An Energy Aware Data Scheduling Approach in Cloud Using GK-ANFIS

HealthCare (HC) applications are vital and also time-sensitive. Due to the Internet of Things (IoT) technology’s capability to enhance the quality and efficiency of treatments, multiple HC applications were implemented through it to augment the patients’ health. IoT technology comprises of scheduling methodologies, which makes it intricate to self-configure and self-adapt to respond with respect to the environmental changes. Prevailing scheduling techniques don’t consider allocating tasks via sleep modes that consecutively bring about additional power consumption in addition to long time delays. Here, an energy-efficient as well as activity aware management framework called Gaussian Kernel-based Adaptive Neuro-Fuzzy Inference System (GK-ANFIS) is proposed for IoT devices on the cloud. The proposed work follows data filtering, Features Extraction (FE), Features Selection (FS), along with scheduling of IoT data. The proposed work allows the distribution of HC data of the patients to the proper Cloud Server (CS) of hospital admin through the implementation of GK-ANFIS centered scheduling along with allocation approach. The proposed method is implemented and its performance is analyzed. The outcomes rendered exhibit that the proposed techniques execute better when weighed against other existing algorithms.