Abstract: A recording medium stores a program for causing a computer to execute a process including: specifying, based on simulation data, related to an operation of a power distribution facility including power distribution lines and one or more transformers coupled to a phase corresponding to two of the power distribution lines, a correlation relationship between a phase current flowing through the transformer and a line current flowing through power distribution line; generating a scatter diagram indicating a degree of correlation between the phase current and each line current; calculating a probability density at each position in the scatter diagram; and determining, based on a position in a case where actual data of the phase current and the line current in the operation of the power distribution facility is plotted in the scatter diagram and a calculation result of the probability density, a coupling phase of the transformer in the actual data.

Abstract: A non-transitory computer-readable medium storing a program that causes a computer to execute a process including, calculating, for each of a plurality of groups each of which is a combination of two power distribution lines selected from a plurality of power distribution lines, an index value that indicates a correlation between time-series data of a sum of line currents that flow through the two power distribution lines included in a group and time-series data of consumed power consumed by at least one consuming subject coupled to a transformer coupled to any one of phases that corresponds to combinations of two of the plurality of power distribution lines or current that corresponds to the power; and determining that a phase that corresponds to the group that corresponds to the index value indicating a highest correlation among the plurality of groups is a connection phase to which the transformer is coupled.

Abstract: A memory stores graph information representing a graph that includes nodes and inter-node edges. The nodes include a first plurality of nodes each associated with node information and a first node. Each of the inter-node edges has a weight. A processor extracts, in accordance with the node information, two or more nodes and transforms the two or more nodes into an aggregate node. The processor generates an aggregate inter-node edge between the aggregate node and the first node. The aggregate inter-node edge is associated with a weight based on two or more weights associated with two or more inter-node edges between the two or more nodes and the first node. The processor estimates first node information to be associated with the first node based on transformed graph information representing a transformed graph including the aggregate node and the aggregate inter-node edge.

Abstract: A data generation method by a computer is disclosed. First waveform data including marking information at a first position on a waveform, and acquiring second waveform data are acquired. A transformation function is specified that transforms the first waveform data to reduce the difference between a first value of a time axis for a first characteristic point in the first waveform data and a second value of the time axis for a second characteristic point, in the second waveform data, corresponding to the first characteristic point. Third waveform data are generated, in which the marking information is applied at a second position corresponding to the first position in the first waveform data, the second position being determined by using the transformation function.

Abstract: A recording medium stores a program for causing a computer to execute a process including: specifying, based on simulation data, related to an operation of a power distribution facility including power distribution lines and one or more transformers coupled to a phase corresponding to two of the power distribution lines, a correlation relationship between a phase current flowing through the transformer and a line current flowing through power distribution line; generating a scatter diagram indicating a degree of correlation between the phase current and each line current; calculating a probability density at each position in the scatter diagram; and determining, based on a position in a case where actual data of the phase current and the line current in the operation of the power distribution facility is plotted in the scatter diagram and a calculation result of the probability density, a coupling phase of the transformer in the actual data.

Abstract: A first time-series data set indicating first measured values obtained by a first device and a second time-series data set indicating second measured values obtained by a second device are obtained. First alignment is performed to convert the positions in the time domain of the first measured values belonging to a second period, based on the first measured values belonging to a first period. Second alignment is performed to convert the positions in the time domain of the second measured values belonging to the second period, based on a relationship between positions before and after the conversion. Correlation analysis is performed between third and fourth time-series data sets respectively obtained by the first and second alignment. The existence or absence of an inclusion relationship in which the second measured values contain a component of the first measured values is determined based on the correlation analysis result.

Abstract: A non-transitory computer-readable medium storing a program that causes a computer to execute a process including, calculating, for each of a plurality of groups each of which is a combination of two power distribution lines selected from a plurality of power distribution lines, an index value that indicates a correlation between time-series data of a sum of line currents that flow through the two power distribution lines included in a group and time-series data of consumed power consumed by at least one consuming subject coupled to a transformer coupled to any one of phases that corresponds to combinations of two of the plurality of power distribution lines or current that corresponds to the power; and determining that a phase that corresponds to the group that corresponds to the index value indicating a highest correlation among the plurality of groups is a connection phase to which the transformer is coupled.

Abstract: A first time-series data set indicating first measured values obtained by a first device and a second time-series data set indicating second measured values obtained by a second device are obtained. First alignment is performed to convert the positions in the time domain of the first measured values belonging to a second period, based on the first measured values belonging to a first period. Second alignment is performed to convert the positions in the time domain of the second measured values belonging to the second period, based on a relationship between positions before and after the conversion. Correlation analysis is performed between third and fourth time-series data sets respectively obtained by the first and second alignment. The existence or absence of an inclusion relationship in which the second measured values contain a component of the first measured values is determined based on the correlation analysis result.

Abstract: A data generation method by a computer is disclosed. First waveform data including marking information at a first position on a waveform, and acquiring second waveform data are acquired. A transformation function is specified that transforms the first waveform data to reduce the difference between a first value of a time axis for a first characteristic point in the first waveform data and a second value of the time axis for a second characteristic point, in the second waveform data, corresponding to the first characteristic point. Third waveform data are generated, in which the marking information is applied at a second position corresponding to the first position in the first waveform data, the second position being determined by using the transformation function.

Abstract: A machine learning device includes: a model generator configured to generate a machine learning model by using first training data that includes image data, the image data including a target to be recognized and a label indicating the target to be recognized; a teaching data generator configured to generate second training data indicating a changed variation in characteristics related to the target to be recognized, based on recognition degrees at which the target to be recognized is recognized from verification data items when the image data is input as the verification data items to the generated machine learning model; and a learning executor configured to execute machine learning by inputting the generated second training data to the generated machine learning, model.

Abstract: A memory stores graph information representing a graph that includes nodes and inter-node edges. The nodes include a first plurality of nodes each associated with node information and a first node. Each of the inter-node edges has a weight. A processor extracts, in accordance with the node information, two or more nodes and transforms the two or more nodes into an aggregate node. The processor generates an aggregate inter-node edge between the aggregate node and the first node. The aggregate inter-node edge is associated with a weight based on two or more weights associated with two or more inter-node edges between the two or more nodes and the first node. The processor estimates first node information to be associated with the first node based on transformed graph information representing a transformed graph including the aggregate node and the aggregate inter-node edge.

Abstract: An estimating method, includes: generating, by a computer, a plurality of frequency spectra based on data measured during movement on a structure at a plurality of speeds; identifying a range of a natural frequency of the structure based on the plurality of frequency spectra; and calculating the natural frequency based on one or more dominant frequencies included in the range among dominant frequencies of the plurality of frequency spectra and speeds when the one or more dominant frequencies included in the range are measured.

Abstract: A transformer connection phase determination device includes a processor that executes a procedure. The procedure includes: computing respective correlation values representing a correlation between current corresponding to power consumed by at least one consumer connected to a transformer connected to one phase corresponding to a combination of two of a plurality of power distribution lines, and line current flowing in each of the plurality of power distribution lines; and determining the phase the transformer is connected to based on the respective correlation values.

Abstract: A non-transitory computer readable storage medium for causing a computer monitoring a power distribution system in which a first customer and a second customer are mixed to execute a process, the process including: acquiring first data measured with a first measurement device which is installed in the first customer and measures the first data at a first time interval; acquiring second data measured with a second measurement device which is installed in the second customer and measures the second data at a second time interval longer than the first time interval; estimating data of the first time interval about an electric power of the second customer by using the acquired first data and the acquired second data; and estimating a value about a voltage or a current for each customer by using the estimated data of the first time interval and the acquired first data.

Abstract: A transformer connection phase determination device includes a processor that executes a process. The process includes: acquiring a power value consumed by at least one consumer connected to a transformer that is connected to a phase corresponding to a combination of two of plural distribution lines, and acquiring respective current values flowing in the plural distribution lines; computing a frequency component of the power value or of a current value caused by the power value, and a frequency component of the respective current values flowing in the plural distribution lines; and computing respective correlation values indicating a correlation between the power value or the current value caused by the power value and the respective current values flowing in the plural distribution lines, using each of the computed frequency components, and determining the phase to which the transformer is connected based on the respective correlation values.

Abstract: An estimating method, includes: generating, by a computer, a plurality of frequency spectra based on data measured during movement on a structure at a plurality of speeds; identifying a range of a natural frequency of the structure based on the plurality of frequency spectra; and calculating the natural frequency based on one or more dominant frequencies included in the range among dominant frequencies of the plurality of frequency spectra and speeds when the one or more dominant frequencies included in the range are measured.

Abstract: An information processing method to be executed by a processor, the processing method includes setting an area target amount of reduction in power consumption of a target area; acquiring a predicted value and a measured value of outdoor temperature at each of a plurality of subareas included in the target area; calculating, for each of the plurality of subareas, a prediction error of outdoor temperature by calculating a difference between the predicted value and the measured value; calculating, for each of the plurality of subareas, a utilization rate indicating a rate of assignment of the area target amount of reduction in power consumption by solving an objective function generated based on the area target amount of reduction and a variance of the prediction error of outdoor temperature; and determining, for each of the plurality of subareas, a subarea target amount of reduction in power consumption based on the utilization rate.

Abstract: An information processing device includes a memory; and a processor coupled to the memory and configured to obtain data including a temperature in a space where each of a plurality of air conditioning apparatuses is installed, a temperature outside the space, and power consumption of the plurality of air conditioning apparatuses, calculate a factor to obtain relationship between the temperature in the space, the temperature outside the space, and the power consumption related to each of the plurality of the air conditioning apparatuses based on the obtained data, and calculate, in a case of changing a setting temperature of the plurality of air conditioning apparatuses, a change width of each of the setting temperatures of the plurality of air conditioning apparatuses in such a manner that variation in the change width becomes a control unit using an objective function expressing a cost of a power supplier and the calculated factor.

Abstract: A transformer connection phase determination device includes a processor that executes a procedure includes: acquiring a power value consumed by at least one consumer connected to a transformer connected to any phase corresponding to a combination of two of a plurality of distribution lines, and acquiring respective current values flowing in each of the plurality of distribution lines, in association with a time axis; applying a filter that attenuates low frequency components in a current value caused by the power value and in the respective current values flowing in the plurality of respective power distribution lines; computing respective correlation values indicating correlation between the current values caused by the power values to which the filter has been applied, and the respective current values flowing in the plurality of respective power distribution lines to which the filter has been applied; and determining the phase that the transformer is connected to.

Abstract: A transformer connection phase determination device includes a processor that executes a process. The process includes: acquiring a power value consumed by at least one consumer connected to a transformer that is connected to a phase corresponding to a combination of two of plural distribution lines, and acquiring respective current values flowing in the plural distribution lines; computing a frequency component of the power value or of a current value caused by the power value, and a frequency component of the respective current values flowing in the plural distribution lines; and computing respective correlation values indicating a correlation between the power value or the current value caused by the power value and the respective current values flowing in the plural distribution lines, using each of the computed frequency components, and determining the phase to which the transformer is connected based on the respective correlation values.