A method and system for intelligently supplementing electricity consumption

Abstract

The present invention relates to an intelligent power consumption supplement method and system, including: obtaining a user's missing power consumption time interval; obtaining a distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval; based on the distance matrix, determining the similar time periods of each time period in the missing power consumption time interval in the historical time interval; based on the power consumption of the user in the similar time period and the missing total power consumption of the user in the missing power consumption time interval, selecting the power consumption of the user in the similar time period or specifying the average power consumption of each time period in the missing power consumption time interval to supplement the power consumption of the user in each time period in the missing power consumption time interval. The present invention solves the problems of daily frozen indication overtaking and low supplement accuracy in the existing power consumption supplement method.

Description

Technical Field

[0001] The present invention relates to the field of electricity consumption information collection, and in particular to a method and system for intelligently supplementing electricity consumption. Background Art

[0002] In actual work, due to various reasons such as the system or network, the power consumption information collection system may have a situation where the active daily frozen indication is missing. Based on this, we need to complete the power consumption information;

[0003] In the prior art, traditional electricity information completion methods such as synchronous fitting or arithmetic average fitting are generally used to complete the missing electricity;

[0004] The same period fitting is an approximate fitting of the electricity data of the same period. Generally speaking, the same period fitting only considers the impact of the date type on information completion. The date type is divided into three types according to the date attributes: one is working days; the second is weekends; the third is national statutory holidays (New Year's Day, Qingming Festival, Dragon Boat Festival, May Day, Mid-Autumn Festival, National Day, Spring Festival). The specific fitting rules are as follows: (1) If the defective time period is within the working day, the average value of the data of the four previous days of the same period is fitted; (2) If the defective time period is within the weekend, the average value of the data of the four previous weekends is fitted; (3) If the defective time period is within the statutory holiday, the fitting is carried out according to the data of the same type of holiday interval last year. If there is no historical analog data to distinguish between long and short holidays, refer to the fitting process of the data of the previous long and short holiday.

[0005] The arithmetic mean fitting is to take the arithmetic mean of the interval electricity at the time points before and after the defect interval as the electricity fitting value.

[0006] However, the concurrent fitting does not take into account the total electricity consumption in the defective interval, and the supplemented electricity consumption has the situation of exceeding the daily frozen indication. In addition, this method does not consider the impact of season, weather, and temperature on different industries, resulting in a deviation between the supplemented electricity consumption and the actual electricity consumption. The arithmetic mean fitting method ignores the impact of season, weather, temperature, working days, weekends and holidays on user electricity consumption, resulting in a large deviation between the supplemented electricity consumption and the actual electricity consumption. Summary of the invention

[0007] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method and system for intelligently supplementing electricity consumption, which solves the problems of daily frozen indication overtaking and low supplement accuracy in the existing electricity consumption supplement methods.

[0008] The purpose of the present invention is achieved by adopting the following technical solutions:

[0009] The present invention provides a method for intelligently supplementing power consumption, wherein the method comprises:

[0010] Obtain the time interval during which the user's electricity consumption is missing;

[0011] Obtain the distance matrix between each time period in the missing electricity consumption time interval and each time period in the historical time interval;

[0012] Based on the distance matrix, determine the similar time periods in the historical time interval for each time period in the missing electricity consumption time interval;

[0013] Based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval, the user's electricity consumption in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval is selected to complete the user's electricity consumption in each time period in the missing electricity consumption time interval.

[0014] Preferably, the historical time interval is [α-μ, ω+π];

[0015] The designated users are other users who are located in the same region as the user and have the same electricity consumption type as the user; wherein α is the starting time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, ω is the ending time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, μ is the first preset value, and π is the second preset value.

[0016] The present invention provides an intelligent power consumption replenishment system, characterized in that the system comprises:

[0017] The first acquisition module is used to obtain the time interval of the user's missing electricity consumption;

[0018] The second acquisition module is used to obtain the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval;

[0019] A determination module, used for determining similar time periods in the historical time interval for each time period in the missing power consumption time interval based on the distance matrix;

[0020] The completion module is used to select the user's electricity consumption in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval.

[0021] Preferably, the historical time interval is [α-μ, ω+π];

[0022] The designated users are other users who are located in the same region as the user and have the same electricity consumption type as the user; wherein α is the starting time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, ω is the ending time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, μ is the first preset value, and π is the second preset value.

[0023] Compared with the closest prior art, the present invention has the following beneficial effects: obtaining the time interval of the user's missing electricity consumption; obtaining the distance matrix between each time period in the missing electricity consumption time interval and each time period in the historical time interval; determining the similar time periods of each time period in the missing electricity consumption time interval in the historical time interval based on the distance matrix; based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval, selecting the user's electricity consumption in similar time periods or specifying the average electricity consumption of each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval. The technical solution provided by the present invention solves the problems of daily frozen indication overtaking and low completion accuracy in the existing electricity consumption completion methods.

[0024] The technical solution provided by the present invention calculates the distance between time periods from multiple dimensions such as festival type, date type, weather type and temperature, and uses the distance between time periods as a basis for finding similar time periods in the missing electricity consumption time interval, thereby ensuring higher reliability in finding similar time periods.

[0025] The technical solution provided by the present invention takes into account the impact of industries on electricity consumption replenishment and improves the accuracy of electricity consumption replenishment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for intelligently supplementing electricity consumption;

[0027] Figure 2 It is a structural diagram of an intelligent power consumption complement system. DETAILED DESCRIPTION

[0028] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] The present invention provides a method for intelligently supplementing power consumption, such as Figure 1 As shown, the method includes:

[0031] Step 101, for obtaining a time interval during which the user's power consumption is missing;

[0032] Step 102, for obtaining a distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval;

[0033] Step 103, for determining similar time periods in the historical time interval for each time period in the missing power consumption time interval based on the distance matrix;

[0034] Step 104 is used to select the user's electricity consumption in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval.

[0035] Preferably, the historical time interval is [α-μ, ω+π];

[0036] The designated users are other users who are located in the same region as the user and have the same electricity consumption type as the user; wherein α is the starting time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, ω is the ending time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, μ is the first preset value, and π is the second preset value.

[0037] Preferably, the step 102 includes:

[0038] Step 102-1, respectively calculating the item-by-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors;

[0039] Step 102-2, determining a distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval according to the sub-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors;

[0040] The various factors include season factors, date factors, weather factors and temperature factors.

[0041] Furthermore, the step 102-1 includes:

[0042] The sub-item distance between the i-th period in the missing electricity consumption time interval and the j-th period in the historical time interval under the influence of seasonal factors is calculated as follows:

[0043]

[0044] In the above formula, x i is the i-th period in the missing electricity consumption time interval, y j is the jth period in the historical time interval, is the sequence number of the day in the Gregorian calendar year to which the ith period of the missing electricity consumption time interval belongs, is the sequence number of the day belonging to the jth period in the historical time interval in the Gregorian calendar year, is the sequence number of the day in the lunar year to which the ith period of the missing electricity consumption time interval belongs, is the sequence number of the day belonging to the jth period in the historical time interval in its lunar year;

[0045] The specific season date is a date included in the annual festival, and the annual festival is a time interval consisting of Q days before the Spring Festival, the Spring Festival, and R days after the Spring Festival, Q is a third preset value, and R is a fourth preset value;

[0046] In a specific embodiment of the present invention, the New Year's Day is from the 16th day of the twelfth lunar month to the 20th day of the first lunar month, and dates not in a specific season refer to dates other than the New Year's Day.

[0047] As shown in Table 1, the sub-item distance between the i-th period in the missing electricity consumption time interval and the j-th period in the historical time interval under the influence of date factors is calculated as follows:

[0048]

[0049] Table 1

[0050]

[0051]

[0052] As shown in Table 2, the sub-item distance between the i-th period in the missing electricity consumption time interval under the influence of weather factors and the j-th period in the historical time interval is calculated as follows:

[0053]

[0054] The set (1) includes the following situations: i The weather type is Class A weather and y j The weather type is B weather, x i The weather type is Class B weather and y j The weather type is A weather, x i The weather type is Class B weather and y j The weather type is C weather, xi The weather type is C weather and y j The weather type is B weather, x i The weather type is C weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class C weather;

[0055] The set (2) includes the following situations: i The weather type is Class A weather and y j The weather type is C weather, x i The weather type is C weather and y j The weather type is A weather, x i The weather type is Class B weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class B weather;

[0056] The set (3) includes the following cases: i The weather type is Class A weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class A weather;

[0057] Table 2

[0058] <![CDATA[d 3 ]]> Weather Category A Weather Category B Weather Category C Weather Category D Weather Category A \ 0.5 0.75 1 Weather Category B 0.5 \ 0.5 0.75 Weather Category C 0.75 0.5 \ 0.5 Weather Category D 1 0.75 0.5 \

[0059] The Class A weather, Class B weather, Class C weather and Class D weather are obtained by clustering various common weather conditions using the EM clustering algorithm based on the expectations and variances of the output curves of the local photovoltaic power station under various common weather conditions;

[0060] The common weather conditions include: sunny, cloudy, overcast, showers, thunderstorms, thunderstorms with hail, sleet, light rain, moderate rain, heavy rain, rainstorms, heavy rainstorms, extremely heavy rainstorms, snow showers, light snow, moderate snow, heavy snow, blizzards, fog, freezing rain, sandstorms, light rain-moderate rain, moderate rain-heavy rain, heavy rain-rainstorms, rainstorms-heavy rainstorms, heavy rainstorms-extremely heavy rainstorms, light snow-moderate snow, moderate snow-heavy snow, heavy snow-blizzards, floating dust, blowing sand, strong sandstorms, and haze;

[0061] In the best embodiment of the present invention, the Class A weather, Class B weather, Class C weather or Class D weather is obtained by clustering various common weather conditions using the EM clustering algorithm based on the expectation and variance of the output curve of the local photovoltaic power station in various common weather conditions; the specific implementation method is shown in the patent A photovoltaic output prediction method and device (2016103707687);

[0062] Among them, a certain place classified the weather using the above method based on the expectation and variance of the output curves of photovoltaic power stations in various common weather conditions in the past year, and the classification results were: sunny, showers, thunderstorms, and thunderstorms with hail were gathered as weather category A; cloudy, overcast, light rain, moderate rain, heavy rain, light rain-moderate rain, moderate rain-heavy rain, and heavy rain-heavy rain were gathered as weather category B; snow showers, light snow, moderate snow, heavy snow, blizzards, freezing rain, light snow-moderate snow, moderate snow-heavy snow, and heavy snow-blizzards were gathered as weather category C; floating dust, blowing sand, strong sandstorms, haze, sleet, heavy rain, heavy rain, extremely heavy rain, heavy rain-heavy rain, and heavy rain-extraordinary rain were gathered as weather category D.

[0063] The sub-item distance between the i-th period in the missing power consumption time interval and the j-th period in the historical time interval under the influence of temperature factors is calculated as follows:

[0064]

[0065] In the formula, is the temperature of the i-th period in the missing electricity consumption time interval, is the temperature of the jth period in the historical time interval.

[0066] Furthermore, the step 102-2 includes:

[0067] The distance matrix D between each time period in the missing electricity consumption time interval and each time period in the historical time interval is determined as follows:

[0068]

[0069] In the formula, is the distance between the i-th time period in the missing power consumption time interval and the j-th time period in the historical time interval, i∈(1~Z), Z is the total number of time periods included in the missing power consumption time interval, j∈(1~L), L is the total number of time periods included in the historical time interval;

[0070] Among them, the following formula is used to determine the

[0071]

[0072] In the above formula, a is the weight corresponding to the seasonal factor, b is the weight corresponding to the date factor, c is the weight corresponding to the weather factor, and e is the weight corresponding to the temperature factor.

[0073] Specifically, the step 103 includes:

[0074] Step 103-1, according to the distance matrix, determine the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval;

[0075] Step 103-2, determining whether the time periods in the missing power consumption time interval have a matching relationship in the historical time interval and whether the time periods are unique;

[0076] Step 103-3: If it is unique, the time period with a matching relationship is used as a similar time period of the corresponding time period in the missing power consumption time interval;

[0077] Otherwise, a time period with the smallest distance from the corresponding time period in the missing power consumption time interval is selected from the time periods with a matching relationship as a similar time period to the corresponding time period.

[0078] Furthermore, the step 103-1 includes:

[0079] Step 103-1-1, initialize i=1, j=1, and go to step B;

[0080] Step 103-1-2, record the jth period y in the historical time interval j The i-th time period in the missing electricity consumption time interval has a matching relationship in the historical time interval, and go to step C;

[0081] Step 103-1-3, if i≠Z and j≠L, select and The smallest one among them, and go to step D;

[0082] If i≠Z and j=L, set i=i+1 and go to step B;

[0083] If i=Z and j≠L, set j=j+1 and go to step B;

[0084] If i=Z and j=L, then output the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval, and end the operation;

[0085] Step 103-1-4, if the smallest is Then let i=i+1 and go to step B;

[0086] If the smallest is Then let j=j+1 and go to step B;

[0087] If the smallest is Then let i=i+1, j=j+1, and go to step B;

[0088] Among them, i∈(1~Z), Z is the total number of time periods included in the missing power consumption time interval, j∈(1~L), L is the total number of time periods included in the historical time interval, is the distance between the i+1th period in the missing electricity consumption time interval and the jth period in the historical time interval, is the distance between the i-th period in the missing electricity consumption time interval and the j+1-th period in the historical time interval, It is the distance between the i+1th period in the missing electricity consumption time interval and the j+1th period in the historical time interval.

[0089] Specifically, the step 104 includes:

[0090] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is not missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i ,

[0091] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i , P i =P i * ·λ;

[0092] If the power consumption of the user in similar periods of each period in the missing power consumption time interval is missing, and the total power consumption of the user in the missing power consumption time interval is not missing, then the power consumption of the user in the i-th period in the missing power consumption time interval is completed as follows: i ,

[0093] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i , P i =P i # β;

[0094] Among them, P all is the total power consumption of the user during the missing power consumption time interval, P i* is the electricity consumption of the user in the similar period of the i-th period in the missing electricity consumption time interval, i∈(1~Z), Z is the total number of time periods included in the missing electricity consumption time interval, and λ is the sequence The median of each element in , λ f is the ratio of the user's power consumption in the fth time period in the time interval closest to the missing power consumption time interval to the power consumption in the similar time period of the fth time period in the time interval closest to the missing power consumption time interval, f∈(1~S f ), S f is the total number of time periods contained in the time interval closest to the missing power consumption time interval, P i # is the average power consumption of the specified user in the i-th period in the missing power consumption time interval, and β is the sequence The median of each element in , β f It is the ratio between the power consumption of the user in the fth period in a time interval closest to the missing power consumption time interval and the average power consumption of the specified user in the fth period in a time interval closest to the missing power consumption time interval.

[0095] In the best embodiment of the present invention, the total electricity consumption in the time interval of missing electricity consumption is calculated by the daily frozen indication of the last time period in the time interval of missing electricity consumption minus the daily frozen indication of the time period before the time interval of missing electricity consumption, and other users with the same electricity consumption type as the user refer to other users in the same industry as the user.

[0096] The present invention provides an intelligent power consumption replenishment system, such as Figure 2 As shown, the system comprises:

[0097] The first acquisition module is used to obtain the time interval of the user's missing electricity consumption;

[0098] The second acquisition module is used to obtain the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval;

[0099] A determination module, used for determining similar time periods in the historical time interval for each time period in the missing power consumption time interval based on the distance matrix;

[0100] The completion module is used to select the user's electricity consumption in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval.

[0101] Wherein, the historical time interval is [α-μ, ω+π];

[0102] The designated users are other users who are located in the same region as the user and have the same electricity consumption type as the user; wherein α is the starting time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, ω is the ending time of the time period corresponding to the previous year of the year to which the missing electricity consumption time interval belongs, μ is the first preset value, and π is the second preset value.

[0103] Furthermore, the second acquisition module includes:

[0104] A calculation unit, used to respectively calculate the sub-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors;

[0105] A first determination unit is used to determine a distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval according to the sub-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors;

[0106] The various factors include season factors, date factors, weather factors and temperature factors.

[0107] Furthermore, the computing unit is used to:

[0108] The sub-item distance between the i-th period in the missing electricity consumption time interval and the j-th period in the historical time interval under the influence of seasonal factors is calculated as follows:

[0109]

[0110] In the above formula, x i is the i-th period in the missing electricity consumption time interval, y j is the jth period in the historical time interval, is the sequence number of the day in the Gregorian calendar year to which the ith period of the missing electricity consumption time interval belongs, is the sequence number of the day belonging to the jth period in the historical time interval in the Gregorian calendar year, is the sequence number of the day in the lunar year to which the ith period of the missing electricity consumption time interval belongs, is the sequence number of the day belonging to the jth period in the historical time interval in its lunar year;

[0111] The specific season date is a date included in the annual festival, and the annual festival is a time interval consisting of Q days before the Spring Festival, the Spring Festival, and R days after the Spring Festival, Q is a third preset value, and R is a fourth preset value;

[0112] The sub-item distance between the i-th period in the missing electricity consumption time interval and the j-th period in the historical time interval under the influence of date factors is calculated as follows:

[0113]

[0114] As shown in Table 2, the sub-item distance between the i-th period in the missing electricity consumption time interval under the influence of weather factors and the j-th period in the historical time interval is calculated as follows:

[0115]

[0116] The set (1) includes the following situations: i The weather type is Class A weather and y j The weather type is B weather, x i The weather type is Class B weather and y j The weather type is A weather, x i The weather type is Class B weather and y j The weather type is C weather, x i The weather type is C weather and y j The weather type is B weather, x i The weather type is C weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class C weather;

[0117] The set (2) includes the following situations: i The weather type is Class A weather and y j The weather type is C weather, x i The weather type is C weather and y j The weather type is A weather, x i The weather type is Class B weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class B weather;

[0118] The set (3) includes the following cases: i The weather type is Class A weather and y j The weather type is D weather and x i The weather type is D weather and y j The weather type is Class A weather;

[0119] The Class A weather, Class B weather, Class C weather and Class D weather are obtained by clustering various common weather conditions using the EM clustering algorithm based on the expectations and variances of the output curves of the local photovoltaic power station under various common weather conditions;

[0120] The common weather conditions include: sunny, cloudy, overcast, showers, thunderstorms, thunderstorms with hail, sleet, light rain, moderate rain, heavy rain, rainstorms, heavy rainstorms, extremely heavy rainstorms, snow showers, light snow, moderate snow, heavy snow, blizzards, fog, freezing rain, sandstorms, light rain-moderate rain, moderate rain-heavy rain, heavy rain-rainstorms, rainstorms-heavy rainstorms, heavy rainstorms-extremely heavy rainstorms, light snow-moderate snow, moderate snow-heavy snow, heavy snow-blizzards, floating dust, blowing sand, strong sandstorms, and haze;

[0121] The sub-item distance between the i-th period in the missing power consumption time interval and the j-th period in the historical time interval under the influence of temperature factors is calculated as follows:

[0122]

[0123] In the formula, is the temperature of the i-th period in the missing electricity consumption time interval, is the temperature of the jth period in the historical time interval.

[0124] Specifically, the first determining unit is used to:

[0125] The distance matrix D between each time period in the missing electricity consumption time interval and each time period in the historical time interval is determined as follows:

[0126]

[0127] In the formula, is the distance between the i-th time period in the missing power consumption time interval and the j-th time period in the historical time interval, i∈(1~Z), Z is the total number of time periods included in the missing power consumption time interval, j∈(1~L), L is the total number of time periods included in the historical time interval;

[0128] Among them, the following formula is used to determine the

[0129]

[0130] In the above formula, a is the weight corresponding to the seasonal factor, b is the weight corresponding to the date factor, c is the weight corresponding to the weather factor, and e is the weight corresponding to the temperature factor.

[0131] Specifically, the determination module includes:

[0132] A second determination unit is used to determine, according to the distance matrix, time periods in the missing power consumption time interval that have a matching relationship in the historical time interval;

[0133] A judgment unit, used to judge whether the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval are unique;

[0134] A selection unit is used for, if it is unique, taking the time period with a matching relationship as a similar time period of the corresponding time period in the missing power consumption time interval;

[0135] Otherwise, a time period with the smallest distance from the corresponding time period in the missing power consumption time interval is selected from the time periods with a matching relationship as a similar time period to the corresponding time period.

[0136] Specifically, the second determining unit includes:

[0137] An initialization subunit, used to initialize i=1, j=1, and go to step B;

[0138] Fill in the subunit for the jth period y in the historical time interval j The i-th time period in the missing electricity consumption time interval has a matching relationship in the historical time interval, and go to step C;

[0139] A selection subunit is used to select the distance matrix if i≠Z and j≠L. and The smallest one among them, and go to step D;

[0140] If i≠Z and j=L, set i=i+1 and go to step B;

[0141] If i=Z and j≠L, set j=j+1 and go to step B;

[0142] If i=Z and j=L, then output the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval, and end the operation;

[0143] Command subunit, used if the minimum is Then let i=i+1 and go to step B;

[0144] If the smallest is Then let j=j+1 and go to step B;

[0145] If the smallest is Then let i=i+1, j=j+1, and go to step B;

[0146] Among them, i∈(1~Z), Z is the total number of time periods included in the missing power consumption time interval, j∈(1~L), L is the total number of time periods included in the historical time interval, is the distance between the i+1th period in the missing electricity consumption time interval and the jth period in the historical time interval, is the distance between the i-th period in the missing electricity consumption time interval and the j+1-th period in the historical time interval, It is the distance between the i+1th period in the missing electricity consumption time interval and the j+1th period in the historical time interval.

[0147] Specifically, the completion module is used to:

[0148] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is not missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i ,

[0149] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i , P i =P i * ·λ;

[0150] If the power consumption of the user in similar periods of each period in the missing power consumption time interval is missing, and the total power consumption of the user in the missing power consumption time interval is not missing, then the power consumption of the user in the i-th period in the missing power consumption time interval is completed as follows: i ,

[0151] If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, then the user's electricity consumption P in the i-th period of the missing electricity consumption time interval is completed as follows: i , P i =P i # β;

[0152] Among them, P all is the total power consumption of the user during the missing power consumption time interval, P i * is the electricity consumption of the user in the similar period of the i-th period in the missing electricity consumption time interval, i∈(1~Z), Z is the total number of time periods included in the missing electricity consumption time interval, and λ is the sequence The median of each element in , λ f is the ratio of the user's power consumption in the fth time period in the time interval closest to the missing power consumption time interval to the power consumption in the similar time period of the fth time period in the time interval closest to the missing power consumption time interval, f∈(1~S f ), S f is the total number of time periods contained in the time interval closest to the missing power consumption time interval, P i # is the average power consumption of the specified user in the i-th period in the missing power consumption time interval, and β is the sequence The median of each element in , β f It is the ratio between the power consumption of the user in the fth period in a time interval closest to the missing power consumption time interval and the average power consumption of the specified user in the fth period in a time interval closest to the missing power consumption time interval.

[0153] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0154] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligently supplementing electricity consumption. It is characterized in that The method comprises: Obtain the time interval during which the user's electricity consumption is missing; Obtain the distance matrix between each time period in the missing electricity consumption time interval and each time period in the historical time interval; Based on the distance matrix, determine the similar time periods in the historical time interval for each time period in the missing electricity consumption time interval; Based on the missing electricity consumption of the user in similar time periods and the total electricity consumption of the user in the missing electricity consumption time interval, select the electricity consumption of the user in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval to complete the electricity consumption of the user in each time period in the missing electricity consumption time interval; The method of selecting the user's electricity consumption in similar time periods or specifying the average electricity consumption of each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval includes: If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is not missing, then the user's total electricity consumption in the missing electricity consumption time interval is completed as follows: Electricity consumption per period , ; If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is not missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, the following formula is used to complete the user's total electricity consumption in the missing electricity consumption time interval: Electricity consumption per period , ; If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is missing, and the user's total electricity consumption in the missing electricity consumption time interval is not missing, then the user's total electricity consumption in the missing electricity consumption time interval is completed as follows: Electricity consumption per period , ; If the user's electricity consumption in similar periods of each period in the missing electricity consumption time interval is missing, and the user's total electricity consumption in the missing electricity consumption time interval is missing, the following formula is used to complete the user's total electricity consumption in the missing electricity consumption time interval: Electricity consumption per period , ; in, is the total power consumption of the user during the time interval of missing power consumption, For users in the missing power consumption time interval The electricity consumption of similar periods in the time period, , is the total number of time periods included in the missing electricity consumption time interval, For sequence The median of each element in , The user's first The power consumption in the first period is related to the power consumption of the user in the closest time interval to the missing power consumption time interval. The ratio of electricity consumption in similar periods of time, , is the total number of time periods contained in the time interval closest to the missing electricity consumption time interval, The specified user is the first The average power consumption in a period of time, For sequence The median of each element in , The user's first The power consumption of the specified user in the time interval closest to the missing power consumption time interval The ratio between the average power consumption in two time periods.

2. The method according to claim 1, It is characterized in that The historical time interval is ; The designated users are other users who are located in the same region as the user and have the same electricity usage type as the user; The starting time of the period corresponding to the previous year of the missing electricity consumption time interval, The missing electricity consumption time interval is the end time of the corresponding period in the previous year of the year to which it belongs. is the first preset value, is the second preset value.

3. The method according to claim 1, It is characterized in that The obtaining of the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval includes: Calculate the item-by-item distances between each time period in the missing electricity consumption time interval and each time period in the historical time interval under the influence of various factors; According to the sub-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors, the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval is determined; The various factors include season factors, date factors, weather factors and temperature factors.

4. The method according to claim 3, It is characterized in that The calculation of the item-by-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors includes: Calculate the missing electricity consumption time interval under the influence of seasonal factors as follows: The period and historical time interval The distance between the sub-items : In the above formula, The missing power consumption time interval time period, For the historical time interval time period, The missing power consumption time interval The sequence number of the day to which each time period belongs in the Gregorian calendar year, For the historical time interval The sequence number of the day to which each time period belongs in the Gregorian calendar year, The missing power consumption time interval The sequence number of the day to which each time period belongs in the lunar year, For the historical time interval The sequence number of the day to which each time period belongs in the lunar year; Among them, the is the date included in the Spring Festival, and the Spring Festival is a time interval consisting of Q days before the Spring Festival, the Spring Festival, and R days after the Spring Festival, Q is the third preset value, and R is the fourth preset value; Calculate the missing electricity consumption time interval under the influence of date factors as follows: The period and historical time interval The distance between the sub-items : Calculate the missing electricity consumption time interval under the influence of weather factors as follows: The period and historical time interval The distance between the sub-items : The set (1) includes the following situations: The weather type is Class A weather and The weather type is Class B weather. The weather type is Class B weather and The weather type is Class A weather, The weather type is Class B weather and The weather type is C weather. The weather type is Class C weather and The weather type is Class B weather. The weather type is C weather and The weather type is D weather and The weather type is D weather and The weather type is Class C weather; The situations included in the set (2) are: The weather type is Class A weather and The weather type is C weather. The weather type is Class C weather and The weather type is Class A weather, The weather type is Class B weather and The weather type is D weather and The weather type is D weather and The weather type is Class B weather; The cases included in set (3) are: The weather type is Class A weather and The weather type is D weather and The weather type is D weather and The weather type is Class A weather; The Class A weather, Class B weather, Class C weather and Class D weather are obtained by clustering various common weather conditions using the EM clustering algorithm based on the expectations and variances of the output curves of the local photovoltaic power station under various common weather conditions; The common weather conditions include: sunny, cloudy, overcast, showers, thunderstorms, thunderstorms with hail, sleet, light rain, moderate rain, heavy rain, rainstorms, heavy rainstorms, extremely heavy rainstorms, snow showers, light snow, moderate snow, heavy snow, blizzards, fog, freezing rain, sandstorms, light rain-moderate rain, moderate rain-heavy rain, heavy rain-rainstorms, rainstorms-heavy rainstorms, heavy rainstorms-extremely heavy rainstorms, light snow-moderate snow, moderate snow-heavy snow, heavy snow-blizzards, floating dust, blowing sand, strong sandstorms, and haze; Calculate the missing power consumption time interval under the influence of temperature factors as follows: The period and historical time interval The distance between the sub-items : In the formula, The missing power consumption time interval The temperature of the time period, For the historical time interval Temperature during a period of time.

5. The method according to claim 4, It is characterized in that Determining the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval according to the sub-item distances between each time period in the missing power consumption time interval and each time period in the historical time interval under the influence of various factors includes: The distance matrix between each period in the missing electricity consumption time interval and each period in the historical time interval is determined by the following formula: : In the formula, The missing power consumption time interval The period and historical time interval The distance between time periods, , is the total number of time periods included in the missing electricity consumption time interval, , is the total number of time periods included in the historical time interval; Among them, the following formula is used to determine the : In the above formula, is the weight corresponding to the seasonal factor, is the weight corresponding to the date factor, is the weight corresponding to the weather factor, is the weight corresponding to the temperature factor.

6. The method according to claim 1, It is characterized in that The determining, based on the distance matrix, of similar time periods of each time period in the missing power consumption time interval in the historical time interval includes: According to the distance matrix, determine the time periods in the missing electricity consumption time interval that have matching relationships in the historical time interval; Determine whether the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval are unique; If it is unique, the time period with matching relationship will be used as the similar time period of the corresponding time period in the missing power consumption time interval; Otherwise, a time period with the smallest distance from the corresponding time period in the missing power consumption time interval is selected from the time periods with a matching relationship as a similar time period to the corresponding time period.

7. The method according to claim 6, It is characterized in that Determining, based on the distance matrix, the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval includes: Step A: Initialization , , and go to step B; Step B: Record the first Time period It is the first The time periods have matching relationships in the historical time interval, and go to step C; Step C: If and , then select the distance matrix , and The smallest one among them, and go to step D; like and , then let , and go to step B; like and , then let , and go to step B; like and , then output the time periods in the missing power consumption time interval that have a matching relationship in the historical time interval, and end the operation; Step D: If the smallest is , then let , and go to step B; If the smallest is , then let , and go to step B; If the smallest is , then let , , and go to step B; in, , is the total number of time periods included in the missing electricity consumption time interval, , is the total number of time periods included in the historical time interval, The missing power consumption time interval The period and historical time interval The distance between time periods, The missing power consumption time interval The period and historical time interval The distance between time periods, The missing power consumption time interval The period and historical time interval The distance between time periods.

8. An intelligent power replenishment system, It is characterized in that The system is used to implement the method for intelligently supplementing power consumption as claimed in claim 1; The system specifically comprises: The first acquisition module is used to obtain the time interval of the user's missing electricity consumption; The second acquisition module is used to obtain the distance matrix between each time period in the missing power consumption time interval and each time period in the historical time interval; A determination module, used for determining similar time periods in the historical time interval for each time period in the missing power consumption time interval based on the distance matrix; The completion module is used to select the user's electricity consumption in similar time periods or the average electricity consumption of the specified user in each time period in the missing electricity consumption time interval to complete the user's electricity consumption in each time period in the missing electricity consumption time interval based on the user's electricity consumption in similar time periods and the missing total electricity consumption of the user in the missing electricity consumption time interval.

9. The system of claim 8, It is characterized in that The historical time interval is ; The designated users are other users who are located in the same region as the user and have the same electricity usage type as the user; The starting time of the period corresponding to the previous year of the missing electricity consumption time interval, The missing electricity consumption time interval is the end time of the corresponding period in the previous year to which it belongs. is the first preset value, is the second preset value.

Images