Samsung Electronics Co., Ltd.

Seowoo Jang

Minsuk Choi

Xue Liu

Gregory Lewis Dudek

Taeseop Lee

Taejeoung Kim

Juhwan Song

Xi Chen

Ju Wang

Chengming Hu

Kyungrae Kim

Di Wu

Yi Tian Xu

Daehyun Ban

Hang Li

Jikun Kang

Seongwon Han

Woojin Park

Changhan Kim

Intaik Park

Unkyu Park

Hyokyung Woo

Tianyu Li

Haksung Kim

Amal Feriani

Daekyoung Jung

Jonghyun Ho

Jongrok Lim

Minsoo Koo

Jimmy Li

Hongjun Jang

Sangung Yi

The present disclosure provides for methods, apparatuses, and non-transitory computer-readable storage media for load balancing traffic scenarios by a network device. In an embodiment, a method includes training a plurality of learning agents to load balance a respective plurality of traffic scenarios to obtain a plurality of control policies. The method further includes performing at least one clustering iteration. Each clustering iteration includes selecting a pair of control policies and merging the pair of control policies into a clustered control policy that replaces the pair of control policies. The method further includes determining to stop the performing of the at least one clustering iteration when a quantity of control policies remaining in the plurality of control policies meets a predetermined value. The method further includes deploying to each base station of a plurality of base stations a corresponding control policy from the plurality of control policies.

Traffic scenario clustering and load balancing with distilled reinforcement learning policies

A server may obtain teacher artificial intelligence (AI) models from source base stations; obtain target traffic data from a target base station; obtain an integrated teacher prediction based on the target traffic data by integrating teacher prediction results of the teacher AI models based on teacher importance weights; obtain a student AI model that is trained to converge a student loss on the target traffic data; update the teacher importance weights to converge a teacher loss between a student prediction of the student AI model on the target traffic data, and the integrated teacher prediction of the teacher AI models on the target traffic data; update the student AI model based on the updated teacher importance weights being applied to the teacher prediction results of the teacher AI models; and predict a communication traffic load of the target base station using the updated student AI model.

Method of load forecasting via knowledge distillation, and an apparatus for the same

An electronic device is provided. The electronic device includes a communication circuit, a memory configured to store a learning model, and at least one processor, wherein the at least one processor is configured to obtain data related to a network situation of a base station from the communication circuit, calculate a performance indicator value related to network performance according to a performance indicator, based on the data related to the network situation, train the model, based on the performance indicator value calculated according to the performance indicator, determine an off threshold of traffic for turning off a cell, based on the trained model, and transmit the determined off threshold to the base station via the communication circuit.

Electronic device and operation method of electronic device for deciding cell on or off threshold based on traffic

Disclosed is a method, performed by an electronic device, of controlling a plurality of cells for providing radio resources to a plurality of user equipments (UEs), including: obtaining information about a load of each of a plurality of cells, calculating a total load of the plurality of cells based on the obtained information, changing a state of at least one cell from among the plurality of cells from an active state to an inactive state or from an inactive state to an active state based on the calculated total load, and controlling the plurality of cells so that a plurality of UEs are connected to active cells from among the plurality of cells in response to the change in the state of the at least one cell.

Method of controlling plurality of cells for providing radio resources to plurality of user equipments, and electronic device for performing the method

A server for predicting a future traffic load of a base station is provided. The server may obtain a first prediction model based on traffic data collected from the base station for a first period of time, obtain a second prediction model based on traffic data collected from the same base station for a second period time, and also based on knowledge transferred from the first prediction model. Each of the first prediction model and the second prediction model may include an encoder module, a reconstruction module, and a prediction module which are connected to form two paths, an encoder-reconstruction path and an encoder-prediction path, to preserve more information of historic traffic data.

Method of communication traffic prediction via continual learning with knowledge distillation, and an apparatus for the same

A method, performed by an electronic device, of controlling a state control parameter for adjusting a state of a network of a base station, using any one of a plurality of models, includes: obtaining information related to the state of the network from the base station, performing simulation on each of the plurality of models based on the obtained information related to the state of the network, selecting any one model from among the plurality of models based on a result of the performed simulation, and transmitting a value of the state control parameter, calculated using the selected any one model, to the base station to update the state control parameter.

Method of controlling state control parameter for adjusting state of network of base station by using any one of plurality of models and electronic device performing the method

A method is provided. The method includes receiving a first dimension set, extracting a first latent feature set from the first dimension set, training a first base predictor based on the first feature set, generating a second dimension set based on the first dimension set, the second dimension set having fewer dimensions than the first dimension set, extracting a second latent feature set from the second dimension set, training a second base predictor based on the second feature set, and generating a traffic prediction based on the first base predictor and the second base predictor.

Communication load forecasting accuracy with adaptive feature boosting

A method of training an image recognition model includes: generating a virtual dynamic vision sensor (DVS) image using a virtual simulator; generating label information including information about a correct answer to a result of recognition of the DVS image by the image recognition model, with respect to the DVS image; and training the image recognition model by modifying the image recognition model so that a difference between the result of recognition of the DVS image by the image recognition model and the label information is reduced.

Electronic device training image recognition model and operation method for same

Provided is a method, performed by an electronic device, of scheduling a plurality of packets to allocate radio resources to a plurality of packets related to tasks of a plurality of user equipments (UEs) and stacked in a queue, the method including: setting priorities for a plurality of packets stacked in the queue at a first point in time based on a preset scheduling parameter, allocating radio resources to at least some of the plurality of packets for which the priorities are set based on the set priorities, updating the scheduling parameter using at least one artificial intelligence (AI) learning model, and setting the priorities for the plurality of packets stacked in the queue at a second point in time later than the first point in time, based on the updated scheduling parameter.

Method of scheduling plurality of packets related to tasks of plurality of user equipments using artificial intelligence and electronic device performing the method

An electronic apparatus is provided. The electronic apparatus includes a communicator comprising communication circuitry, a memory storing information on an artificial intelligence model, and a processor configured to: obtain a map generated based on sensing data obtained by an external electronic apparatus, simulate driving of the external electronic apparatus on the obtained map based on a plurality of parameter values and obtain driving result data for the plurality of parameter values, train the artificial intelligence model based on the plurality of parameter values and the obtained driving result data and obtain a plurality of parameter values related to driving of the external electronic apparatus, and control the communicator to transmit the plurality of obtained parameter values to the external electronic apparatus.

Electronic apparatus and controlling method thereof

An electronic device configured to adjust a state of an access network including at least one cell may include: at least one processor, and a memory connected to the at least one processor, wherein the at least one processor is configured to control the electronic device to: obtain state history information of the access network at a first time point, determine, based on the obtained state history information, a first time period required to adjust a state of the access network, determine, based on the first time point and the first time period, a second time point, the second time point being a reference time point at which the state of the access network is to be adjusted, estimate a state of the access network at the second time point based on the obtained state history information, determine values of state control parameters for adjusting the state of the access network, based on the estimated state of the access network at the second time point, and transmit the determined values of the state control parameters to the access network, wherein the values of the state control parameters transmitted to the access network are applied, at the second time point, to the state control parameters of the access network, to adjust the state of the access network.

Method of implementing self-organizing network for plurality of access network devices and electronic device for performing the same

Disclosed are an autonomous driving apparatus for performing autonomous driving of a vehicle and a controlling method thereof. An autonomous driving apparatus according to an example aspect of the present disclosure includes a sensor configured to acquire sensing information to determine a driving state of the vehicle; a storage configured to store a plurality of autonomous driving models; and at least one processor configured to perform autonomous driving of the vehicle using one of the plurality of autonomous driving models stored in the storage based on sensing information sensed by the sensor. Accordingly, the autonomous driving apparatus is capable of performing autonomous driving of a vehicle by rapidly changing a driving mode to an autonomous driving mode suitable for an event occurring during autonomous driving of the vehicle.

Autonomous driving apparatus and method for autonomous driving of a vehicle

A method for controlling an autonomous driving apparatus of a vehicle includes receiving a destination for setting a route, obtaining driving history of a user and traffic information, determining a driving route to the destination based on information on the destination, information on the driving history, and the traffic information provided to a model trained through an artificial intelligence algorithm as input data, and performing autonomous driving along the determined driving route.

Growing community of inventors

Suwon-si, South Korea

Seowoo Jang