Energy-aware Incremental OTA Update for Flash-based Batteryless IoT Devices

TL;DR

This paper introduces an energy-efficient incremental OTA firmware update method for flash-based, energy-harvesting IoT devices, reducing energy consumption and update time by segmenting updates, deferring flash writes, and enabling checkpoint-free resumption.

Contribution

It presents a novel incremental OTA update approach specifically designed for energy-harvesting IoT devices, addressing flash memory and energy constraints with new techniques.

Findings

Significantly reduces energy consumption during OTA updates

Decreases average update time in energy harvesting environments

Enables efficient recovery from power interruptions

Abstract

Over-the-air (OTA) firmware updates are essential for updating and maintaining IoT devices, especially those batteryless devices reliant on energy harvesting power sources. Flash memory, favored for its low cost and high density, is extensively used for data storage in many IoT devices. However, due to its high energy demands for update operations, there is often insufficient energy for code updates. This paper proposes an incremental flash-based OTA update approach tailored for energy harvesting IoT devices, tackling the challenges brought by limited memory resources and fluctuating energy availability. Our approach is composed of three techniques: segmentbased update packet design, deferred flash segment writes, and checkpoint-free update resumption. Segment-based update packet design segments firmware updates into smaller packets, each tailored for specific memory segments, thereby minimizing unnecessary flash operations and conserving energy. Deferred flash segment writes accumulate packets in Static Random-Access Memory (SRAM) for collective processing, reducing the frequency of energy-intensive operations. Crucially, our checkpointfree update resumption ensures efficient recovery from power interruptions without significant energy cost on data backup. Through thorough experimental evaluation, we have observed that our approach significantly reduces the total energy consumed during OTA updates, and decreases the average total update time in energy harvesting environments.