Tools
Tools
Singla, Anmol (2023) Optimizing Long-Short Term Memory (LSTM) Algorithm for Enhanced Energy Efficiency and Green Computing in Cloud Environments. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
This research focuses on the optimization of Long Short-Term Memory (LSTM) networks in the cloud computing environment. The custom LSTM model of this study reliably predicts the different cloud computing indicators including the utilization of memory, CPU, network traffic and consumption of power. Critical methods include cleaning and pre-processing of data, advanced parameters of LSTM model and Grid search for the optimization of hyperparameters. The ability of the model to handle the complex and multi-dimensional data in cloud systems is assessed by using Mean Squared Error (MSE) as the primary criteria for performance evaluation. The study highlights the significance of LSTM in cloud computing and its practical implications by comparing the results with those of prior studies. Despite the impressive prediction accuracy, the research finds a trade-off between the complexity of the model and computing efficiency. With a focus on striking a balance between performance and efficiency, future research should examine hybrid models and real-world applications. This study enhances the comprehension of LSTM implementations in cloud computing by providing valuable insights into approaches for optimising models and possible avenues for future research. LSTM and the custom LSTM models have been created in this work. The optimization of these two models is also performed. For the evaluation of the models, MSE value has been used. With the basic LSTM model, the MSE score is 0.0755 while the custom LSTM model with novel optimization technique is demonstrating a slight lower MSE value of 0.0730.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Mijumbi, Rashid UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms |
| Divisions: | School of Computing > Master of Science in Cloud Computing |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 11 Apr 2025 08:38 |
| Last Modified: | 11 Apr 2025 08:38 |
| URI: | https://norma.ncirl.ie/id/eprint/7415 |
Actions (login required)
 |
View Item |