Search for: All records

Wildfires are an escalating environmental concern, closely linked to power grid infrastructure in two significant ways. High-voltage power lines can inadvertently spark wildfires when they contact vegetation, while wildfires originating elsewhere can damage the power grid, causing severe disruptions. This paper proposes a self-powered cyber-physical system framework with sensing, processing, and communication capabilities to enable early wildfire detection. The proposed framework first analyzes the probability of the presence of a wildfire using lightweight smoke detection models that can be deployed on embedded processors at the edge. Then, it identifies the Pareto-optimal configurations that co-optimize the wildfire detection probability and expected time to detect a wildfire under energy constraints. Experimental evaluations on Jetson Orin Nano and STM Nucleo boards show that the Pareto-optimal solutions achieve wildfire detection within 5–15 minutes while consuming 1.2–3.5x lower energy than transmitting images to the cloud. 

Continuous monitoring of areas nearby the electric grid is critical for preventing and early detection of devastating wildfires. Existing wildfire monitoring systems are intermittent and oblivious to local ambient risk factors, resulting in poor wildfire awareness. Ambient sensor suites deployed near the gridlines can increase the monitoring granularity and detection accuracy. However, these sensors must address two challenging and competing objectives at the same time. First, they must remain powered for years without manual maintenance due to their remote locations. Second, they must provide and transmit reliable information if and when a wildfire starts. The first objective requires aggressive energy savings and ambient energy harvesting, while the second requires continuous operation of a range of sensors. To the best of our knowledge, this paper presents the first self-sustained cyber-physical system that dynamically co-optimizes the wildfire detection accuracy and active time of sensors. The proposed approach employs reinforcement learning to train a policy that controls the sensor operations as a function of the environment (i.e., current sensor readings), harvested energy, and battery level. The proposed cyber-physical system is evaluated extensively using real-life temperature, wind, and solar energy harvesting datasets and an open-source wildfire simulator. In long-term (5 years) evaluations, the proposed framework achieves 89% uptime, which is 46% higher than a carefully tuned heuristic approach. At the same time, it averages a 2-minute initial response time, which is at least 2.5× faster than the same heuristic approach. Furthermore, the policy network consumes 0.6 mJ per day on the TI CC2652R microcontroller using TensorFlow Lite for Micro, which is negligible compared to the daily sensor suite energy consumption. 

Domain-specific systems-on-chip (DSSoCs) combine general-purpose processors and specialized hardware accelerators to improve performance and energy efficiency for a specific domain. The optimal allocation of tasks to processing elements (PEs) with minimal runtime overheads is crucial to achieving this potential. However, this problem remains challenging as prior approaches suffer from non-optimal scheduling decisions or significant runtime overheads. Moreover, existing techniques focus on a single optimization objective, such as maximizing performance. This work proposes DTRL, a decision-tree-based multi-objective reinforcement learning technique for runtime task scheduling in DSSoCs. DTRL trains a single global differentiable decision tree (DDT) policy that covers the entire objective space quantified by a preference vector. Our extensive experimental evaluations using our novel reinforcement learning environment demonstrate that DTRL captures the trade-off between execution time and power consumption, thereby generating a Pareto set of solutions using a single policy. Furthermore, comparison with state-of-the-art heuristic–, optimization–, and machine learning-based schedulers shows that DTRL achieves up to 9× higher performance and up to 3.08× reduction in energy consumption. The trained DDT policy achieves 120 ns inference latency on Xilinx Zynq ZCU102 FPGA at 1.2 GHz, resulting in negligible runtime overheads. Evaluation on the same hardware shows that DTRL achieves up to 16% higher performance than a state-of-the-art heuristic scheduler. 

Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given domain with a single training is critical. To this end, we propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. The proposed approach, Preference-Driven MORL (PD-MORL), utilizes the preferences as guidance to update the network parameters. It also employs a novel parallelization approach to increase sample efficiency. We show that PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches. 

Energy harvesting (EH) and management (EM) have emerged as enablers of self-sustained wearable devices. Since EH alone is not sufficient for self-sustainability due to uncertainties of ambient sources and user activities, there is a critical need for a user-independent EM approach that does not rely on expected EH predictions. We present a generalized energy management framework (GEM-RL) using multi-objective reinforcement learning. GEM-RL learns the trade-off between utilization and the battery energy level of the target device under dynamic EH patterns and battery conditions. It also uses a lightweight approximate dynamic programming (ADP) technique that utilizes the trained MORL agent to optimize the utilization of the device over a longer period. Thorough experiments show that, on average, GEM-RL achieves Pareto front solutions within 5.4% of the offline Oracle for a given day. For a 7-day horizon, it achieves utility up to 4% within the offline Oracle and up to 50% higher utility compared to baseline EM approaches. The hardware implementation on a wearable device shows negligible execution time (1.98 ms) and energy consumption (23.17 μJ) overhead.