Abstract: A requested communication quality estimation device estimating a requested communication quality for a macroflow, which is a set of microflows, includes a first estimation unit configured to estimate a requested communication quality for each of a plurality of microflows constituting a macroflow, and a second estimation unit configured to estimate a requested communication quality for the macroflow based on the requested communication quality for each of the plurality of microflows which is obtained by the first estimation unit.

Abstract: A processing request management apparatus includes: an estimation unit which estimates a time required for processing for each of a plurality of processing requests for which desired processing completion times are designated; and a determination unit which determines an execution order of processing for the plurality of processing requests such that a sum of delays of estimated processing completion times based on the required time with respect to the desired processing completion times for the respective processing requests in the plurality of processing requests is minimized, to increase a likelihood of restrictions with respect to processing requests being satisfied.

Abstract: A throughput estimation apparatus includes a memory and a processor configured to execute estimating a QoE (quality of experience) for each of a plurality of selection candidates for a parameter set related to a quality of a video to be distributed via a network; and estimating a throughput required for satisfying a target QoE by using, as inputs, the estimated QoE for each of the selection candidates, the parameter set for each of the selection candidates, and the target QoE.

Abstract: A macro-flow generation apparatus includes: a macro-flow generation unit that divides, for individual flows of each of a plurality of terminals which use a service provided via a network, a set of a plurality of individual flows into macro-flows each of which includes one or more of the individual flows based on a similarity of requested qualities of the plurality of the individual flows, the requested qualities being collected from each of the terminals; and a macro-flow requested-quality calculation unit that calculates, for each of the macro-flows, a requested quality of the macro-flow based on requested qualities of one or more of the individual flows belonging to the macro-flow. Thereby, it is possible to generate a macro-flow capable of reducing a possibility that path assignment causing a deterioration in communication quality is performed.

Abstract: An IP address assigning device can reduce registration information required for controlling traffic by calculating, for traffic between a plurality of user terminals and a plurality of services in a past period, a statistic of the traffic for each of a plurality of combinations of a user terminal, a service, and a time period, and extracting a plurality of patterns relating to the traffic based on a plurality of the statistics; classifying the plurality of user terminals into a plurality of groups based on the patterns; and assigning IP addresses belonging to a subnetwork to corresponding ones of the plurality of user terminals for each of the plurality of groups.

Abstract: A control device includes a first calculation unit configured to calculate for each control target a control solution for controlling said each control target; a second calculation unit configured to calculate an evaluation of the control solution for said each control target; a solution change unit configured to change the control solution based on the evaluation calculated by the second calculation unit; and a control unit configured to control said each control target based on the control solution changed by the solution change unit.

Abstract: A prediction apparatus includes, a first calculation unit configured to calculate, for traffic in a past time period between a plurality of users and a plurality of services, statistics of the traffic in units of combinations of the users, the services, and time zones, an extraction unit configured to extract, based on the statistics, a plurality of patterns from the traffic, a classification unit configured to classify, by pattern, at least one of each user or each service into groups, a second calculation unit configured to calculate, based on the classification result from the classification unit and the statistics, per-time-zone statistics for each group, and a third calculation unit configured to apply a prediction technique to the per-time-zone statistics for each group, to calculate, for each group, a prediction value of the statistics for a time period later than the past time period, resulting improved accuracy of traffic prediction.

Abstract: Provided is a control device that includes one or more processors configured to: select an agent gk that executes an action that represents allocation of a virtual network onto a physical network at a time point t from a plurality of agents; observe a state st at the time point t with an input of network configuration information of the physical network, network observation information, and user demand information; select and execute, on basis of an action value function Q representing an expected value of a sum total of a reward received in future, an action atk from possible actions for the agent gk; calculate a reward rt using of the action atk, the state st, and a state st+1 at a time point t+1; and update the action value function Q with use of the action ajk, the state sj, and the state sj+1, where 1?j?t is satisfied.

Abstract: A control apparatus for allocating, by use of reinforcement learning, a virtual network to a physical network having links and servers comprises: a pre-learning unit that learns a first action value function corresponding to an action performing a virtual network allocation so as to improve the use efficiency of a physical resource in the physical network and further learns a second action value function corresponding to an action performing a virtual network allocation so as to suppress violations of constraints in the physical network; and an allocation unit that uses the first action value function and the second action value function to allocate the virtual network to the physical network.

Abstract: Provided is a control device that dynamically allocates a virtual network that provides a network service on a physical network by multi-agent deep reinforcement learning, the control device including: selection means for selecting an agent gk that executes an action that represents allocation of the virtual network onto the physical network at a time point t; observation means for observing a state st with an input of network configuration information, network observation information indicating a physical resource amount, and user demand information indicating an amount demanded for a physical resource; allocation means for selecting and executing, on basis of an action value function Q, an action atk from possible actions for the agent gk; reward calculation means for calculating a reward rt at the time point t with use of the action atk, the state st, and a state st+1 at a time point t+1; and learning means for updating the action value function Q with use of the action ajk, the state sj, and the state sj+

Abstract: A control apparatus that dynamically allocates a virtual network for providing a network service to a physical network through deep reinforcement learning, includes: observation means for receiving input of network configuration information regarding the physical network, network observation information indicating an amount of physical resource of the physical network, and user demand information indicating an amount of demand for the physical resource generated due to a communication action of a user terminal for the network service, and observing a state st at a time t; allocation means for selecting an action at to change allocation of the virtual network to the physical network in accordance with a policy ? in the state st; reward calculation means for calculating a reward rt+1 based on a state st+1 to which the state st has transitioned due to the action at; and learning means for learning the policy ? using the reward rt+1.

Abstract: A requested communication quality estimation device estimating a requested communication quality for a macroflow, which is a set of microflows, includes a first estimation unit configured to estimate a requested communication quality for each of a plurality of microflows constituting a macroflow, and a second estimation unit configured to estimate a requested communication quality for the macroflow based on the requested communication quality for each of the plurality of microflows which is obtained by the first estimation unit.

Abstract: A scheduling control device performs scheduling that includes generating a directed graph having a source node, n layers of nodes, each layer of nodes of the n layers of nodes consisting of k nodes respectively corresponding to k job processing devices, and a destination node, a cost required for processing a job being allocated to each node of the n layers of nodes as a weight, a cost required for migrating the job from one of job processing devices to another one of the job processing devices being allocated as a weight on an edge; and calculating a shortest path from the source node to the destination node in the directed graph as a result of scheduling.

Abstract: An IP address assigning device can reduce registration information required for controlling traffic by including an extraction unit configured to calculate, for traffic between a plurality of user terminals and a plurality of services in a past period, a statistic of the traffic for each of a plurality of combinations of a user terminal, a service, and a time period, and extract a plurality of patterns relating to the traffic based on a plurality of the statistics; a classification unit configured to classify the plurality of user terminals into a plurality of groups based on the patterns; and an assignment unit configured to assign IP addresses belonging to a subnetwork to corresponding ones of the plurality of user terminals for each of the plurality of groups.

Abstract: A control apparatus configured to allocate a virtual network for providing a network service on a physical network includes: acquisition means for acquiring information indicating an outside temperature of each node included in the physical network, physical resource information of the physical network, information indicating a predicted traffic amount of the physical network, and an allocation request for the virtual network; and calculation means for calculating an optimal allocation of the virtual network using a target function defined using a unit cost defined for each region and for each time slot and a power consumption model taking into consideration the outside temperature and a load rate calculated based on the predicted traffic amount, and a restrictive condition obtained based on the physical resource information and the allocation request.

Abstract: A prediction apparatus includes, a first calculation unit configured to calculate, for traffic in a past time period between a plurality of users and a plurality of services, statistics of the traffic in units of combinations of the users, the services, and time zones, an extraction unit configured to extract, based on the statistics, a plurality of patterns from the traffic, a classification unit configured to classify, by pattern, at least one of each user or each service into groups, a second calculation unit configured to calculate, based on the classification result from the classification unit and the statistics, per-time-zone statistics for each group, and a third calculation unit configured to apply a prediction technique to the per-time-zone statistics for each group, to calculate, for each group, a prediction value of the statistics for a time period later than the past time period, resulting improved accuracy of traffic prediction.

Abstract: A control apparatus that dynamically allocates a virtual network for providing a network service to a physical network through deep reinforcement learning, includes: observation means for receiving input of network configuration information regarding the physical network, network observation information indicating an amount of physical resource of the physical network, and user demand information indicating an amount of demand for the physical resource generated due to a communication action of a user terminal for the network service, and observing a state st at a time t; allocation means for selecting an action at to change allocation of the virtual network to the physical network in accordance with a policy n in the state st; reward calculation means for calculating a reward rt+1 based on a state st+1 to which the state st has transitioned due to the action at; and learning means for learning the policy n using the reward rt+1.

Abstract: An access source classification apparatus has: a first calculation unit that calculates a statistic related to access to each service by each access source based on a set of access logs indicating access to any service of a plurality of services by any access source of a plurality of access sources; an extraction unit that, for each of the services, calculates an index value indicating distribution of access status to the service for each of the access sources based on the access logs related to the service, and extracts some services based on the index value; a second calculation unit that calculates relevance between each access source and each service extracted by the extraction unit by applying a clustering approach to the statistic; and a classification unit that classifies an access source to any service extracted by the extraction unit into any of groups each including one or more access sources based on the relevance, thereby assisting improvement of efficiency in identifying the terminal type of an a

Abstract: A control apparatus configured to allocate a virtual network for providing a network service on a physical network includes: acquisition means for acquiring information indicating an outside temperature of each node included in the physical network, physical resource information of the physical network, information indicating a predicted traffic amount of the physical network, and an allocation request for the virtual network; and calculation means for calculating an optimal allocation of the virtual network using a target function defined using a unit cost defined for each region and for each time slot and a power consumption model taking into consideration the outside temperature and a load rate calculated based on the predicted traffic amount, and a restrictive condition obtained based on the physical resource information and the allocation request.

Abstract: A processing request management apparatus includes: an estimation unit which estimates a time required for processing for each of a plurality of processing requests for which desired processing completion times are designated; and a determination unit which determines an execution order of processing for the plurality of processing requests such that a sum of delays of estimated processing completion times based on the required time with respect to the desired processing completion times for the respective processing requests in the plurality of processing requests is minimized, to increase a likelihood of restrictions with respect to processing requests being satisfied.