BrainyEdge: An AI-enabled framework for IoT edge computing

Abstract

Along with the proliferation of the Internet of Things (IoT) and the surge in the use of artificial intelligence (AI), Edge Computing has proved considerable success in reducing latency, network traffic consumption, and security risks. The convergence of AI and Edge Computing, emerging a brand-new paradigm called edge intelligence, has been expected to unleash the full potential of intelligent IoT services. Unfortunately, integrating AI and Edge Computing into IoT is highly challenging due to the concerns over IoT device performance, energy efficiency, and privacy. In this paper, we present brainyEdge, an AI-enabled framework for edge devices able to jointly satisfy the Quality of Experience (QoE) criteria of IoT applications. We enhanced the intelligence of AI models operating at edges by designing a learning procedure consisting of transfer learning and incremental learning to dynamically retrain the models with personalized and incremental data locally stored. These data are classified into private data permanently stored in edges and public data shared in the cloud. This increases the edge-cloud collaboration level while preserving data privacy. To minimize the network cost of deploying the models to edge devices, we developed a lightweight deployment paradigm supporting cloud-compression and edge-decompression based on a user-desired compression ratio. Our prototype-based evaluation results indicate the superiority of brainyEdge over a typical edge-cloud paradigm.