Jointly Optimizing Content Caching and Recommendations in Small Cell Networks

Chatzieleftheriou, Livia Elena; Karaliopoulos, Merkourios; Koutsopoulos, Iordanis

doi:10.1109/tmc.2018.2831690

Cited by 88 publications

(152 citation statements)

References 25 publications

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…Meanwhile, they prove the optimal problem of edge caching is NP-hard, and efficient approximation algorithms solve this problem. The study in [91] proposes a simpler heuristic algorithm to solve the NP-hard problem.…”

Section: B Social-driven Strategymentioning

confidence: 99%

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Sun

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Under the explosive growth of information available on the Web, recommender systems have been used as an effective technology to filter useless information and attempt to recommend the most useful items. The proliferation of smart phones, smart wearable devices and other Internet of Thing (IoT) devices has gradually driven many novel emerging services which are latency-sensitive and computation-intensive with a higher quality-of-service. Under such circumstances, the data sources contain four key characteristics (i.e., sparsity, heterogeneity, mobility, volatility). The conventional recommender systems based on cloud computing are incapable of digging the information of user demands. Mobile edge computing is a novel computing paradigm via pushing computation/storage resource from the remote cloud servers to the network edge servers to provide more intelligent and personalized service. This paper comprehensively reviews the state of the art literature on the convergence of recommender systems and edge computing, and identify the future directions along this dimension. This paper can provide an array of new perspectives on the convergence for researchers, practitioners, and tap into the richness of this interdisciplinary research area.

show abstract

Section: B Social-driven Strategymentioning

confidence: 99%

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Sun

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, to improve the long term average performance of cache, the number of requests to the not-yet requested contents (missing requests) needs to be known. As mentioned earlier, it is difficult to collect the UCR, hence, machine learning methods have been adopted to accurately model and estimate UCR probability for missing requests in recommendation systems [11], [17], [18]. For non-stationary UCR, it is important to design an iterative recommendation model to predict future content popularity.…”

Section: Introductionmentioning

confidence: 99%

Active Content Popularity Learning and Caching Optimization With Hit Ratio Guarantees

Bommaraveni

Chatzinotas

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Edge caching is an effective solution to reduce delivery latency and network congestion by bringing contents close to end-users. A deep understanding of content popularity and the principles underlying the content request sequence are required to effectively utilize the cache. Most existing works design caching policies based on global content requests with very limited consideration of individual content requests which reflect personal preferences. To enable the optimal caching strategy, in this paper, we propose an Active learning (AL) approach to learn the content popularities and design an accurate content request prediction model. We model the content requests from user terminals as a demand matrix and then employ AL-based query-by-committee (QBC) matrix completion to predict future missing requests. The main principle of QBC is to query the most informative missing entries of the demand matrix. Based on the prediction provided by the QBC, we propose an adaptive optimization caching framework to learn popularities as fast as possible while guaranteeing an operational cache hit ratio requirement. The proposed framework is model-free, thus does not require any statistical knowledge about the underlying traffic demands. We consider both the fixed and time-varying nature of content popularities. The effectiveness of the proposed learning caching policies over the existing methods is demonstrated in terms of root mean square error, cache hit ratio, and cache size on a simulated dataset. INDEX TERMS Edge caching, Active learning, Matrix completion, Content popularity.

show abstract

“…Essa influência, por outro lado, pode ser explorada para induzir padrões de acesso que beneficiam os mecanismos de cache. Recentemente, essa ideia começou a ser investigada [Chatzieleftheriou et al 2017, Chatzieleftheriou et al 2019] e apresenta resultados promissores, tanto para os provedores de serviço que mantêm as caches quanto para os usuários que consomem os vídeos.…”

Section: Introductionunclassified

“…Em [Chatzieleftheriou et al 2019], os autores apresentam um modelo de otimização que combina armazenamento em cache e recomendação de vídeo visando maximizar a taxa de acertos da cache afetando minimamente as preferências dos usuários. Os autores assumem que todos os vídeos em cache são independentes e os tratam separadamente, desconsiderando a existência de vídeos idênticos codificados com resoluções diferentes.…”

Section: Introductionunclassified

“…No entanto, para que um dispositivo seja capaz de reproduzir uma dessas versões de um vídeo, recursos como o tamanho da tela, a capacidade do processador, o tipo da placa de vídeo instalada, entre outros precisam ser considerados. Ao realizar o acoplamento da política de cache com um algoritmo de recomendação sem levar em conta as diferentes resoluções de um vídeo recomendado para um dispositivo móvel, a solução de [Chatzieleftheriou et al 2019] perde oportunidade de elevar a taxa de acerto da cache e de satisfazer aos usuários aproveitando os recursos disponíveis em seus dispositivos, conforme ilustraremos na Seção 6.…”

Section: Introductionunclassified

See 1 more Smart Citation

Recomendação de vídeo e política de cache cientes de recursos dos dispositivos dos usuários

Monção¹,

Corrêa²,

Cardoso³

2020

Anais Do Workshop De Computação Urbana (CoUrb 2020)

View full text Add to dashboard Cite

Recentemente, o acoplamento entre algoritmos de recomendação de vídeo e políticas de manutenção de cache tem mostrado resultados promissores, tanto para melhorar a experiência dos usuários quanto para otimizar o uso de recursos da infraestrutura. No entanto, os recursos disponíveis nos dispositivos dos usuários não têm sido levado em conta nessa abordagem. Neste trabalho, introduzimos esse conceito através da modificação de um modelo e de uma métrica da literatura de forma a capturar a limitação de resolução de cada dispositivo de usuário, assim como a introdução de uma nova métrica para representar a satisfação com a recomendação. Avaliamos a nossa proposta e comparamos com outra solução de estado-da-arte, usando a base de dados do projeto MovieLens. Com exceção do cenário onde todos os vídeos possuem baixa qualidade, a nossa proposta apresenta maior taxa de acerto da cache na maioria das configurações de tamanho de armazenamento. Além disso, nossa proposta melhora de maneira significativa a experiência dos usuários ao permitir que eles usufruam da maior qualidade disponível em seus dispositivos.

show abstract

Jointly Optimizing Content Caching and Recommendations in Small Cell Networks

Cited by 88 publications

References 25 publications

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Active Content Popularity Learning and Caching Optimization With Hit Ratio Guarantees

Recomendação de vídeo e política de cache cientes de recursos dos dispositivos dos usuários

Contact Info

Product

Resources

About