13.4: Latency Considerations and Workload Distribution

A core rationale for incorporating edge computing is the need to meet stringent latency requirements. When designing a system that spans cloud and edge, one of the most important tasks is to decide which workloads run where – what should be done on the device or edge versus what should be done in the cloud. This section delves into how project managers and architects can distribute workloads between cloud and edge to optimize performance and meet application requirements, using latency considerations as a guiding factor.

---