An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies
Abstract The traditional optimal-path algorithm can address a single constraint in small and straightforward networks. However, in complex multipath distributed cloud services, the network nodes no longer exhibit singular or deterministic path characteristics. It requires the optimal paths that not...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-025-00728-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571336225980416 |
|---|---|
| author | Jian Yu Qiong Yu Zhixing Lin Xiangmei Xiao |
| author_facet | Jian Yu Qiong Yu Zhixing Lin Xiangmei Xiao |
| author_sort | Jian Yu |
| collection | DOAJ |
| description | Abstract The traditional optimal-path algorithm can address a single constraint in small and straightforward networks. However, in complex multipath distributed cloud services, the network nodes no longer exhibit singular or deterministic path characteristics. It requires the optimal paths that not only determines the shortest routes, but also combine the safety, speed, and enhanced service quality across multiple service nodes in the network topology. The Golden Eagle Optimization Algorithm (GEO) is specialized for optimizing these network service combinations. On this basis, the Golden Eagle Optimizer with Double Learning Strategies (GEO-DLS) resolved the multipath optimal service selection issues within intricate network environments. The algorithm modeled the hunting tactics of wild golden eagles, efficiently targeting the best prey in minimal time by dynamically adjusting two critical components, such as the attack and cruising strategies. In GEO-DLS, the enhanced GEO significantly broadened the search scope for food sources by using personalized learning and mirror reflection techniques. These advancements notably enhanced the GEO search capabilities and improved the solution accuracy. Key contribution include GEO-DLS can converge to the optimal solution faster by optimizing the search strategy and parameter settings. This means that in the problem of network service composition, algorithms can quickly find the optimal path that meets the quality of service (QoS) requirements. To validate the effectiveness of GEO, a set of ten standard benchmark functions was utilized to evaluate its performance. The results from these evaluations consistently presented its superior performance in tackling optimization challenges compared to other five metaheuristic algorithms and five enhanced algorithms. |
| format | Article |
| id | doaj-art-d423244822174551894678bb255b0449 |
| institution | Kabale University |
| issn | 2192-113X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj-art-d423244822174551894678bb255b04492025-02-02T12:42:42ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2025-01-0114113410.1186/s13677-025-00728-xAn approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategiesJian Yu0Qiong Yu1Zhixing Lin2Xiangmei Xiao3Network Center, Sanming UniversityHigh School, Sanming No. 2Network Center, Sanming UniversityNetwork Center, Sanming UniversityAbstract The traditional optimal-path algorithm can address a single constraint in small and straightforward networks. However, in complex multipath distributed cloud services, the network nodes no longer exhibit singular or deterministic path characteristics. It requires the optimal paths that not only determines the shortest routes, but also combine the safety, speed, and enhanced service quality across multiple service nodes in the network topology. The Golden Eagle Optimization Algorithm (GEO) is specialized for optimizing these network service combinations. On this basis, the Golden Eagle Optimizer with Double Learning Strategies (GEO-DLS) resolved the multipath optimal service selection issues within intricate network environments. The algorithm modeled the hunting tactics of wild golden eagles, efficiently targeting the best prey in minimal time by dynamically adjusting two critical components, such as the attack and cruising strategies. In GEO-DLS, the enhanced GEO significantly broadened the search scope for food sources by using personalized learning and mirror reflection techniques. These advancements notably enhanced the GEO search capabilities and improved the solution accuracy. Key contribution include GEO-DLS can converge to the optimal solution faster by optimizing the search strategy and parameter settings. This means that in the problem of network service composition, algorithms can quickly find the optimal path that meets the quality of service (QoS) requirements. To validate the effectiveness of GEO, a set of ten standard benchmark functions was utilized to evaluate its performance. The results from these evaluations consistently presented its superior performance in tackling optimization challenges compared to other five metaheuristic algorithms and five enhanced algorithms.https://doi.org/10.1186/s13677-025-00728-xCloud serviceGolden eagle optimization algorithmOptimal selectionGlobal optimizationService combination |
| spellingShingle | Jian Yu Qiong Yu Zhixing Lin Xiangmei Xiao An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies Journal of Cloud Computing: Advances, Systems and Applications Cloud service Golden eagle optimization algorithm Optimal selection Global optimization Service combination |
| title | An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| title_full | An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| title_fullStr | An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| title_full_unstemmed | An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| title_short | An approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| title_sort | approach for multipath optimal selection of network service combinations based on golden eagle optimizer with double learning strategies |
| topic | Cloud service Golden eagle optimization algorithm Optimal selection Global optimization Service combination |
| url | https://doi.org/10.1186/s13677-025-00728-x |
| work_keys_str_mv | AT jianyu anapproachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT qiongyu anapproachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT zhixinglin anapproachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT xiangmeixiao anapproachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT jianyu approachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT qiongyu approachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT zhixinglin approachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies AT xiangmeixiao approachformultipathoptimalselectionofnetworkservicecombinationsbasedongoldeneagleoptimizerwithdoublelearningstrategies |