Edge devices are often deployed at scale, yet their environmental impact, shaped by complex interactions between hardware choices, workload demands, power systems, and deployment context, has been overlooked by the mobile computing community. We present MicroGreen, a design-time framework that enables carbon-aware design for edge ML systems. By combining component-level carbon models with workload profiling and environment-aware energy analysis, MicroGreen identifies carbon-optimal configurations across diverse conditions. Our results show that the most energy-efficient processor is not always the most sustainable, and that ambient energy availability, inference rate, and deployment lifetime can shift the carbon-optimal design by over an order of magnitude. Through a real vision-based visitor detection and counting deployment in New York City parks, we demonstrate that heterogeneous, location-aware designs reduce total emissions by 47.72% compared to a homogeneous baseline.

We introduce BIONIC (duraBle tImekeeper fOr iNtermIttent Computing), a novel power system architecture and software runtime that facilitates time-sensitive intermittent computing for battery-less Internet of Things. BIONIC integrates timekeeping into energy storage hardware: its power system comprises two energy storage capacitors. BIONIC switches between these two energy storage capacitors to estimate ambient power. Using these estimations, BIONIC can predict and track charging times (i.e., off-time durations) to schedule time-sensitive tasks and complete them on time. Our evaluations showed that BIONIC significantly extends the measurable off-time intervals by a factor of 15 to 1620 compared to state-of-the-art, while achieving an accuracy of up to 99.1% and effectively adapting to new energy conditions. Besides, in a typical batteryless application, BIONIC's power-aware intermittent computing runtime boosted the number of completed time-sensitive operations by 30% while reducing failed timely operations by 29%.

We present a novel architecture for Human-AI Teaming with a swarm of role-based agents supporting healthy behavior change. The system consists of a Triage Agent, RAG agent, and four specialized agents (Empathic Companion, Persuasive Challenging Coach, Medical Domain Expert, and Neutral Assistant) that communicate decentrally. Evaluated with six participants, results showed positive attitudes toward behavior change, with participants finding the system useful and responding favorably to personalized suggestions across physical activity, nutrition, alcohol, and recovery domains.

This research aims to address designing an experiment to evaluate the impact of a developed posture correction system. Also, the correct posture learning habits of users can be estimated with an artificial neural network (ANN) structure that predicts the poor posture count (PPC) in the last session of the experiment using the information received from the users and the developed system. The developed system aims to collect data from different individuals about their sitting posture information. An ANN analysis tool is developed to predict the individuals’ habits of learning the correct posture. This setup is based on a flex sensor and has the capability of collecting posture information data and warning the user when the posture is not correct. A three-session experiment was conducted on 12 healthy participants to investigate his/her posture habits. The data was analyzed to determine the average PPC value. It was observed that PPC decreased by 56.27% from session one to session three, and the average improvement evaluation (IE) value after each session was found to be positive. In addition to experimental analysis, the collected posture data was used to train and validate an ANN architecture capable of predicting PPC values. The developed device is effective in improving posture habits and has the potential to predict PPC values with the ANN architecture.

Battery-free devices collect the harvested ambient energy in their energy storage capacitors. The size of the storage capacitor is one of the main factors affecting the device’s active time and power failure rate. In fact, a larger capacitor ensures energy autonomy for longer operations, while a smaller capacitor charges faster and shrinks inefficient cold starts. This paper presents CapDYN , a new energy storage architecture that can self-adapt its capacity based on incoming ambient energy. CapDYN automatically reconfigures the size of its capacitor bank to both speed up charging and improve execution rate. CapDYN reduces the startup time by up to 98% and can schedule tasks up to 38% faster, compared to a fixed-size capacitor. CapDYN operates in a fully autonomous manner consuming down to 11.6 µW in its simplest implementation and replaces the power-hungry microcontroller governing the switching operation with a dedicated ultra-low-power circuit built with COTS components. Its power consumption improves the previous state of the art by 73%, all the while featuring uncompromising reactivity. CapDYN can instantly react to sudden power transients without incurring extra power draw by foregoing MCU-driven reconfiguration used in state-of-the-art dynamic energy storages.

Continuous health monitoring is crucial to ensuring better health and taking preventive measures just-in-time. Existing battery-powered health wearables pose a significant limitation to continuous monitoring as batteries wear out after fixed energy cycles and need replacement. Ambient energy harvesting unlocks battery-free sensing but it suffers from spatio-temporal variability, making it unfit for health sensing. Intra-body power transfer (IBPT) provides an alternative energy source for battery-free operation, however, it can only provide limited energy in order to ensure wearer's safety. Existing system support is designed to maximize computational progress in a single energy cycle, thus wasting energy on computations that become stale in the next energy cycle. We instantiate an IBPT-powered health wearable capable of supporting multiple health sensors. To cope with lower incoming energy, we introduce BodyOS; a system support that exposes programming constructs for domain experts to express health applications in terms of the inherent dependencies of bio-signals being monitored by the application. By avoiding unnecessary sensing operations, BodyOS allows energy-efficient application execution and faster capacitor recharge while ensuring that the data sensed by the application is always useful. We evaluate BodyOS to show that it significantly improves energy efficiency, thus increasing the on-time and number of data points collected by the device.

Batteryless energy harvesting devices compute intermittently due to power failures that frequently interrupt the computational activity and lead to charging delays. To ensure functional correctness in intermittent computing, applications must exhibit several unique properties, such as guarantees for computational progress despite power failures and prevention of stale operations caused by charging delays. We observe that current software support for intermittent computing allows for checking only a fixed set of properties and leads to tightly coupled application and property-checking, thus hampering modularity, scalability, and maintainability.

Batteryless edge devices are extremely resource-constrained compared to traditional mobile platforms. Existing tiny deep neural network (DNN) inference solutions are problematic due to their slow and resource-intensive nature, rendering them unsuitable for batteryless edge devices. To address this problem, we propose a new approach to embedded intelligence, called Fast-Inf, which achieves extremely lightweight computation and minimal latency. Fast-Inf uses binary tree-based neural networks that are ultra-fast and energy-efficient due to their logarithmic time complexity. Additionally, Fast-Inf models can skip the leaf nodes when necessary, further minimizing latency without requiring any modifications to the model or retraining. Moreover, Fast-Inf models have significantly lower backup and runtime memory overhead. Our experiments on an MSP430FR5994 platform showed that Fast-Inf can achieve ultra-fast and energy-efficient inference (up to 700x speedup and reduced energy) compared to a conventional DNN.

Task-based intermittent software systems always re-execute peripheral input/output (I/O) operations upon power failures since tasks have all-or-nothing semantics. Re-executed I/O wastes significant time and energy and risks memory inconsistency. This paper presents EaseIO, a new task-based intermittent system that remedies these problems. EaseIO programming interface introduces re-execution semantics for I/O operations to facilitate safe and efficient I/O management for intermittent applications. EaseIO compiler front-end considers the programmer-annotated I/O re-execution semantics to preserve the task's energy efficiency and idem-potency. EaseIO runtime introduces regional privatization to eliminate memory inconsistency caused by idempotence bugs. Our evaluation shows that EaseIO reduces the wasted useful I/O work by up to 3× and total execution time by up to 44% by avoiding 76% of the redundant I/O operations, as compared to the state-of-the-art approaches for intermittent computing. Moreover, for the first time, EaseIO ensures memory consistency during DMA-based I/O operations.

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 article 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 evaluate ETAP by comparing the compile-time analysis results of our benchmark codes and real-world application with the results of their executions on real hardware. Our evaluation shows that ETAP’s prediction error rate is between 0.0076% and 10.8%, and it speeds up the timing analysis by at least two orders of magnitude compared to manual testing.

In this study, we propose SQUID, a software-based solution to predict the off-time of batteryless devices that operate in environments with short-term energy-harvesting stability. The key insight of SQUID is to sample the power in the environment when the device is on and use these samples to extrapolate the power availability when the device is off and charging its capacitor. Therefore, SQUID can predict the charging time of the batteryless sensors by using the predicted power availability. Our initial experiments showed that SQUID has a promising estimation accuracy by consuming up to 10 times less energy than existing timekeeping solutions.