Wireless Superposition Signal Decoding for Network Capacity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wireless communication systems face inefficiencies and increased overhead when retrieving user context data from multiple devices, as each device requires reserved access time and frequency, leading to reduced network capacity and resource utilization.
Innovation Solution
An apparatus and method utilizing a machine learning system to decode and determine parameter values from a wireless superposition signal containing multiple signals transmitted simultaneously at the same frequency, allowing for simultaneous transmission and reception of context information from multiple devices, thereby reducing the need for individual reserved access times and frequencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional polling or pushing processes are used for each user device to transmit context data, then each device can reliably transmit its data, but the network overhead increases and network capacity is reduced
Solution Approach 1:
Multiple user devices transmit their context data simultaneously on the same frequency without reserving individual time slots. The server uses a machine learning model to separate and decode the superimposed signals from multiple devices, merging the transmission resources of multiple devices into a single shared frequency channel.
Solution Approach 2:
The system changes the transmission parameter from orthogonal multiplexing (different time slots or frequencies for each device) to non-orthogonal superposition (same frequency and time for all devices), relying on machine learning-based signal separation to resolve the mixing.
2Reliability
If each user device reserves individual transmission time slots and frequencies, then data transmission is organized and reliable, but the regulating overhead increases and resource availability for other communications decreases
Solution Approach 1:
A single frequency resource is made universal and can be simultaneously used by multiple user devices for context data transmission. The machine learning model at the server side performs the function of separating and decoding signals from multiple devices that share the same frequency, making the frequency resource multi-functional.
3Productivity
If multiple devices transmit simultaneously at the same frequency, then network capacity and resource utilization improve, but signal collision and interference occur that inhibits decoding
Solution Approach 1:
A machine learning model acts as an intermediary between the superimposed transmitted signals and the decoded parameter values. The model learns to separate the mixed signals from multiple devices and extract the individual context data, mediating the decoding process that would otherwise be impossible due to signal collision.
Data Source
Figure 1~4
Figure 5
Figure 6
AI summary
Certain examples of the present invention relate to an apparatus comprising means configured to: receive a wireless superposition signal, the wireless superposition signal comprising a plurality of wireless signals, received substantially simultaneously, that are individually transmitted from a respective plurality of devices substantially simultaneously and at the same frequency, wherein each signal represents a set of parameter values of a set of parameters; determine one or more sets of parameter values from the received wireless superposition signal by applying the wireless superposition signal to a model, wherein the model is configured to: receive, as an input, a wireless superposition signal comprising an aggregation of a plurality of signals each representative of a set of parameter values of a set of parameters, and output one or more sets of parameter values.