Abstract: Methods (1100) and systems (800) for updating ML models. The method is performed by a client computing device (704(1)). In one aspect, the method comprises obtaining (s1102) a first machine learning (ML) model. The first ML model is configured to receive input data set and to generate first output data set. The method further comprises training (s1104) a second ML model 5 based at least on the input data set and the first output data set, obtaining (s1106), as a result of training the second ML model, a third ML model, and deploying the third ML model.

Abstract: A method for dynamically configuring a network is proposed for training a machine learning model. The network includes a server computing device and a plurality of client computing devices. The method is performed at a computing device communicatively coupled to the network and includes the following: selecting client computing devices to participate in training the model; determining a first value of an evaluation metric of the model based on the selected client computing devices; determining the presence of an adjustment trigger; adjusting the number of client computing devices used to determine the value of the evaluation metric in response to the adjustment trigger; determining a second value of the evaluation metric based on the adjusted number of client computing devices; and setting the number of client computing devices participating in training the model accordingly.

Abstract: A method for enabling forecasting of key performance indicators, KPIs, in a communication network is presented. The method is performed by a network node and comprises collecting (S100) time series data of KPIs in the communication network, extracting (S110) k-principal components of the collected time series data, determining (S120) a principal component score, PCS, from the collected time series data and the extracted k-principal components, and building (S130) a PCS forecast model from the determined PCS and period of time-attributes. Network nodes and computer program products thereof are also presented.

Abstract: A computing device for supporting an Augmented-Reality (AR) software application is provided. The computing device is operative to select a physical location for placing a current virtual object, where the current virtual object appears to be placed when overlaid onto a video sequence capturing a physical scene in the surroundings of a user, based on an expected physical location which the user assumes in response to displaying the physical scene and the overlaid current virtual object to the user, and an attribute which is spatially dependent and which has an impact on a user experience of the AR software application. Taking the spatially-dependent attribute at the expected physical location of the user into consideration in selecting physical locations for placing virtual objects is advantageous in that virtual objects may be deployed at physical locations so as to provide an improved, or at least satisfactory, user experience to the users.

Abstract: A method for enabling forecasting of key performance indicators, KPIs, in a communication network is presented. The method is performed by a network node and comprises collecting (S100) time series data of KPIs in the communication network, extracting (S110) k-principal components of the collected time series data, determining (S120) a principal component score, PCS, from the collected time series data and the extracted k-principal components, and building (S130) a PCS forecast model from the determined PCS and period of time-attributes. Network nodes and computer program products thereof are also presented.

Abstract: A method for analysing performance of a telecommunications network is disclosed. The method comprises assembling values observed for a network performance parameter over a time window and constructing a time series by associating each performance parameter value with a representation of a time at which the value was observed. The method further comprises encoding the time series to generate a compressed representation of the time series, decoding the compressed representation of the time series to reconstruct the time series, calculating a reconstruction error between the time series and the reconstructed time series, and analysing the reconstruction error to determine if the assembled performance parameter values indicate an anomalous behaviour during the time window. Also disclosed are an apparatus and a computer program product configured to conduct methods for analysing performance of a telecommunications network.

Abstract: A method for analysing performance of a telecommunications network is disclosed. The method comprises assembling values observed for a network performance parameter over a time window and constructing a time series by associating each performance parameter value with a representation of a time at which the value was observed. The method further comprises encoding the time series to generate a compressed representation of the time series, decoding the compressed representation of the time series to reconstruct the time series, calculating a reconstruction error between the time series and the reconstructed time series, and analysing the reconstruction error to determine if the assembled performance parameter values indicate an anomalous behaviour during the time window. Also disclosed are an apparatus and a computer program product configured to conduct methods for analysing performance of a telecommunications network.