اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDynamic Coded Caching in Wireless Networks Using Multi-Agent Reinforcement Learning
110
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We consider distributed caching of content across several small base stations (SBSs) in a wireless network, where the content is encoded using a maximum distance separable code. Specifically, we apply soft time-to-live (STTL) cache management policies, where coded packets may be evicted from the caches at periodic times. We propose a reinforcement learning (RL) approach to find coded STTL policies minimizing the overall network load. We demonstrate that such caching policies achieve almost the same network load as policies obtained through optimization, where the latter assumes perfect knowledge of the distribution of times between file requests as well the distribution of the number of SBSs within communication range of a user placing a request. We also suggest a multi-agent RL (MARL) framework for the scenario of non-uniformly distributed requests in space. For such a scenario, we show that MARL caching policies achieve lower network load as compared to optimized caching policies assuming a uniform request placement. We also provide convincing evidence that synchronous updates offer a lower network load than asynchronous updates for spatially homogeneous renewal request processes due to the memory of the renewal processes.
قيم البحث
اقرأ أيضاً
This letter studies a basic wireless caching network where a source server is connected to a cache-enabled base station (BS) that serves multiple requesting users. A critical problem is how to improve cache hit rate under dynamic content popularity.
To solve this problem, the primary contribution of this work is to develop a novel dynamic content update strategy with the aid of deep reinforcement learning. Considering that the BS is unaware of content popularities, the proposed strategy dynamically updates the BS cache according to the time-varying requests and the BS cached contents. Towards this end, we model the problem of cache update as a Markov decision process and put forth an efficient algorithm that builds upon the long short-term memory network and external memory to enhance the decision making ability of the BS. Simulation results show that the proposed algorithm can achieve not only a higher average reward than deep Q-network, but also a higher cache hit rate than the existing replacement policies such as the least recently used, first-in first-out, and deep Q-network based algorithms.
For ultra-dense networks with wireless backhaul, caching strategy at small base stations (SBSs), usually with limited storage, is critical to meet massive high data rate requests. Since the content popularity profile varies with time in an unknown wa
y, we exploit reinforcement learning (RL) to design a cooperative caching strategy with maximum-distance separable (MDS) coding. We model the MDS coding based cooperative caching as a Markov decision process to capture the popularity dynamics and maximize the long-term expected cumulative traffic load served directly by the SBSs without accessing the macro base station. For the formulated problem, we first find the optimal solution for a small-scale system by embedding the cooperative MDS coding into Q-learning. To cope with the large-scale case, we approximate the state-action value function heuristically. The approximated function includes only a small number of learnable parameters and enables us to propose a fast and efficient action-selection approach, which dramatically reduces the complexity. Numerical results verify the optimality/near-optimality of the proposed RL based algorithms and show the superiority compared with the baseline schemes. They also exhibit good robustness to different environments.
The multi-access variant of the coded caching problem in the presence of an external wiretapper is investigated . A multi-access coded caching scheme with $K$ users, $K$ caches and $N$ files, where each user has access to $L$ neighbouring caches in a
cyclic wrap-around manner, is proposed, which is secure against the wiretappers. Each transmission in the conventional insecure scheme will be now encrypted by a random key. The proposed scheme uses a novel technique for the key placement in the caches. It is also shown that the proposed secure multi-access coded caching scheme is within a constant multiplicative factor from the information-theoretic optimal rate for $Lgeq frac{K}{2}$ and $Ngeq 2K$.
The demand private coded caching problem in a multi-access network with $K$ users and $K$ caches, where each user has access to $L$ neighbouring caches in a cyclic wrap-around manner, is studied. The additional constraint imposed is that one user sho
uld not get any information regarding the demands of the remaining users. A lifting construction of demand private multi-access coded caching scheme from conventional, non-private multi-access scheme is introduced. The demand-privacy for a user is ensured by placing some additional textit{keys} in a set of caches called the textit{private set} of that user. For a given $K$ and $L$, a technique is also devised to find the private sets of the users.
We consider multi-access coded caching problem introduced by Hachem et.al., where each user has access to $L$ neighboring caches in a cyclic wrap-around fashion. We focus on the deterministic schemes for a specific class of multi-access coded caching
problem based on the concept of PDA. We construct new PDAs which specify the delivery scheme for the specific class of multi-access coded caching problem discussed in this paper. For the proposed scheme, the coding gain is larger than that of the state-of-the-art while the sub-packetization level varies only linearly with the number of users. Hence, we achieve a lower transmission rate with the least sub-packetization level compared to the existing schemes.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
