Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems

TL;DR

This paper introduces Julienning, an automated partitioning method for batteryless IoT applications that minimizes energy storage needs by optimizing execution cycles based on data dependencies, significantly reducing energy overhead.

Contribution

The paper presents Julienning, a novel automated partitioning approach that leverages data dependencies to optimize energy use in batteryless systems, enabling smaller energy buffers and reliable operation.

Findings

Reduces energy storage requirements by over 94%.

Increases system efficiency with only 0.12% additional energy overhead.

Validated on energy-intensive machine learning applications in batteryless cameras.

Abstract

Sensing systems powered by energy harvesting have traditionally been designed to tolerate long periods without energy. As the Internet of Things (IoT) evolves towards a more transient and opportunistic execution paradigm, reducing energy storage costs will be key for its economic and ecologic viability. However, decreasing energy storage in harvesting systems introduces reliability issues. Transducers only produce intermittent energy at low voltage and current levels, making guaranteed task completion a challenge. Existing ad hoc methods overcome this by buffering enough energy either for single tasks, incurring large data-retention overheads, or for one full application cycle, requiring a large energy buffer. We present Julienning: an automated method for optimizing the total energy cost of batteryless applications. Using a custom specification model, developers can describe transient applications as a set of atomically executed kernels with explicit data dependencies. Our optimization flow can partition data- and energy-intensive applications into multiple execution cycles with bounded energy consumption. By leveraging interkernel data dependencies, these energy-bounded execution cycles minimize the number of system activations and nonvolatile data transfers, and thus the total energy overhead. We validate our methodology with two batteryless cameras running energy-intensive machine learning applications. Results demonstrate that compared to ad hoc solutions, our method can reduce the required energy storage by over 94% while only incurring a 0.12% energy overhead.