@Article{cmc.2025.059355,
AUTHOR = {Arif Ullah, Siti Fatimah Abdul Razak, Sumendra Yogarayan, Md Shohel Sayeed},
TITLE = {Modified Neural Network Used for Host Utilization Predication in Cloud Computing Environment},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {82},
YEAR = {2025},
NUMBER = {3},
PAGES = {5185--5204},
URL = {http://www.techscience.com/cmc/v82n3/59894},
ISSN = {1546-2226},
ABSTRACT = {Networking, storage, and hardware are just a few of the virtual computing resources that the infrastructure service model offers, depending on what the client needs. One essential aspect of cloud computing that improves resource allocation techniques is host load prediction. This difficulty means that hardware resource allocation in cloud computing still results in hosting initialization issues, which add several minutes to response times. To solve this issue and accurately predict cloud capacity, cloud data centers use prediction algorithms. This permits dynamic cloud scalability while maintaining superior service quality. For host prediction, we therefore present a hybrid convolutional neural network long with short-term memory model in this work. First, the suggested hybrid model is input is subjected to the vector auto regression technique. The data in many variables that, prior to analysis, has been filtered to eliminate linear interdependencies. After that, the persisting data are processed and sent into the convolutional neural network layer, which gathers intricate details about the utilization of each virtual machine and central processing unit. The next step involves the use of extended short-term memory, which is suitable for representing the temporal information of irregular trends in time series components. The key to the entire process is that we used the most appropriate activation function for this type of model a scaled polynomial constant unit. Cloud systems require accurate prediction due to the increasing degrees of unpredictability in data centers. Because of this, two actual load traces were used in this study’s assessment of the performance. An example of the load trace is in the typical dispersed system. In comparison to CNN, VAR-GRU, VAR-MLP, ARIMA-LSTM, and other models, the experiment results demonstrate that our suggested approach offers state-of-the-art performance with higher accuracy in both datasets.},
DOI = {10.32604/cmc.2025.059355}
}