View source for 18147284. DETERMINATION OF INACTIVE EDRX CONFIGURATIONS FOR USER EQUIPMENT simplified abstract (Telefonaktiebolaget LM Ericsson (publ))

=DETERMINATION OF INACTIVE EDRX CONFIGURATIONS FOR USER EQUIPMENT=


==Organization Name==

[[:Category:Telefonaktiebolaget LM Ericsson (publ)|Telefonaktiebolaget LM Ericsson (publ)]]


[[Category:Telefonaktiebolaget LM Ericsson (publ)]]

==Inventor(s)==

[[:Category:Hamza Khan of Helsinki (FI)|Hamza Khan of Helsinki (FI)]][[Category:Hamza Khan of Helsinki (FI)]]

[[:Category:Mohammad Mozaffari of Fremont CA (US)|Mohammad Mozaffari of Fremont CA (US)]][[Category:Mohammad Mozaffari of Fremont CA (US)]]

==DETERMINATION OF INACTIVE EDRX CONFIGURATIONS FOR USER EQUIPMENT - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18147284 titled 'DETERMINATION OF INACTIVE EDRX CONFIGURATIONS FOR USER EQUIPMENT

==Simplified Explanation==
The patent application describes a method for determining INACTIVE eDRX configurations for User Equipments (UEs) by a core network node using an iterative learning process with access network nodes.

* The method involves transmitting a global parameter vector of a machine learning model to the access network nodes to determine the INACTIVE eDRX configurations of the UEs.
* Local model parameter vectors with locally updated coefficients are received from the access network nodes, and the global parameter vector is updated for the next iteration based on these vectors.
* The iterative learning process continues until a stopping criterion is met.

==Key Features and Innovation==
* Determining INACTIVE eDRX configurations for UEs using machine learning models.
* Iterative learning process with access network nodes to update coefficients for the machine learning model.
* Global parameter vector transmission and reception of local model parameter vectors for updating.

==Potential Applications==
This technology can be applied in telecommunications networks to optimize energy consumption and network efficiency by determining the most suitable eDRX configurations for UEs.

==Problems Solved==
* Efficiently determining and updating INACTIVE eDRX configurations for UEs.
* Enhancing network performance and energy efficiency in telecommunications systems.

==Benefits==
* Improved network efficiency and energy savings.
* Enhanced user experience with optimized eDRX configurations.
* Streamlined management of UEs in the network.

==Commercial Applications==
Optimizing energy consumption in IoT devices, improving battery life in mobile devices, and enhancing network performance in telecommunications infrastructure.

==Questions about the Technology==
===How does the iterative learning process improve the determination of INACTIVE eDRX configurations?===
The iterative learning process allows for the refinement of coefficients in the machine learning model based on local updates from access network nodes, leading to more accurate and efficient configuration determinations.

===What are the potential implications of this technology on network management and optimization?===
This technology can significantly impact network management by automating the process of determining INACTIVE eDRX configurations, leading to improved network efficiency and performance.


==Original Abstract Submitted==

There is provided techniques for determining INACTIVE eDRX configurations for UEs. The method is performed by a core network node. The method comprises performing an iterative learning process with the access network nodes to determine the INACTIVE eDRX configurations. The iterative learning process comprises transmitting a global parameter vector of a machine learning model to the access network nodes for determining the INACTIVE eDRX configurations of the UEs. The global parameter vector defines coefficients for the machine learning model for the current iteration. The iterative learning process comprises receiving local model parameter vectors with locally updated coefficients for the machine learning model from the access network nodes. The iterative learning comprises updating the global parameter vector for the next iteration as a function of all received local model parameter vectors until a stopping criterion is fulfilled.



[[Category:H04W76/28]]
[[Category:G06N3/08]]
[[Category:CPC_H04W76/28]]