Edge Computing

5G provides higher quality of service, throughput, security, and lower latency. Edge computing enables the evolution of 5G by bringing cloud capabilities close to the end user.  5G has three characteristics 1) massive data, 2) strict QoS for interactive applications (ultra-low latency and high throughput), and 3) heterogeneous networks. 5G also leverages three technologies 1) mmWaves 2) small cells and 3) massive MIMO. Data has three characteristics 1) Hard real-time (strict latency like video steaming, gaming, and healthcare services) 2) Soft real-time with bounded latency like traffic signal control system, and 3) Non-real time that can tolerate some latency. Edge computing supports applications and services with hard real-time requirements using edge servers positioned closer to end users. For applications and services with soft-real time requirements, or bounded end-to-end delay, tasks are handled by edge servers if the response delay between UEs and the cloud is higher than the requirement;  Otherwise, the tasks can be offloaded to the cloud. For applications and services with non-real- time requirements, tasks can be offloaded to the cloud for load balancing.

​

Our patents cover four requirements with a balanced trade-off for different applications. 1) real-time interaction with low latency, 2) local processing rather than the cloud, 3) high data rate, 4) high availability. These requirements allow us to support applications like remote surgery, tactile internet, URLLC, and autonomous driving. We can also reduce the traffic across the link between a small cell and the core network so we can avoid any bottleneck and the traffic in the core network is reduced. This way the Edge servers, which can be close to BBUs, have easy access to edge clouds without the need to access the core network. The use of mmWave small cells also provides a high data rate transmission.

​

Since edge computing pushes data and application logic to the edge clouds, the availability of the edge clouds is important. We show five objectives of Edge computing in 5G: 1) improvement in data management 2) improvement in QoS 3) Predicting network demand 4) Managing location awareness 5) improvement in resource management.  We also cover six roles for Edge computing 1) Local storage, 2) local computation, 3) local data analysis, 4) local decision making, 5) local operations, 6) local security. Our architecture includes intelligent E2E orchestration with open API. It also includes Edge orchestration, transport SDN, NFV layers with open programable hardware, massive MIMO, and other features that reduce TCO, increase QoS and energy efficiency.