Communication device predicted future interference information
A method performed by a network node for a telecommunications network for handling interference variations for a communication device is provided. The method includes configuring the communication device to measure on a set of resources and to build a machine learning, ML, model to predict a future interference measurement from the set of resources. The method further includes signaling a request to the communication device to provide a prediction of the future interference measurement on the set of resources. The method further includes receiving, from the communication device, at least one prediction of future interference on the set of resources. The method further includes changing a network configuration for the communication device based on the received at least one prediction of future interference.
1 . A method performed by a network node for a telecommunications network for handling interference variations for a communication device, the method comprising:
configuring the communication device to measure on a set of resources and to build a machine learning (ML) model to predict a future interference measurement from the set of resources;
signaling a request to the communication device to provide a prediction of the future interference measurement on the set of resources;
receiving, from the communication device, at least one prediction of future interference on the set of resources; and
changing a network configuration for the communication device based on the received at least one prediction of future interference.
2 . The method of claim 1 , wherein the changing a network configuration for the communication device comprises a scheduling, an inter-frequency handover decision, an intra-frequency handover decision, or at least one link-adaptation setting.
3 . The method of claim 1 , wherein the set of resources comprise a set of resources that are not planned for any traffic in a source cell of the network node.
4 . The method of claim 1 , wherein the at least one prediction of future interference received from the communication device based on a historical interference measurement comprises historical observations of the communication device of interference values from a specific resource, wherein the specific resource indicates a signal type and/or a time-frequency location where the communication device can predict an interference magnitude.
5 . The method of claim 4 , wherein the specific resource comprises one of a reference signal in a serving network node or a set of resources when there is no traffic or reference signal scheduled in the serving network node.
6 . The method of claim 1 , wherein the set of resources take into account history information of a communication device or a communication device related configuration.
7 . The method of claim 6 , wherein the configuration comprises one of the following:
a configuration specific to an area, wherein the area is a region of a serving cell, wherein the serving cell quality is above a certain threshold, or the serving cell quality is below a threshold, or
one or more of a neighboring cell quality is above a threshold, or
a specific neighboring cell quality is above a threshold, or
a specific neighboring cell quality is below a threshold, or
when the UE can hear a specific set of wireless local area network applications, or when the UE can hear a specific set of Bluetooth beacons, or
when the UE is in a geographical region as bounded by a configured coordinates.
8 . The method of claim 1 , further comprising:
signaling a request to the communication device to provide capabilities of a predicted future interference for a specified time-frequency resource; and
receiving, from the communication device, an indication that the communication device is able to use the ML model to learn which signals are from a neighboring network node and from the serving network node, respectively, wherein indication is based on the communication device observing at least one of a reference signal received power (RSRP) measurement, a reference signal received quality (RSRQ) measurement, and a reference signal strength indicator (RSSI) measurement over a time period.
9 . The method of claim 1 , wherein the configuring comprises a configuration of at least one of the following:
a time-frequency resource for use in predicting the at least one prediction of future interference,
indicating to the communication device to build the at least one prediction of future interference using a transmitted reference signal of the communication device,
a resource used for a periodic Channel State Information Interference Measurement (CSI-IM), and
indicating to the communication device to build the ML model based on historical interference of the communication device with a neighboring network node.
10 . The method of claim 1 , further comprising:
configuring the communication device to report a condition related to the at least one prediction of future interference to the network node.
11 . The method of claim 1 , wherein the at least one prediction of future interference is based on at least one of a non-reference signal and a reference signal.
12 . The method of claim 1 , wherein the ML model comprises one of a decision tree, a random forest, a feed forward neural network, an autoregressive model, or a convolutional neural network.