问题.本文从文件请求的时变性出发,针对实际的城市场景,采用Simulation of Urban MObility(SUMO)对交通流进行建模;其次,通过采集实际网站分时分类的点击量数据,并根据各路段交通流规律进行预处理,构建用户请求模型;最后,利用Long Short-Term Memory(LSTM)深度学习模型进行训练,预测各基站的文件请求.仿真结果表明,在网易新闻流行度分布和请求间隔分布形成的文件请求下,vanillaLSTM模型对娱乐类型数据集预测时的均方根误差在1.3左右.

面向组播的动态虚拟网络功能放置算法

组播在支持日益增长的多媒体应用方面具有广阔的应用前景,面向组播的虚拟网络功能放置是网络功能虚拟化中不可避免的研究趋势.然而,对于该问题的大多数研究都聚焦于静态网络环境,难以应对网络中的各种资源随着时间动态变化,组播服务功能链(Service Function Chaining,SFC)请求动态到达的真实场景.本文提出一种基于组播SFC请求预测的足球联赛竞争算法,以Informer模型为基础,预测即将到达的组播SFC请求.基于足球联赛竞争的组播虚拟网络功能放置算法,设计多维个体编码策略,一次性求解所有活动组播组的SFC映射方案,提前部署预测的请求.针对预测结果与真实结果不一致的情况,提出一种由正向搜索与反向搜索组成的快速修复策略以完成对请求的快速响应.仿真结果表明,对比其它两种预测模型,Informer在组播SFC请求预测上取得了更低的均方误差与平均绝对误差.此外,与七种经典的启发式算法和深度强化学习算法相比,提出的算法在端到端时延和计算资源消耗方面达到更优性能的同时,取得了更低的组播SFC请求响应时间.

基于OpenFlow的流媒体云服务迁移方法

传统基于应用层中间件或代理的服务迁移技术容易造成单点故障且扩展性差,并且流媒体的交互性和长会话特性使其难以实现对用户透明。为此,提出一种基于Open Flow的流媒体云服务迁移方法。通过在网络层进行流媒体云迁移实现对用户的服务透明,同时针对网络层的服务迁移代价问题,提出一种基于用户请求预测的迁移策略,在提升系统容量的同时优化服务迁移数。实验结果表明,该迁移策略可有效地提高服务请求接受率,进而增强系统服务能力。

CTCPPre: A prediction method for accepted pull requests in GitHub

As the popularity of open source projects,the volume of incoming pull requests is too large,which puts heavy burden on integrators who are responsible for accepting or rejecting pull requests.An accepted pull request prediction approach can help integrators by allowing them either to enforce an immediate rejection of code changes or allocate more resources to overcome the deficiency.In this paper,an approach CTCPPre is proposed to predict the accepted pull requests in GitHub.CTCPPre mainly considers code features of modified changes,text features of pull requests’description,contributor features of developers’previous behaviors,and project features of development environment.The effectiveness of CTCPPre on 28 projects containing 221096 pull requests is evaluated.Experimental results show that CTCPPre has good performances by achieving accuracy of 0.82,AUC of 0.76 and F1-score of 0.88 on average.It is compared with the state of art accepted pull request prediction approach RFPredict.On average across 28 projects,CTCPPre outperforms RFPredict by 6.64%,16.06%and 4.79%in terms of accuracy,AUC and F1-score,respectively.

Intelligent Resources Management System Design in Information Centric Networking

Information centric networking(ICN) is a new network architecture that is centred on accessing content. It aims to solve some of the problems associated with IP networks, increasing content distribution capability and improving users' experience. To analyse the requests' patterns and fully utilize the universal cached contents, a novel intelligent resources management system is proposed, which enables effi cient cache resource allocation in real time, based on changing user demand patterns. The system is composed of two parts. The fi rst part is a fi ne-grain traffi c estimation algorithm called Temporal Poisson traffi c prediction(TP2) that aims at analysing the traffi c pattern(or aggregated user requests' demands) for different contents. The second part is a collaborative cache placement algorithm that is based on traffic estimated by TP2. The experimental results show that TP2 has better performance than other comparable traffi c prediction algorithms and the proposed intelligent system can increase the utilization of cache resources and improve the network capacity.

An energy-saving scheduling scheme for streaming media storage systems

The rapid growth of streaming media applications on the Internet is proposing higher requirements on energy consumption and I/O performance of the storage systems.However,the optimized I/O requests from different initiators will be mixed disorderly when they are reaching the storage system concurrently,which leads to increasing energy consumption.This paper proposes an energy-saving scheduling scheme based on I/O Stream(ES-IOS).The ES-IOS scheme can take the advantage of the I/O characteristics of streaming media and reorganize the mixed and disordered I/O requests into "streams".Technically,The ES-IOS scheme includes two main points,a priority-based weighted stream scheduling algorithm(PWSS) and a regression-fitting-based popularity prediction algorithm(RFPP).The PWSS algorithm can schedule the I/O streams in weighted queue based on priority to limit energy consumption.The priority of each stream is determined by its popularity.According to the I/O access records over a period,the RFPP algorithm can predict the popularity of each stream via regression fitting.Based on the popularities,the PWSS algorithm assigns more continuous service time to the hot streams and reversely less service time to the cold ones.Trace-driven experiments show that the ES-IOS scheme can reduce the energy consumption by 38%and enhance the I/O throughput by 27%approximately.