The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
En raison de l'augmentation du volume de données et de l'intensification des requêtes simultanées, la mise en cache distribuée est couramment utilisée pour gérer les requêtes hautement simultanées et alléger la pression sur les bases de données. Cependant, les recherches sur la mise en cache de mappage d'enregistrements distribués sont limitées, et les algorithmes de mise en cache traditionnels ont des performances de résolution sous-optimales pour le mappage d'enregistrements qui suivent généralement une distribution à longue traîne. Pour résoudre le problème susmentionné, nous proposons dans cet article une méthode de mise en cache auxiliaire adaptative basée sur des recommandations, AC-REC, qui fournit l'enregistrement de cache principal ainsi qu'une liste d'enregistrements de cache supplémentaires. Le procédé utilise des corrélations de requêtes comme base de recommandations, personnalise le nombre d'entrées de cache supplémentaires fournies et ajuste dynamiquement la durée de vie. Nous avons mené des évaluations pour comparer les performances de notre méthode par rapport à diverses stratégies de référence. Les résultats montrent que notre méthode proposée, par rapport à la méthode LCE conventionnelle, augmente le taux de réussite du cache de 20 % en moyenne. De plus, cette amélioration est obtenue tout en utilisant efficacement l'espace du cache. Nous pensons que notre stratégie apportera une solution efficace aux études connexes sur l'architecture de réseau traditionnelle et la mise en cache dans des paradigmes comme ICN.
Zhaolin MA
Chinese Academy of Sciences
Jiali YOU
Chinese Academy of Sciences
Haojiang DENG
Chinese Academy of Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Zhaolin MA, Jiali YOU, Haojiang DENG, "A Recommendation-Based Auxiliary Caching for Mapping Record" in IEICE TRANSACTIONS on Communications,
vol. E107-B, no. 2, pp. 286-295, February 2024, doi: 10.23919/transcom.2023EBP3117.
Abstract: Due to the increase in the volume of data and intensified concurrent requests, distributed caching is commonly used to manage high-concurrency requests and alleviate pressure on databases. However, there is limited research on distributed record mapping caching, and traditional caching algorithms have suboptimal resolution performance for mapping records that typically follow a long-tail distribution. To address the aforementioned issue, in this paper, we propose a recommendation-based adaptive auxiliary caching method, AC-REC, which delivers the primary cache record along with a list of additional cache records. The method uses request correlations as a basis for recommendations, customizes the number of additional cache entries provided, and dynamically adjusts the time-to-live. We conducted evaluations to compare the performance of our method against various benchmark strategies. The results show that our proposed method, as compared to the conventional LCE method, increased the cache hit ratio by an average of 20%, Moreover, this improvement is achieved while effectively utilizing the cache space. We believe that our strategy will contribute an effective solution to the related studies in both traditional network architecture and caching in paradigms like ICN.
URL: https://global.ieice.org/en_transactions/communications/10.23919/transcom.2023EBP3117/_p
Copier
@ARTICLE{e107-b_2_286,
author={Zhaolin MA, Jiali YOU, Haojiang DENG, },
journal={IEICE TRANSACTIONS on Communications},
title={A Recommendation-Based Auxiliary Caching for Mapping Record},
year={2024},
volume={E107-B},
number={2},
pages={286-295},
abstract={Due to the increase in the volume of data and intensified concurrent requests, distributed caching is commonly used to manage high-concurrency requests and alleviate pressure on databases. However, there is limited research on distributed record mapping caching, and traditional caching algorithms have suboptimal resolution performance for mapping records that typically follow a long-tail distribution. To address the aforementioned issue, in this paper, we propose a recommendation-based adaptive auxiliary caching method, AC-REC, which delivers the primary cache record along with a list of additional cache records. The method uses request correlations as a basis for recommendations, customizes the number of additional cache entries provided, and dynamically adjusts the time-to-live. We conducted evaluations to compare the performance of our method against various benchmark strategies. The results show that our proposed method, as compared to the conventional LCE method, increased the cache hit ratio by an average of 20%, Moreover, this improvement is achieved while effectively utilizing the cache space. We believe that our strategy will contribute an effective solution to the related studies in both traditional network architecture and caching in paradigms like ICN.},
keywords={},
doi={10.23919/transcom.2023EBP3117},
ISSN={1745-1345},
month={February},}
Copier
TY - JOUR
TI - A Recommendation-Based Auxiliary Caching for Mapping Record
T2 - IEICE TRANSACTIONS on Communications
SP - 286
EP - 295
AU - Zhaolin MA
AU - Jiali YOU
AU - Haojiang DENG
PY - 2024
DO - 10.23919/transcom.2023EBP3117
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E107-B
IS - 2
JA - IEICE TRANSACTIONS on Communications
Y1 - February 2024
AB - Due to the increase in the volume of data and intensified concurrent requests, distributed caching is commonly used to manage high-concurrency requests and alleviate pressure on databases. However, there is limited research on distributed record mapping caching, and traditional caching algorithms have suboptimal resolution performance for mapping records that typically follow a long-tail distribution. To address the aforementioned issue, in this paper, we propose a recommendation-based adaptive auxiliary caching method, AC-REC, which delivers the primary cache record along with a list of additional cache records. The method uses request correlations as a basis for recommendations, customizes the number of additional cache entries provided, and dynamically adjusts the time-to-live. We conducted evaluations to compare the performance of our method against various benchmark strategies. The results show that our proposed method, as compared to the conventional LCE method, increased the cache hit ratio by an average of 20%, Moreover, this improvement is achieved while effectively utilizing the cache space. We believe that our strategy will contribute an effective solution to the related studies in both traditional network architecture and caching in paradigms like ICN.
ER -