Data processing device, data processing method, and program
A data processing device includes: a data obtaining section obtaining time series data on a total value of current consumed by a plurality of electric apparatuses; and a parameter estimating section obtaining a model parameter when states of operation of the plurality of electric apparatuses are modeled by a factorial HMM on a basis of the obtained time series data.
1. A electrical apparatus estimating device comprising:
a data obtaining section including at least a voltmeter and an ammeter configured to obtain time series data on a total value of current consumed by a plurality of electric apparatuses, wherein the voltmeter and the ammeter are located on a secondary side of a distribution board; and
a microprocessor including a parameter estimating section configured to:
obtain a model parameter when states of operation of said plurality of electric apparatuses are modeled by a stochastic model on a basis of the obtained time series data,
wherein in a parameter estimating process based on an algorithm which alternately calculates expectation and maximizes likelihood, under constraint conditions that converted values or a vector of an observation parameter W(m) corresponding to a pattern of a current waveform of a factor m of said stochastic model are nonnegative, said stochastic model maximizes a likelihood function as a degree of said stochastic model describing a pattern of the total value of said consumed current indicated by said time series data, whereby said parameter estimating section obtains the observation parameter W(m) as said model parameter, and
adjust the model parameter, when new time series data is obtained, to minimize an error between said pattern of the current waveform of said factor m and said pattern of the total value of said consumed current indicated by said time series data for all factors; and
a state predicting section predicting a state of said factor at a future time after passage of a predetermined time from a present time; and
a controlling section controlling at least one electric apparatus of the plurality of electric apparatuses, which are located on the secondary side of the distribution board, based on a result, from the state predicting section, of a prediction of the state of said factor at the future time.
2. The electrical apparatus estimating device according to claim 1 , wherein said stochastic model is Factorial HMM.
3. The electrical apparatus estimating device according to claim 2 , in said parameter estimating process based on said algorithm, under constraint conditions that a number of states assumable by each state of said factorial HMM is two, said Factorial HMM maximizes said likelihood function as a degree of said factorial HMM describing said pattern of the total value of said consumed current indicated by said time series data.
4. The electrical apparatus estimating device according to claim 2 , wherein in said parameter estimating process based on said algorithm, under constraint conditions that one of a first column and a second column corresponding to said number of states is zero at all times, said Factorial HMM maximizes said likelihood function as a degree of said factorial HMM describing said pattern of the total value of said consumed current indicated by said time series data.
5. The electrical apparatus estimating device according to claim 2 , further comprising an identical apparatus determining section determining that a plurality of predetermined factors of said factorial HMM correspond to said time series data.
6. The electrical apparatus estimating device according to claim 5 , wherein said identical apparatus determining section selects combinations that satisfy a necessary condition at all times among all combinations of each factor of said factorial HMM as identical apparatus candidates, and determines that a combination that has satisfied a hint condition a predetermined number of times among the selected identical apparatus candidates corresponds to said time series data, whereby said identical apparatus determining section determines that the plurality of predetermined factors correspond to said time series data.
7. The electrical apparatus estimating device according to claim 1 , wherein said data obtaining section obtains a total value of current consumed by said plurality of electric apparatuses in predetermined cycles in synchronism with a phase of voltage supplied to said electric apparatuses.
8. The electrical apparatus estimating device according to claim 1 , further comprising an electrical apparatus identifying section identifying plurality of electrical apparatuses.
9. The electrical apparatus estimating device according to claim 8 , further comprising a displaying unit displaying an operating state of said plurality electrical apparatuses identified by the electrical apparatus identifying section based on the result estimated by said parameter estimating section.
10. The electrical apparatus estimating device according to claim 1 , wherein said data obtaining section obtains time series data on a total value of current consumed by a plurality of electric apparatuses on predetermined cycles synchronizing phase of supply voltage to said electrical apparatuses.
11. A non-transitory computer readable medium storing a computer program for making a system function as:
a data obtaining section including at least a voltmeter and an ammeter configured to obtain time series data on a total value of current consumed by a plurality of electric apparatuses, wherein the voltmeter and the ammeter are located on a secondary side of a distribution board; and
a microprocessor including a parameter estimating section configured to:
obtain a model parameter when states of operation of said plurality of electric apparatuses are modeled by a stochastic model on a basis of the obtained time series data,
wherein in a parameter estimating process based on an algorithm which alternately calculates expectation and maximizes likelihood, under constraint conditions that converted values or a vector of an observation parameter W(m) corresponding to a pattern of a current waveform of a factor m of said stochastic model are nonnegative, said stochastic model maximizes a likelihood function as a degree of said stochastic model describing a pattern of the total value of said consumed current indicated by said time series data, whereby said parameter estimating section obtains the observation parameter W(m) as said model parameter, and
adjust the model parameter, when new time series data is obtained, to minimize an error between said pattern of the current waveform of said factor m and said pattern of the total value of said consumed current indicated by said time series data for all factors; and
a state predicting section predicting a state of said factor at a future time after passage of a predetermined time from a present time; and
a controlling section controlling at least one electric apparatus of the plurality of electric apparatuses, which are located on the secondary side of the distribution board, based on a result, from the state predicting section, of a prediction of the state of said factor at the future time.