Edge Computing: An Orchestration of Devices

The advancements of Artifcial Intelligence (AI) introduces challenges in integrating its technology into resource limited devices. Many AI technology requires substantial resources to run e˙ectively. Object detection is an example that usescomplex neural network models that requires both memory and heavy computation to run eÿciently. With the emergence of the Internet of Things (IoT), this will be a problem for those IoT that are battery powered and resource limited. Fortunately,edge computing has shown promising results in improving the performance of resource heavy applications. This paper introduces an edge computing architecture, Edge Orchestration Architecture that works with the Cloud. The Edge OrchestrationArchitecture orchestrates a set of devices in determining where computation should occur to meet ideal system performance. This architecture is implemented in an object detection system and enforces the potentials that edge computing has for thiscurrent AI generation.