To Risk or Not to Risk: Learning with Risk Quantification for IoT Task Offloading in UAVs
This addresses risk management in IoT task offloading for smart farms, but it is incremental as it builds on existing deep reinforcement learning and financial risk concepts.
The paper tackled task offloading in UAV networks for IoT smart farms by developing a deep reinforcement learning method that uses CVaR to quantify risks, reducing deadline violations for critical tasks like fire detection with minimal energy increase.
A deep reinforcement learning technique is presented for task offloading decision-making algorithms for a multi-access edge computing (MEC) assisted unmanned aerial vehicle (UAV) network in a smart farm Internet of Things (IoT) environment. The task offloading technique uses financial concepts such as cost functions and conditional variable at risk (CVaR) in order to quantify the damage that may be caused by each risky action. The approach was able to quantify potential risks to train the reinforcement learning agent to avoid risky behaviors that will lead to irreversible consequences for the farm. Such consequences include an undetected fire, pest infestation, or a UAV being unusable. The proposed CVaR-based technique was compared to other deep reinforcement learning techniques and two fixed rule-based techniques. The simulation results show that the CVaR-based risk quantifying method eliminated the most dangerous risk, which was exceeding the deadline for a fire detection task. As a result, it reduced the total number of deadline violations with a negligible increase in energy consumption.