Edge Cloud Infrastructurefor the future network
Technology convergence promotesthe next-generation information infrastructureQuantum computingCalculateabilityData & PerceptionUbiquitous & Connected5G/6GInternet of thingsNew generationLearning and AdaptationAIinformation infrastructurein everywhereSecurity and CreditBlock chain2
Network Evolution: Internet - Internet ofThings - Value NetworkInternetInformation sharing——connection & sharingInternet of ThingsData exchange——data & perceptionValue NetworkValue transfer——credit & exchangePortal for e-commerceand webWeb 1.0User relationship& Data monopolistWeb 2.0IoT connectivity will bemore complete, and datacollection will be morereal-time with the boost of5GThe distributed andautonomous globalizedeconomic era based on“trust” will graduallyemerge3
Architecture Evolution: Centralization - DecentralizationFrom 1940s to 1990s1990s-2000MainframeDistributed tunitiesin streamingmedia fieldfrom 2006 to2016Edge computationRapid developmentsince 2008It was proposed in2004 and achieved ascale of production in2011.HadoopCentralized architectureBlock chainIt has graduallydeveloped andinnovated sincethe conceptformation in 2016.Decentralized architecture4
New business promotes the evolution anddevelopment of DC technology Data center transforms from "resource carrier" to "service carrier"Cloud data centerSaaSData centerfor rental ofbasicresourcesHostingdatacenterPaaSConverged data center Clouding platform ,resourceheterogeneity, cloudedge collaboration Ecologicalization andfragmentation ofbusinessData-orientedoperation andintelligence Trade-off betweenReliability andavailability Rental ofinfrastructureresources IaaSIT infrastructureservices Large, virtualized,integrated, and ondemand cloud services Green technology5
Decentralization mode will push edge DCinto a new form of DCThe edge of the infrastructurefrom the carrier's perspective The IT resources of networkoperators or service providerslocated in the "last mile" aremainly constructed by edge DC.&The edge of the device fromthe end user's perspective Edge computing resources on thenetwork terminal or device side,including traditional Internet devices(such as mobile phones) and newsmart devices (such as smart cars) Edge DCemphasizes thedistribution ofnodes rather thancentralization,which is highlycomplementary tocloud computingdata center.6
Edge cloud is the extension from centercloud DC to edge DC Edge cloud extends someservices or capabilities of thecloud (including but notlimited to storage, computing,network, AI, large data,Center-edge CoordinationNetwork-wide ComputingSchedulingUnified management and controlover the entire networksecurity, etc.) to edge DC. Center DC and edge DCcooperate with each other toCenter cloudrealize the "ubiquitous" cloud. Solve the problem of longlatency and bandwidthoccupancy caused bycentralized deployment ofcloud computing7
Edge cloud from the perspective of serviceNew service in the futureProblemsCharacteristics of the service1、Massive Data 50 billion connected wirelessAutopilotdevices, generating 600 terabytes1msof data, but only a small amount50Mbps Public safety AR/VR Remote operation of key data in 2020, according toCisco's forecast.20ms1 10ms20ms Sensors and cameras on driverless1Gbps300Mbps10Mbcars produce 1GB of data perpsHD videoUAVdeliverysecond.Intelligent “Skynet” has installed more thanvenues10ms20ms20 million high-definition Real-timeprocessingcollaboration Servicessuchas autopilot and1ms10ms1 10Mbptelemedicinewhosedata requires50Mbpssreal-time processing and timelyTelemedicine diagnosisresponse.The existing cloud is difficultto meet the low-latency andreal-time processingrequirements of massivedata services.Cloud centerTypicaldistance200km 500kmDelay tion“low cost”Contentdistribution“Large bandwidth”Calculationmarginalization“Ultra low latency”AccessWith the vigorous development of IoT, big data and big video, the existing networkand cloud centralized deployment are difficult to meet the new business needs. Itis an industry trend to make the network and cloud migrate to the edge with"business flow" through edge computing.8
Edge computing (MEC) scenarios defined by ETSIFor service scenarios such as enterprise parks, venues, manufacturing and households, edgecomputing brings potential business innovation while satisfying and optimizing experience needs.Video optimizationVideo stream analysisInternet of vehicles.Augmented realityAssisted Sensitive ComputingEdge applications provide high-performancecomputing power, perform time-sensitive dataprocessing, and feedback the results to enddevices, such as intelligent robots.。Enterprise diversionIoT/Industrialinterconnection9
Scenario of the edge cloud—— CDN sinking The CDN cache node sinks to the network edge DC, reducing network backhaul costand central node pressure, reducing latency and improving user experience:: Fixed-line CDNs generally sink to the core area of each metropolitan now. With the development oflarge video services, there is a need for further sinking;; mobile network traffic generally needs to be exported to the IDC through the provincial center of themobile core network, and the relative delay is large, requiring the sinking demand;; sinking increases the cost of edge nodes, requiring comprehensive analysis of experience, cost,and benefits;BBUEdgeOnlinecaching transcodingapplication applicationCDN serviceNetwork element ofcontrol plane /Centralized gatewayContent source @ Centraldata centerMEC edge cloudNetwork delay is 5-15ms, ensuring video service experienceKPIHD video(720p)HD video(1080p)VR videoIncrease of video download rate14.71% 47.41% 7.76% Decrease of round trip delay19.04% 32.58% 27.10% Decrease of dragging wait delay61.18% 14.65% 12.12% Note: this is the preliminary test result and further testing and verification is ongoing;10
Scenario of edge cloud-industrial internet In intelligence industrial manufacturingindustry, The factory intelligence is implementedon the edge. An example: Taking the quality inspection ofintelligent machine vision in industrialmanufacturing , making real-time analysis based onproduct images captured by the camera on theproduction line, detecting product defects andadjusting the parameters of control manipulator inreal time; Edge computing cooperates with cloudcomputing : the central cloud is responsible for AImodel training, and the factory edge performslocal reasoning on the trained AI modelCloud edge collaborationin intelligent industrial manufacturing11
The requirements of edge cloud applicationsfor future networkSmart portIndustrial parkMine parkManufacturing① Intelligent connectioncapabilities② Intrinsic securityRemote control: 1msVideo surveillance: 100M uplinkStadiumData transmission: 2GbpsVideo surveillance: 100M uplinkStationUAV image return: 10msExhibition hallAR Maintenance: 1GbpsIntelligent sorting: 10msV2Xcapabilities③ Cloud & edgecollaboration capabilities④ Smart operation &maintenance capabilities :⑤ Low-cost networkingVideo: throughput 1TAR/VR: rate 2G/userFree video: throughput 1T/sVideo surveillance: rate 100MbpsVR guide: delay 20ms,Bandwidth 2GbpsAutopilot: 1mscapabilities12
The impact on future networks 1:SGW of edge cloud will move close to the userIn order to effectively reduce the delay and provide the nearestNB-IoT accessservice, the service gateway(SGW) of the operator's multipleaccess networks must be moved down to the edge cloud forMobile accessdeployment.Internet/headquarters/branch networkingvCPEPGW-UWi-Fi accessUPFFixed access (family)vBNGUEdge cloudThe edge cloud infrastructure and the bearer network from multipleFixed access (enterprise)EPC5GCvBNG-CCore cloudaccess points to edge clouds must meet the requirements of lowlatency, high bandwidth, security and stability for various edgecomputing applications.13
The impact on future networks 2:Edge server towards customization Edge nodes have strong physicalconstraints in space and power supply,Customized server scheme for edge roomload bearing, etc,the deployment ofedge cloud infrastructure has to meetthe performance requirements of thebusiness on the premise of limitedspace, power resources, and load-bearing capacity. Edge room server of single OTII Applicable to scenarios where networkEdge room server of dualOTIItraffic is mainly forwarded, and powerApplicable to scenarios with highconsumption and space constraintsCPU and memory requirements,are strict.and good room conditions.OTII (Open Telecom IT Infrastructure):forming server technology solutionsand prototype products of deepcustomization, open standards andunified norms for telecomapplications in operator industryDimensions 465mm(D) x 438mm(W) x 87mm(H) 19.7“ x 17.1”x 3.4”14
The impact on future networks 3:Edge acceleration to support ble for data packet forwardingwith simple business and highthroughputAcceleratedresource pool offorwardingserviceService computingacceleration:FPGAProgrammable and suitable forinfrequently changing servicesAcceleratedresource poolof computingserviceGraphic computingacceleration:GPUAI computingacceleration:AI chipsGood at parallel computing,whole data stream processingTypical AI algorithmsAcceleratedresource poolofgraphic serviceAcceleratedresource poolof AI service15
The impact on future networks 4: Unifiedmanagement & control for cloud, network, edge andterminal Edge cloud drives the evolution of network architecture It is necessary to consider the cooperation between the edge intra-cloud network(physical/virtual) and the extra-cloud network (access network/metropolitan areanetwork), and the network should be optimized and evolved from the architecture. Edge cloud management requires to build a unified management and control system toachieve the optimal forwarding path of network① Infrastructure resource management of EdgeDC and access site② Network orchestration of edge cloud③ Management of edge cloud elements(VM/container/specific)④ Coordination between edge cloud, publiccloud, network and terminal16
Summary Decentralized cloud infrastructure will be the main development direction inthe future The edge cloud infrastructure and the basic bearer network from multipleaccess points to edge clouds must meet the basic requirements of low latency,high bandwidth, security and stability for various edge computing applications. The diversity of edge computing services leads to the diversity of edgeacceleration devices. More acceleration hardware is needed to form aheterogeneous hardware acceleration platform. A unified and coordinated management and control system for “edge could,center cloud , cloud network & teminal“ is needed.17
THANKS
It is necessary to consider the cooperation between the edge intra-cloud network (physical/virtual) and the extra-cloud network (access network/metropolitan area network), and the network should be optimized and evolved from the architecture. Edge cloud management requires to build a unified management and control system to
May 02, 2018 · D. Program Evaluation ͟The organization has provided a description of the framework for how each program will be evaluated. The framework should include all the elements below: ͟The evaluation methods are cost-effective for the organization ͟Quantitative and qualitative data is being collected (at Basics tier, data collection must have begun)
Silat is a combative art of self-defense and survival rooted from Matay archipelago. It was traced at thé early of Langkasuka Kingdom (2nd century CE) till thé reign of Melaka (Malaysia) Sultanate era (13th century). Silat has now evolved to become part of social culture and tradition with thé appearance of a fine physical and spiritual .
On an exceptional basis, Member States may request UNESCO to provide thé candidates with access to thé platform so they can complète thé form by themselves. Thèse requests must be addressed to esd rize unesco. or by 15 A ril 2021 UNESCO will provide thé nomineewith accessto thé platform via their émail address.
̶The leading indicator of employee engagement is based on the quality of the relationship between employee and supervisor Empower your managers! ̶Help them understand the impact on the organization ̶Share important changes, plan options, tasks, and deadlines ̶Provide key messages and talking points ̶Prepare them to answer employee questions
Dr. Sunita Bharatwal** Dr. Pawan Garga*** Abstract Customer satisfaction is derived from thè functionalities and values, a product or Service can provide. The current study aims to segregate thè dimensions of ordine Service quality and gather insights on its impact on web shopping. The trends of purchases have
Bruksanvisning för bilstereo . Bruksanvisning for bilstereo . Instrukcja obsługi samochodowego odtwarzacza stereo . Operating Instructions for Car Stereo . 610-104 . SV . Bruksanvisning i original
Chính Văn.- Còn đức Thế tôn thì tuệ giác cực kỳ trong sạch 8: hiện hành bất nhị 9, đạt đến vô tướng 10, đứng vào chỗ đứng của các đức Thế tôn 11, thể hiện tính bình đẳng của các Ngài, đến chỗ không còn chướng ngại 12, giáo pháp không thể khuynh đảo, tâm thức không bị cản trở, cái được
10 tips och tricks för att lyckas med ert sap-projekt 20 SAPSANYTT 2/2015 De flesta projektledare känner säkert till Cobb’s paradox. Martin Cobb verkade som CIO för sekretariatet för Treasury Board of Canada 1995 då han ställde frågan