2019· International Journal of Artificial Intelligence & Digital Transformation· Vol 2, pp. 01-19· 0 citations
TL;DR
The study highlights the potential of serverless computing as a sustainable backbone for next-generation IoT–ML systems, offering guidelines for building carbon-aware and cost-efficient inference pipelines for real-world applications.
Abstract
The rapid proliferation of Internet of Things (IoT) devices has resulted in massive, continuous data generation, demanding scalable, low-latency, and energy-efficient processing methodologies. Traditional cloud-based machine learning (ML) inference pipelines often incur high energy consumption due to persistent server provisioning and inefficient resource utilization. This paper proposes an energy-efficient ML inference framework using serverless cloud functions that dynamically scale with IoT workloads. The architecture leverages event-driven execution, model optimization techniques (quantization, pruning, edge pre-filtering), and adaptive model selection based on workload intensity. Experimental evaluations conducted on widely used serverless platforms demonstrate significant reductions in energy consumption, cold-start latency, and operational cost while maintaining high inference accuracy. The study highlights the potential of serverless computing as a sustainable backbone for next-generation IoT–ML systems, offering guidelines for building carbon-aware and cost-efficient inference pipelines for real-world applications.
As the Internet of Things (IoT) proliferates, vast volumes of streaming sensor data are being generated in real-time, creating both opportunities and challenges for data-driven decision-making. This paper proposes a cloud-native architecture that integrates Snowflake’s scalable data platform with AWS Lambda's serverless compute capabilities to build real-time predictive analytics pipelines for IoT data. By leveraging AWS services for ingestion (such as Kinesis or MQTT over IoT Core), Lambda for event-driven processing, and Snowflake for scalable storage and analysis, the proposed solution enables rapid deployment of machine learning models to process streaming data. The architecture is designed to be low-latency, cost-effective, and easily extensible for a variety of industrial applications. A prototype implementation and performance evaluation are presented, demonstrating the effectiveness of the architecture in handling high-throughput, low-latency IoT workloads.
Ritu Agarwal· International Journal of Dat...· 0 citations
The extensive deployment of battery-powered and resource-constrained edge devices makes energy efficiency a major challenge in Internet of Things (IoT) systems. Accurate energy prediction is important to enable intelligent energy management. However, traditional machine learning models are usually computationally expensive and unsuitable for micro-controller based platforms. In this paper, we present a TinyML-based energy prediction framework for low-power IoT edge devices. The proposed approach employs lightweight machine learning models which are optimized for ultra-low memory and computation footprints, but still retain acceptable prediction accuracy. We collect energy consumption data from a real IoT testbed, and train and evaluate several TinyML compatible models. The experimental results show that the proposed TinyML-based predictor can provide reliable energy estimation with low inference latency and low memory overhead, and thus can be deployed on resource-constrained IoT devices. This work lays a fundamental foundation for intelligent and adaptive energy management in future IoT systems.
S. Rawat, Neha Tuli· International Journal of Inn...· 0 citations
The CPS, in combination with the IoT sensor networks, has experienced massive growth, which results in massive data generation per second that presents extreme challenges to latency, scalability, and efficient data processing. The current paper presents a cloud-edge-integrated machine learning system for real-time monitoring of CPS environments. The suggested system combines IoT data collection, edge processing, and cloud-based model optimisation to enable fast, intelligent decision-making. Edge computing reduces communication overhead by performing local inference, while the cloud provides large-scale analytics and model training. The evaluation of the framework is conducted on a dataset of 10,000 sensor records that represent industrial parameters such as temperature, pressure, and vibration. The experimental findings showed that prediction accuracy was 91.2%, processing efficiency was 88.5%, and stability was 0.86, with a much lower latency of 205 ms. The overall performance index of 0.88 indicates that the computer's responsiveness, scalability, and efficiency have improved equally. The comparative analysis demonstrates that the proposed approach is significantly superior to traditional and standalone machine learning models, which is why it can be widely applied in real-time CPS monitoring applications.
Jayan Sharma· International Journal on Eng...· 0 citations
This study investigates energy-efficient distributed machine learning techniques, including federated learning, model compression, adaptive resource management, dynamic task offloading, and communication-efficient optimization, and proposes a distributed learning framework that integrates local model training, adaptive communication scheduling, gradient compression, and workload balancing to minimize energy consumption while maintaining learning accuracy.
Venkatesh Iyer· International Journal of App...· 0 citations
The Adaptivecoreset Selection Engine (ACS-Engine), a unified framework for adaptive, differentiable, and resource-aware coreset selection on streaming IoT data, is proposed, a unified framework for adaptive, differentiable, and resource-aware coreset selection on streaming IoT data.
Juan Gabriel, Kyoung-Don Kang, Fatema A. Albalooshi et al.· Technologies· 0 citations
The proliferation of Internet of Things (IoT) devices has intensified the demand for efficient and accurate deep learning models capable of operating under stringent resource constraints at the edge. Neural Architecture Search (NAS) offers a promising avenue to automate the design of optimized neural networks tailored for edge computing environments. This paper investigates the application of NAS for optimizing neural network architectures deployed on IoT edge devices, balancing accuracy, latency, and energy efficiency. We propose a multi-objective NAS framework that incorporates hardware-aware constraints specific to typical IoT edge platforms. Experimental results on benchmark datasets demonstrate that NAS-generated models outperform conventional architectures in terms of inference speed and power consumption, while maintaining competitive accuracy. Our findings highlight the potential of NAS as a vital tool for enhancing edge intelligence in IoT systems.
Lydia Languish· International Journal of Art...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
