Toward Energy-Efficient and Low-Power Arrhythmia Detection for Wearable Devices

Cardiovascular diseases are the leading cause of death worldwide, and conditions such as arrhythmia often require long-term monitoring for effective detection and diagnosis. However, current wearable monitoring devices are bulky, uncomfortable, and typically rely on clinicians to manually evaluate electrocardiograms (ECGs). While Deep Learning (DL) algorithms have shown superior performance in arrhythmia detection and classification, their computational complexity coupled with high power consumption limit deployment in wearable devices. To address this challenge, this paper investigates the use of approximation techniques to reduce the power and energy consumption of DL architectures while maintaining acceptable classification performance. Specifically, techniques such as data precision reduction and approximate multiplication are investigated in a state-of-the-art DL model and its corresponding hardware architecture. The model is trained and validated using the MIT-BIH Arrhythmia Database, and hardware implementations employing various approximate multipliers are synthesized and evaluated. Compared with the state-of-the-art 8.75 μW (and 2.08 μJ) reference architecture, our proposed architecture consumes 3.07 μW (and 2.17 μJ) at 12 kHz, showing 64.9% reduction in power consumption while providing an acceptable output quality, i.e., 93.7% classification accuracy and 92.1% sensitivity. At 100 MHz, our proposed architecture consumes 9.45 mW (and 0.8 μJ), showing 61.5% reduction in energy consumption as compared to the state-of-the-art architecture. These results demonstrate that our proposed approximations significantly extend wearable device battery life while preserving the required arrhythmia classification performance.

Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations

Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this paper, we present a large-scale controlled study of three selected vLLM configuration options: attention kernel type, prefix caching, and chunked prefill. We evaluate all combinations of these configurations across 5 open-weight LLMs and 5 diverse inference tasks, totaling $9,000$ runs and $93,600$ measures. We analyze energy consumption, latency, and accuracy, and examine both main effects and interaction effects between configuration options and tasks. Our results show that the studied configuration options significantly impact energy and performance, mainly driven by attention type and prefix caching, while chunked prefill has a limited effect under the default vLLM serving configuration and evaluated workloads. These effects are highly model- and workload-dependent, and no configuration is universally optimal. We further show that model choice dominates global trade-offs, while configuration tuning provides local improvements along the Pareto frontier. Unexpectedly, inference options can also affect model accuracy.

Static Metrics Are Insufficient: Predicting Java Method Energy Usage with Execution Time

The increasing energy demand of software systems is raising concerns about their environmental impact and associated costs. Reasoning on energy usage early in the development flow has the potential to significantly reduce the overall energy usage of a software system, as it allows developers to make informed design and refactoring decisions before inefficiencies propagate. However, assessing energy usage without repeated profiling and direct measurement is difficult, which limits early reasoning in practice. This study investigates the limits of method-level energy prediction in Java, examining whether static source code metrics complemented with method-level execution time can estimate the energy consumption of Java methods. We profile 2,786 Java methods to extract 33 static features and measure execution time and energy, then train and compare eleven regression models. Our findings show that static source code metrics alone yield poor predictive performance, with average R2 values close to zero. Incorporating execution time as a lightweight dynamic input significantly improves accuracy, raising R2 to as high as 0.46. Execution time, internal method calls, and cyclomatic complexity consistently emerge as the strongest predictors of energy consumption.

Ten Years of Teaching Empirical Software Engineering in the context of Energy-efficient Software

In this chapter we share our experience in running ten editions of the Green Lab course at the Vrije Universiteit Amsterdam, the Netherlands. The course is given in the Software Engineering and Green IT track of the Computer Science Master program of the VU. The course takes place every year over a 2-month period and teaches Computer Science students the fundamentals of Empirical Software Engineering in the context of energy-efficient software. The peculiarity of the course is its research orientation: at the beginning of the course the instructor presents a catalog of scientifically relevant goals, and each team of students signs up for one of them and works together for 2 months on their own experiment for achieving the goal. Each team goes over the classic steps of an empirical study, starting from a precise formulation of the goal and research questions to context definition, selection of experimental subjects and objects, definition of experimental variables, experiment execution, data analysis, and reporting. Over the years, the course became well-known within the Software Engineering community since it led to several scientific studies that have been published at various scientific conferences and journals. Also, students execute their experiments using \textit{open-source tools}, which are developed and maintained by researchers and other students within the program, thus creating a virtuous community of learners where students exchange ideas, help each other, and learn how to collaboratively contribute to open-source projects in a safe environment.

A Controlled Experiment on the Energy Efficiency of the Source Code Generated by Code Llama

Context. Nowadays, 83% of software developers use Large Language Models (LLMs) to generate code. LLMs recently became essential to increase the productivity of software developers and decrease the time and cost of software development. Developers ranging from novices to experts use LLM tools not only to detect and patch bugs, but also to integrate generated code into their software. However, as of today there is no objective assessment of the energy efficiency of the source code generated by LLM tools. Released in August 2023, Code Llama is one of the most recent LLM tools. Goal. In this paper, we present an empirical study that assesses the energy efficiency of Code Llama with respect to human-written source code. Method. We design an experiment involving three human-written benchmarks implemented in C++, JavaScript, and Python. We ask Code Llama to generate the code of the benchmarks using different prompts and temperatures. Therefore, we execute both implementations and profile their energy efficiency. Results. Our study shows that the energy efficiency of code generated by Code Llama is heavily-dependent on the chosen programming language and the specific code problem at hand. Also, human implementations tend to be more energy efficient overall, with generated JavaScript code outperforming its human counterpart. Moreover, explicitly asking Code Llama to generate energy-efficient code results in an equal or worse energy efficiency, as well as using different temperatures seems not to affect the energy efficiency of generated code. Conclusions. According to our results, code generated using Code Llama does not guarantee energy efficiency, even when prompted to do so. Therefore, software developers should evaluate the energy efficiency of generated code before integrating it into the software system under development.

How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detection

ML-enabled systems that are deployed in a production environment typically suffer from decaying model prediction quality through concept drift, i.e., a gradual change in the statistical characteristics of a certain real-world domain. To combat this, a simple solution is to periodically retrain ML models, which unfortunately can consume a lot of energy. One recommended tactic to improve energy efficiency is therefore to systematically monitor the level of concept drift and only retrain when it becomes unavoidable. Different methods are available to do this, but we know very little about their concrete impact on the tradeoff between accuracy and energy efficiency, as these methods also consume energy themselves. To address this, we therefore conducted a controlled experiment to study the accuracy vs. energy efficiency tradeoff of seven common methods for concept drift detection. We used five synthetic datasets, each in a version with abrupt and one with gradual drift, and trained six different ML models as base classifiers. Based on a full factorial design, we tested 420 combinations (7 drift detectors * 5 datasets * 2 types of drift * 6 base classifiers) and compared energy consumption and drift detection accuracy. Our results indicate that there are three types of detectors: a) detectors that sacrifice energy efficiency for detection accuracy (KSWIN), b) balanced detectors that consume low to medium energy with good accuracy (HDDM_W, ADWIN), and c) detectors that consume very little energy but are unusable in practice due to very poor accuracy (HDDM_A, PageHinkley, DDM, EDDM). By providing rich evidence for this energy efficiency tactic, our findings support ML practitioners in choosing the best suited method of concept drift detection for their ML-enabled systems.