Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021026944 - ADAPTIVE TRANSMISSION METHOD FOR INDUSTRIAL WIRELESS STREAMING MEDIA EMPLOYING PARTICLE SWARM AND NEURAL NETWORK

Publication Number WO/2021/026944
Publication Date 18.02.2021
International Application No. PCT/CN2019/101360
International Filing Date 19.08.2019
IPC
H04N 21/24 2011.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand
20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
23Processing of content or additional data; Elementary server operations; Server middleware
24Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth or upstream requests
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
CPC
G06N 3/006
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
004Artificial life, i.e. computers simulating life
006based on simulated virtual individual or collective life forms, e.g. single "avatar", social simulations, virtual worlds or particle swarm optimisation
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
H04N 21/2402
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand [VOD]
20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
23Processing of content or additional data; Elementary server operations; Server middleware
24Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
2402Monitoring of the downstream path of the transmission network, e.g. bandwidth available
H04N 21/26216
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand [VOD]
20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
25Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
262Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
26208the scheduling operation being performed under constraints
26216involving the channel capacity, e.g. network bandwidth
H04N 21/64738
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand [VOD]
60Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client ; , e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
63Control signaling ; related to video distribution; between client, server and network components; Network processes for video distribution between server and clients ; or between remote clients; , e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
647Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
64723Monitoring of network processes or resources, e.g. monitoring of network load
64738Monitoring network characteristics, e.g. bandwidth, congestion level
Applicants
  • 东北大学 NORTHEASTERN UNIVERSITY [CN]/[CN]
Inventors
  • 张晓玲 ZHANG, Xiaoling
  • 李梦豪 LI, Menghao
  • 丁进良 DING, Jinliang
  • 柴天佑 CHAI, Tianyou
Agents
  • 沈阳东大知识产权代理有限公司 SHENYANG DONGDA INTELLECTUAL PROPERTY AGENCY CO., LTD
Priority Data
201910733205.309.08.2019CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) ADAPTIVE TRANSMISSION METHOD FOR INDUSTRIAL WIRELESS STREAMING MEDIA EMPLOYING PARTICLE SWARM AND NEURAL NETWORK
(FR) PROCÉDÉ DE TRANSMISSION ADAPTATIVE POUR DES MILIEUX DE TRANSMISSION EN CONTINU SANS FIL INDUSTRIELS UTILISANT UN ESSAIM DE PARTICULES ET UN RÉSEAU NEURONAL
(ZH) 基于粒子群和神经网络的工业无线流媒体自适应传输方法
Abstract
(EN)
Adaptive transmission method for industrial wireless streaming media employing particle swarm and a neural network, applicable to the technical field of videos. The method comprises: step 1, acquiring, from a cloud server database, historical data within a specified range, completing training of a neural network model, and monitoring various status parameters of a wireless channel in real time; step 2, acquiring, by means of a particle swarm algorithm, a wireless network transmission parameter that achieves the optimal quality of experience (QoE) of a video, such that a video of a next time point has a maximum frame rate and minimum fluctuation, and is the smoothest; step 3, using a mapping function of the trained neural network model to predict an optimal system configuration parameter, and completing system configuration; and step 4, acquiring and storing actual data, and applying same to train and correct the neural network again. By using the method, parameter optimization is completed quickly by means of a particle swarm algorithm, and a system configuration parameter is directly acquired by means of direct mapping of a neural network instead of conventional trials, such that a system parameter is configured accurately, and a video is transmitted smoothly.
(FR)
L'invention concerne un procédé de transmission adaptative pour des supports de diffusion en continu sans fil industriels utilisant un essaim de particules et un réseau neuronal, applicables au domaine technique des vidéos. Le procédé consiste à : étape 1, acquérir, à partir d'une base de données de serveur en nuage, des données historiques dans une plage spécifiée, achever l'apprentissage d'un modèle de réseau neuronal, et surveiller divers paramètres d'état d'un canal sans fil en temps réel ; étape 2, acquérir, au moyen d'un algorithme d'essaim de particules, un paramètre de transmission de réseau sans fil qui atteint la qualité d'expérience (QoE) optimale d'une vidéo, de sorte qu'une vidéo d'un point temporel suivant ait un taux de trame maximal et une fluctuation minimale, et soit le plus lisse ; étape 3, utiliser une fonction de mappage du modèle de réseau neuronal entraîné pour prédire un paramètre de configuration de système optimal, et achever la configuration du système ; et étape 4, acquérir et mémoriser des données réelles, et les appliquer pour entraîner et corriger à nouveau le réseau neuronal. Au moyen du procédé, l'optimisation des paramètres est achevée rapidement au moyen d'un algorithme à essaim de particules, et un paramètre de configuration de système est directement acquis au moyen d'un mappage direct d'un réseau neuronal au lieu d'essais classiques, de sorte qu'un paramètre de système soit configuré avec précision, et une vidéo soit transmise sans à-coups.
(ZH)
一种基于粒子群和神经网络的工业无线流媒体自适应传输方法,适用于视频技术领域。该方法包括:步骤一,从云服务器数据库获得指定范围的历史数据,完成神经网络模型的训练,并实时监测无线信道的各种状态参数;步骤二,由粒子群算法获得使视频体验质量(Quality of Experience,QoE)最优的无线网络传输参数,使得下一时刻的视频帧率最大、波动最小、视频最流畅;步骤三,利用已经训练完成的神经网络模型的映射功能预测出最优的系统设置参数,并完成系统的设置;步骤四,获得实际数据并存储,并重新运用于神经网络的训练和矫正。该方法能够通过粒子群算法更快地完成参数寻优,且通过神经网络直接映射的方式取代传统的尝试探索的方式直接获得系统设置参数,有助于系统参数更准确的设置和视频更流畅的传输。
Also published as
Latest bibliographic data on file with the International Bureau