Caching Transient Data for Internet of Things: A Deep Reinforcement Learning Approach

Zhu, Hao; Cao, Yang; Wei, Xiao; Wang, Wei; Jiang, Tao; Jin, Shi

doi:10.1109/jiot.2018.2882583

Cited by 133 publications

(91 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since every cache hit results in the content being cached one hop closer to the requesting consumer, popular content that is requested with high frequency will gradually move the content closer to consumers with each step. if canSatisfy(Interest) then 3: Data ← getData(Interest) 4: reply(Data) 5: if rand() < p then 12: cache(Data) 13: end if 14: forward(Data) 15: end function…”

Section: B Leave Copy Down (Lcd)mentioning

confidence: 99%

See 1 more Smart Citation

Performance comparison of caching strategies for information-centric IoT

Pfender

Valera

Seah

2018

Proceedings of the 5th ACM Conference on Information-Centric Networking

View full text Add to dashboard Cite

In-network caching is a central aspect of Information-Centric Networking (ICN). It enables the rapid distribution of content across the network, alleviating strain on content producers and reducing content delivery latencies. ICN has emerged as a promising candidate for use in the Internet of Things (IoT). However, IoT devices operate under severe constraints, most notably limited memory. This means that nodes cannot indiscriminately cache all content; instead, there is a need for a caching strategy that decides what content to cache. Furthermore, many applications in the IoT space are timesensitive; therefore, finding a caching strategy that minimises the latency between content request and delivery is desirable. In this paper, we evaluate a number of ICN caching strategies in regards to latency and hop count reduction using IoT devices in a physical testbed. We find that the topology of the network, and thus the routing algorithm used to generate forwarding information, has a significant impact on the performance of a given caching strategy. To the best of our knowledge, this is the first study that focuses on latency effects in ICN-IoT caching while using real IoT hardware, and the first to explicitly discuss the link between routing algorithm, network topology, and caching effects.

show abstract

Section: B Leave Copy Down (Lcd)mentioning

confidence: 99%

“…The question of where in the network content should be cached is one of the most defining problems of in-network caching research [12]- [15]. In particular, it has not been definitively established whether it is better to cache content towards the edge of the network (i.e.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of caching strategies for information-centric IoT

Pfender

Valera

Seah

2018

Proceedings of the 5th ACM Conference on Information-Centric Networking

View full text Add to dashboard Cite

show abstract

“…2) Caching: Caching IoT data at the network edge is considered to be able to alleviate the congestions and delays in transmitting IoT data through wireless networks. The research in [129] solves the problem of caching IoT data at the edge with the help of DRL. The proposed data caching policy aims to strike a balance between the communication cost and the loss of data freshness.…”

Section: E Aiot Application Layer -Iot Edge/fog/cloud Computing Systemsmentioning

confidence: 99%

Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges

Lei

Tan

Zheng

et al. 2020

IEEE Commun. Surv. Tutorials

217

View full text Add to dashboard Cite

The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices around the world, which collect and share information to reflect the status of physical world. The Autonomous Control System (ACS), on the other hand, performs control functions on the physical systems without external intervention over an extended period of time. The integration of IoT and ACS results in a new concept -autonomous IoT (AIoT). The sensors collect information on the system status, based on which intelligent agents in IoT devices as well as Edge/Fog/Cloud servers make control decisions for the actuators to react. In order to achieve autonomy, a promising method is for the intelligent agents to leverage the techniques in the field of artificial intelligence, especially reinforcement learning (RL) and deep reinforcement learning (DRL) for decision making. In this paper, we first provide comprehensive survey of the state-of-art research, and then propose a general model for the applications of RL/DRL in AIoT. Finally, the challenges and open issues for future research are identified.

show abstract

“…One of the RL based caching scheme is proposed by Zhu et al in [68]. The authors defined the action space where each action indicates the data item to be replaced in the cache.…”

Section: Recommendation Via Q Learningmentioning

confidence: 99%

Data Caching at Fog Nodes Under IoT Networks: Review of Machine Learning Approaches

Tapwal¹,

Gupta²,

Xin³

2020

Preprint

View full text Add to dashboard Cite

<div>IoT devices (wireless sensors, actuators, computer devices) produce large volume and variety of data and the data</div><div>produced by the IoT devices are transient. In order to overcome the problem of traditional IoT architecture where</div><div>data is sent to the cloud for processing, an emerging technology known as fog computing is proposed recently.</div><div>Fog computing brings storage, computing and control near to the end devices. Fog computing complements the</div><div>cloud and provide services to the IoT devices. Hence, data used by the IoT devices must be cached at the fog nodes</div><div>in order to reduce the bandwidth utilization and latency. This chapter discusses the utility of data caching at the</div><div>fog nodes. Further, various machine learning techniques can be used to reduce the latency by caching the data</div><div>near to the IoT devices by predicting their future demands. Therefore, this chapter also discusses various machine</div><div>learning techniques that can be used to extract the accurate data and predict future requests of IoT devices.</div>

show abstract

Caching Transient Data for Internet of Things: A Deep Reinforcement Learning Approach

Cited by 133 publications

References 24 publications

Performance comparison of caching strategies for information-centric IoT

Performance comparison of caching strategies for information-centric IoT

Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges

Data Caching at Fog Nodes Under IoT Networks: Review of Machine Learning Approaches

Contact Info

Product

Resources

About