Kasım Sinan Yıldırım

Pietro Farina, Subrata Biswas, Eren Yıldız et al.

Batteryless systems frequently face power failures, requiring extra runtime buffers to maintain inference progress and leaving only a memory space for storing ultra-tiny deep neural networks (DNNs). Besides, making these models responsive to stochastic energy harvesting dynamics during inference requires a balance between inference accuracy, latency, and energy overhead. Recent works on compression mostly focus on time and memory, but often ignore energy dynamics or significantly reduce the accuracy of pre-trained DNNs. Existing energy-adaptive inference works modify the architecture of pre-trained models and have significant memory overhead. Thus, energy-adaptive and accurate inference of pre-trained DNNs on batteryless devices with extreme memory constraints is more challenging than traditional microcontrollers. We combat these issues by proposing FreeML, a framework to optimize pre-trained DNN models for memory-efficient and energy-adaptive inference on batteryless systems. FreeML comprises (1) a novel compression technique to reduce the model footprint and runtime memory requirements simultaneously, making them executable on extremely memory-constrained batteryless platforms; and (2) the first early exit mechanism that uses a single exit branch for all exit points to terminate inference at any time, making models energy-adaptive with minimal memory overhead. Our experiments showed that FreeML reduces the model sizes by up to $95 \times$, supports adaptive inference with a $2.03-19.65 \times$ less memory overhead, and provides significant time and energy benefits with only a negligible accuracy drop compared to the state-of-the-art.

Ferhat Erata, Arda Goknil, Eren Yıldız et al.

Energy harvesting battery-free embedded devices rely only on ambient energy harvesting that enables stand-alone and sustainable IoT applications. These devices execute programs when the harvested ambient energy in their energy reservoir is sufficient to operate and stop execution abruptly (and start charging) otherwise. These intermittent programs have varying timing behavior under different energy conditions, hardware configurations, and program structures. This paper presents Energy-aware Timing Analysis of intermittent Programs (ETAP), a probabilistic symbolic execution approach that analyzes the timing and energy behavior of intermittent programs at compile time. ETAP symbolically executes the given program while taking time and energy cost models for ambient energy and dynamic energy consumption into account. We evaluated ETAP on several intermittent programs and compared the compile-time analysis results with executions on real hardware. The results show that ETAP's normalized prediction accuracy is 99.5%, and it speeds up the timing analysis by at least two orders of magnitude compared to manual testing.

Qingzhi Liu, Kasım Sinan Yıldırım, Przemysław Pawełczak et al.

RF-based wireless power transfer networks (WPTNs) are deployed to transfer power to embedded devices over the air via RF waves. Up until now, a considerable amount of effort has been devoted by researchers to design WPTNs that maximize several objectives such as harvested power, energy outage and charging delay. However, inherent security and safety issues are generally overlooked and these need to be solved if WPTNs are to be become widespread. This article focuses on safety and security problems related WPTNs and highlight their cruciality in terms of efficient and dependable operation of RF-based WPTNs. We provide a overview of new research opportunities in this emerging domain.