Edge computing-assisted artificial intelligence (edge-AI) has enabled a new paradigm of smart applications that have very stringent latency requirements, especially for applications on mobile devices (e.g., smartphones, wearable devices, and autonomous vehicles). However, the high mobility of users and instability in wireless networks decrease the overall Quality-of-Service (QoS) of an edge-AI application running on mobile devices with non-linear battery discharge properties. The objective of this research is to provide mobile AI applications with an energy-efficient wireless infrastructure to enhance the overall QoS.
This dissertation presents a comprehensive experimental study of mobile AI applications, including a novel performance analysis modeling framework and a Gaussian process regression-based general predictive energy model, focusing on computational resource utilization, delay, and energy consumption. To enhance mobile AI performance, this dissertation presents a novel periodic predictive AoI-based service aggregation method for high-mobility AI applications, which processes information updates according to their update cycles with satisfactory latency. Furthermore, an H.264 video encoding-based edge-AI system is proposed to overcome the challenges posed by unstable wireless networks. Finally, a novel deep reinforcement learning-based smart edge-AI system is proposed in this research, where the edge server provides smart and dynamic offloading and data processing decisions.