Network Friendly Recommendations: Optimizing for Long Viewing Sessions

@article{Giannakas2021NetworkFR,
  title={Network Friendly Recommendations: Optimizing for Long Viewing Sessions},
  author={Theodoros Giannakas and Pavlos Sermpezis and Thrasyvoulos Spyropoulos},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.00772}
}
Caching algorithms try to predict content popularity, and place the content closer to the users. Additionally, nowadays requests are increasingly driven by recommendation systems (RS). These important trends, point to the following: make RSs favor locally cached content, this way operators reduce network costs, and users get better streaming rates. Nevertheless, this process should preserve the quality of the recommendations (QoR). In this work, we propose a Markov Chain model for a stochastic… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 47 REFERENCES
Jointly Optimizing Content Caching and Recommendations in Small Cell Networks
TLDR
A simpler heuristic algorithm is introduced that essentially serves as a form of lightweight control over recommendations so that they are both appealing to end-users and friendly to network resources.
Show me the Cache: Optimizing Cache-Friendly Recommendations for Sequential Content Access
TLDR
This paper proposes a Markovian model for recommendation-driven user requests, formulates the problem of biasing the recommendation algorithm to minimize access cost, while maintaining acceptable recommendation quality, and proposes an iterative ADMM-based algorithm that outperforms existing schemes, and shows significant potential for performance improvement on real content datasets.
The Order of Things: Position-Aware Network-friendly Recommendations in Long Viewing Sessions
TLDR
A stochastic model is proposed that incorporates position-aware recommendations into a Markovian traversal model of the content catalog, and the average cost of a user session is derived using absorbing Markov chain theory.
CABaRet: Leveraging Recommendation Systems for Mobile Edge Caching
TLDR
The results show that significant caching gains can be achieved in practice; 8 to 10 times increase in the cache hit ratio from cache-aware recommendations, and an extra 2 times increase from caching optimization.
A Learning-Based Approach to Joint Content Caching and Recommendation at Base Stations
TLDR
This paper proposes a model to capture the impact of recommendation on user demands, which is controlled by a user-specific psychological threshold, and develops a hierarchical iterative algorithm to solve the problem when the threshold is known.
Caching in Base Station with Recommendation via Q-Learning
TLDR
A simple idea of informing the users about what the BS has cached to make local caching efficient, which can be regarded as a form of recommendation is introduced and a cache replacement policy is optimized.
Distributed Caching Algorithms for Content Distribution Networks
TLDR
This paper develops light-weight cooperative cache management algorithms aimed at maximizing the traffic volume served from cache and minimizing the bandwidth cost, and establishes that the performance of the proposed algorithms is guaranteed to be within a constant factor from the globally optimal performance.
Soft Cache Hits: Improving Performance Through Recommendation and Delivery of Related Content
TLDR
The concept of “soft cache hits” (SCHs) is introduced and it is shown that optimal caching with SCH is NP-hard even for a single cache, which means that the optimal caching policy should be revisited when SCHs are allowed.
Approximation Algorithms for Mobile Data Caching in Small Cell Networks
TLDR
A novel reduction to a variant of the facility location problem is presented, which allows for algorithms with approximation guarantees for the joint routing and caching problem aiming to maximize the fraction of content requests served locally by the deployed SBSs.
Towards QoS-Aware Recommendations
TLDR
It is proposed that recommendation systems (RSs) should take into account the expected QoS with which a content can be delivered to a user, to increase the user satisfaction and retention rates.
...
...