Cache-Enabled Multicast Content Pushing With Structured Deep Learning

Chen, Qi; Wang, Wei; Chen, Wei; Yu, Feng; Zhang, Zhaoyang

doi:10.1109/jsac.2021.3078493

Cited by 17 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Strategies based on reinforcement learning and deep learning use observable user data or environmental states, such as user contextual information, channel gain or cache state, for online caching decisions and resource allocation. Wireless channels have a finite amount of data that can be transmitted per unit time, and proactive caching strategies are investigated in order to maximise bandwidth utilisation [21]- [24]. However, when the user request or environment state space is large, centralised Reinforcement Learning caching strategies are complex and difficult to handle, hence distributed reinforcement learning approaches are proposed [25].…”

Section: B Joint Caching and Resource Optimizationmentioning

confidence: 99%

“…Similar to the contributions in [14] and [15], we predict user preference popularity by analyzing historical request information. Similar to the contributions in [23], [24], [25], [26], [27], and [28], we utilize reinforcement learning for dynamic cache decision optimization. However, what sets our work apart from these contributions is that we employ predicted user preferences for D2D shared node selection.…”

Section: Our Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Lyapunov Optimization and Deep Reinforcement Learning for D2D Assisted Heterogeneous Collaborative Edge Caching

Teng,

Fang,

Liu

2024

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

The problem of shared node selection and cache placement in wireless networks is challenging due to the difficulty of finding low-complexity optimal solutions. This paper proposes a new approach combining Lyapunov optimization and reinforcement learning (LoRL) to address content sharing in heterogeneous mobile edge computing (MEC) networks with base station (BS) and device-to-device (D2D) communication. Device in this network can choose to establish D2D links with neighboring devices for content sharing or send requests directly to the base station for content. Content access and energy consumption of shared nodes are modeled as a queuing system. The goal is to assign content sharing nodes to stabilize all queues while maximizing D2D sharing gain and minimizing latency, even in the presence of unknown network state distribution and user sharing costs. The proposed approach enables edge device to independently select associated nodes and make caching decisions, thereby minimizing time-averaged network costs and stabilizing the queuing system. Experimental results show that the proposed algorithm converges to the optimal policy and outperforms other policies in terms of total queue backlog tradeoff and network cost.

show abstract

Section: B Joint Caching and Resource Optimizationmentioning

confidence: 99%

Section: Our Contributionmentioning

confidence: 99%

Combining Lyapunov Optimization and Deep Reinforcement Learning for D2D Assisted Heterogeneous Collaborative Edge Caching

Teng,

Fang,

Liu

2024

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…Finally, the joint scheduling of memories and wireless links generalizes the concept of cross-layer design by involving both the communication and memory units. Deep learning and deep reinforcement learning are expected to play key roles in dealing with the dynamic nature of user requests and radio environments [33][34][35].…”

Section: Memory Costsmentioning

confidence: 99%

Wireless Caching: Making Radio Access Networks More than Bit-Pipelines

Chen

Poor

2021

Network

Self Cite

View full text Add to dashboard Cite

Caching has attracted much attention recently because it holds the promise of scaling the service capability of radio access networks (RANs). We envision that caching will ultimately make next-generation RANs more than bit-pipelines and emerge as a multi-disciplinary area via the union with communications, pricing, recommendation, compression, and computation units. By summarizing cutting-edge caching policies, we trace a common root of their gains to the prolonged transmission time, which is then traded for higher spectral or energy efficiency. To realize caching, the physical layer and higher layers have to function together, with the aid of prediction and memory units, which substantially broadens the concept of cross-layer design to a multi-unit collaboration methodology. We revisit caching from a generalized cross-layer perspective, with a focus on its emerging opportunities, challenges, and theoretical performance limits. To motivate the application and evolution of caching, we conceive a hierarchical pricing infrastructure that provides incentives to network operators and users. To make RANs even more proactive, we design caching and recommendation jointly, showing a user what it might be interested in and what has been done for it. Furthermore, the user-specific demand prediction motivates edge compression and proactive MEC as new applications. The beyond-bit-pipeline RAN is a paradigm shift that brings with it many cross-disciplinary research opportunities.

show abstract

“…Joint proactive caching and caching designs that can improve system performance by proactively transferring and replacing cached content during low-traffic times to meet future user needs have been extensively studied [10]- [13]. Somuyiwa et al [10] proposes a threshold-based proactive caching strategy that requires causal knowledge of channel quality, content profile, and user access behavior.…”

Section: Introductionmentioning

confidence: 99%

“…However, these proactive caching schemes above do not consider the limitation of the wireless transmission channel between the server and the user. On the other hand, Chen et al [13] develops a multi-cast proactive content strategy based on structured deep learning, which considers the complex coupling of time-varying transmission capacity and proactive caching decisions between users, but only focuses on proactive caching at the user end, ignoring the its impact on the server side.…”

Section: Introductionmentioning

confidence: 99%

Attention Mechanism-Aided Deep Reinforcement Learning for Dynamic Edge Caching

Teng,

Fang,

Yang

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

The dynamic mechanism of joint proactive caching and cache replacement, which involves placing content items close to cache-enabled edge devices ahead of time until they are requested, is a promising technique for enhancing traffic offloading and relieving heavy network loads. However, due to limited edge cache capacity and wireless transmission resources, accurately predicting users' future requests and performing dynamic caching is crucial to effectively utilizing these limited resources. This paper investigates joint proactive caching and cache replacement strategies in a general mobile edge computing (MEC) network with multiple users under a cloud-edge-device collaboration architecture. The joint optimization problem is formulated as a markov decision process (MDP) problem with an infinite range of average network load costs, aiming to reduce network load traffic while efficiently utilizing the limited available transport resources. To address this issue, we design an Attention Weighted Deep Deterministic Policy Gradient (AWD2PG) model, which uses attention weights to allocate the number of channels from server to user, and applies deep deterministic policies on both user and server sides for Cache decision-making, so as to achieve the purpose of reducing network traffic load and improving network and cache resource utilization. We verify the convergence of the corresponding algorithms and demonstrate the effectiveness of the proposed AWD2PG strategy and benchmark in reducing network load and improving hit rate.

show abstract

Cache-Enabled Multicast Content Pushing With Structured Deep Learning

Cited by 17 publications

References 32 publications

Combining Lyapunov Optimization and Deep Reinforcement Learning for D2D Assisted Heterogeneous Collaborative Edge Caching

Combining Lyapunov Optimization and Deep Reinforcement Learning for D2D Assisted Heterogeneous Collaborative Edge Caching

Wireless Caching: Making Radio Access Networks More than Bit-Pipelines

Attention Mechanism-Aided Deep Reinforcement Learning for Dynamic Edge Caching

Contact Info

Product

Resources

About