Demand calculation method, device and equipment based on photovoltaic power generation

Abstract

The invention provides a demand calculation method, device and equipment based on photovoltaic power generation, and relates to the technical field of power grids. The electric energy meters are respectively arranged between the photovoltaic power generation and the power utilization enterprise and between the power utilization enterprise and the power grid to respectively detect the generated power of the photovoltaic power generation and the transmission power of the power grid, so that the calculation of the actual demand of the power utilization enterprise in each unit time period is realized; therefore, the actual maximum demand of the power utilization enterprise is calculated based on the actual demand in each unit time period, the influence of photovoltaic power generation on the demand of the power utilization enterprise is fully considered, and the accuracy of demand calculation of the power utilization enterprise is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power grid, and in particular to a method, device and equipment for calculating demand based on photovoltaic power generation. Background Art

[0002] As an important link in the power supply, incremental distribution network companies play a key role in providing power services to power users. They are not only responsible for delivering electricity to power users, but also bear the task of collecting electricity charges. These electricity charges usually consist of two parts: electricity charges per kilowatt-hour and basic fees. Electricity charges per kilowatt-hour are calculated based on the actual amount of electricity consumed by the power user, that is, the principle of "paying how much electricity you use". The basic fee is set up to cover the fixed costs of distribution network companies (such as equipment maintenance, network operation, etc.), and its calculation method is relatively complicated.

[0003] There are two main charging modes for the calculation of basic fees: capacity-based charging and demand-based charging. Capacity-based charging, as the name implies, is to charge a certain fee based on the total capacity of the power equipment installed by the power user, regardless of whether these devices are actually running or running at full capacity. Demand-based charging, on the other hand, is based on the actual maximum power demand (i.e. demand) of the power user within a certain period (such as a month or a quarter). This charging method can better reflect the actual power consumption behavior of the power user and better reflect the principle of fairness.

[0004] At present, with the rapid development of renewable energy, more and more incremental distribution network companies have installed photovoltaic power generation systems on the power user side. These photovoltaic systems can not only supply power to enterprises when there is sufficient sunlight, reducing dependence on traditional power grids, but also reduce the demand of power users to a certain extent. Because when the photovoltaic power generation is large enough, it can meet or partially meet the power demand of enterprises, thereby reducing the amount of electricity obtained by enterprises from the distribution network, thereby reducing the peak demand.

[0005] However, since the basic fee is based on actual demand, if the calculation is inaccurate, it may lead to unfair or unreasonable electricity charges. The complex and changeable photovoltaic power generation system makes it difficult for electricity users to calculate the actual demand, and the accuracy is low. Summary of the invention

[0006] The present invention provides a method, device and equipment for calculating demand based on photovoltaic power generation, which can improve the accuracy of demand calculation of electricity consuming enterprises.

[0007] In a first aspect, the present invention provides a method for calculating demand based on photovoltaic power generation, the method comprising: obtaining metering data of a first electric energy meter and a second electric energy meter in a historical period; the first electric energy meter is used to measure the power generation power of photovoltaic power generation in an electricity consuming enterprise, and the second electric energy meter is used to measure the transmission power between the electricity consuming enterprise and the power grid; based on the metering data of the first electric energy meter and the second electric energy meter in the historical period, unit time periods are divided to obtain metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods, the actual demand of the electricity consuming enterprise in each unit time period is calculated; based on the actual demand of the electricity consuming enterprise in each unit time period, the maximum demand of the electricity consuming enterprise is determined.

[0008] In one possible implementation, the actual demand of the electricity consuming enterprise in each unit time period is calculated based on the metering data of the first electricity meter and the second electricity meter in multiple unit time periods, including: determining the actual demand of the electricity consuming enterprise in each unit time period based on the sum of the metering data of the first electricity meter and the metering data of the second electricity meter in each unit time period.

[0009] In a possible implementation, the maximum demand of the electricity consuming enterprise is determined based on the actual demand of the electricity consuming enterprise in each unit time period, including: calculating the maximum daily demand and the maximum monthly demand of the electricity consuming enterprise based on the actual demand of the electricity consuming enterprise in each unit time period.

[0010] In a possible implementation, the method also includes: obtaining multivariate data of the area of ​​the power consuming enterprise in the historical period; the multivariate data includes seasonal data, peak and valley data, holiday data and weather data; dividing the unit time period based on the multivariate data of the area of ​​the power consuming enterprise in the historical period to obtain the multivariate data of each unit time period; based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods, the actual demand of the power consuming enterprise in each unit time period, and the multivariate data of each unit time period, feature extraction and fusion are performed to obtain the load characteristics of the power consuming enterprise in each unit time period; based on the load characteristics of the power consuming enterprise in each unit time period, multiple training samples are generated; wherein each training sample takes the load characteristics of multiple consecutive unit time periods as an input vector, and takes the load characteristics of multiple consecutive unit time periods after the multiple consecutive unit time periods as an output vector; based on the training samples, neural network training is performed to obtain a load prediction model.

[0011] In a possible implementation, the method also includes: determining the load characteristics of multiple unit time periods before the current moment based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods before the current moment, and multivariate data; generating an input vector at the current moment based on the load characteristics of multiple unit time periods before the current moment; predicting a load forecast result based on the input vector at the current moment and a load forecasting model, the load forecast result including the load characteristics of multiple unit time periods after the current moment; determining the predicted demand of the power user in multiple unit time periods after the current moment based on the load forecast result; determining the predicted maximum demand of the power user in the predicted time period after the current moment based on the predicted demand of the power user in multiple unit time periods after the current moment.

[0012] In a possible implementation, after determining the maximum demand of the electricity user based on the actual demand of the electricity user in each unit time period, it also includes: determining the basic electricity fee of the electricity user based on the maximum demand of the electricity user and a preset demand unit price.

[0013] In a possible implementation, the method also includes: calculating the demand difference of the current metering cycle based on the maximum demand and predicted maximum demand of the electricity consuming enterprise in the current metering cycle; the current metering cycle includes multiple unit time periods; if the demand difference of the current metering cycle is greater than the set difference, the metering data of the first electric energy meter and the second electric energy meter in the current metering cycle are verified to obtain the verification result; based on the verification result, an alarm message is generated, and the alarm message is used to instruct the staff to confirm the verification result and metering data of the current metering cycle; receiving the confirmation result of the staff, the confirmation result includes that the metering data is normal or the metering data is abnormal; if the confirmation result is that the metering data is normal, the training sample is regenerated based on the metering data of the current metering cycle, and the load prediction model is updated based on the regenerated training sample.

[0014] In a possible implementation, the metering data of the first electric energy meter and the second electric energy meter in the current metering cycle are calibrated to obtain a calibration result, including: based on the multivariable data of the current metering cycle, querying a database to obtain metering data of multiple metering cycles similar to the multivariable data of the current metering cycle; the database stores multivariable data, metering data and demand data of the area where the electricity users are located in the historical period; based on the metering data of multiple metering cycles and the multivariable data of the current metering cycle, a unit-by-unit time period data comparison is performed to determine the calibration data of each unit time period in the current metering cycle, the calibration data including the photovoltaic power generation power difference, the power grid transmission power difference, the maximum demand difference and the average demand difference; based on the calibration data of each unit time period in the current metering cycle, a calibration result is generated.

[0015] In the second aspect, an embodiment of the present invention provides a demand calculation device based on photovoltaic power generation, the device comprising: a communication module and a processing module, the communication module being used to obtain metering data of a first electric energy meter and a second electric energy meter in a historical period; the first electric energy meter being used to measure the power generation power of photovoltaic power generation in the power consuming enterprise, and the second electric energy meter being used to measure the transmission power between the power consuming enterprise and the power grid; the processing module being used to divide the unit time periods based on the metering data of the first electric energy meter and the second electric energy meter in the historical period, and obtain the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; calculating the actual demand of the power consuming enterprise in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; and determining the maximum demand of the power consuming enterprise based on the actual demand of the power consuming enterprise in each unit time period.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect and any possible implementation method of the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the steps of the method described in the first aspect and any possible implementation method of the first aspect are implemented.

[0018] The present invention provides a method, device and equipment for calculating demand based on photovoltaic power generation. The present invention respectively sets electric energy meters between photovoltaic power generation and power users, and between power users and power grids, and respectively detects the power generation power of photovoltaic power generation and the transmission power of power grids, thereby realizing the calculation of the actual demand of power users in each unit time period, thereby obtaining the actual maximum demand of power users based on the actual demand calculation in each unit time period, fully considering the impact of photovoltaic power generation on the demand of power users, and improving the accuracy of demand calculation of power users. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a schematic flow chart of a method for calculating demand based on photovoltaic power generation provided by an embodiment of the present invention;

[0021] Figure 2This is a schematic diagram of power demand calculation for a power consuming enterprise provided by an embodiment of the present invention;

[0022] Figure 3 It is a structural schematic diagram of a photovoltaic power generation demand calculation device provided by an embodiment of the present invention;

[0023] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0025] In the description of the present invention, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" and "plurality" refer to two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0026] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0027] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0029] like Figure 1 As shown, an embodiment of the present invention provides a method for calculating demand based on photovoltaic power generation. The method includes steps S101-S104.

[0030] S101. Obtain metering data of a first electric energy meter and a second electric energy meter in a historical period.

[0031] In the embodiment of the present application, the first electric energy meter is used to measure the power generation power of photovoltaic power generation within the power consuming enterprise, and the second electric energy meter is used to measure the transmission power between the power consuming enterprise and the power grid.

[0032] S102: Based on the metering data of the first electric energy meter and the second electric energy meter in the historical period, divide the unit time period to obtain the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods.

[0033] S103: Calculate the actual demand of the electricity consuming enterprise in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods.

[0034] As a possible implementation manner, the embodiment of the present invention can determine the actual demand of the electricity consuming enterprise in each unit time period based on the sum of the metering data of the first electric energy meter and the metering data of the second electric energy meter in each unit time period.

[0035] S104. Determine the maximum demand of the electricity consuming enterprise based on the actual demand of the electricity consuming enterprise in each unit time period.

[0036] As a possible implementation manner, the embodiment of the present invention can calculate the daily maximum demand and the monthly maximum demand of the electricity consuming enterprise based on the actual demand of the electricity consuming enterprise in each unit time period.

[0037] The embodiment of the present invention can calculate demand in the following manner: Maximum demand refers to the average power of the electricity user during a certain period of time (eg, 15 minutes) within a certain settlement period (usually one month), and the maximum one-time indication value is retained as the maximum demand for this settlement period.

[0038] like Figure 2 As shown, the power value of the current minute is recorded starting from the first minute of the month, and it is recorded every minute from 0 to the 15th minute to obtain the first 15-minute time period. The total power recorded from point 0 to point 15 is divided by the time to obtain the average power of this period, which is the demand.

[0039] When the time comes to the 16th minute, continue the calculation. At this time, use the power values ​​recorded from the 1st to the 16th point to obtain the total power of the 15 minutes. Similarly, calculate the average power. If it is greater than the previous average value, it will replace it as the actual maximum demand. Otherwise, the previous average value will still be maintained as the actual maximum demand.

[0040] The actual maximum demand value is a rolling calculation. Instead of comparing 96 values ​​every day, 1440 values ​​are compared. If it is a month, such a comparison is performed every day, and the final winner is the actual maximum demand value of the month. The minute demand calculation formula is as follows.

[0041] Xi = avg (P = i-14, P = i-13, P = i-12, P = i-11, P = i-10, ..., P = i);

[0042] The formula for calculating the daily maximum demand is: dayMaxX=max(X1,X2,X3,....,X96).

[0043] Monthly maximum demand (settlement maximum demand) monMaxX = max(dayMaxX1, dayMaxX2, dayMaxX3, ..., dayMaxXmaxdateofmonth)

[0044] The present invention provides a demand calculation method based on photovoltaic power generation. By respectively setting electric energy meters between photovoltaic power generation and power users, and between power users and power grids, and respectively detecting the power generation power of photovoltaic power generation and the transmission power of the power grid, the actual demand of the power users in each unit time period is calculated, so that the actual maximum demand of the power users is calculated based on the actual demand in each unit time period, the influence of photovoltaic power generation on the demand of power users is fully considered, and the accuracy of demand calculation of power users is improved.

[0045] Optionally, after step S105, the embodiment of the present invention may also determine the basic electricity fee of the electricity consuming enterprise based on the maximum demand of the electricity consuming enterprise and a preset demand unit price.

[0046] Electricity charges for electricity users: monDf = DdDf + BasicFee, where DdDf is the electricity charge, DdDf = electricity consumption * electricity price, BasicFee is the basic fee, BasicFee = monthly maximum demand * unit price of demand.

[0047] After the power supply company deploys photovoltaic power generation, in addition to the income from photovoltaic power generation, this method also greatly increases the income from basic fees, which plays a positive role in the deployment of photovoltaic power generation by power supply companies.

[0048] Optionally, the photovoltaic power generation demand calculation method provided in the embodiment of the present invention further includes steps S201 - S205 .

[0049] S201. Obtain multivariate data of electricity-consuming enterprise areas in a historical period.

[0050] In some embodiments, the multivariate data includes seasonal data, peak and valley data, holiday data, and weather data.

[0051] For example, the embodiment of the present invention can collect minute power data of the gateway table and photovoltaic table, with a frequency of one point per minute. The collected power data is cleaned. Gateway table and photovoltaic table data cleaning: repair and clean missing or abnormal data items.

[0052] As shown in Table 1, the embodiment of the present invention can obtain power data every minute.

[0053] Table 1

[0054] 2024-01-01 00:01 8 2024-01-01 00:02 8 2024-01-01 00:03 8 ... ...

[0055] The embodiment of the present invention can sort out characteristic values ​​based on the above multivariate data and metering data, including seasons, holidays, weather conditions, etc. Load forecasting is performed under the influence of multiple variables.

[0056] Exemplarily, the embodiment of the present invention can extract the time of the data set and divide it by month, day, rate period point, season, and hourly average temperature.

[0057] Among them, the seasons include 1: spring, 2: spring, 3: spring, 4: summer, 5: summer, 6: summer, 7: autumn, 8: autumn, 9: autumn, 10: winter, 11: winter, 12: winter. Season definition = {spring: 1, summer: 2, autumn: 3, winter: 4}.

[0058] For example, the monthly peak and trough periods vary according to the season.

[0059] (1) Summer (June, July, August)

[0060] Rate period point = {0: valley, 1: valley, 2: valley, 3: valley, 4: valley, 5: valley, 6: valley, 7: flat, 8: flat, 9: flat, 10: peak, 11: peak, 12: flat, 13: flat, 14: flat, 15: flat, 16: peak, 17: peak, 18: peak, 19: peak, 20: peak, 21: peak, 22: flat, 23: valley}.

[0061] (2) Winter (November, December and January of the following year)

[0062] Rate period point = {0: flat, 1: valley, 2: valley, 3: valley, 4: valley, 5: valley, 6: valley, 7: flat, 8: peak, 9: peak, 10: flat, 11: flat, 12: valley, 13: valley, 14: flat, 15: flat, 16: peak, 17: peak, 18: peak, 19: peak, 20: peak, 21: peak, 22: flat, 23: valley}.

[0063] (3) Other seasons (February, March, April, May, September and October every year)

[0064] Rate period point = {0: flat, 1: valley, 2: valley, 3: valley, 4: valley, 5: valley, 6: valley, 7: flat, 8: peak, 9: peak, 10: flat, 11: flat, 12: valley, 13: valley, 14: flat, 15: flat, 16: peak, 17: peak, 18: peak, 19: peak, 20: peak, 21: peak, 22: flat, 23: flat}.

[0065] Definition of peaks and valleys: {peak: 1, peak: 2, flat: 3, valley: 4}.

[0066] The temperature is processed as the hourly average value, and the data after sorting are shown in Table 2.

[0067] Table 2

[0068]

[0069] S202, dividing the unit time periods based on the multivariate data of the power consumption enterprise areas in the historical period to obtain the multivariate data of each unit time period.

[0070] S203, based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods, the actual demand of the power user in each unit time period, and the multivariate data of each unit time period, feature extraction and fusion are performed to obtain the load characteristics of the power user in each unit time period.

[0071] S204: Generate multiple training samples based on the load characteristics of the electricity consuming enterprises in each unit time period.

[0072] Each training sample uses the load characteristics of multiple consecutive unit time periods as an input vector, and uses the load characteristics of multiple consecutive unit time periods after the multiple consecutive unit time periods as an output vector.

[0073] S205. Perform neural network training based on the training samples to obtain a load forecasting model.

[0074] It should be noted that the load forecasting model can use the LSTM algorithm for deep learning. In power system load forecasting, the advantage of LSTM is that it can better handle the time correlation and seasonal characteristics of load data. By introducing a gating mechanism (input gate, forget gate, and output gate), LSTM can effectively remember long-term information and ignore unimportant details, thereby improving the accuracy of the forecast.

[0075] First, collect the historical load data and the factors affecting the load (month, day, hour, rate period, season, temperature) as the input sample set x of the model. t , xt =[[x 11 ...x 1f ],[x 21 ...x 2f ],...,[x N1 ...x Nf ]], where f is the dimension of characteristic factors affecting the data, and N is the dimension of historical load.

[0076] Based on the six eigenvalues ​​and power characteristic data in Table 2, the data of a certain day is taken as an example to sort out x t :

[0077] The characteristic matrix of the gateway table

[0078] Among them, x t1 [0] represents the data at 2024-01-01 00:01, x t1 [1] represents the data at 2024-01-01 00:02, ..., x t1

[405] represents the data at 2024-01-01 06:45, x t1

[1125] represents the time data of 2024-01-01 18:45, and so on, ..., x t1

[1440] represents the time data of 2024-01-01 24:00.

[0079] x t1

[405] as an example, x t1

[405] is the feature matrix x of the gateway table t1 The first element of the feature vector in the 406th row is the power measured by the gateway meter at 2024-01-01 06:45, and the second to seventh elements are the month, day, hour, peak and valley time period, season, and temperature at 2024-01-01 06:45, respectively.

[0080] The characteristic matrix of the photovoltaic table

[0081] Among them, x t2 [0] represents the data at 2024-01-01 00:01, x t2 [1] represents the data at 2024-01-01 00:02, ..., x t2

[405] represents the data at 2024-01-01 06:45, x t2

[1125] represents the time data of 2024-01-01 18:45, and so on, ..., x t2

[1440] represents the time data of 2024-01-01 24:00.

[0082] x t2

[405] as an example, x t2

[405] is the characteristic matrix x of the photovoltaic table t2 The first element of the feature vector in the 406th row is the measured power of the photovoltaic meter at 2024-01-01 06:45, and the second to seventh elements are the month, day, hour, peak and valley time period, season, and temperature at 2024-01-01 06:45, respectively.

[0083] LSTM maps the x-value input sequence to the corresponding order and outputs y. The learning and training process needs to be performed at each step from t=1 to t=1440. For each time point t, the specific construction process of the LSTM parameters of each layer is as follows:

[0084] f t =σ(W f *[h t-1 ,x t ]+b f );

[0085] i t =σ(W i *[h t-1 ,x t ]+b i )

[0086]

[0087] o t =σ(W o *[h t-1 ,x t ]+b o )

[0088] h t =tanh(c t ) t ;

[0089] Among them, f t 、i t , c t , o t 、h t They are respectively the forget gate, input gate, state candidate vector, current cell state, output gate, and output signal. k is the bias term, W kis the weight matrix. σ(x) is the sigmoid neural network layer, which can convert the output signal into a value between 0 and 1 to describe how much input signal can pass through. tanh(·) converts the output signal into a value between -1 and 1.

[0090] In this way, the embodiment of the present invention can train a load forecasting model before performing load forecasting, which is convenient for accurate calculation of power demand by power consuming enterprises.

[0091] Optionally, the photovoltaic power generation demand calculation method provided in the embodiment of the present invention further includes steps S301 - S305 .

[0092] S301. Determine load characteristics of multiple unit time periods before the current moment based on metering data of a first electric energy meter and a second electric energy meter in multiple unit time periods before the current moment, as well as multivariate data.

[0093] Exemplarily, the original power data + eigenvalues ​​are normalized to obtain a training data set.

[0094] The embodiment of the present invention can perform normalization processing on the data.

[0095] The normalized formula is

[0096] Among them, x norm is the normalized result, x is the original value of the sequence, x min is the minimum value of the sequence, x max is the maximum value of the sequence.

[0097] Since the experimental data has one sampling point per minute, that is, 1440 sampling points per day, when setting the input and label of the neural network, set the first 1-1440 sampling points of the data to predict the 1441th point, and the 2-1441 sampling points to predict the 1442nd point, and continue rolling according to the above rules.

[0098] The embodiment of the present invention can also clean the data, and the data after cleaning is as follows.

[0099] P Gate = [P Gate 1, P Gate 2, P Gate 3, P Gate 4, P Gate 5, P Gate 6, ...., P Gate 1440]

[0100] PPV=[PPV1,PPV2,PPV3,PPV4,PPV5,PPV6,....,PPV1440]

[0101] The embodiment of the present invention can perform synthetic calculation on the power data after cleaning to obtain synthetic power data.

[0102] When the power of the gateway meter is greater than or equal to 0, the electricity user uses both city electricity and photovoltaic power generation at the same time, then the power of the enterprise user is:

[0103] Ptotal = Pgate - PPV, since PPV < 0, Pgate > = 0, Ptotal = Pgate + |PPV|

[0104] When the gateway power is less than 0, the electricity user has not fully absorbed all the photovoltaic power generation. The power of the enterprise user is: Ptotal = |PPV|-|Pgate|, where PPV<0, Pgate<0.

[0105] S302: Generate an input vector at the current moment based on load characteristics of multiple unit time periods before the current moment.

[0106] S303: Based on the input vector at the current moment and the load forecasting model, a load forecasting result is obtained.

[0107] In some embodiments, the load forecast result includes load characteristics of multiple unit time periods after the current moment.

[0108] S304: Based on the load forecast result, determine the forecast demand of the electricity consuming enterprise in multiple unit time periods after the current moment.

[0109] S305: Based on the predicted demand of the electricity consuming enterprise in multiple unit time periods after the current moment, determine the predicted maximum demand of the electricity consuming enterprise in the predicted time period after the current moment.

[0110] In this way, the embodiment of the present invention can predict the demand of the power consuming enterprise in the prediction period according to the load prediction model, so as to facilitate the comparison of the actual demand of the power consuming enterprise.

[0111] In addition, the embodiments of the present invention combine multivariate data such as seasonal data, peak and valley data, holiday data and weather data to achieve accurate prediction of the maximum demand of electricity users in the forecast period, providing accurate data support for the verification of the maximum demand of electricity users.

[0112] Optionally, the photovoltaic power generation demand calculation method provided in the embodiment of the present invention further includes steps S401-S405.

[0113] S401, based on the maximum demand and predicted maximum demand of the electricity user in the current metering period, calculating the demand difference of the current metering period; the current metering period includes multiple unit time periods;

[0114] S402: If the demand difference in the current metering period is greater than the set difference, the metering data of the first electric energy meter and the second electric energy meter in the current metering period are verified to obtain a verification result;

[0115] Exemplarily, step S402 may be specifically implemented as steps A1-A3.

[0116] A1. Based on the multivariate data of the current metering cycle, query the database to obtain metering data of multiple metering cycles similar to the multivariate data of the current metering cycle.

[0117] In some embodiments, the database stores multivariate data, metering data, and demand data of the areas where the electricity users are located during a historical period.

[0118] A2. Based on the metering data of multiple metering cycles and the multivariate data of the current metering cycle, a unit-by-unit period data comparison is performed to determine the calibration data of each unit period in the current metering cycle.

[0119] In some embodiments, the calibration data includes a photovoltaic power generation power difference, a grid transmission power difference, a maximum demand difference, and an average demand difference.

[0120] A3. Generate calibration results based on the calibration data of each unit period in the current measurement cycle.

[0121] S403, based on the verification result, generating an alarm message, the alarm message is used to instruct the staff to confirm the verification result and measurement data of the current measurement cycle;

[0122] S404, receiving the confirmation result from the staff, the confirmation result includes that the measurement data is normal or the measurement data is abnormal;

[0123] S405: If the confirmation result shows that the metering data is normal, regenerate the training samples based on the metering data of the current metering period, and update the load forecasting model based on the regenerated training samples.

[0124] In this way, the embodiment of the present invention can improve the calculation accuracy of the maximum demand of the power consuming enterprise by comparing the actual demand and predicted demand of the power consuming enterprise and updating the load prediction model in real time.

[0125] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0126] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0127] Figure 3 The schematic diagram of the structure of a photovoltaic power generation demand calculation device provided by an embodiment of the present invention is shown. The demand calculation device 500 includes a communication module 501 and a processing module 502 .

[0128] The communication module 501 is used to obtain metering data of a first electric energy meter and a second electric energy meter in a historical period; the first electric energy meter is used to measure the power generation power of photovoltaic power generation in the power-consuming enterprise, and the second electric energy meter is used to measure the transmission power between the power-consuming enterprise and the power grid.

[0129] Processing module 502 is used to divide the unit time period based on the metering data of the first electric energy meter and the second electric energy meter in the historical period, and obtain the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; calculate the actual demand of the power consuming enterprise in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; determine the maximum demand of the power consuming enterprise based on the actual demand of the power consuming enterprise in each unit time period.

[0130] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 600 includes: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program 603, the steps in the above-mentioned method embodiments are implemented, for example Figure 1 Alternatively, when the processor 601 executes the computer program 603, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of the communication module 501 and the processing module 502 are shown.

[0131] Exemplarily, the computer program 603 may be divided into one or more modules / units, which are stored in the memory 602 and executed by the processor 601 to implement the present invention. The one or more modules / units may be capable of implementing a particular Figure 3 A series of computer program instruction segments with certain functions, which are used to describe the execution process of the computer program 603 in the electronic device 600. For example, the computer program 603 can be divided into Figure 3 A communication module 501 and a processing module 502 are shown.

[0132] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0133] The memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. The memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 600. Further, the memory 602 may also include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store the computer program and other programs and data required by the terminal. The memory 602 may also be used to temporarily store data that has been output or is to be output.

[0134] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for calculating demand based on photovoltaic power generation, characterized in that: include: Obtaining metering data of a first electric energy meter and a second electric energy meter in a historical period; The first electric energy meter is used to measure the power generated by photovoltaic power generation within the power-consuming enterprise, and the second electric energy meter is used to measure the transmission power between the power-consuming enterprise and the power grid; Based on the metering data of the first electric energy meter and the second electric energy meter in the historical period, unit time periods are divided to obtain metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; Calculate the actual demand of the electricity user in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; Based on the actual demand of the electricity consuming enterprise in each unit time period, the maximum demand of the electricity consuming enterprise is determined.

2. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: The calculating the actual demand of the electricity consuming enterprise in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods includes: Based on the sum of the metering data of the first electric energy meter and the metering data of the second electric energy meter in each unit time period, the actual demand of the electricity consuming enterprise in each unit time period is determined.

3. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: The determining of the maximum demand of the electricity consuming enterprise based on the actual demand of the electricity consuming enterprise in each unit time period includes: Based on the actual demand of electricity users in each unit time period, the maximum daily and monthly demand of electricity users is calculated.

4. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: The method further comprises: Acquire multivariate data of the area of ​​the electricity user in the historical period; the multivariate data includes seasonal data, peak and valley data, holiday data and weather data; Dividing the unit time period based on the multivariate data of the area of ​​the electricity consuming enterprise in the historical period to obtain the multivariate data of each unit time period; Based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods, the actual demand of the power user in each unit time period, and the multivariate data of each unit time period, feature extraction and fusion are performed to obtain the load characteristics of the power user in each unit time period; Based on the load characteristics of the power user in each unit time period, a plurality of training samples are generated; wherein each training sample takes the load characteristics of a plurality of consecutive unit time periods as an input vector and takes the load characteristics of a plurality of consecutive unit time periods after the plurality of consecutive unit time periods as an output vector; Based on the training samples, neural network training is performed to obtain a load forecasting model.

5. The method for calculating demand based on photovoltaic power generation according to claim 4, characterized in that: The method further comprises: Determine load characteristics of multiple unit time periods before the current moment based on metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods before the current moment, and multivariate data; Generate an input vector at the current moment based on the load characteristics of multiple unit periods before the current moment; Based on the input vector at the current moment and the load forecasting model, a load forecasting result is predicted, wherein the load forecasting result includes load characteristics of multiple unit time periods after the current moment; Based on the load forecast result, determining the forecast demand of the electricity consuming enterprise in multiple unit time periods after the current moment; Based on the predicted demand of the electricity consuming enterprise in a plurality of unit time periods after the current moment, the predicted maximum demand of the electricity consuming enterprise in the predicted time period after the current moment is determined.

6. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: After determining the maximum demand of the electricity consuming enterprise based on the actual demand of the electricity consuming enterprise in each unit time period, the method further includes: Based on the maximum demand of the electricity consuming enterprise and a preset demand unit price, the basic electricity fee of the electricity consuming enterprise is determined.

7. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: The method further comprises: Based on the maximum demand and predicted maximum demand of the electricity user in the current metering period, calculating the demand difference of the current metering period; the current metering period includes multiple unit time periods; If the demand difference in the current metering period is greater than the set difference, the metering data of the first electric energy meter and the second electric energy meter in the current metering period are calibrated to obtain a calibration result; Based on the verification result, an alarm message is generated, wherein the alarm message is used to instruct the staff to confirm the verification result and the measurement data of the current measurement cycle; Receive the confirmation result from the staff, where the confirmation result includes whether the measurement data is normal or abnormal; If the confirmation result shows that the metering data is normal, the training samples are regenerated based on the metering data of the current metering period, and the load forecasting model is updated based on the regenerated training samples.

8. The method for calculating demand based on photovoltaic power generation according to claim 1, characterized in that: The step of verifying the metering data of the first electric energy meter and the second electric energy meter in the current metering cycle to obtain a verification result includes: Based on the multivariate data of the current metering cycle, query the database to obtain metering data of multiple metering cycles similar to the multivariate data of the current metering cycle; the database stores multivariate data, metering data and demand data of the area where the electricity user is located in the historical period; Based on the metering data of the multiple metering cycles and the multivariate data of the current metering cycle, a unit time period data comparison is performed to determine the calibration data of each unit time period in the current metering cycle, wherein the calibration data includes the photovoltaic power generation power difference, the power grid transmission power difference, the maximum demand difference and the average demand difference; The calibration result is generated based on the calibration data of each unit time period in the current metering cycle.

9. A demand calculation device based on photovoltaic power generation, characterized in that: include: A communication module, used for obtaining metering data of the first electric energy meter and the second electric energy meter in a historical period; The first electric energy meter is used to measure the power generated by photovoltaic power generation within the power-consuming enterprise, and the second electric energy meter is used to measure the transmission power between the power-consuming enterprise and the power grid; A processing module, configured to divide the measurement data of the first electric energy meter and the second electric energy meter in the historical period into unit time periods, and obtain the measurement data of the first electric energy meter and the second electric energy meter in a plurality of unit time periods; Calculate the actual demand of the electricity user in each unit time period based on the metering data of the first electric energy meter and the second electric energy meter in multiple unit time periods; Based on the actual demand of the electricity consuming enterprise in each unit time period, the maximum demand of the electricity consuming enterprise is determined.

10. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 8.

Images