PRO-BiGRU: Performance Evaluation Index System for Hardware and Software Resource Sharing Based on Cloud Computing
This study aims to address the performance evaluation challenges of computer hardware and software resource sharing in cloud computing environments. To achieve this, we propose an enhanced performance evaluation method by integrating the Poor-Rich Optimization (PRO) algorithm with the Bidirectional...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2025-06-01
|
| Series: | HighTech and Innovation Journal |
| Subjects: | |
| Online Access: | https://hightechjournal.org/index.php/HIJ/article/view/1126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study aims to address the performance evaluation challenges of computer hardware and software resource sharing in cloud computing environments. To achieve this, we propose an enhanced performance evaluation method by integrating the Poor-Rich Optimization (PRO) algorithm with the Bidirectional Gated Recurrent Unit (BiGRU) network. We first construct a comprehensive multi-dimensional performance evaluation index system that encompasses resource utilization, response time, throughput, and scalability. Subsequently, the PRO algorithm is employed to optimize the hyper-parameter design of the BiGRU network, thereby enhancing the model's learning ability and evaluation accuracy. Performance data is collected using system monitoring tools, and experiments are conducted to validate the model's effectiveness. The results demonstrate that the PRO-BiGRU model achieves an average evaluation accuracy of over 97% across four independent experiments, significantly outperforming traditional algorithms such as CNN, RNN, LSTM, and GRU. The proposed model not only improves the accuracy of performance evaluation but also provides a reliable basis for resource optimization and decision-making in cloud service platforms. The novelty of this research lies in the combination of the PRO algorithm with the BiGRU network, which effectively captures complex data features and enhances the model's reliability and robustness in performance assessment tasks.
|
|---|---|
| ISSN: | 2723-9535 |