DeepCache

Narayanan, Arvind; Verma, Saurabh; Ramadan, Eman; Babaie, Pariya; Zhang, Zhili

doi:10.1145/3229543.3229555

Cited by 110 publications

(8 citation statements)

References 13 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models of deep learning and machine learning have also been exploited by researchers to forward request in ICN. The use of convolution neural networks, recurrent neural network (RNN) and reinforcement learning in ICN routing field are explored in Narayanan et al 22 Boutaba et al 23 have introduced an ICN based Q‐learning driven mechanism for storing routers' caches for SDN based IoT scenarios. A request forwarding mechanism driven by support vector machine is introduced in Yuan et al 24 They have exploited SVM based model to predict the probability of locating content in a cache and forward requests based on prediction.…”

Section: Related Workmentioning

confidence: 99%

Reinforcement learning inspired forwarding strategy for information centric networks using Q‐learning algorithm

Delvadia,

Dutta

2024

Int J Communication

View full text Add to dashboard Cite

SummaryContent interest forwarding is a prominent research area in Information Centric Network (ICN). An efficient forwarding strategy can significantly improve data retrieval latency, origin server load, network congestion, and overhead. The state‐of‐the‐art work is either driven by flooding approach trying to minimize the adverse effect of Interest flooding or path‐driven approach trying to minimize the additional cost of maintaining routing information. These approaches are less efficient due to storm issues and excessive overhead. Proposed protocol aims to forward interest to the nearest cache without worrying about FIB construction and with significant improvement in latency and overhead. This paper presents the feasibility of integrating reinforcement learning based Q‐learning strategy for forwarding in ICN. By revising Q‐learning to address the inherent challenges, we introduce Q‐learning based interest packets and data packets forwarding mechanisms, namely, IPQ‐learning and DPQ‐learning. It aims to gain self‐learning through historical events and selects best next node to forward interest. Each node in the network acts as an agent with aim of forwarding packet to best next hop according to the Q value such that content can be fetched within fastest possible route and every action returns to be a learning process, which improves the accuracy of the Q value. The performance investigation of protocol in ndnSIM‐2.0 shows the improvement in a range of 10%–35% for metrics such as data retrieval delay, server hit rate, network overhead, network throughput, and network load. Outcomes are compared by integrating proposed protocol with state‐of‐the‐art caching protocols and also against recent forwarding mechanisms.

show abstract

Section: Related Workmentioning

confidence: 99%

Reinforcement learning inspired forwarding strategy for information centric networks using Q‐learning algorithm

Delvadia,

Dutta

2024

Int J Communication

View full text Add to dashboard Cite

show abstract

“…This model empowers routers to employ a softmax classifier, selecting crucial nodes based on betweenness centrality to strategically place popular content ( Liu et al, 2017b ; Mughees et al, 2021 ). In the article ( Narayanan et al, 2018 ), the authors employed the Long Short-Term Memory (LSTM) model for popularity prediction, but the lack of a strategically implemented placement approach results in heightened retrieval latency.…”

Section: Literature Reviewmentioning

confidence: 99%

Controller-driven vector autoregression model for predicting content popularity in programmable named data networking devices

Qaiser,

Hussain,

Ahad

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Named Data Networking (NDN) has emerged as a promising network architecture for content delivery in edge infrastructures, primarily due to its name-based routing and integrated in-network caching. Despite these advantages, sub-optimal performance often results from the decentralized decision-making processes of caching devices. This article introduces a paradigm shift by implementing a Software Defined Networking (SDN) controller to optimize the placement of highly popular content in NDN nodes. The optimization process considers critical networking factors, including network congestion, security, topology modification, and flowrules alterations, which are essential for shaping content caching strategies. The article presents a novel content caching framework, Popularity-aware Caching in Popular Programmable NDN nodes (PaCPn). Employing a multi-variant vector autoregression (VAR) model driven by an SDN controller, PaCPn periodically updates content popularity based on time-series data, including ‘request rates’ and ‘past popularity’. It also introduces a controller-driven heuristic algorithm that evaluates the proximity of caching points to consumers, considering factors such as ‘distance cost,’ ‘delivery time,’ and the specific ‘status of the requested content’. PaCPn utilizes customized DATA named packets to ensure the source stores content with a valid residual freshness period while preventing intermediate nodes from caching it. The experimental results demonstrate significant improvements achieved by the proposed technique PaCPn compared to existing schemes. Specifically, the technique enhances cache hit rates by 20% across various metrics, including cache size, Zipf parameter, and exchanged traffic within edge infrastructure. Moreover, it reduces content retrieval delays by 28%, considering metrics such as cache capacity, the number of consumers, and network throughput. This research advances NDN content caching and offers potential optimizations for edge infrastructures.

show abstract

“…In previous work, most studies have assumed by default that content popularity obeys a Zipf distribution [ 30 , 31 , 32 ]. In practice, due to the high-velocity mobility of vehicles and time-varying user demand, content popularity characteristics are difficult to capture in a timely manner and can only be predicted from historical information.…”

Section: Cooperative Caching Decisions Based On Temporal Convolutiona...mentioning

confidence: 99%

Hybrid Cooperative Cache Based on Temporal Convolutional Networks in Vehicular Edge Network

Jin

Xing

2023

Sensors

View full text Add to dashboard Cite

With the continuous development of intelligent vehicles, people’s demand for services has also rapidly increased, leading to a sharp increase in wireless network traffic. Edge caching, due to its location advantage, can provide more efficient transmission services and become an effective method to solve the above problems. However, the current mainstream caching solutions only consider content popularity to formulate caching strategies, which can easily lead to cache redundancy between edge nodes and lead to low caching efficiency. To solve these problems, we propose a hybrid content value collaborative caching strategy based on temporal convolutional network (called THCS), which achieves mutual collaboration between different edge nodes under limited cache resources, thereby optimizing cache content and reducing content delivery latency. Specifically, the strategy first obtains accurate content popularity through temporal convolutional network (TCN), then comprehensively considers various factors to measure the hybrid content value (HCV) of cached content, and finally uses a dynamic programming algorithm to maximize the overall HCV and make optimal cache decisions. We have obtained the following conclusion through simulation experiments: compared with the benchmark scheme, THCS has improved the cache hit rate by 12.3% and reduced the content transmission delay by 16.7%.

show abstract

DeepCache

Cited by 110 publications

References 13 publications

Reinforcement learning inspired forwarding strategy for information centric networks using Q‐learning algorithm

Reinforcement learning inspired forwarding strategy for information centric networks using Q‐learning algorithm

Controller-driven vector autoregression model for predicting content popularity in programmable named data networking devices

Hybrid Cooperative Cache Based on Temporal Convolutional Networks in Vehicular Edge Network

Contact Info

Product

Resources

About