US Patent Application 18248237. NETWORK DESIGN AND OPTIMIZATION USING DEEP LEARNING simplified abstract

From WikiPatents
Jump to navigation Jump to search

NETWORK DESIGN AND OPTIMIZATION USING DEEP LEARNING

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

Mohammad Mozaffari of Fremont CA (US)

Xingqin Lin of San Jose CA (US)

Talha Khan of Santa Clara CA (US)

Mehrnaz Afshang of Fremont CA (US)

Yun Chen of Austin TX (US)

NETWORK DESIGN AND OPTIMIZATION USING DEEP LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18248237 titled 'NETWORK DESIGN AND OPTIMIZATION USING DEEP LEARNING

Simplified Explanation

- The patent application describes a method and apparatus for designing and optimizing a network. - The method involves using a first deep neural network to establish a relationship between the design parameters of the network and the network performance metrics. - A second deep neural network is then used to identify a subset of potential network deployment configurations that optimize the performance metrics. - From this subset, the optimal network deployment configuration is selected based on maximizing the network's performance as defined by the performance metrics.


Original Abstract Submitted

A method and apparatus for design and optimization of a network are described. A first deep neural network is used to obtain a function that represents a relationship between design parameters of the network and network performance metrics of the network. A second deep neural network is used to obtain a subset of one or more candidate network deployment configurations that optimize the performance metrics for the network. An optimal candidate network deployment configuration for the network is selected from the subset of candidate network deployment configurations wherein the optimal candidate network deployment configuration maximizes performance of the network as defined based on the performance metrics.