Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020094630 - ONE SHOT MULTI-USER MULTIPLE-INPUT MULTIPLE-OUTPUT (MU-MIMO) RESOURCE PAIRING USING REINFORCEMENT LEARNING BASED DEEP Q NETWORK (DQN)

Publication Number WO/2020/094630
Publication Date 14.05.2020
International Application No. PCT/EP2019/080217
International Filing Date 05.11.2019
IPC
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
H04B 7/0452 2017.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
BTRANSMISSION
7Radio transmission systems, i.e. using radiation field
02Diversity systems; Multi-antenna systems, i.e. transmission or reception using multiple antennas
04using two or more spaced independent antennas
0413MIMO systems
0452Multi-user MIMO systems
H04B 7/06 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
BTRANSMISSION
7Radio transmission systems, i.e. using radiation field
02Diversity systems; Multi-antenna systems, i.e. transmission or reception using multiple antennas
04using two or more spaced independent antennas
06at the transmitting station
CPC
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
H04B 7/0452
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
BTRANSMISSION
7Radio transmission systems, i.e. using radiation field
02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
04using two or more spaced independent antennas
0413MIMO systems
0452Multi-user MIMO systems
H04B 7/0695
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
BTRANSMISSION
7Radio transmission systems, i.e. using radiation field
02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
04using two or more spaced independent antennas
06at the transmitting station
0686Hybrid systems, i.e. switching and simultaneous transmission
0695using beam selection
Applicants
  • NOKIA SOLUTIONS AND NETWORKS OY [FI]/[FI]
Inventors
  • SANKARAN, Chandrasekar
Agents
  • AARNIO, Ari
  • UUSITALO, Arttu
Priority Data
2018593705.11.2018FI
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) ONE SHOT MULTI-USER MULTIPLE-INPUT MULTIPLE-OUTPUT (MU-MIMO) RESOURCE PAIRING USING REINFORCEMENT LEARNING BASED DEEP Q NETWORK (DQN)
(FR) APPARIEMENT DE RESSOURCES MU-MIMO (MULTIPLES ENTRÉES, MULTIPLES SORTIES, MULTIPLES UTILISATEURS) EN UNE FOIS GRÂCE À L'APPRENTISSAGE PAR RENFORCEMENT BASÉ SUR UN RÉSEAU Q PROFOND (DQN)
Abstract
(EN)
Systems, methods, apparatuses, and computer program products for scheduling radio resources across a group of one or more user equipment (UEs) are provided. One method may include encoding every sequence of multi-user multiple-input multiple-output (MU MIMO) beam combinations into a unique numerical value, adding a Q value into the encoded numerical value to produce a Q encoded value (Qencoded), providing each of the sequence of beam combinations with a unique designated bin, passing a matrix comprising a state representation for each of the beam combinations through a deep Q network (DQN), and outputting, by the deep Q network (DQN), one or more optimal beams to assign to a user equipment (UE).
(FR)
L'invention concerne des systèmes, des procédés, des appareils et des produits programmes informatiques permettant d'ordonnancer des ressources radio dans un groupe d'un ou de plusieurs équipements d'utilisateur (UE). Un procédé peut consister à encoder chaque séquence de combinaisons de faisceaux MU-MIMO (multiples entrées, multiples sorties, multiples utilisateurs) en une valeur numérique unique, ajouter une valeur Q à la valeur numérique encodée pour produire une valeur à encodage par Q (encodage par Q), fournir à chaque combinaison de la séquence de combinaisons de faisceaux une catégorie désignée unique, fournir une matrice comprenant une représentation d'état pour chacune des combinaisons de faisceaux en entrée d'un réseau Q profond (DQN), et produire, par le réseau Q profond (DQN), un ou plusieurs faisceaux optimaux à attribuer à un équipement d'utilisateur (UE).
Latest bibliographic data on file with the International Bureau