Jayashree Kanniappan

Cloud computing supports data-intensive applications by providing efficient resource management and task scheduling. However, existing resource allocation methods often struggle to handle dynamic workloads, heterogeneous virtual machine (VM) environments, and changing user behavior. To address these challenges, this paper proposes an Ontology-Driven Trust-Based Virtual Machine Allocation and Migration with Fuzzy Logic (OTVAM-FL) framework. The proposed framework combines ontology-based semantic matching, user trust evaluation, and fuzzy logic to improve VM allocation, task scheduling, and migration decisions. First, a User Reputation Score (URS) is calculated from historical task success, completion time, and failure rate to prioritize user tasks. An ontology model is then used to represent users, tasks, and virtual machines, enabling semantic matching between task requirements and available resources. Fuzzy logic uses CPU utilization, RAM utilization, and bandwidth utilization to support resource allocation and VM migration under changing workload conditions. The proposed framework was evaluated using the CloudSim simulation environment and compared with MSGO-RNN, I-ANFIS, and SEBF-EIOT. The results show that OTVAM-FL achieves lower CPU utilization, lower RAM utilization, reduced bandwidth usage, fewer VM migrations, and shorter task execution time than the compared methods under the evaluated simulation settings. These results demonstrate that the proposed framework improves resource utilization and task scheduling efficiency in a simulated cloud environment.

Cloud computing offers scalable and adaptable resources on demand, and has emerged as an essential technology for contemporary enterprises. Nevertheless, it is still challenging work to efficiently handle cloud resources because of dynamic changes in load requirement. Existing forecasting approaches are unable to handle the intricate temporal symmetries and nonlinear patterns in cloud workload data, leading to degradation of prediction accuracy. In this manuscript, a Symmetry-Aware Multi-Dimensional Attention Spiking Neural Network with Optimization Techniques for Accurate Workload and Resource Time Series Prediction in Cloud Computing Systems (MASNN-WL-RTSP-CS) is proposed. Here, the input data from the Google cluster trace dataset were preprocessed using Multi Window Savitzky–Golay Filter (MWSGF) to remove noise while preserving important data patterns and maintaining structural symmetry in time series trends. Then, the Multi-Dimensional Attention Spiking Neural Network (MASNN) effectively models symmetric patterns in workload fluctuations to predict workload and resource time series. To enhance accuracy, the Secretary Bird Optimization Algorithm (SBOA) was utilized to optimize the MASNN parameters, ensuring accurate workload and resource time series predictions. Experimental results show that the MASNN-WL-RTSP-CS method achieves 35.66%, 32.73%, and 31.43% lower Root Mean Squared Logarithmic Error (RMSLE), 25.49%, 32.77%, and 28.93% lower Mean Square Error (MSE), and 24.54%, 23.65%, and 23.62% lower Mean Absolute Error (MAE) compared with other approaches, like ICNN-WL-RP-CS, PA-ENN-WLP-CS, and DCRNN-RUP-RP-CCE, respectively. These advances emphasize the utility of MASNN-WL-RTSP-CS in achieving more accurate workload and resource forecasts, thereby facilitating effective cloud resource management.

Semantic interoperability (SI) is defined as the capability of interpreting the nature of the information exchanged inside cloud computing (CC). For SI, ontology is selected as a solution. A hierarchical structure is offered by an ontology that comprises semantic relations between the application and the cloud server (CS). Even though different methods are introduced, ontology centered on semantic relation between the application and CS is not yet attained for achieving accurate interoperability. An ontology‐centered SI in CC utilizing a modified Shell Game optimization‐centered recurrent neural network (MSGO‐RNN) is presented in this work. Here, accessing the data from the data warehouse is initiated that experiences different standardization functions for improving the data’s quality, namely, data extraction, data cleaning, data transformation, data loading, and refreshing. Then, the data are passed via the semantic layer (SL), which offers a constant way of interpreting data. Then, for enhancing the accuracy rate of interoperability along with offering a low computational time, the relevant feature is chosen utilizing genetic crossover mutation‐centered improved fertile field (GCM‐IFF) optimization. Ontology is created utilizing the Protégé tool centered on the data, and respective manipulation is executed utilizing HermiT ontology web language (OWL) reasoner. Lastly, to attain cloud interoperability, the features are trained and tested by employing the MSGO‐RNN. The experimental outcome exhibits that when compared with the top‐notch methods, an accuracy of 96.32% is acquired by the framework for choosing the CS, and less time of 22567 ms is acquired by the framework for training.

KSII Transactions on Internet and Information Systems TIIS Paper Details