Power control for interference mitigation by evolutionary game theory in uplink NOMA for 5G networks

Riaz, Sidra; Park, Unsang

doi:10.1080/02533839.2017.1419075

Cited by 16 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Solutions to this problem run the gamut from classical optimization techniques [2] to information and game theory [3], [4]. As emerging applications demand growth in scale and complexity, modern machine learning techniques have also been explored as alternatives to solve RRM problems in the presence of model and/or algorithmic deficits [5].…”

Section: A Motivationmentioning

confidence: 99%

“…We study the case in which where the number of nodes in the network, K τ , is fixed, but the topology changes across periods; as well as the case in which the number of nodes in the network is also time-varying. 2) Dynamic network size: In the second scenario, the size of the network is chosen uniformly at random as K τ ∼ Uniform ( [4,20]). Each meta-training data set D τ corresponds to a realization of the network size and to a random drop of the transmitter-receiver pairs as discussed above.…”

Section: Data Setsmentioning

confidence: 99%

See 1 more Smart Citation

Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

Nikoloska¹,

Simeone²

2021

Preprint

View full text Add to dashboard Cite

In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes. A data-driven design methodology that leverages graph neural networks (GNNs) is adopted in order to efficiently parametrize the power control policy mapping the channel state information (CSI) to transmit powers. The specific GNN architecture, known as random edge GNN (REGNN), defines a non-linear graph convolutional filter whose spatial weights are tied to the channel coefficients. While prior work assumed a joint training approach whereby the REGNN-based policy is shared across all topologies, this paper targets adaptation of the power control policy based on limited CSI data regarding the current topology. To this end, we propose both black-box and modular meta-learning techniques. Black-box meta-learning optimizes a general-purpose adaptation procedure via (stochastic) gradient descent, while modular meta-learning finds a set of reusable modules that can form components of a solution for any new network topology.Numerical results validate the benefits of meta-learning for power control problems over joint training schemes, and demonstrate the advantages of modular meta-learning when data availability is extremely limited.

show abstract

Section: A Motivationmentioning

confidence: 99%

Section: Data Setsmentioning

confidence: 99%

Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

Nikoloska¹,

Simeone²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Considering

G = (][, N, (}{, A i), (}{, U i false(\cdot false)))

, where G denoting the non‐cooperative MIMO power control game (NMPCG), with N = { l , 2, …, i } is the directory set for the itinerant users presently in the cell [12–14], the total transmit power strategy Pi is selected by the i th user , such that

P i \in A i

, where

A_{i}

signifies the tactic space of the i th user. Let the end result of the game be denoted in terms of the suitable power levels by the vector P = ( P 1 , …, P n ) of all users, P −i denotes the vector comprising of fundamentals of P other than the i th element and let A −i expresses the strategy gap of all the users not including the i th user.…”

Section: Power Control Game For Mimomentioning

confidence: 99%

Game theory‐based modulation techniques for fifth‐generation cellular system

Thankaraj¹,

Nagarajan²

2019

IET Communications

View full text Add to dashboard Cite

“…As the extensive variety of obstacles for the power enhancement, MAI switch into wide spreading and might be critically lessen the data inaccuracy speed of the model. so as to effectively reduce the MAI in a MC CDMA situation by calculating with Walsh spreading sequences leads to attain the aim (non‐cooperative power control game (NPGP) along with chaotic order) 15–21 . Optimization of interference parameter is done by reducing the MAI.…”

Section: Introductionmentioning

confidence: 99%

“…so as to effectively reduce the MAI in a MC CDMA situation by calculating with Walsh spreading sequences leads to attain the aim (non-cooperative power control game (NPGP) along with chaotic order). [15][16][17][18][19][20][21] Optimization of interference parameter is done by reducing the MAI.…”

mentioning

confidence: 99%

Chaotic sequence‐based MC‐CDMA for 5G

raj

Sankaran²,

Nagarajan³

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary A unique chaotic spreading sequence‐based MC‐CDMA (multi‐carrier code division multiple accesses) is studied in this article. By employing this spreading sequence, interference effect that is inherent in a multi‐user environment can be lessened by deciding on the spreading series with suitable cross‐correlation properties. The simulation study exhibits that chaotic sequence‐based MC‐CDMA acts well in a multiuser setting, resulting in better attainable error rates. Moreover, results confirm that chaotic sequence‐based MC‐CDMA beats the Walsh Hadamard code spreading‐based MC CDMA system. The inception of MIMO (Multiple Input Multiple Output) scheme leads to the augment in the number of antennas that are present in the transmitting in addition to receiving side. This induces an enhancement in the throughput and the robustness of the communication system. Further, the simulation outcomes exhibit that the suggested technique is far beneficial in the context of combating MAI (multiple access interference) and aids to achieve performance amelioration concerning the utility of approximately 9%.

show abstract

Power control for interference mitigation by evolutionary game theory in uplink NOMA for 5G networks

Cited by 16 publications

References 23 publications

Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

Game theory‐based modulation techniques for fifth‐generation cellular system

Chaotic sequence‐based MC‐CDMA for 5G

Contact Info

Product

Resources

About