Article
Telecommunications
Monolina Dutta, Anoop Thomas
Summary: This study focuses on addressing network congestion caused by temporal variance in client demands in the client-server framework, and proposes a decentralized shared caching scheme. The proposed scheme, utilizing index coding techniques, is shown to be optimal among all linear schemes, achieving a comparable rate to existing centralized prefetching schemes.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Elizabath Peter, B. Sundar Rajan
Summary: This study focuses on designing coded caching schemes for shared caches with lower sub-packetization requirements by leveraging PDA constructions, achieving superior performance in both single and multi-antenna settings.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Telecommunications
Shreya Shrestha Meel, B. Sundar Rajan
Summary: The problem of secretive coded caching in shared cache setup where perfect secrecy is required is studied, and a secretively achievable coded caching scheme is proposed.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Computer Science, Theory & Methods
Chunlin Li, Jun Liu, Qingchuan Zhang, Youlong Luo
Summary: The study proposes a mobile edge caching strategy to improve service quality, reduce access latency, and maintain load balance in 5G networks through cache prefetching algorithm, load balancing algorithm, and optimized cache replacement policy, offering support for realizing the potential of 5G networks.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Information Systems
Min Wook Kang, Yun Won Chung
Summary: Efficient content caching in information-centric networking (ICN) is studied by considering both popularity and priority of content. A weighted delivery cost is defined to measure the content delivery cost, and an optimized content cache placement problem is formulated to minimize the weighted content delivery cost. The proposed scheme utilizes a hierarchical network architecture with multi-access edge computing (MEC) and software-defined networking (SDN) controller, and predicts the content requests using a seq2seq long short-term memory (LSTM) model in MECs.
Article
Computer Science, Information Systems
Long Shi, Kui Cai, Wentu Song, Zhe Wang, Jun Li
Summary: We investigate a basic decentralized caching network with coded prefetching under nonuniform requests and arbitrary file popularities. A new asymmetric delivery procedure is developed to address the problem in decentralized caching network with arbitrary MDS code rates and cache weights. The expected normalized rate induced by the asymmetric delivery is characterized using user grouping and leader set, leading to the derivation of rate-memory tradeoff and optimization of cache weights for a decentralized two-user and two-file caching network, which is supported by numerical results.
IEEE SYSTEMS JOURNAL
(2022)
Article
Computer Science, Information Systems
Kai Wan, Daniela Tuninetti, Mingyue Ji, Pablo Piantanida
Summary: This paper studies the balance between memory size and network load in combination networks with end-user caches and proposes a novel tight converse bound for such networks. It also introduces several novel caching schemes that outperform existing schemes in numerical evaluations.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2022)
Article
Computer Science, Hardware & Architecture
Junaid Shuja, Kashif Bilal, Waleed Alasmary, Hassan Sinky, Eisa Alanazi
Summary: Edge networking is a computing paradigm that aims to bring cloud resources closer to end users to improve responsiveness, with user mobility, preferences, and content popularity being key features. In next generation edge networks, machine learning techniques can be applied to predict content popularity and optimize cache strategies.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Yong Deng, Min Dong
Summary: This paper investigates the caching system for multiple cache-enabled users with random demands. It characterizes the optimal uncoded cache placement structure for the coded caching scheme (CCS) under nonuniform file popularity. The study shows that the optimal cache placement has at most three file groups, and proposes a simple algorithm to obtain the final optimal cache placement. Furthermore, it analyzes the file subpacketization in CCS with the optimal cache placement solution.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2022)
Article
Computer Science, Hardware & Architecture
Yong Deng, Min Dong
Summary: This paper characterizes the memory-rate tradeoff for decentralized caching under nonuniform file popularity and size. Two algorithms, a successive Geometric Programming (GP) approximation algorithm and a low-complexity file-group-based approach, are proposed to optimize the cache placement for a decentralized modified coded caching scheme (D-MCCS). Numerical results show that both algorithms perform closely to each other and achieve close to the lower bound for decentralized caching. The optimized D-MCCS further achieves the lower bound for specific scenarios and closely approximates it for general cases.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Information Systems
Fang Xiao, Siyuan Yu, Yuze Li
Summary: Designing a high-capacity cache is crucial for improving accessibility of cloud storage. This study introduces a file similarity strategy based on skip-gram to optimize caching and prefetching in cloud storage. By judging the correlation between files, this strategy allows for efficient prefetching and replacement in the cache. The use of this prefetching strategy significantly improves cache hit rate and consumes minimal time during online operations.
Article
Telecommunications
Yong Deng, Min Dong
Summary: This letter proposes an efficient nested coded caching scheme to reduce the average delivery rate under nonuniform file popularity. The scheme uses a nested coded delivery strategy to eliminate zero-padding and maximize multicasting gain. It is further optimized by jointly optimizing the cache placement and nested coded delivery strategy. Numerical results show that the optimized scheme outperforms other state-of-the-art coded caching schemes and achieves near-optimal performance.
IEEE COMMUNICATIONS LETTERS
(2023)
Article
Telecommunications
Yong Deng, Min Dong
Summary: This letter proposes an efficient nested coded caching scheme (NCCS) to reduce the average delivery rate under nonuniform file popularity. The NCCS uses a nested coded delivery strategy to ensure the subfiles of the files being coded into the same message are of the same size, eliminating zero-padding and maximizing multicasting gain. The optimized NCCS outperforms other state-of-the-art coded caching schemes and achieves near-optimal performance.
IEEE COMMUNICATIONS LETTERS
(2023)
Article
Computer Science, Information Systems
Martina Pappalardo, Antonio Virdis, Enzo Mingozzi
Summary: The Internet of Things brings internet connectivity to everyday devices, and edge-caching is effective in reducing the frequency of sensing and transmission. By minimizing energy consumption and considering information freshness, a model-driven and AoI-aware optimization scheme for information caching at the network edge can significantly lower the energy cost while satisfying the application's requirements.
Article
Computer Science, Information Systems
Lamis Abdo, Imtiaz Ahmad, Sa'ed Abed
Summary: Content Delivery Networks (CDNs) are currently the main method to distribute data traffic. Their content caching system relies on storing objects in a network of servers to minimize latency and provide requested content to users. This study proposes a methodology that includes an admission control phase and a cache replacement phase. The admission control phase uses reinforcement learning algorithms to determine which requests to accept based on training and maximizing the hit ratio. The cache replacement phase utilizes predictive models, such as the Long-Short-Term Memory (LSTM) model, to estimate an object's future popularity and make decisions on caching and evicting objects. Experimental results demonstrate that the proposed methodology outperforms conventional replacement policies and machine learning-based algorithms with a cache size of 130.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Eman Ramadan, Pariya Babaie, Zhi-Li Zhang
COMPUTER COMMUNICATIONS
(2019)
Proceedings Paper
Computer Science, Hardware & Architecture
Rostand A. K. Fezeu, Eman Ramadan, Wei Ye, Benjamin Minneci, Jack Xie, Arvind Narayanan, Ahmad Hassan, Feng Qian, Zhi-Li Zhang, Jaideep Chandrashekar, Myungjin Lee
Summary: 5G aims to provide higher throughput and lower latency than previous cellular networks. However, our measurement study found that various factors such as channel conditions, re-transmissions, and scheduling mechanisms can contribute to increased 5G PHY latency. Optimizing these factors can improve 5G latency performance.
PASSIVE AND ACTIVE MEASUREMENT, PAM 2023
(2023)
Proceedings Paper
Computer Science, Information Systems
Arvind Narayanan, Eman Ramadan, Jason Carpenter, Qingxu Liu, Yu Liu, Feng Qian, Zhi-Li Zhang
WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020)
(2020)
Proceedings Paper
Computer Science, Hardware & Architecture
Pariya Babaie, Eman Ramadan, Zhi-Li Zhang
IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2019)
(2019)
Proceedings Paper
Engineering, Electrical & Electronic
Arvind Narayanan, Eman Ramadan, Zhi-Li Zhang
IEEE INFOCOM 2018 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS)
(2018)
Proceedings Paper
Computer Science, Hardware & Architecture
Eman Ramadan, Arvind Narayanan, Zhi-Li Zhang
2015 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW)
(2015)