Energy-Efficient Subchannel and Power Allocation for HetNets Based on Convolutional Neural Network

Xu, Di; Che, Xiaojing; Changhao, Wu; Zhang, Shunqing; Xu, Shugong; Cao, Shan

doi:10.48550/arxiv.1903.00165

Cited by 3 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The REGNNs we consider in this paper are defined by recursive application of (13). The input to layer l = 1 is the (single feature) signal x = z 1 0 .…”

Section: Random Edge Graph Neural Networkmentioning

confidence: 99%

“…Scalability is attained in the processing of signals in time and space with convolutional neural networks (CNNs). Recognizing this fact has led to proposals that adapt CNNs to wireless resource allocation problems [13], [14], [17]. A particularly enticing alternative is the use of a spatial CNN that exploits the spatial geometry of wireless networks to attain scalability to large scale systems with hundreds of nodes [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks

Eisen

Ribeiro

2020

IEEE Trans. Signal Process.

258

205

View full text Add to dashboard Cite

We consider the problem of optimally allocating resources across a set of transmitters and receivers in a wireless network. The resulting optimization problem takes the form of constrained statistical learning, in which solutions can be found in a model-free manner by parameterizing the resource allocation policy. Convolutional neural networks architectures are an attractive option for parameterization, as their dimensionality is small and does not scale with network size. We introduce the random edge graph neural network (REGNN), which performs convolutions over random graphs formed by the fading interference patterns in the wireless network. The REGNN-based allocation policies are shown to retain an important permutation equivariance property that makes them amenable to transference to different networks. We further present an unsupervised model-free primal-dual learning algorithm to train the weights of the REGNN. Through numerical simulations, we demonstrate the strong performance REGNNs obtain relative to heuristic benchmarks and their transference capabilities.

show abstract

“…The REGNNs we consider in this paper are defined by recursive application of (13). The input to layer l = 1 is the (single feature) signal x = z 1 0 .…”

Section: Random Edge Graph Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks

Eisen

Ribeiro

2020

IEEE Trans. Signal Process.

258

205

View full text Add to dashboard Cite

show abstract

“…Consider a function q with binary output that determines channel access decision based on transmission powers and channel states. The actual transmission rate for transmitter i depends upon whether or not collisions have occurred and can be written as (9) where the function c i (h i , p i (H i )) defines the transmission rate, the exact form of which is determined by the physical layer. The utility function u 0 (r) = r T 1 is set as the sum of the actual transmission rates.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Learned heuristics can often outperform designed heuristics but they also have some other advantages. They are computationally less costly [9], [10]. They can learn from interactions with the environment and are therefore not necessarily reliant on access to channel and rate models [11]- [13].…”

Section: Introductionmentioning

confidence: 99%

Learning Decentralized Wireless Resource Allocations with Graph Neural Networks

Wang,

Eisen,

Ribeiro

2021

Preprint

View full text Add to dashboard Cite

We consider the broad class of decentralized optimal resource allocation problems in wireless networks, which can be formulated as a constrained statistical learning problems with a localized information structure. We develop the use of Aggregation Graph Neural Networks (Agg-GNNs), which process a sequence of delayed and potentially asynchronous graph aggregated state information obtained locally at each transmitter from multi-hop neighbors. We further utilize model-free primal-dual learning methods to optimize performance subject to constraints in the presence of delay and asynchrony inherent to decentralized networks. We demonstrate a permutation equivariance property of the resulting resource allocation policy that can be shown to facilitate transference to dynamic network configurations. The proposed framework is validated with numerical simulations that exhibit superior performance to baseline strategies.

show abstract

“…Resource allocation methods, generally speaking, are usually addressed through optimization methods. Because of their non-convex nature in wireless systems, standard centralized resource allocation policies are obtained through heuristic optimization methods [1][2][3] or data-driven machine learning methods [4][5][6][7][8][9]. The latter case is seeing growing interest due to its applicability in a wide range of application scenarios and lack of reliance on explicit or accurate system modeling.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning for Asynchronous Resource Allocation In Ad-Hoc Wireless Networks

Wang

Eisen

Ribeiro

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We consider optimal resource allocation problems under asynchronous wireless network setting. Without explicit model knowledge, we design an unsupervised learning method based on Aggregation Graph Neural Networks (Agg-GNNs). Depending on the localized aggregated information structure on each network node, the method can be learned globally and asynchronously while implemented locally. We capture the asynchrony by modeling the activation pattern as a characteristic of each node and train a policy-based power allocation method. We also propose a permutation invariance property which indicates the transferability of the trained Agg-GNN. We finally verify our strategy by numerical simulations compared with baseline methods.

show abstract

Energy-Efficient Subchannel and Power Allocation for HetNets Based on Convolutional Neural Network

Cited by 3 publications

References 13 publications

Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks

Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks

Learning Decentralized Wireless Resource Allocations with Graph Neural Networks

Unsupervised Learning for Asynchronous Resource Allocation In Ad-Hoc Wireless Networks

Contact Info

Product

Resources

About