ML-RASPF: A Machine Learning-Based Rate-Adaptive Framework for Dynamic Resource Allocation in Smart Healthcare IoT DOI Creative Commons
Wajid Rafique

Algorithms, Год журнала: 2025, Номер 18(6), С. 325 - 325

Опубликована: Май 29, 2025

The growing adoption of the Internet Things (IoT) in healthcare has led to a surge real-time data from wearable devices, medical sensors, and patient monitoring systems. This latency-sensitive environment poses significant challenges traditional cloud-centric infrastructures, which often struggle with unpredictable service demands, network congestion, end-to-end delay constraints. Consistently meeting stringent QoS requirements smart healthcare, particularly for life-critical applications, requires new adaptive architectures. We propose ML-RASPF, machine learning-based framework efficient delivery Unlike existing methods, ML-RASPF jointly optimizes latency rate through predictive analytics control across modular mist–edge–cloud architecture. formulates task provisioning as joint optimization problem that aims minimize maximize throughput. evaluate using realistic hospital scenario involving IoT-enabled kiosks devices generate both latency-tolerant requests. Experimental results demonstrate achieves up 20% lower latency, 18% higher rate, 19% reduced energy consumption compared leading baselines.

Язык: Английский

ML-RASPF: A Machine Learning-Based Rate-Adaptive Framework for Dynamic Resource Allocation in Smart Healthcare IoT DOI Creative Commons
Wajid Rafique

Algorithms, Год журнала: 2025, Номер 18(6), С. 325 - 325

Опубликована: Май 29, 2025

The growing adoption of the Internet Things (IoT) in healthcare has led to a surge real-time data from wearable devices, medical sensors, and patient monitoring systems. This latency-sensitive environment poses significant challenges traditional cloud-centric infrastructures, which often struggle with unpredictable service demands, network congestion, end-to-end delay constraints. Consistently meeting stringent QoS requirements smart healthcare, particularly for life-critical applications, requires new adaptive architectures. We propose ML-RASPF, machine learning-based framework efficient delivery Unlike existing methods, ML-RASPF jointly optimizes latency rate through predictive analytics control across modular mist–edge–cloud architecture. formulates task provisioning as joint optimization problem that aims minimize maximize throughput. evaluate using realistic hospital scenario involving IoT-enabled kiosks devices generate both latency-tolerant requests. Experimental results demonstrate achieves up 20% lower latency, 18% higher rate, 19% reduced energy consumption compared leading baselines.

Язык: Английский

Процитировано

0