idnits 2.17.1 draft-liu-apn-edge-usecase-03.txt: Checking boilerplate required by RFC 5378 and the IETF Trust (see https://trustee.ietf.org/license-info): ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/1id-guidelines.txt: ---------------------------------------------------------------------------- No issues found here. Checking nits according to https://www.ietf.org/id-info/checklist : ---------------------------------------------------------------------------- ** There are 8 instances of too long lines in the document, the longest one being 1 character in excess of 72. Miscellaneous warnings: ---------------------------------------------------------------------------- == The copyright year in the IETF Trust and authors Copyright Line does not match the current year == The document doesn't use any RFC 2119 keywords, yet seems to have RFC 2119 boilerplate text. -- The document date (June 02, 2021) is 1059 days in the past. Is this intentional? Checking references for intended status: Informational ---------------------------------------------------------------------------- == Unused Reference: 'I-D.li-apn-framework' is defined on line 475, but no explicit reference was found in the text == Unused Reference: 'I-D.li-apn-problem-statement-usecases' is defined on line 481, but no explicit reference was found in the text == Outdated reference: A later version (-07) exists of draft-li-apn-framework-02 == Outdated reference: A later version (-08) exists of draft-li-apn-problem-statement-usecases-01 Summary: 1 error (**), 0 flaws (~~), 6 warnings (==), 1 comment (--). Run idnits with the --verbose option for more detailed information about the items above. -------------------------------------------------------------------------------- 2 Network Working Group P. Liu 3 Internet-Draft Z. Du 4 Intended status: Informational China Mobile 5 Expires: December 4, 2021 S. Peng 6 Z. Li 7 Huawei 8 June 02, 2021 10 Use cases of Application-aware Networking (APN) in Edge Computing 11 draft-liu-apn-edge-usecase-03 13 Abstract 15 The ever-emerging new services are imposing more and more highly 16 demanding requirements on the network. However, the current 17 deployments could not fully accommodate those requirements due to 18 limited capabilities. For example, it is difficult to utilize the 19 traditional centralized deployment mode to meet the low-latency 20 demand of some latency-sensitive applications. Moreover, the total 21 amount of centralized service data is growing exponentially, which 22 brings great pressure on the network bandwidth. There has been a 23 clear trend that decentralized sites comprising of computing and 24 storage resources are deployed at various locations to provide 25 services. In particular, when the sites are deployed at the network 26 edge, i.e. the Edge Computing, it can better handle the business 27 needs of the users nearby, which provides the possibilities to 28 provide differentiated network and computing services. In order to 29 achieve the full benefits of the edge computing, it actually implies 30 a precondition that the network should be aware of the applications' 31 requirements in order to steer their traffic to the network paths 32 that can satisfy their requirements. Application-aware networking 33 (APN) aims to accommodate the edge services' needs, fully releasing 34 the benefits of the edge computing. 36 This document describes the various application scenarios in edge 37 computing to which the APN can be beneficial, including augmented 38 reality, cloud gaming and remote control, which empowers the video 39 business, users interaction business and user-device interaction 40 business. In those scenarios, APN can identify the specific 41 requirements of edge computing applications on the network, process 42 close to the users, provide SLA guaranteed network services such as 43 low latency and high reliability. 45 Requirements Language 47 The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", 48 "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this 49 document are to be interpreted as described in RFC 2119 [RFC2119]. 51 Status of This Memo 53 This Internet-Draft is submitted in full conformance with the 54 provisions of BCP 78 and BCP 79. 56 Internet-Drafts are working documents of the Internet Engineering 57 Task Force (IETF). Note that other groups may also distribute 58 working documents as Internet-Drafts. The list of current Internet- 59 Drafts is at https://datatracker.ietf.org/drafts/current/. 61 Internet-Drafts are draft documents valid for a maximum of six months 62 and may be updated, replaced, or obsoleted by other documents at any 63 time. It is inappropriate to use Internet-Drafts as reference 64 material or to cite them other than as "work in progress." 66 This Internet-Draft will expire on December 4, 2021. 68 Copyright Notice 70 Copyright (c) 2021 IETF Trust and the persons identified as the 71 document authors. All rights reserved. 73 This document is subject to BCP 78 and the IETF Trust's Legal 74 Provisions Relating to IETF Documents 75 (https://trustee.ietf.org/license-info) in effect on the date of 76 publication of this document. Please review these documents 77 carefully, as they describe your rights and restrictions with respect 78 to this document. Code Components extracted from this document must 79 include Simplified BSD License text as described in Section 4.e of 80 the Trust Legal Provisions and are provided without warranty as 81 described in the Simplified BSD License. 83 Table of Contents 85 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 86 2. Edge Computing and APN . . . . . . . . . . . . . . . . . . . 3 87 3. Usage Scenarios of APN in edge computing . . . . . . . . . . 4 88 3.1. Augmented Reality (AR) . . . . . . . . . . . . . . . . . 4 89 3.1.1. Use Case Description . . . . . . . . . . . . . . . . 4 90 3.1.2. Augmented Reality Today . . . . . . . . . . . . . . . 4 91 3.1.3. Augmented Reality with Edge Computing and APN . . . . 5 92 3.2. Cloud Gaming . . . . . . . . . . . . . . . . . . . . . . 6 93 3.2.1. Use Case Description . . . . . . . . . . . . . . . . 6 94 3.2.2. Cloud Gaming Today . . . . . . . . . . . . . . . . . 6 95 3.2.3. Cloud Gaming with Edge Computing and APN . . . . . . 7 96 3.3. Remote control of industry . . . . . . . . . . . . . . . 8 97 3.3.1. Use Case Description . . . . . . . . . . . . . . . . 8 98 3.3.2. Remote control of industry Today . . . . . . . . . . 8 99 3.3.3. Remote control of industry with Edge Computing and 100 APN . . . . . . . . . . . . . . . . . . . . . . . . . 9 101 4. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . 10 102 5. Security Considerations . . . . . . . . . . . . . . . . . . . 10 103 6. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 10 104 7. Normative References . . . . . . . . . . . . . . . . . . . . 11 105 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 11 107 1. Introduction 109 Edge computing is to deploy service sites near the user side to 110 provide users with better network and computing services. The 111 services of edge computing can not only be implemented in the edge 112 data center, but also be integrated in the network equipment, which 113 brings the possibility for the convergence of network and computing, 114 and also puts forward the requirements for the technology combining 115 of different industries. On the one hand, the demand of different 116 applications for the network need to be exposed; on the other hand, 117 the network needs to be aware of computing power and steers the 118 traffic along the appropriate path towards the suitable sites. 120 The existing network can only identify the application demands in a 121 coarse granularity. When the application demand is high causing the 122 heavy network load, it usually fails to guarantee the latency and 123 reliability of the applications especially the mission-critical 124 applications. Application-aware networking (APN) faciliates service 125 provisioning in a fine granularity, and then either steer the 126 corresponding traffic onto the appropriate network path (if exist) 127 that can satisfy these requirements or establish an exclusive network 128 path which wouldn't be influenced by other applications' traffic 129 flow. 131 2. Edge Computing and APN 133 In a whole edge computing network, there are user terminal, edge 134 gateway and edge data center. The edge gateway can be the UPF In 5G 135 network. Edge data center is usually close to users and serves a 136 limited group of users, the network and computing tasks performed by 137 edge computing are more specific and customized. Both computing 138 resources and network resources need to be able to provide fine- 139 grained service guarantee. The goal of APN is to provide fine- 140 grained network service, including latency, jitter, reliability and 141 others, which can be well matched with edge computing. 143 Appilication-aware networking includes the app-aware edge (APN-Edge), 144 app-aware process head-end (APN-Head), app-aware process mid-point 145 (APN-Midpoint) and app-aware process end-point (APN-Endpoint). A 146 user's request is sent from the client, and then passes through all 147 the nodes of the APN network to the server. The function of APN-Edge 148 can be deployed in the edge gateway, so the request traffic of client 149 can be distinguished by the edge gateway/APN-Edge and sent to the 150 edge data center through the APN. In some cases, the reply of the 151 edge data center will not return to the original client, and may be 152 sent to another client through the APN. 154 +------+ +----------------+ +-------------+ +---------+ 155 | | | Edge Gateway/ | | APN | | Edge | 156 |Client|<-->| |<-->| |<-->| Data | 157 | | | APN-Edge | | Network | | Center | 158 +------+ +----------------+ +-------------+ +---------+ 160 Edge Computing and APN 162 3. Usage Scenarios of APN in edge computing 164 This section presents several typical scenarios which require edge 165 computing to interconnect and to co-ordinate with APN to meet the 166 service requirements and ensure user experience. 168 3.1. Augmented Reality (AR) 170 3.1.1. Use Case Description 172 Augmented reality is a relatively new application that promotes the 173 integration of real world information and virtual world information 174 content. It includes several technologies, such as track 175 registration, display, virtual object generation, interaction and 176 merging. 178 3.1.2. Augmented Reality Today 180 AR gives users an immersive experience. It is widely used in the 181 consumer industry presently, and may also be applied in industrial 182 fields such as health care and education in the future. The general 183 process of AR / VR is as follows: 185 * Image acquisition equipment (such as camera) collects image or 186 video information and sends it to data center. 188 * Data center carries out identification, feature extraction and 189 template rendering, and sends them to AR terminal. 191 * The AR terminal plays the synthesized information. 193 Considering the user experience, AR usually needs a high bandwidth of 194 100mbps due to multi-channel acquisition of image or video data, and 195 a low end-to-end latency less than 60ms. With centralized 196 deployment, the network transmission distance is too long, so the 197 latency demand can't be met; the large volume of traffic load also 198 imposes high challenge on the network bandwidth. 200 3.1.3. Augmented Reality with Edge Computing and APN 202 If the deployment mode of edge computing is adopted, the following 203 functions can be realized: 205 * The collected image or video information can be encoded/decode and 206 compressed by the edge equipment to reduce the bandwidth requirements 207 of data transmission. 209 * The edge data center can process the collected image or video data 210 nearby and send it to the AR terminal equipment, which reduces the 211 distance of network transmission and greatly reduces the latency. 213 Although edge computing can reduce the overall latency of services 214 and reduce the demand for network bandwidth, it still needs 215 differentiated network services to provide the ultimate guarantee for 216 application with high SLA requirements. APN can achieve: 218 * Edge device obtains and encapsulates AR application feature 219 information and sends it to the headend node. 221 * Headend node in the APN identifies the AR data flow and steers it 222 into a specific transmission path according to the demanded 223 bandwidth, latency and reliability. 225 * Mid point in the APN forwards the data stream along the specific 226 path. 228 * End point in the APN receives AR data stream and forwards it either 229 to Data Centre for processing or to the AR player for playing. 231 In the whole process, because APN identifies the traffic of AR 232 application, it can provide corresponding network services to provide 233 customized high reliability, low latency and other SLA guarantee. 235 +------+ Camera +------+ 236 |Source| ->| AR | 237 |data |-\ / |Player| 238 +------+| +-----+ +-------+ +---------+ +-------+ / +------+ 239 \->|APN | | APN | | Edge | | APN |-/ 240 |- |-->| |-->| Data |-->| | 241 /->|Edge | |Network| | Center | |Network|-\ 242 +------+ | +-----+ +-------+ +---------+ +-------+ \ +------+ 243 |Source|-/ \ | AR | 244 |data | ->|Player| 245 +------+ Camera +------+ 247 Augmented Reality with Edge Computing and APN 249 3.2. Cloud Gaming 251 3.2.1. Use Case Description 253 Cloud gaming is to deploy the game application in the data center, 254 and realize the functions includes the logical process of game 255 command control, as well as the tasks of game acceleration, video 256 rendering and other tasks with high requirements for chips. In this 257 way, the terminal is a video player. Users can get a good game 258 experience without the support of high-end system and chips. 260 Compared with the traditional game mode, there are several advantages 261 of cloud game, such as no installation, no upgrade, no repair, quick 262 to play and reduce the terminal cost, so it will have stronger 263 promotion. 265 3.2.2. Cloud Gaming Today 267 The biggest feature of cloud games is that users interact with each 268 other through the network. The general process is as follows: 270 * The data center sends game video streaming information to the 271 terminal, including game background picture, characters, etc. 273 * The user makes corresponding operation instructions according to 274 the received game video stream information and sends them to the data 275 center. 277 * The data center constantly updates the video stream and other data 278 of the game according to the user's operation instructions. 280 Game users usually pursue consumption experience. Currently, most 281 users are willing to spend extra money in order to obtain better user 282 experience. Generally speaking, the network latency of game is 283 required to be less than 30ms. For competitive game, the latency 284 will be required to be less than 10ms, because professional players 285 usually can feel the millisecond level latency difference. With 286 centralized deployment, the network transmission distance is too 287 long, which is a huge challenge to the network load, so the latency 288 demand can't be met; the large volume of traffic load also imposes 289 high challenge on the network bandwidth. 291 3.2.3. Cloud Gaming with Edge Computing and APN 293 If the deployment of edge computing is adopted, the following 294 functions can be realized with the deployment of edge data center: 296 * The edge data center sends the game video stream information to the 297 terminal, and receives the user's control instruction information for 298 processing. 300 * users can make corresponding operation instructions according to 301 the received video stream information, and get quick response. 303 Edge computing can reduce the latency of game data transmission as a 304 whole, but it should be noted that cloud games usually have multiple 305 players playing a game together, which requires the deterministic 306 latency of multi-party network path, which needs to be realized with 307 APN: 309 * Multiple edge devices obtain and encapsulate cloud game application 310 feature information and send it to the head end node. 312 * Headend node in the APN identifies the data flow of cloud games 313 (maybe the same game), and steers it into a specific transmission 314 path according to its requirements for bandwidth, delay, reliability, 315 etc., which needs to ensure that the latency of multi-user control 316 instructions arriving at the edge data center is consistent. 318 * Midpoint in the APN forwards game data stream according to the 319 predetermined path. 321 * The endpoint in the APN receives the cloud game data stream and 322 steers it either to the data center for processing the users' control 323 instruction or to the user for playing. 325 The whole process requires APN not only to identify the cloud game 326 traffic and provide customized network forwarding services for it, 327 but also to ensure the deterministic latency of multi-user in the 328 same game and provide better game experience. 330 Client A 331 +---------+ 332 |Game data| 333 +---------+-\ +----------+ +-----------+ +-----------+ 334 |<->| APN- |-A-| APN |-A-| | 335 | Edge A | | Network A | | | 336 +----------+ +-----------+ | Edge Data | 337 +----------+ +-----------+ | Center | 338 | APN- | | APN | | | 339 |<->| Edge B |-B-| Network B |-B-| | 340 +---------+-/ +----------+ +-----------+ +-----------+ 341 |Game data| 342 +---------+ 343 Client B 345 Cloud Gaming with Edge Computing and APN 347 3.3. Remote control of industry 349 3.3.1. Use Case Description 351 Industrial remote control refers to the remote control of field 352 equipment in areas that are not convenient for manual field control, 353 such as high-temperature and high-risk areas. In the past, signaling 354 was usually transmitted through industrial private networks and 355 protocols. With the development of industrial Internet, the industry 356 also gradually has the demand of network interconnection. Its 357 network tends to adopt L3 protocol and flat architecture, which makes 358 it possible for cross distance remote control service. 360 3.3.2. Remote control of industry Today 362 In the process of remote control, workers constantly make control 363 instructions according to the received image or video information of 364 field equipment, which requires interaction between personnel and 365 equipment through the network. Because the field environment that 366 needs remote control is generally poor, it is also a challenge for 367 the security of the operation equipment. If the latency is too large 368 or the reliability is not enough, it may cause the operation failure, 369 equipment damage and other serious consequences. Therefore, the 370 remote control service requires low latency and high reliability. 371 The general process of remote control is as follows: 373 * Field equipment (such as camera) collects image or video 374 information and sends it to data center. 376 * The data center receives the field information of the equipment and 377 sends it to the workers in the office. 379 * Workers send control instructions and control equipment according 380 to the received field information. 382 Many industrial enterprises rent public cloud resources to construct 383 their own data center, but the long distance of network transmission 384 is not conducive to the timely transmission of image / video data 385 stream, which will cause large latency and packet loss. 387 3.3.3. Remote control of industry with Edge Computing and APN 389 If the deployment mode of edge computing is adopted, and the data 390 center and edge computing access equipment (such as gateway) are 391 deployed in a location or enterprise park close to the business site, 392 the following functions can be realized: 394 * The collected image or video information can be encoded/ decoded 395 and compressed by edge access equipment to reduce the bandwidth 396 requirements. 398 * The control instruction information can be identified by the edge 399 equipment, so as to provide exclusive network transmission service. 401 * The forwarding path of image / video and control information is 402 shortened, which can greatly reduce the latency. 404 Although edge computing can reduce the overall delay of services and 405 reduce the demand of network bandwidth, it still needs to achieve 406 differentiated network services through APN to provide the ultimate 407 network guarantee for the services with the highest network 408 requirements. 410 For users, APN can realize those functions. 412 * Edge device obtains and encapsulates the image or video information 413 of the remote field device, then sends it to the headend node. 415 * Headend in the APN identifies the information and steers the flow 416 into a specific transmission path according to its requirements for 417 bandwidth, delay, reliability, etc.. 419 * Midpoint in the APN forwards along the specific path. 421 * Endpoint receives image or video data stream of field equipment and 422 forwards it to users. 424 For field equipment, APN can realize those functions. 426 * Edge device obtains and encapsulates the control instruction 427 information and sends it to the head end node. 429 * Headend in the APN identifies the control data flow and steers into 430 a specific transmission path according to the demand for bandwidth, 431 latency and reliability. 433 * Midpoint in the APN forwards along the specific path. 435 * Endpoint receives control information and forwards to the field 436 equipment. 438 In the whole process, APN identifies the traffic of remote control 439 service, which can provide customized high reliability, low latency 440 and other network guarantee. 442 Worker 443 +------------+ 444 |Control data| 445 +------------+-\ +----------+ +-----------+ +-----------+ 446 |<->| APN- |-W->| APN |-W->| | 447 | Edge A |<-C-| Network A |<-C-| | 448 +----------+ +-----------+ | Edge Data | 449 +----------+ +-----------+ | Center | 450 | APN- |-C->| APN |-C->| | 451 Camera |<->| Edge B |<-W-| Network B |<-W-| | 452 +------------+-/ +----------+ +-----------+ +-----------+ 453 | Video data | 454 +------------+ 455 On-site Device 457 Remote control of industry with Edge Computing and APN 459 4. Conclusion 461 APN enables low latency and high reliability network services in 462 various edge computing scenarios such as AR, cloud gaming, remote 463 industrial control, etc. 465 5. Security Considerations 467 TBD. 469 6. IANA Considerations 471 TBD. 473 7. Normative References 475 [I-D.li-apn-framework] 476 Li, Z., Peng, S., Voyer, D., Li, C., Liu, P., Cao, C., 477 Ebisawa, K., Previdi, S., and J. N. Guichard, 478 "Application-aware Networking (APN) Framework", draft-li- 479 apn-framework-02 (work in progress), February 2021. 481 [I-D.li-apn-problem-statement-usecases] 482 Li, Z., Peng, S., Voyer, D., Xie, C., Liu, P., Qin, Z., 483 Ebisawa, K., Previdi, S., and J. N. Guichard, "Problem 484 Statement and Use Cases of Application-aware Networking 485 (APN)", draft-li-apn-problem-statement-usecases-01 (work 486 in progress), September 2020. 488 [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate 489 Requirement Levels", BCP 14, RFC 2119, 490 DOI 10.17487/RFC2119, March 1997, 491 . 493 Authors' Addresses 495 Peng Liu 496 China Mobile 497 Beijing 100053 498 China 500 Email: liupengyjy@chinamobile.com 502 Zongpeng Du 503 China Mobile 504 Beijing 100053 505 China 507 Email: duzongpeng@chinamobile.com 509 Shuping Peng 510 Huawei 511 Beijing 100053 512 China 514 Email: pengshuping@huawei.com 515 Zhenbin Li 516 Huawei 517 Beijing 100053 518 China 520 Email: lizhenbin@huawei.com