Continuous Intelligence for Dynamic Control of 5G Capacity
by Simon Crosby, on Jun 25, 2021 8:15:00 AM
One of the most frequently discussed features of 5G, beyond increased bandwidth, is the opportunity for carriers to deliver secure, isolated, QoS-assured network services. A customer can avoid the complexity of a dedicated network or ensure that traffic from mobile devices in the hands of employees is isolated cleanly from the Internet. So called "slicing" reduces the risk of cyber-attacks and supports the growth of a distributed workforce.
Slicing offers both isolation and QoS, but there are challenges: Each base station needs meet its QoS guarantees and the provider must ensure that the network can satisfy the aggregate demand. But devices are mobile and traffic is bursty, so real-time intelligence is needed to solve the capacity allocation problem.
Real-time capacity management hard because data volumes are huge and the state of the edge environment changes quickly. This is a problem that demands in-memory, “on-the-fly” analysis of the data needs of endpoints and the edge environment to enable per-base station and network-wide performance optimization. Fortunately the problem can be solved in real-time with an Edge Computing solution that uses Continuous Intelligence.
Continuous Intelligence is a recent innovation in streaming data analysis and is becoming key to rapid solution of the capacity management problem in both 4G and 5G networks. In Swim smart actors - digital twins - of every device (network elements and endpoints) analyze streaming data on-the-fly. They analyze raw data (measurements of connection quality, bitrate, transmission rate, QoS committed and received etc.) concurrently, and are intimately aware of the real-world context (eg: location and trajectory) of every device. These actors, which we call Web Agents, run on a distributed execution platform that includes both per-base station and regional compute. Each represents a single entity, and the graph of digital twins represents relationships that are continuously evaluated, such as proximity, containment and even correlation.
Each actor continuously and concurrently processes its own real-world data, and shares its state over the graph with related digital twins to enable real-time contextual analysis. The state of every real-world device and virtual object is mirrored, in real-time, by the set of digital twins. The distributed graph enables real-time state sharing – a bit like a “LinkedIn for things”.
Web Agents analyze their own state and the states of others they are linked to – enabling analysis, learning and even prediction. Each statefully evolves and analyzes its own state and the state of its linked “neighbors” – and then can stream its insights in real time to the capacity management application. The distributed computation helps to solve the capacity assignment and monitoring problem using the states of the digital twins. This reduces the data volume and offers a huge speedup because computation can be done at memory speeds. The net result is that the computing capacity required is substantially reduced – typically to less than 10% of the resources required for a store-then-analyze approach - and results are continually available.