A method for detecting coverage problems is provided. The method includes receiving, at data processing hardware, from at least one user equipment (UE), observations. Each observation includes a signal measurement of a signal emitted from a base station and a corresponding location of the signal measurement. The method also includes generating, by the data processing hardware, a coverage map for the base station based on the received observations, the coverage map indicating a signal characteristic of the emitted signal about the base station. The method further includes determining, by the data processing hardware, an estimated characteristic of the base station by feeding the coverage map into a neural network configured to output the estimated characteristic of the base station.

This document discloses a solution for estimating network traffic capacity demand in an area of interest. According to an aspect, a computer-implemented method comprises: forming, by using one or more social media applications, a social media layer storing records of a plurality of places in the area of interest; forming, by using at least one source storing real geolocations of the places, a geolocation layer mapping the places to geolocations; classifying the places into a plurality of classes and assigning to each place a weight indicative of a traffic capacity demand dependent on a class of said place; building a capacity layer for the area of interest on the basis of the real geolocations of the places provided by the geolocation layer and the traffic capacity demand per place indicated by the weights, the capacity layer indicating spatial distribution of network traffic capacity demand in a plurality of sub-areas of the area of interest, the plurality of sub-areas comprising sub-areas having at least one of the places and sub-areas between the places

This document discloses a solution for estimating network traffic capacity demand in an area of interest. According to an aspect, a computer-implemented method comprises: forming, by using one or more social media applications, a social media layer storing records of a plurality of places in the area of interest; forming, by using at least one source storing real geolocations of the places, a geolocation layer mapping the places to geolocations; classifying the places into a plurality of classes and assigning to each place a weight indicative of a traffic capacity demand dependent on a class of said place; building a capacity layer for the area of interest on the basis of the real geolocations of the places provided by the geolocation layer and the traffic capacity demand per place indicated by the weights, the capacity layer indicating spatial distribution of network traffic capacity demand in a plurality of sub-areas of the area of interest, the plurality of sub-areas comprising sub-areas having at least one of the places and sub-areas between the places

Provided is a coverage indicator prediction method. The method includes: obtaining a wireless cell feature of a wireless cell to be predicted, a geographical environment feature of the wireless cell to be predicted, a grid geographical environment feature, and a feature of a wireless propagation path from the wireless cell to be predicted to a corresponding grid, where grids are obtained by dividing a designated region; and predicting, according to the wireless cell feature of the wireless cell to be predicted, the geographical environment feature of the wireless cell to be predicted, the grid geographical environment feature, and the feature of the wireless propagation path from the wireless cell to be predicted to the corresponding grid, a coverage indicator value of the grids using a trained coverage indicator prediction model. Coverage indicator prediction apparatus, model training method and apparatus, electronic device, and computer-readable storage medium are also provided.

A method for dynamically assigning communication resources between two or more radio access technologies (RAT) in a wireless access network. The method includes obtaining a network observation o.sub.t indicating a current state of the wireless access network, predicting a sequence of future states of the wireless access network by iteratively simulating hypothetical communication resource assignments a.sup.1, a.sup.2, a.sup.3 over a time window w starting from the current state, evaluating a reward function for each hypothetical communication resource assignment a.sup.1, a.sup.2, a.sup.3 over the time window w, and dynamically assigning the communication resources based on the simulated hypothetical communication resource assignment a.sup.1 associated with maximized reward function over the time window w when the wireless access network is in the current state.

A method for dynamically assigning communication resources between two or more radio access technologies (RAT) in a wireless access network. The method includes obtaining a network observation o.sub.t indicating a current state of the wireless access network, predicting a sequence of future states of the wireless access network by iteratively simulating hypothetical communication resource assignments a.sup.1, a.sup.2, a.sup.3 over a time window w starting from the current state, evaluating a reward function for each hypothetical communication resource assignment a.sup.1, a.sup.2, a.sup.3 over the time window w, and dynamically assigning the communication resources based on the simulated hypothetical communication resource assignment a.sup.1 associated with maximized reward function over the time window w when the wireless access network is in the current state.

A small cell for automatic configuration of an operational parameter includes at least one processor configured to determine a provisioned list of operational parameters. The at least one processor is also configured to sort the provisioned list into a sorted list. The at least one processor is also configured to select the operational parameter from the sorted list based on a BC ID for the small cell, a sector ID for a sector implemented by the small cell, or some combination.

A small cell for automatic configuration of an operational parameter includes at least one processor configured to determine a provisioned list of operational parameters. The at least one processor is also configured to sort the provisioned list into a sorted list. The at least one processor is also configured to select the operational parameter from the sorted list based on a BC ID for the small cell, a sector ID for a sector implemented by the small cell, or some combination.

Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.

Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.