公开(公告)号：US20240196272A1

公开(公告)日：2024-06-13

申请号：US18554522

申请日：2022-04-27

申请人： TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

发明人： Philipp Bruhn ,  Angelo Centonza ,  Luca Lunardi ,  Pablo Soldati ,  Reem Karaki ,  Henrik Rydén ,  Ali Parichehrehteroujeni

IPC分类号： H04W28/086 ,  H04L47/70 ,  H04W28/02

CPC分类号： H04W28/0861 ,  H04L47/823 ,  H04W28/0236 ,  H04W28/0284

摘要： Embodiments include methods for a first network node of a wireless network. Such methods include receiving, from a second network node of the wireless network, a first message comprising traffic status information for the second network node and performing one or more of the following operations based on the traffic status information: predicting a change in load and/or interference in a coverage area of the first network node; adjusting configurations of one or more cells and/or one or more beams served by the first network node; requesting the second network node to adjust configurations of one or more cells and/or one or more beams served by the second network node; mobility load balancing with respect to one or more user equipment (UEs) served by the first network node; and configuring one or more UEs served by the first network node to use communication settings that are more robust to interference.

公开(公告)号：US20240211768A1

公开(公告)日：2024-06-27

申请号：US18288415

申请日：2021-04-28

申请人： Telefonaktiebolaget LM Ericsson (publ)

发明人： Henrik Rydén ,  Ali Parichehrehteroujeni ,  Luca Lunardi ,  Pradeepa Ramachandra ,  Angelo Centonza ,  Paul Schliwa-Bertling ,  Philipp Bruhn

IPC分类号： G06N3/092

CPC分类号： G06N3/092

摘要： Systems and methods are disclosed herein that relate to influencing training of a Machine Learning (ML) model based on a training policy provided by an actor node are disclosed herein. In one embodiment, a method performed by a first node for training a ML model comprises receiving a training policy for a ML model from a second node, the training policy comprising information that indicates two or more accuracy or importance metrics for two or more ranges of values for a variable to be predicted by the ML model. The method further comprises training the ML model based on a training dataset and the training policy. In one embodiment, the first node is either a training and inferring node or a training node that operates to train the ML model, and the second node is an actor node to which predictions made using the ML model are to be provided.