意图驱动是自主网络的关键一步

Contents Introduction3Differentiated connectivity services4Intents and utility functions6Intent-driven autonomous networks8Intents in RAN12RAN application examples14Technology feasibility16Intent-driven operations18Industry alignment and standardization20Conclusion22Glossary23References24Further reading25Authors26 Introduction “Intents” allow the expression of objectives that a system must achieve, withouttelling the system how to achieve them. Intents can be used across a communicationsservice provider’s organization, allowing business objectives to be shared with network Transforming network operations to become intent driven is a key step in the journeyto autonomous networks, where a gradual evolution is expected over time. Operatingmobile networks with an increased use of AI and automation will enable service providersto control costs and address new business opportunities. It will also speed up the In a recent report on differentiated 5G connectivity[1] the monetization potentialof 5G standalone (SA) was analyzed. Differentiated connectivity services beyondbest-effort mobile broadband are anticipated to enable increased revenue growthand profitability, providing new value for users. Consequently, networks must beable to assure connectivity services in line with service providers' business objectives. Differentiatedconnectivity For the industry to move beyond best-effort mobile broadband services, members ofthe application service provider (ASP) community need clear guidelines on what can beexpected from differentiated connectivity and how their application behaviors fit with thoseguidelines. Network connectivity services define which connectivity KPIs to expect from anetwork connection, such as throughput and latency. The characteristics of the connectivitycould further be described according to if it is suited for an application service flow thatis buffered or not, with a fixed or adaptive bitrate. Differentiation between services could To create a full network connectivity service offering, a service provider must alsospecify targets for availability, geographical validity and other complementary The requirements on the network connectivity service infer requirements on sub-domainssuch as radio access network (RAN) and the adherent RAN connectivity service. Managing multiple differentiated services that share the same spectrum, while also balancingconnectivity service performance with energy saving, will become a challenge. This wouldlead to unsustainable operational costs if a service provider continued to operate its mobilenetwork in the traditional way. The thousands of individual parameters configured today willgrow with the number of connectivity services and will require tuning per service. To manage Intents andutility functions “Intent” is defined slightly differently across standardization organizations, but theconsensus is that intent is “declarative information about requirements.” This means thatintent can be used to express the requirements that need to be met by a network, or bya subsystem within that network. Furthermore, intent excludes a description of how therequirements are supposed to be met. Decisions about actions to be taken or configurationsto be applied in networks are made autonomously by the system that receives the intent.Thus, it provides a clear separation of concerns between subsystems involved in operations, While it is generally understood that improvements to the performance metrics arepreferential, the autonomous network has no means to quantify the degree of preference.This is particularly interesting when multiple performance metrics are used in combination In autonomous networks, utility refers to the value or usefulness of a particular systemstate for a service provider and its customers. It is described as “knowledge about whatmakes an outcome or situation preferential” [2]. This information can be conveyed withinintents in the form of utility functions. They associate every possible performance metric Using this information, the autonomous network knows the relative value of its state.Furthermore, it can assess if an action would improve or degrade the value of the systemstate by scoring the expected outcome of the action being considered, and comparing thiswith the current state’s utility. This directly facilitates optimization processes aimed at The same utility-based assessment can also balance conflicting requirements. An actionthat is improving certain performance metrics at the expense of others constitutes a conflict. Utility information provides the means for analysis and decision making that is alsohighly adaptive to changes in system behavior and intent requirements. It does not rely onhuman-designed policy rules based on pre-defined situations. Instead, utility informationenables a generic decision-finding algorithm capable of dealing with any situation. This The shape and scale of utility functions are determined by the issuer of t