Abstract: In order to enable stabilizing control of communication in a communication network, a system according to an aspect of the present disclosure includes: an obtaining means for obtaining work-related information related to human work in network operation; and a training means for training a machine learning based controller for controlling communication in a communication network, based on the work-related information.

Abstract: To perform flexible communication control according to variation in traffic so as to satisfy a plurality of QoS (Quality of Service) indexes. A communication apparatus (1) according to the present invention includes: a distribution unit (12) configured to distribute, based on a distribution rule for satisfying a plurality of different QoS indexes set in a plurality of queues (111 to 11n), respectively, a received packet to any one of the plurality of queues; and an update unit (13) configured to update the distribution rule based on performance information of each of the plurality of queues, the performance information being calculated for the QoS index set in each of the queues.

Abstract: An object of the present disclosure is to provide a method capable of estimating the radio quality more accurately. The method includes acquiring first weather information and first geographic information at a first observation point, second weather information and second geographic information at a second observation point, and radio quality information at a radio base station; learning a model for estimating radio quality based on the first weather information and the first geographic information, the second weather information and the second geographic information, and the radio quality information; and estimating the radio quality using the model and at least one of third weather information at the first observation point or fourth weather information at the second observation point.

Abstract: A video quality estimation apparatus (100) according to the present disclosure includes a first collection unit (101) configured to collect network quality information about a network pertaining to distribution of a video, a second collection unit (102) configured to collect video quality information about the video, and an estimation unit (103) configured to estimate a first bit rate corresponding to a resolution of the video based on the network quality information and the video quality information.

Abstract: A remote monitoring system (100) according to the present disclosure includes: an observation unit (101) configured to observe traffic in a network that corresponds to a movement section where a mobile object moves, the mobile object serving as a target to be monitored; and a specification unit (102) configured to divide the movement section on the basis of the observed traffic, and specify a delay jitter distribution in each divided section.

Abstract: A remote control system (100) according to the present disclosure includes: a delay jitter specification unit (101) configured to specify a delay jitter distribution in a network that performs communication with a mobile object serving as a target to be monitored; a degree-of-risk specification unit (102) configured to specify a degree of risk of the mobile object on the basis of the specified delay jitter distribution, and a state of the mobile object; and a control unit (103) configured to control the mobile object on the basis of the specified degree of risk.

Abstract: An estimating apparatus (1) according to the present invention includes a plurality of feature quantity calculating units (111 to 11n) configured to implement processing of calculating, from a communication traffic, a differing feature quantity group for each of a plurality of types of control attributes relating to communication control, the plurality of feature quantity calculating units being each associated with each of the plurality of types of control attributes, a calculating unit (12) configured to calculate, with regard to each of two or more of the plurality of types of control attributes, each of the feature quantity groups from the communication traffic by use of the feature quantity calculating unit being associated with each of the control attributes, and an estimating unit (13) configured to estimate an attribute value of each of the two or more control attributes from each of the calculated feature quantity groups.

Abstract: A priority control apparatus includes: load information acquisition part which acquires communication load information per priority at relay apparatus that controls allocation of communication resources relative to individual communication depending on a priority that is set for the individual communication between two or more communication apparatuses; communication quality acquisition part which acquires communication quality as to control target communication; and priority control part which calculates a first priority, with which communication quality as to the control target communication can satisfy a predetermined condition, by using a mathematical model that indicates a relationship between a piece of communication load information before a priority as to the control target communication is set as the first priority and a communication quality when the priority as to the control target communication concerned is set as the first priority, and which sets the calculated first priority as the priority of

Abstract: In order to able to mislead estimation regarding a transmission source through analysis of a communication traffic, a method according to an aspect of the present disclosure includes: dividing an original communication flow from a source apparatus into a plurality of communication flows matching a selected traffic characteristic; and transmitting a packet belonging to each of the plurality of communication flows to a reconstructing apparatus reconstructing the plurality of communication flows into the original communication flow.

Abstract: A throughput division means (11) divides a throughput of a communication between a video delivery server configured to deliver, in a plurality of delivery modes, video data to a user terminal device used by a user and the user terminal device in a delivery period of the video data, according to a period of each delivery mode. A playback bit rate estimation means (12) estimates a playback bit rate of the video data, based on a throughput divided according to a period of the delivery mode. Thus, estimation precision of a video playback bit rate can be improved even when a video delivery server delivers video data in a plurality of delivery modes.

Abstract: A traffic analysis apparatus includes: a first means that estimates a state sequence from time-series data of communication traffic based on a hidden Markov model, and groups, into one group, a plurality of patterns with resembling state transitions in the state sequence to perform extraction of a state sequence, with taking the plurality of patterns grouped into one group as one state; and a second means that determines an application state corresponding to the time-series data based on the state sequence extracted by the first means and predetermined application characteristics.

Abstract: In order to provide a control apparatus achieving an efficient control of network using a machine learning, a control apparatus includes a learning unit and a control unit. The learning unit learns an action for controlling the network. The control unit controls the network by setting a control parameter to an apparatus included in the network based on an action obtained from a learning model generated by the learning unit. The control unit decides the control parameter based on an influence of the action obtained from the learning model on a state of the network.

Abstract: In order to provide an information processing apparatus that easily finds a network configuration corresponding to characteristics of a terminal to be connected, the information processing apparatus includes a model generation section and a specifying section, the model generation section being configured to generate a traffic pattern generation model, based on learning of a traffic pattern of a terminal, and the specifying section being configured to specify traffic for an output of the traffic pattern generation model, based on virtual traffic in the traffic pattern generation model. The information processing apparatus may further include a packet generation section configured to generate a packet, based on the specified traffic.

Abstract: In order to enable communication control to promptly comply with a communication environment, a system according to an aspect of the present disclosure includes: a first adjusting means for adjusting a parameter for controlling communication in a communication network by using a parameter determining method; and a second adjusting means for adjusting the parameter by using reinforcement learning, after adjusting the parameter using the parameter determining method.

Abstract: There is provided a control apparatus including a memory storing instructions, and one or more processors configured to execute the instructions to function as a plurality of learners each configured to learn an action for controlling a network, the one or more processors being further configured to set learning information of a second learner that is not mature among the plurality of learners, based on learning information of a first learner that is mature among the plurality of learners.

Abstract: In order to provide a control apparatus achieving an efficient control of network using a machine learning, a control apparatus includes a learning unit and a storage unit. The learning unit learns an action for controlling the network. The storage unit stores learning information generated by the learning unit. The learning unit takes an action on the network. The learning unit decides a reward for the action taken on the network based on stationarity of the network after the action is taken to learn the action for controlling the network. The learning unit may give a positive reward to the action taken on the network if the network after the action is taken is in a stationary state, and give a negative reward to the action taken on the network if the network after the action is taken is in a non-stationary state.

Abstract: In order to more easily perform communication control suitable for a communication environment in a communication network, a system according to an aspect of the present disclosure includes: an obtaining means for obtaining state information related to a state of a communication network; and a selecting means for selecting one of a plurality of machine learning based controllers for controlling communication in the communication network, based on the state information.

Abstract: In order to enable stabilizing control of communication in a communication network, a system according to an aspect of the present disclosure includes: an obtaining means for obtaining work-related information related to human work in network operation; and a training means for training a machine learning based controller for controlling communication in a communication network, based on the work-related information.

Abstract: To realize real-time estimation when estimating the type and state of an application from time-series data of communication traffic. A communication traffic analyzing apparatus of the present invention has a state transition model generating unit configured to generate a probabilistic state transition model from time-series data of communication traffic, at each predetermined timing, a state transition model update unit configured to update a state transition model when a difference between the state transition models at two timings generated by the state transition model generating unit is greater than or equal to a predetermined difference and a communication state of network satisfies a predetermined condition, and an application type and state estimating unit configured to estimate a type and a state of an application using the updated state transition model.

Abstract: In order to provide a communication control method that enables resolution of a distributed moving image to be changed, a communication apparatus includes a first estimation section, and a calculation section. The first estimation section estimates a first resolution of a distributed moving image, based on traffic of the distributed moving image. The calculation section calculates a first bit rate for distributing the distributed moving image at a second resolution, based on the first resolution. The communication apparatus may further include a control section that performs traffic control of the distributed moving image, based on the first bit rate. The first estimation section may estimate the first resolution by using statistical information on resolutions of a plurality of distributed moving images.