Deep neural network based resource allocation in D2D wireless networks
    
    
  
  
  
      
      
      
        
Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ, Tome 19 (2023) no. 4, pp. 529-539
    
  
  
  
  
  
    
      
      
        
      
      
      
    Voir la notice de l'article provenant de la source Math-Net.Ru
            
              			The increased complexity of future 5G wireless communication networks presents a fundamental issue for optimal resource allocation. This continuous, constrained optimal control problem must be solved in real-time since the power allocation should be consistent with the instantly evolving channel state. This paper emphasizes the application of deep learning to develop solutions for radio resource allocation problems in multiple-input multiple-output systems. We introduce a supervised deep neural network model combined with particle swarm optimization to address the issue using heuristic-generated data. We train the model and evaluate its ability to anticipate resource allocation solutions accurately. The simulation result indicates that the trained DNN-based model can deliver the near-optimal solution.
			
            
            
            
          
        
      
                  
                    
                    
                    
                        
Keywords: 
multiple-input multiple-output systems, deep neural networks, heuristics, particle swarm optimization.
                    
                    
                    
                  
                
                
                @article{VSPUI_2023_19_4_a8,
     author = {Q. Sun and Y. Zhang and H. Wu and O. L. Petrosian},
     title = {Deep neural network based resource allocation in {D2D} wireless networks},
     journal = {Vestnik Sankt-Peterburgskogo universiteta. Prikladna\^a matematika, informatika, processy upravleni\^a},
     pages = {529--539},
     publisher = {mathdoc},
     volume = {19},
     number = {4},
     year = {2023},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/VSPUI_2023_19_4_a8/}
}
                      
                      
                    TY - JOUR AU - Q. Sun AU - Y. Zhang AU - H. Wu AU - O. L. Petrosian TI - Deep neural network based resource allocation in D2D wireless networks JO - Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ PY - 2023 SP - 529 EP - 539 VL - 19 IS - 4 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/VSPUI_2023_19_4_a8/ LA - en ID - VSPUI_2023_19_4_a8 ER -
%0 Journal Article %A Q. Sun %A Y. Zhang %A H. Wu %A O. L. Petrosian %T Deep neural network based resource allocation in D2D wireless networks %J Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ %D 2023 %P 529-539 %V 19 %N 4 %I mathdoc %U http://geodesic.mathdoc.fr/item/VSPUI_2023_19_4_a8/ %G en %F VSPUI_2023_19_4_a8
Q. Sun; Y. Zhang; H. Wu; O. L. Petrosian. Deep neural network based resource allocation in D2D wireless networks. Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ, Tome 19 (2023) no. 4, pp. 529-539. http://geodesic.mathdoc.fr/item/VSPUI_2023_19_4_a8/
