CN114036820A - Method and system for calculating electric quantity lost by abnormal equipment string and computer equipment - Google Patents
Method and system for calculating electric quantity lost by abnormal equipment string and computer equipment Download PDFInfo
- Publication number
- CN114036820A CN114036820A CN202111210412.4A CN202111210412A CN114036820A CN 114036820 A CN114036820 A CN 114036820A CN 202111210412 A CN202111210412 A CN 202111210412A CN 114036820 A CN114036820 A CN 114036820A
- Authority
- CN
- China
- Prior art keywords
- string
- abnormal
- current
- group
- current date
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 219
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003062 neural network model Methods 0.000 claims abstract description 54
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 238000010606 normalization Methods 0.000 claims description 46
- 238000010248 power generation Methods 0.000 claims description 29
- 230000002354 daily effect Effects 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 3
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Geometry (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to a method and a system for calculating electric quantity lost by abnormal group strings of equipment and computer equipment, wherein the method comprises the following steps: acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label; determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment; simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date; and determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment corresponding to the current date and the acquired current and voltage data of the abnormal string. According to the technical scheme provided by the invention, the electric quantity loss value caused by abnormal string in the photovoltaic equipment can be quantized, and the accuracy is high.
Description
Technical Field
The invention relates to the field of abnormal string electric quantity loss in photovoltaic equipment, in particular to a method and a system for calculating the abnormal string electric quantity loss of the equipment and computer equipment.
Background
With the popularization of photovoltaic power stations, the photovoltaic power stations have strong requirements on economic and efficient operation and maintenance of the power stations. A photovoltaic power plant typically includes a string inverter and a plurality of photovoltaic strings, each photovoltaic string including a plurality of photovoltaic modules. A plurality of photovoltaic strings are connected to the same string inverter, and the string inverter converts direct current into alternating current so as to be connected to a power grid. The method is characterized in that the power station is strongly critical to economical and efficient operation and maintenance of the power station by recognizing abnormal photovoltaic strings in advance and calculating the electric quantity loss generated by the abnormal photovoltaic strings.
At present, only an abnormal string identification method is used, and electric quantity loss caused by abnormal strings is not quantified, so that a power station cannot be subjected to fine management, and further cannot stably operate.
Disclosure of Invention
The application provides a method and a system for calculating the electric quantity lost by an abnormal group string of equipment and computer equipment, which are used for at least solving the technical problem that the electric quantity lost by the abnormal group string in the related technology cannot be quantized.
An embodiment of a first aspect of the present application provides a method for calculating a power loss of an abnormal group of devices, including:
acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date;
and determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment corresponding to the current date and the acquired current and voltage data of the abnormal string.
An embodiment of a second aspect of the present application provides a system for calculating a power loss of an abnormal group of devices, including:
the photovoltaic equipment comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
the first determining module is used for determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
the second acquisition module is used for simultaneously inputting the current of each normal group string at each moment at the current date into the pre-established full-connection neural network model corresponding to each abnormal group string, and respectively acquiring the predicted current of each abnormal group string at each moment at the current date;
and the second determining module is used for determining daily loss electric quantity caused by abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment at the current date and the acquired current and voltage data of the abnormal string.
A computer storage medium provided in an embodiment of the third aspect of the present application, where the computer storage medium stores computer-executable instructions; the computer executable instructions, when executed by a processor, are capable of performing the method of the first aspect as described above.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
the invention provides a method and a system for calculating the electric quantity lost by an abnormal group string of equipment and computer equipment, wherein current and voltage data of each group string of photovoltaic equipment at each moment on the current date and a group string day abnormal label are obtained firstly; then, determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all group strings in the photovoltaic equipment; then, simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date; and finally, determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment under the current date and the acquired current and voltage data of the abnormal string. According to the technical scheme provided by the invention, the electric quantity loss caused by abnormal string in the equipment is quantized, so that the management of the power station can be refined, and the power grid can run safely and stably.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a method for calculating a power loss of an abnormal group of devices according to an embodiment of the present application;
fig. 2 is a specific flowchart of a daily power loss calculation method for an abnormal string in a device according to an embodiment of the present application;
FIG. 3 is a graph of predicted current error provided in accordance with one embodiment of the present application;
fig. 4 is a block diagram of a system for calculating power loss of an abnormal group of devices according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
In the method and the system for calculating the electric quantity lost by the abnormal group strings of the equipment and the computer equipment, current and voltage data of each group string of the photovoltaic equipment at each moment on the current date and a group string day abnormal label are obtained firstly; then, determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all group strings in the photovoltaic equipment; then, simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date; and finally, determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment under the current date and the acquired current and voltage data of the abnormal string. According to the technical scheme provided by the invention, the electric quantity loss caused by abnormal string in the equipment is quantized, so that the management of the power station can be refined, and the power grid can run safely and stably.
Example 1
Fig. 1 is a flowchart of a method for calculating power loss of an abnormal group of devices according to an embodiment of the present disclosure, and as shown in fig. 1, the method includes:
step 1: acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
step 2: determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
and step 3: simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date;
and 4, step 4: and determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment corresponding to the current date and the acquired current and voltage data of the abnormal string.
Wherein, before step 3, the method further comprises:
and establishing a full-connection neural network model corresponding to each abnormal group string on the current date.
Specifically, the process of establishing the fully-connected neural network model includes:
step a: acquiring current of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date and abnormal tag data of each group of strings in the photovoltaic equipment;
for example, the current of each group of strings in the photovoltaic device 30 days before the current date and the abnormal tag data of each group of strings at each moment are obtained.
Step b: cleaning the acquired current data of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date based on the daily abnormal label data;
it should be noted that, the cleaning, based on the daily abnormal label data, the acquired current data of each group of strings in the photovoltaic device at each time in the preset time period before the current date includes:
and if the day abnormal label data of the string group shows that the string group is abnormal on the corresponding date, setting the current data of the string group on the corresponding date as a null value.
For example, the abnormal group string number in each day in 30 days is determined based on the acquired abnormal day tag of each group string in 30 days, and the current data of the abnormal group string in each day is set to be a null value;
step c: respectively carrying out transverse normalization and longitudinal normalization on the cleaned data to obtain current data after transverse normalization and current data after longitudinal normalization;
it should be noted that the lateral normalization includes: performing transverse normalization based on the maximum and minimum values of each group of string current values in a preset time period;
the longitudinal normalization comprises: performing longitudinal normalization based on the maximum and minimum values of the current values of all groups of a certain device every day;
determining the current value W of the current value of the mth group string at the moment j in the preset time period and performing transverse normalization according to the following formulam,j：
In the formula Im,jThe current value of the mth group string at the moment j in the preset time period belongs to h, and h is a set of all the moments in the preset time period;
determining the current value W of the current value of the mth group string of a certain device in the preset time period d at the moment j in the preset time period after longitudinal normalization according to the following formulad m,j：
In the formula (I), the compound is shown in the specification,
the method comprises the steps that the current value of a certain equipment group string with the number m in a preset time period D at the moment j in the preset time period is set as D, D is the number of days in the preset time period, T is set as T, T is a set formed by all the moments in one day in the preset time period, and n is a set of the serial numbers of a certain equipment group string in a photovoltaic power station.
Step d: respectively selecting the current data after transverse normalization and the current data after longitudinal normalization required when the fully-connected neural network model corresponding to each abnormal group string is established according to the number of each abnormal group string in the photovoltaic equipment corresponding to the current date;
it should be noted that if the group 1 string and the group 2 string in the photovoltaic device are abnormal at the current date, when the fully-connected neural network model corresponding to the group 1 string is trained, other normalized data except the current data corresponding to the group 2 string within 30 days are selected.
Step e: inputting current data which is required by transversely normalizing a normal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by transversely normalizing an abnormal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully connected neural network model to obtain a first fully connected neural network model corresponding to the qth abnormal string;
inputting current data which is required by longitudinal normalization of a normal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by longitudinal normalization of an abnormal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully-connected neural network model to obtain a second fully-connected neural network model corresponding to the qth abnormal string;
it should be noted that the initial fully-connected neural network model includes: one input layer, one hidden layer and one output layer.
For example, when the group strings No. 1 and No. 2 in the photovoltaic device are abnormal at the current date, when the first fully-connected neural network model corresponding to the jth moment of the group string No. 1 is established, the data corresponding to the jth moment of the other group strings except the data corresponding to the group string No. 1 in the selected horizontal normalization data is used as input, the data corresponding to the jth moment of the group string No. 1 in the selected horizontal normalization data is used as output, the initial fully-connected neural network model is input, and the first fully-connected neural network model corresponding to the jth moment of the group string No. 1 is obtained.
Step f: respectively calculating the mean square error loss values of the predicted current data of the abnormal string at each moment in a preset time period output by the first fully-connected neural network model and the corresponding current data obtained in the step a, judging whether each mean square error loss value is less than or equal to a preset loss threshold value, if so, finishing the training of the corresponding model, otherwise, adjusting the model parameters by a back propagation algorithm and a gradient descent method until the mean square error loss value is less than or equal to the preset loss threshold value;
step g: when training is completed, selecting a model corresponding to the value with the minimum mean square error loss value as a full-connection neural network model corresponding to the qth abnormal string;
step h: and e, returning to the step e until Q is equal to Q, wherein Q is the total number of the abnormal group strings in the photovoltaic equipment on the current date.
The step 4 specifically comprises the following steps:
respectively determining the actual power generation amount of each abnormal group string at the current date according to the current and voltage data of each time of each abnormal group string at the current date;
respectively determining the corresponding power generation amount of each abnormal group string on the current date according to the predicted flow and voltage data of each time of each abnormal group string on the current date;
and determining the daily abnormal power loss of the photovoltaic power station string based on the actual power generation amount of each abnormal string and the corresponding power generation amount of each abnormal string at the current date.
Wherein the actual power generation amount R of the f-th abnormal string at the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fIs the voltage value at the t moment of the f-th abnormal string at the current date, It fThe current value at the t moment of the f-th abnormal string at the current date is the current value, and E is a preset duration coefficient;
the amount of power generation A of the f-th abnormal string on the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fThe voltage value at the time t of the f-th abnormal string at the current date,
and E is a preset duration coefficient, and is the predicted current value of the f-th abnormal string at the moment t at the current date.
The method for determining the abnormal daily loss electric quantity of the photovoltaic power station string based on the actual electric quantity of each abnormal string and the corresponding electric quantity of each abnormal string at the current date comprises the following steps:
acquiring the sum of the real power generation amount and the sum of the required power generation amount of each abnormal photovoltaic group string in the photovoltaic power station at the current date;
and subtracting the sum of the power generation amount and the sum of the actual electric quantity to obtain the abnormal loss electric quantity of the photovoltaic power station string at the current date.
The specific method of the present application is exemplified by combining the above calculation of the electric quantity lost by the abnormal group of the equipment:
as shown in fig. 2, a specific flowchart of a daily power loss calculation method for an abnormal string in a device is provided, where the method includes:
firstly, acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date, acquiring abnormal tags of the group strings at each moment on the current date, and acquiring current and voltage data of each group of strings in 30 days before the current date; secondly, performing data cleaning based on the group of string-day abnormal label data; then, carrying out transverse normalization and longitudinal normalization on the data; then, constructing a fully-connected neural network model, determining a loss function MSE, and adjusting model parameters based on loss values corresponding to the model to obtain two fully-connected neural network models; and then preferentially selecting a full-connection neural network model to predict the abnormal string current, and calculating the daily loss electric quantity of the photovoltaic equipment based on the predicted current value.
The method is tested, as shown in fig. 3, the error between the current predicted by the trained model and the actual current value is extremely small, and the prediction accuracy is ensured.
In summary, the method for calculating the electric quantity lost by the abnormal string in the equipment provided by the invention can be used for finely managing the power station by quantifying the electric quantity lost by the abnormal string in the equipment, so that the power grid can run safely and stably.
Example 2
Fig. 2 is a structural diagram of a system for calculating power loss of an abnormal group of devices according to an embodiment of the present disclosure, and as shown in fig. 2, the system includes:
the photovoltaic equipment comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
the first determining module is used for determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
the second acquisition module is used for simultaneously inputting the current of each normal group string at each moment at the current date into the pre-established full-connection neural network model corresponding to each abnormal group string, and respectively acquiring the predicted current of each abnormal group string at each moment at the current date;
and the second determining module is used for determining daily loss electric quantity caused by abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment at the current date and the acquired current and voltage data of the abnormal string.
Specifically, the process of establishing the fully-connected neural network model corresponding to each abnormal group string includes:
step a: acquiring current of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date and abnormal tag data of each group of strings in the photovoltaic equipment;
step b: cleaning the acquired current data of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date based on the daily abnormal label data;
step c: respectively carrying out transverse normalization and longitudinal normalization on the cleaned data to obtain current data after transverse normalization and current data after longitudinal normalization;
step d: respectively selecting the current data after transverse normalization and the current data after longitudinal normalization required when the fully-connected neural network model corresponding to each abnormal group string is established according to the number of each abnormal group string in the photovoltaic equipment corresponding to the current date;
step e: inputting current data which is required by transversely normalizing a normal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by transversely normalizing an abnormal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully connected neural network model to obtain a first fully connected neural network model corresponding to the qth abnormal string;
inputting current data which is required by longitudinal normalization of a normal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by longitudinal normalization of an abnormal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully-connected neural network model to obtain a second fully-connected neural network model corresponding to the qth abnormal string;
step f: respectively calculating the mean square error loss values of the predicted current data of the abnormal string at each moment in a preset time period output by the first fully-connected neural network model and the corresponding current data obtained in the step a, judging whether each mean square error loss value is less than or equal to a preset loss threshold value, if so, finishing the training of the corresponding model, otherwise, adjusting the model parameters by a back propagation algorithm and a gradient descent method until the mean square error loss value is less than or equal to the preset loss threshold value;
step g: when training is completed, selecting a model corresponding to the value with the minimum mean square error loss value as a full-connection neural network model corresponding to the qth abnormal string;
step h: and e, returning to the step e until Q is equal to Q, wherein Q is the total number of the abnormal group strings in the photovoltaic equipment on the current date.
In this embodiment, the cleaning, based on the daily abnormal label data, the acquired current data of each group of strings in the photovoltaic device at each time in a preset time period before the current date includes:
and if the day abnormal label data of the string group shows that the string group is abnormal on the corresponding date, setting the current data of the string group on the corresponding date as a null value.
Wherein the lateral normalization comprises: performing transverse normalization based on the maximum and minimum values of each group of string current values in a preset time period;
the longitudinal normalization comprises: performing longitudinal normalization based on the maximum and minimum values of all the group string current values every day;
determining the current value W of the current value of the mth group string at the moment j in the preset time period and performing transverse normalization according to the following formulam,j：
In the formula, Wm,jThe current value of the mth group string at the moment j in the preset time period belongs to h, and h is a set of all the moments in the preset time period;
determining the current value W of the current value of the m number group string of a certain device in the preset time period d at the moment j in the preset time period after longitudinal normalization according to the following formulad m,j：
In the formula (I), the compound is shown in the specification,
the method comprises the steps that the current value of a certain equipment group string with the number m in a preset time period D at the moment j in the preset time period is set as D, D is the number of days in the preset time period, T is set as T, T is a set formed by all the moments in one day in the preset time period, and n is a set of the serial numbers of a certain equipment group string in a photovoltaic power station.
Specifically, the second determining module includes:
the first determining unit is used for respectively determining the actual power generation amount of each abnormal group string at the current date according to the current and voltage data of each time of each abnormal group string at the current date;
the second determining unit is used for respectively determining the power generation amount of each abnormal group string on the current date according to the predicted flow and voltage data of each time of each abnormal group string on the current date;
and the third determining unit is used for determining the daily abnormal electric quantity loss of the photovoltaic power station string based on the actual electric quantity of each abnormal string at the current date and the corresponding electric quantity of each abnormal string.
Further, the actual power generation amount R of the f-th abnormal string at the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fIs the voltage value at the t moment of the f-th abnormal string at the current date, It fThe current value at the t moment of the f-th abnormal string at the current date is the current value, and E is a preset duration coefficient;
the amount of power generation A of the f-th abnormal string on the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fThe voltage value at the time t of the f-th abnormal string at the current date,
and E is a preset duration coefficient, and is the predicted current value of the f-th abnormal string at the moment t at the current date.
In this application, the third determining unit is specifically configured to:
and acquiring the sum of the actual power generation amount and the sum of the required power generation amount of each abnormal photovoltaic group string in the photovoltaic power station at the current date, and subtracting the sum of the required power generation amount and the sum of the actual power amount to obtain the abnormal loss power amount of the photovoltaic power station group string at the current date.
In summary, the present invention provides a system for calculating electric quantity lost by abnormal strings in equipment, which can perform fine management of power stations by quantifying electric quantity lost due to abnormal strings in equipment, so as to enable a power grid to operate safely and stably.
Example 3
In order to implement the above embodiments, the present disclosure also provides a computer device.
The computer device provided in this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method in embodiment 1 is implemented.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for calculating loss electric quantity of an abnormal group string of equipment is characterized by comprising the following steps:
acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
simultaneously inputting the current of each normal group string at each moment at the current date into a pre-established full-connection neural network model corresponding to each abnormal group string, and respectively obtaining the predicted current of each abnormal group string at each moment at the current date;
and determining the daily loss electric quantity caused by the abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment corresponding to the current date and the acquired current and voltage data of the abnormal string.
2. The method of claim 1, wherein the process of establishing the fully-connected neural network model corresponding to each abnormal string set comprises:
step a: acquiring current of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date and abnormal tag data of each group of strings in the photovoltaic equipment;
step b: cleaning the acquired current data of each group of strings in the photovoltaic equipment at each moment in a preset time period before the current date based on the daily abnormal label data;
step c: respectively carrying out transverse normalization and longitudinal normalization on the cleaned data to obtain current data after transverse normalization and current data after longitudinal normalization;
step d: respectively selecting the current data after transverse normalization and the current data after longitudinal normalization required when the fully-connected neural network model corresponding to each abnormal group string is established according to the number of each abnormal group string in the photovoltaic equipment corresponding to the current date;
step e: inputting current data which is required by transversely normalizing a normal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by transversely normalizing an abnormal string and is used for establishing a fully connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully connected neural network model to obtain a first fully connected neural network model corresponding to the qth abnormal string;
inputting current data which is required by longitudinal normalization of a normal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as input, inputting current data which is required by longitudinal normalization of an abnormal string and is used for establishing a fully-connected neural network model corresponding to the qth abnormal string as output, and inputting the current data into the initial fully-connected neural network model to obtain a second fully-connected neural network model corresponding to the qth abnormal string;
step f: respectively calculating the mean square error loss values of the predicted current data of the abnormal string at each moment in a preset time period output by the first fully-connected neural network model and the corresponding current data obtained in the step a, judging whether each mean square error loss value is less than or equal to a preset loss threshold value, if so, finishing the training of the corresponding model, otherwise, adjusting the model parameters by a back propagation algorithm and a gradient descent method until the mean square error loss value is less than or equal to the preset loss threshold value;
step g: when training is completed, selecting a model corresponding to the value with the minimum mean square error loss value as a full-connection neural network model corresponding to the qth abnormal string;
step h: and e, returning to the step e until Q is equal to Q, wherein Q is the total number of the abnormal group strings in the photovoltaic equipment on the current date.
3. The method of claim 2, wherein the step of cleaning the acquired current data of the groups of strings in the photovoltaic device at each moment in a preset time period before the current date based on the daily anomaly tag data comprises:
and if the day abnormal label data of the string group shows that the string group is abnormal on the corresponding date, setting the current data of the string group on the corresponding date as a null value.
4. The method of claim 2, wherein the lateral normalization comprises: performing transverse normalization based on the maximum and minimum values of each group of string current values in a preset time period;
the longitudinal normalization comprises: performing longitudinal normalization based on the maximum and minimum values of all the group string current values every day;
determining the current value W of the current value of the mth group string at the moment j in the preset time period and performing transverse normalization according to the following formulam,j：
In the formula, Wm,jThe current value of the mth group string at the moment j in the preset time period belongs to h, and h is a set of all the moments in the preset time period;
determining the current value W of the current value of the m number group string of a certain device in the preset time period d at the moment j in the preset time period after longitudinal normalization according to the following formulad m,j：
In the formula (I), the compound is shown in the specification,
the method comprises the steps that the current value of a certain equipment group string with the number m in a preset time period D at the moment j in the preset time period is set as D, D is the number of days in the preset time period, T is set as T, T is a set formed by all the moments in one day in the preset time period, and n is a set of the serial numbers of a certain equipment group string in a photovoltaic power station.
5. The method of claim 1, wherein the determining the daily loss electric quantity caused by the abnormality of the photovoltaic device string based on the predicted current at each time corresponding to each abnormal string on the current date and the acquired current and voltage data of the abnormal string comprises:
respectively determining the actual power generation amount of each abnormal group string at the current date according to the current and voltage data of each time of each abnormal group string at the current date;
respectively determining the corresponding power generation amount of each abnormal group string on the current date according to the predicted flow and voltage data of each time of each abnormal group string on the current date;
and determining the daily abnormal power loss of the photovoltaic power station string based on the actual power generation amount of each abnormal string and the corresponding power generation amount of each abnormal string at the current date.
6. The method according to claim 5, wherein the actual power generation amount R of the f-th abnormal group string at the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fIs the voltage value at the t moment of the f-th abnormal string at the current date, It fThe current value at the t moment of the f-th abnormal string at the current date is the current value, and E is a preset duration coefficient;
the amount of power generation A of the f-th abnormal string on the current datefThe calculation formula of (a) is as follows:
in the formula of Ut fThe voltage value at the time t of the f-th abnormal string at the current date,
and E is a preset duration coefficient, and is the predicted current value of the f-th abnormal string at the moment t at the current date.
7. The method of claim 6, wherein determining the abnormal daily lost power of the photovoltaic power plant string based on the actual power generation amount of the abnormal string at the current date and the expected power generation amount of the abnormal string comprises:
acquiring the sum of the real power generation amount and the sum of the required power generation amount of each abnormal photovoltaic group string in the photovoltaic power station at the current date;
and subtracting the sum of the power generation amount and the sum of the actual electric quantity to obtain the abnormal loss electric quantity of the photovoltaic power station string at the current date.
8. An equipment abnormal string power loss calculation system, the system comprising:
the photovoltaic equipment comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring current and voltage data of each group of strings in the photovoltaic equipment at each moment on the current date and a group string day abnormal label;
the first determining module is used for determining abnormal group strings and normal group strings in the photovoltaic equipment corresponding to the current date by using group string day abnormal labels of all the group strings in the photovoltaic equipment;
the second acquisition module is used for simultaneously inputting the current of each normal group string at each moment at the current date into the pre-established full-connection neural network model corresponding to each abnormal group string, and respectively acquiring the predicted current of each abnormal group string at each moment at the current date;
and the second determining module is used for determining daily loss electric quantity caused by abnormality of the photovoltaic equipment string based on the predicted current of each abnormal string at each moment at the current date and the acquired current and voltage data of the abnormal string.
9. The system of claim 8, wherein the second determination module comprises:
the first determining unit is used for respectively determining the actual power generation amount of each abnormal group string at the current date according to the current and voltage data of each time of each abnormal group string at the current date;
the second determining unit is used for respectively determining the power generation amount of each abnormal group string on the current date according to the predicted flow and voltage data of each time of each abnormal group string on the current date;
and the third determining unit is used for determining the daily abnormal electric quantity loss of the photovoltaic power station string based on the actual electric quantity of each abnormal string at the current date and the corresponding electric quantity of each abnormal string.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111210412.4A CN114036820B (en) | 2021-10-18 | 2021-10-18 | Method and system for calculating lost electric quantity of abnormal equipment strings and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111210412.4A CN114036820B (en) | 2021-10-18 | 2021-10-18 | Method and system for calculating lost electric quantity of abnormal equipment strings and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114036820A true CN114036820A (en) | 2022-02-11 |
| CN114036820B CN114036820B (en) | 2024-07-12 |
Family
ID=80135260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111210412.4A Active CN114036820B (en) | 2021-10-18 | 2021-10-18 | Method and system for calculating lost electric quantity of abnormal equipment strings and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114036820B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539550A (en) * | 2020-03-13 | 2020-08-14 | 远景智能国际私人投资有限公司 | Method, device and equipment for determining working state of photovoltaic array and storage medium |
| CN111740698A (en) * | 2020-07-01 | 2020-10-02 | 江苏新塔物联网研究院有限公司 | Photovoltaic module parameter on-line monitoring and fault diagnosis system |
| CN113074773A (en) * | 2020-01-03 | 2021-07-06 | 四方特变电工智能电气有限公司 | Intelligent non-electric quantity online monitoring device and method for mutual inductor |
| WO2021179700A1 (en) * | 2020-03-12 | 2021-09-16 | 深圳前海微众银行股份有限公司 | Electricity generation prediction method, apparatus and device, and computer readable storage medium |
-
2021
- 2021-10-18 CN CN202111210412.4A patent/CN114036820B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113074773A (en) * | 2020-01-03 | 2021-07-06 | 四方特变电工智能电气有限公司 | Intelligent non-electric quantity online monitoring device and method for mutual inductor |
| WO2021179700A1 (en) * | 2020-03-12 | 2021-09-16 | 深圳前海微众银行股份有限公司 | Electricity generation prediction method, apparatus and device, and computer readable storage medium |
| CN111539550A (en) * | 2020-03-13 | 2020-08-14 | 远景智能国际私人投资有限公司 | Method, device and equipment for determining working state of photovoltaic array and storage medium |
| CN111740698A (en) * | 2020-07-01 | 2020-10-02 | 江苏新塔物联网研究院有限公司 | Photovoltaic module parameter on-line monitoring and fault diagnosis system |
Non-Patent Citations (1)
| Title |
|---|
| 郑建飞;刘恒;王海明;郑海;: "确保地面光伏电站多发电量的实践", 水电与新能源, no. 11, 30 November 2017 (2017-11-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114036820B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10289765B2 (en) | Fast model generating and solving method for security-constrained power system operation simulation | |
| US8996185B2 (en) | Method for scheduling power generators based on optimal configurations and approximate dynamic programming | |
| Dehghani et al. | Adaptive network reliability analysis: Methodology and applications to power grid | |
| Mohammadi et al. | Machine learning assisted stochastic unit commitment during hurricanes with predictable line outages | |
| CN113159341A (en) | Power distribution network aid decision-making method and system integrating deep reinforcement learning and expert experience | |
| Yao et al. | Management of cascading outage risk based on risk gradient and Markovian tree search | |
| CN106776316A (en) | A kind of power information software defect prevention method | |
| CN115564310A (en) | Reliability evaluation method for new energy power system based on convolutional neural network | |
| CN116014722A (en) | Sub-solar photovoltaic power generation prediction method and system based on seasonal decomposition and convolution network | |
| CN117634971A (en) | Roadbed construction quality control method and system based on multi-source data | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN110991729A (en) | Load prediction method based on transfer learning and multi-head attention mechanism | |
| CN117557047A (en) | Power distribution equipment operation and maintenance optimization method and system based on deep reinforcement learning | |
| CN117787915A (en) | Digital twin intelligent brain construction method for power distribution network | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN109242304B (en) | Method for evaluating reliability of small-probability event of power system | |
| CN111864728B (en) | Important equipment identification method and system for reconfigurable power distribution network | |
| ul Hassan et al. | Online static security assessment for cascading failure using stacked De-noising Auto-encoder | |
| CN114036820B (en) | Method and system for calculating lost electric quantity of abnormal equipment strings and computer equipment | |
| CN113128130B (en) | Real-time monitoring method and device for judging stability of direct-current power distribution system | |
| CN114759579A (en) | Power grid active power optimization control system, method and medium based on data driving | |
| Shan et al. | Root Cause Analysis of Failures for Power Communication Network Based on CNN | |
| CN113793003A (en) | Toughness improvement-oriented electric power system maintenance and operation cooperative decision method | |
| CN111682574B (en) | Method for identifying running scene of alternating current-direct current hybrid system, storage medium and equipment | |
| CN110322113A (en) | Based on markovian Line Loss of Distribution Network System processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |