A computation offloading scheme leveraging parameter tuning for real-time IoT devices

In recent years, proliferation of the Internet of things (IoT) devices and applications like video processing have caused a paradigm shift in computation requirement and power management in these devices. Furthermore, processing huge amount of data generated by connected IoT devices and meeting real-Time deadline requirement of IoT applications is also a challenging problem. To address these challenges, we propose a computation offloading scheme where computing services requested by an IoT device are processed by a relatively resourceful computing devices (e.g., personal computer) in the same local network. In our proposed scheme, both client and server devices tune their tunable parameters, such as operating frequency and number of active cores, to meet the application's real-Time deadline requirements. We compare our proposed scheme with contemporary computation offloading models that use cloud computing. Results verify that our proposed scheme provides a performance improvement of 21.4% on average as compared to cloud-based computation offloading schemes.