Spectrum and Power Allocation for Vehicular Communications With Delayed CSI Feedback

IEEE J. Select. Areas Commun.

Hao

2019

Self Cite

402

205

This paper investigates the spectrum sharing problem in vehicular networks based on multi-agent reinforcement learning, where multiple vehicle-to-vehicle (V2V) links reuse the frequency spectrum preoccupied by vehicle-to-infrastructure (V2I) links. Fast channel variations in high mobility vehicular environments preclude the possibility of collecting accurate instantaneous channel state information at the base station for centralized resource management. In response, we model the resource sharing as a multi-agent reinforcement learning problem, which is then solved using a fingerprint-based deep Q-network method that is amenable to a distributed implementation. The V2V links, each acting as an agent, collectively interact with the communication environment, receive distinctive observations yet a common reward, and learn to improve spectrum and power allocation through updating Q-networks using the gained experiences. We demonstrate that with a proper reward design and training mechanism, the multiple V2V agents successfully learn to cooperate in a distributed way to simultaneously improve the sum capacity of V2I links and payload delivery rate of V2V links.Index Terms-Vehicular networks, distributed spectrum access, spectrum and power allocation, multi-agent reinforcement learning.

Section: B Related Workmentioning

confidence: 99%

Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning

IEEE J. Select. Areas Commun.

Hao

2019

Self Cite

402

205

“…The large-scale fading components remain unchanged for a fixed distance between the two corresponding nodes, while the smallscale fading components remain unchange in one frame, but vary in different frames. We use Jakes' model to represent the variation of the small-scale fading component for each channel in frame t, which yields [26] h m (t) = ρh m (t − 1) + e m (t),…”

Section: A Channel Modelmentioning

confidence: 99%

Intelligent User Association for Symbiotic Radio Networks Using Deep Reinforcement Learning

Zhang

2019 IEEE Global Communications Conference (GLOBECOM)

Poor

2019

In this paper, we are interested in symbiotic radio networks, in which an Internet-of-Things (IoT) network parasitizes in a primary network to achieve spectrum-, energy-, and infrastructure-efficient communications. Specifically, the BS serves multiple cellular users using time division multiple access (TDMA) and each IoT device is associated with one cellular user for information transmission. We focus on the user association problem, whose objective is to link each IoT device to an appropriate cellular user by maximizing the sum rate of all IoT devices. However, the difficulty in obtaining the full real-time channel information makes it difficult to design an optimal policy for this problem. To overcome this issue, we propose two deep reinforcement learning (DRL) algorithms, both use the historical information to infer the current information in order to make appropriate decisions. One algorithm, centralized DRL, makes decisions for all IoT devices at one time with global information. The other algorithm, distributed DRL, makes a decision only for one IoT device at one time using local information. Finally, simulation results show that the two DRL algorithms achieve comparable performance as the optimal user association policy which requires perfect real-time information, and the distributed DRL algorithm has the advantage of scalability.Index Terms-Symbiotic radio networks (SRN), ambient backscatter communication (AmBC), user association, deep reinforcement learning.

“…To this end, the D2D-enabled vehicular communications should carefully address the challenge caused by the channel uncertainty. The work in [8] have considered the case of delayed feedback of the CSI of the V2V links and proposed a spectrum and power allocation scheme to maximize the sum capacity of the V2I links with guarantee on the V2V links' signal-to-interference-plus-noise ratio (SINR) outage probability. Resource management in [9] have maximized the sum and minimum ergodic capacity of the V2I links while guaranteeing the SINR outage probabilities of the V2V links, based on only the large-scale channel information.…”

Section: Introductionmentioning

confidence: 99%

Resource Allocation for Low-Latency Vehicular Communications with Packet Retransmission

Guo

2018 IEEE Global Communications Conference (GLOBECOM)

2018

Self Cite

Vehicular communications have stringent latency requirements on safety-critical information transmission. However, lack of instantaneous channel state information due to high mobility poses a great challenge to meet these requirements and the situation gets more complicated when packet retransmission is considered. Based on only the obtainable large-scale fading channel information, this paper performs spectrum and power allocation to maximize the ergodic capacity of vehicular-toinfrastructure (V2I) links while guaranteeing the latency requirements of vehicular-to-vehicular (V2V) links. First, for each possible spectrum reusing pair of a V2I link and a V2V link, we obtain the closed-form expression of the packets' average sojourn time (the queueing time plus the service time) for the V2V link. Then, an optimal power allocation is derived for each possible spectrum reusing pair. Afterwards, we optimize the spectrum reusing pattern by addressing a polynomial time solvable bipartite matching problem. Numerical results show that the proposed queueing analysis is accurate in terms of the average packet sojourn time. Moreover, the developed resource allocation always guarantees the V2V links' requirements on latency.