Electric power market operation simulation deduction system with green value cooperation

Abstract

The invention, which relates to the technical field of green energy, discloses a green value-coordinated power market operation simulation deduction system comprising a feature record extraction module used for obtaining historical carbon emission records of a power enterprise and extracting feature records from the carbon emission records according to the carbon content and the power generation amount in the carbon emission records; the deviation range calculation module is used for analyzing carbon content and generating capacity changes in the characteristic records to obtain a deviation range; the data correction module is used for acquiring a current carbon emission record, obtaining data with abnormal carbon content and correcting the data; and the early warning prompt module is used for judging whether to carry out early warning on the data correction technology or not according to the corrected virtual carbon content. According to the method, the current carbon content correction data is analyzed by summarizing the historical carbon emission rule, whether the current data correction technology needs to be prompted or not is judged, and the accuracy and rationality of current data restoration are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of green energy, and specifically to a simulation and deduction system for the operation of a power market with coordinated green value. Background Art

[0002] In the current power market, the accuracy of carbon emission data is of great significance to the industry development and environmental protection decision-making. At present, the emission factor method, the mass balance method, and the actual measurement method are commonly used carbon emission accounting means. Among them, the actual measurement method relies on analyzing the actual data obtained by deploying sensors to obtain corresponding results. However, during the process of monitoring or transmitting data by sensors, problems such as data loss may occur due to equipment or network failures. Although there are currently various technologies to correct the missing data, the actual situation of power enterprises during the carbon emission process and the historical carbon emission rules are not taken into account, resulting in the corrected data deviating from the actual situation from time to time. Summary of the Invention

[0003] The purpose of the present invention is to provide a simulation and deduction system for the operation of a power market with coordinated green value to solve the problems raised in the prior art.

[0004] To achieve the above purpose, the present invention provides the following technical solutions: A simulation and deduction system for the operation of a power market with coordinated green value, including a feature record extraction module, a deviation range calculation module, a data correction module, and a warning and prompt module; Feature record extraction module: used to obtain the historical carbon emission records of power enterprises, where the power enterprises are thermal power enterprises that generate electricity by burning carbon-containing energy fuels; monitor the carbon content and power generation at each moment during the power generation process through sensors, establish a carbon content line graph and a power generation line graph corresponding to each carbon emission record, and analyze the carbon content line graph and the power generation line graph to extract feature records from the carbon emission records; Deviation range calculation module: used to analyze the changes in carbon content and power generation at the same moment in the corresponding carbon content line graph and power generation line graph in the feature record, calculate the first deviation coefficient and the second deviation coefficient corresponding to the feature record, and then obtain the deviation range based on the first deviation coefficient and the second deviation coefficient; Data correction module: used to obtain the carbon emission record after transmitting the current sensor data to a computer program, analyze the carbon content and power generation in the carbon emission record to obtain the data with abnormal carbon content, and correct the abnormal data through data correction technology, and use the corrected value as the virtual carbon content; Warning and prompt module: used to obtain the warning coefficient of the corrected data based on the corrected virtual carbon content, judge whether to give a warning to the data correction technology according to the warning coefficient, and prompt relevant personnel to correct it again.

[0005] Furthermore, the feature record extraction module includes a carbon content line graph building unit, a power generation line graph building unit, and a feature record extraction unit; In this solution, the power enterprise is a thermal power enterprise that generates electricity by burning carbon-containing energy fuels. Thermal power generation usually uses fossil fuels such as coal, oil, and natural gas as energy sources. These fossil fuels are deposited from the fossils of ancient organisms and contain a large amount of carbon elements. For thermal power plants, a large amount of carbon dioxide is emitted during the combustion of fossil fuels such as coal. In order to monitor the emission situation and conduct environmental protection control, sensors generally have a fixed collection frequency; Carbon content line graph building unit: used to deploy a carbon content sensor at the pollutant emission port of the power enterprise, randomly extract the time period F during the power generation process corresponding to a certain historical carbon emission record; obtain the collection frequency of the carbon content sensor to get the interval duration g between two adjacent carbon content data collections. According to the interval duration g, collect the carbon content data of the carbon content sensor within the time period F. The number of carbon content data is m = F / g, and transmit it to the computer program to build a carbon content line graph; Power generation line graph building unit: used to deploy a power generation sensor for monitoring the power generation during the power generation process at the outlet end of the generator, obtain the collection frequency of the power generation sensor to get the interval duration h between two adjacent power generation data collections. According to the interval duration h, collect the power generation data of the power generation sensor within the time period F. The number of power generation data is n = F / h, and transmit it to the computer program to build a power generation line graph.

[0006] Based on the carbon content generated in real time at each moment during the power generation process, a carbon content line graph is obtained. Based on the power generation generated in real time at each moment, a power generation line graph is obtained; generally, due to the instantaneity of energy conversion, thermal power generation is a process of converting chemical energy into thermal energy and then into electrical energy by burning fossil fuels. In this process, the release of carbon dioxide and the generation of electrical energy by fuel combustion occur simultaneously. When the power generation increases, it means that more fuel is burned at the same moment, and inevitably more carbon dioxide emissions will be generated at the same time, so the carbon emissions will also immediately increase; conversely, when the power generation decreases, the fuel combustion amount decreases, and the carbon emissions will also immediately decrease. Therefore, generally speaking, the power generation line graph and the carbon content line graph of the thermal power plant move up and down together; Furthermore, the feature record extraction unit: used to obtain the DTW distance between the two line graphs using the dynamic time warping method according to the values of each element in the carbon content line graph and the power generation line graph. If the DTW distance is less than the preset distance threshold and the values of each element in the carbon content line graph and the power generation line graph are all greater than 0, then a certain carbon emission record is used as a feature record, and all feature records are obtained accordingly.

[0007] Further, the deviation range calculation module includes a feature record analysis unit and a deviation range calculation unit; Feature record analysis unit: used to obtain the carbon emission line chart L c and the power generation line chart L e The total time period corresponding to the line charts L c and L e is both F; randomly obtain Q moments from the time period F, and obtain the ratio of the carbon content to the power generation corresponding to each moment, a total of Q ratios are obtained, and the minimum and maximum values of the ratios are extracted; furthermore, the minimum and maximum values of the ratios corresponding to each feature record are obtained.

[0008] Dynamic Time Warping (DTW) is an algorithm for measuring the similarity between two time series, which is an existing technology, including steps such as constructing a distance matrix, initializing the cumulative distance matrix, filling the cumulative distance matrix, and calculating the DTW distance, which will not be elaborated here. The advantage of dynamic time warping is that it can effectively handle the similarity calculation between time series with different lengths. In this solution, due to the different acquisition frequencies of the carbon content sensor and the power generation sensor, the number of elements in the obtained carbon content line chart and power generation line chart is also different, which are m and n respectively. Therefore, using dynamic time warping here can more conveniently and quickly obtain the DTW distance between the two line charts. Since the larger the DTW distance, the greater the difference between the two sequences in time, that is, the smaller the similarity between the two line charts. Therefore, the smaller the DTW distance here, and the value of each element in the carbon content line chart and the power generation line chart is greater than 0, indicating that the carbon emission record conforms more to the actual change law. Therefore, this part of the carbon emission record is used as a feature record; Further, the deviation range calculation unit: uses the total number of feature records as D, extracts the record time corresponding to each feature record, and sorts the feature records from 1 to D in the order from front to back according to the record time, and adds up all the serial numbers to get the serial number sum S D Furthermore, the weight of the feature record with serial number d is obtained as W d =d / S D , where 1≤d≤D; according to the minimum value, maximum value and weight of the ratio corresponding to each feature record, the first deviation coefficient is obtained as , where R min d is the minimum value of the ratio of the feature record with serial number d, and the second deviation coefficient is obtained as , where R max d is the maximum value of the ratio of the feature record with serial number d. Furthermore, the deviation range is [R 1, R 2 .

[0009] Further, the data correction module includes a to-be-detected set determination unit, an objective function establishment unit, and a data correction unit; To-be-detected set determination unit: used to extract the carbon content and power generation at each moment in the current carbon emission record; among them, if the next moment of a certain moment a is b, and the difference in carbon content between moment a and moment b is greater than a preset difference threshold, or the ratio result of the carbon content of moment a to the power generation is not within the deviation range, then moment a is marked; all marked moments are obtained, and all adjacent marked moments are used as a to-be-detected set, and several to-be-detected sets are obtained.

[0010] Here, for the reliability of data calculation, the power generation sensor is a sensor that has passed inspection and has a qualified quality inspection result.

[0011] Further, the objective function establishment unit: used to take the moment before the earliest moment in a certain to-be-detected set as T 1 , the moment after the latest moment as T 2 , and take a certain moment in a certain to-be-detected set as T x ; take the actual carbon content corresponding to moment T 1 , moment T 2 and moment T x as C 1 , C 2 and C x ; establish an objective function for the change of carbon content over time, and mark the position points (T 1 , C 1 ) and the position point (T 2 , C 2 ) in the objective function, and connect the two position points to obtain line segment S; Further, the data correction unit: used to obtain the carbon content C x corresponding to line segment S when the moment is T x 、 ; take the actual power generation at moment T x as E x , and according to the carbon content C x and C x 、 , if it satisfies that the ratio of C x divided by E x is outside the deviation range and the ratio of C x 、 divided by E x is within the deviation range, then the actual carbon content C xAs abnormal data; furthermore, all abnormal data are obtained, and all abnormal data are corrected according to the data correction technology, and the corrected value is used as the virtual carbon content.

[0012] There are many existing data correction technologies, such as mean filling method, K-nearest neighbor algorithm, multi-source data fusion correction, etc. If only the data itself is concerned when correcting data without combining the actual change law, it will lead to deviations in the correction results of the data correction technology and cannot accurately present the change trend of carbon content. Therefore, in this solution, it is necessary to analyze according to the power generation and the corresponding deviation range between the power generation and the carbon content to ensure the reliability of data calculation; Furthermore, the early warning prompt module includes an early warning prompt unit; Early warning prompt unit: used to obtain a certain corrected virtual carbon content y 0 , and the carbon content y 0 adjacent to the corresponding time before and after the virtual carbon content y 1 and y 2 , respectively obtain the power generation z 0 、y 1 and y 2 at the corresponding times of the carbon content y 0 、z 1 and z 2 , obtain the vector Y=(y 1 ,y 0 ,y 2 ) and the vector Z=(z 1 ,z 0 ,z 2 ), and obtain the cosine similarity between the vector Y and the vector Z as the eigenvalue corresponding to the carbon content y 0 . Furthermore, obtain the eigenvalues corresponding to several virtual carbon contents, and add them up and take the average as the early warning coefficient of the data correction technology. If the early warning coefficient is less than the preset coefficient threshold, give an early warning prompt for the current data correction technology and prompt relevant personnel to correct it again.

[0013] Cosine similarity is a method to measure the similarity between two vectors in a vector space. It is calculated based on the cosine value of the angle between vectors, and the value range is [-1,1]. When the cosine similarity is 1, it means that the two vectors are exactly the same, which is the most similar situation; when the cosine similarity is -1, it means that the two vectors are in exactly opposite directions, which is the least similar situation; when the cosine similarity is 0, it means that the two vectors are perpendicular to each other and have no similarity. Therefore, the closer to 1, the more similar the two vectors are.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a simulation and deduction system for the operation of a power market with coordinated green value, including: a feature record extraction module, which is used to obtain the historical carbon emission records of power enterprises, and extract feature records from the carbon emission records according to the carbon content and power generation amount in the carbon emission records; a deviation range calculation module, which is used to analyze the changes in carbon content and power generation amount in the feature records to obtain the deviation range; a data correction module, which is used to obtain the current carbon emission records, obtain the data with abnormal carbon content therein, and correct it; an early warning prompt module, which is used to judge whether to give an early warning to the data correction technology according to the corrected virtual carbon content. By summarizing the historical carbon emission rules and analyzing the current carbon content correction data, the present invention judges whether the current data correction technology needs to be prompted, which helps to improve the accuracy and rationality of the current data repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural diagram of the simulation and deduction system for the operation of a power market with coordinated green value of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment: As Figure 1 shown, the present invention provides a technical solution for a simulation and deduction system for the operation of a power market with coordinated green value, including a feature record extraction module, a deviation range calculation module, a data correction module, and an early warning prompt module; The feature record extraction module: It is used to obtain the historical carbon emission records of power enterprises, and the power enterprises are thermal power enterprises that generate electricity by burning carbon-containing energy fuels; monitor the carbon content and power generation amount at each moment during the power generation process through sensors, establish a carbon content line chart and a power generation amount line chart corresponding to each carbon emission record, and analyze the carbon content line chart and the power generation amount line chart to extract feature records from the carbon emission records; The feature record extraction module includes a carbon content line chart establishment unit, a power generation amount line chart establishment unit, and a feature record extraction unit; In this solution, the power enterprise is a thermal power enterprise that generates electricity by burning carbon-containing energy fuels. Thermal power usually uses fossil fuels such as coal, oil, and natural gas as energy sources. These fossil fuels are deposited from the fossils of ancient organisms and contain a large amount of carbon elements. For thermal power plants, a large amount of carbon dioxide is emitted during the combustion of fossil fuels such as coal. In order to monitor the emission situation and conduct environmental protection control, sensors generally have a fixed acquisition frequency. In this embodiment, the carbon content sensor has an acquisition frequency of 10 seconds per time, and the power generation sensor has an acquisition frequency of 12 seconds per time. The actual sensor acquisition frequency depends on the actual situation.

[0018] Carbon content line graph establishment unit: used to deploy a carbon content sensor at the pollutant emission outlet of the power enterprise, randomly extract the time period F during the power generation process corresponding to a certain historical carbon emission record; obtain the acquisition frequency of the carbon content sensor, get the interval duration g between two adjacent carbon content data acquisitions, and according to the interval duration g, collect the carbon content data of the carbon content sensor during the time period F. The number of carbon content data is m = F / g, and transmit it to the computer program to establish a carbon content line graph; Power generation line graph establishment unit: used to deploy a power generation sensor for monitoring the power generation during the power generation process at the generator outlet end, obtain the acquisition frequency of the power generation sensor, get the interval duration h between two adjacent power generation data acquisitions, and according to the interval duration h, collect the power generation data of the power generation sensor during the time period F. The number of power generation data is n = F / h, and transmit it to the computer program to establish a power generation line graph; According to the carbon content generated in real time at each moment during the power generation process, a carbon content line graph is obtained. According to the power generation generated in real time at each moment, a power generation line graph is obtained; Generally, due to the instantaneity of energy conversion, thermal power generation is a process of converting chemical energy into thermal energy and then into electrical energy by burning fossil fuels. In this process, the release of carbon dioxide and the generation of electrical energy by fuel combustion occur simultaneously. When the power generation increases, it means that more fuel is burned at the same moment, and more carbon dioxide emissions will inevitably be generated at the same time, so the carbon emissions will also immediately increase; conversely, when the power generation decreases, the fuel combustion amount decreases, and the carbon emissions will also immediately decrease. Therefore, generally speaking, the power generation line graph and the carbon content line graph of the thermal power plant move up and down together.

[0019] Feature record extraction unit: used to obtain the DTW distance between the two line graphs using the dynamic time warping method according to the numerical values of each element in the carbon content line graph and the power generation line graph. If the DTW distance is less than the preset distance threshold and the numerical values of each element in the carbon content line graph and the power generation line graph are all greater than 0, then a certain carbon emission record is used as a feature record, and then all feature records are obtained.

[0020] Dynamic Time Warping (DTW) is an algorithm used to measure the similarity between two time series. It is an existing technology, including steps such as constructing a distance matrix, initializing an accumulated distance matrix, filling the accumulated distance matrix, and calculating the DTW distance, which will not be elaborated here. The advantage of dynamic time warping is that it can effectively handle the similarity calculation between time series of different lengths. In this solution, since the sampling frequencies of the carbon content sensor and the power generation sensor are different, the number of elements in the obtained carbon content line chart and power generation line chart is also different, which are m and n respectively. Therefore, using dynamic time warping here can more conveniently and quickly obtain the DTW distance between the two line charts. Since the larger the DTW distance indicates the greater the difference in time between the two sequences, that is, the smaller the similarity between the two line charts, the smaller the DTW distance here, and the value of each element in the carbon content line chart and the power generation line chart is greater than 0, indicating that the carbon emission record conforms more to the actual change law. Therefore, this part of the carbon emission record is used as a feature record.

[0021] Deviation range calculation module: It is used to analyze the changes in carbon content and power generation at the same moment in the corresponding carbon content line chart and power generation line chart of the feature record, calculate the first deviation coefficient and the second deviation coefficient corresponding to the feature record, and then obtain the deviation range based on the first deviation coefficient and the second deviation coefficient; The deviation range calculation module includes a feature record analysis unit and a deviation range calculation unit; Feature record analysis unit: It is used to obtain the carbon emission line chart L corresponding to a certain feature record c and the power generation line chart L e , and the total time period corresponding to the line charts L c and L e is both F; randomly obtain Q moments from the time period F, obtain the ratio of the corresponding carbon content to the power generation at each moment, a total of Q ratios are obtained, and the minimum value and the maximum value of the ratios are extracted; furthermore, the minimum value and the maximum value of the ratios corresponding to each feature record are obtained; Deviation range calculation unit: It is used to take the total number of feature records as D, extract the recording moments corresponding to each feature record, and sort the feature records from 1 to D in the order of the recording moments from front to back, and add up all the serial numbers to obtain the serial number sum S D , and then obtain the weight of the feature record with the serial number d as W d =d / S D , where 1≤d≤D; according to the minimum value, maximum value and weight of the ratios corresponding to each feature record, the first deviation coefficient is obtained as , where, R min dThe minimum ratio value recorded for the feature with serial number d is obtained, and the second deviation coefficient is , where R max d is the maximum ratio value of the feature record with serial number d. Furthermore, the deviation range is obtained as [R 1 , R 2 .

[0022] Data correction module: It is used to obtain the carbon emission records after transmitting the current sensor data to the computer program, analyze the carbon content and power generation amount in the carbon emission records, obtain the data with abnormal carbon content, and correct the abnormal data through data correction technology, and use the corrected value as the virtual carbon content.

[0023] The data correction module includes a to-be-detected set determination unit, an objective function establishment unit, and a data correction unit; To-be-detected set determination unit: It is used to extract the carbon content and power generation amount at each moment in the current carbon emission record; among them, if the next moment of a certain moment a is b, and the difference in carbon content between moment a and moment b is greater than the preset difference threshold, or the ratio result of the carbon content and power generation amount at moment a is not within the deviation range, then moment a is marked; all marked moments are obtained, and all adjacent marked moments are used as a to-be-detected set, and several to-be-detected sets are obtained.

[0024] Objective function establishment unit: It is used to use the moment before the earliest moment in a certain to-be-detected set as T 1 , and the moment after the latest moment as T 2 , and use a certain moment in a certain to-be-detected set as T x ; use the actual carbon content corresponding to moment T 1 , moment T 2 and moment T x as C 1 , C 2 and C x ; establish an objective function for the change of carbon content over time, and mark the position points (T 1 , C 1 ) and the position point (T 2 , C 2 ) in the objective function, and connect the two position points to obtain line segment S.

[0025] Data correction unit: It is used to obtain the carbon content C x corresponding to line segment S when the moment is T x 、 ; use the actual power generation amount at moment T x as E x , and according to the carbon content C x and C x、 If C satisfies x divided by E x and the ratio is outside the deviation range, and C x 、 divided by E x is within the deviation range, then the actual carbon content C x is regarded as abnormal data; then all abnormal data are obtained, and all abnormal data are corrected according to the data correction technology, and the corrected value is used as the virtual carbon content.

[0026] There are many existing data correction technologies, such as mean filling method, K-nearest neighbor algorithm, multi-source data fusion correction, etc. If only the data itself is concerned when correcting the data without combining the actual change law, it will lead to deviation in the correction result of the data correction technology and cannot accurately present the change trend of the carbon content. Therefore, in this solution, it is necessary to analyze according to the power generation and the corresponding deviation range between the power generation and the carbon content to ensure the reliability of data calculation.

[0027] Early warning prompt module: used to obtain the early warning coefficient of the corrected data according to the corrected virtual carbon content, and judge whether to give an early warning to the data correction technology according to the early warning coefficient, and prompt relevant personnel to correct again.

[0028] The early warning prompt module includes an early warning prompt unit; Early warning prompt unit: used to obtain a certain corrected virtual carbon content y 0 , and the carbon contents y 0 adjacent to the time corresponding to the virtual carbon content y 1 and y 2 , respectively obtain the power generations z 0 , z 1 and z 2 corresponding to the times at the carbon contents y 0 , z 1 and z 2 , obtain the vector Y = (y 1 , y 0 , y 2 ) and the vector Z = (z 1 , z 0 , z 2 ), and obtain the cosine similarity between the vector Y and the vector Z as the eigenvalue corresponding to the carbon content y 0 . Then, the eigenvalues corresponding to several virtual carbon contents are obtained, and the average value is obtained by adding them as the early warning coefficient of the data correction technology. If the early warning coefficient is less than the preset coefficient threshold, give an early warning prompt to the current data correction technology and prompt relevant personnel to correct again.

[0029] Cosine similarity is a method for measuring the similarity between two vectors in a vector space. It is calculated based on the cosine value of the angle between the vectors, and the value range is [-1, 1]. When the cosine similarity is 1, it means that the two vectors are exactly the same, which is the most similar situation; when the cosine similarity is -1, it means that the two vectors are in exactly opposite directions, which is the least similar situation; when the cosine similarity is 0, it means that the two vectors are perpendicular to each other and have no similarity. Therefore, the closer to 1, the more similar the two vectors are. In this embodiment, the preset coefficient threshold is 0.9.

[0030] The present invention includes a feature record extraction module for obtaining the historical carbon emission records of power enterprises and extracting feature records from the carbon emission records according to the carbon content and power generation amount in the carbon emission records; a deviation range calculation module for analyzing the changes in carbon content and power generation amount in the feature records to obtain a deviation range; a data correction module for obtaining the current carbon emission records, obtaining the data with abnormal carbon content therein, and performing correction; and a warning prompt module for judging whether to give a warning about the data correction technology according to the corrected virtual carbon content. By summarizing the historical carbon emission rules and analyzing the current carbon content correction data, the present invention judges whether the current data correction technology needs to be prompted, which helps to improve the accuracy and rationality of the current data repair.

[0031] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. The green value-coordinated power market operation simulation system is characterized by: The system includes a feature record extraction module, a deviation range calculation module, a data correction module and an early warning prompt module; Feature record extraction module: used to obtain the historical carbon emission records of power companies, which are thermal power companies that generate electricity by burning carbon-containing energy fuels; monitor the carbon content and power generation at each moment in the power generation process through sensors, establish a carbon content line graph and a power generation line graph corresponding to each carbon emission record, and analyze the carbon content line graph and the power generation line graph to extract feature records from the carbon emission records; Deviation range calculation module: used to analyze the carbon content and power generation changes of the carbon content line graph and power generation line graph corresponding to the characteristic record at the same time, calculate the first deviation coefficient and the second deviation coefficient corresponding to the characteristic record, and then obtain the deviation range according to the first deviation coefficient and the second deviation coefficient; Data correction module: used to obtain the carbon emission record after the current sensor data is transmitted to the computer program, analyze the carbon content and power generation in the carbon emission record, obtain the data with abnormal carbon content, and correct the abnormal data through data correction technology, and use the corrected value as the virtual carbon content; Early warning prompt module: It is used to obtain the early warning coefficient of the corrected data according to the corrected virtual carbon content, determine whether to issue an early warning for the data correction technology according to the early warning coefficient, and prompt relevant personnel to make corrections again.

2. The green value-coordinated power market operation simulation and deduction system according to claim 1 is characterized in that: The feature record extraction module includes a carbon content line graph establishment unit, a power generation line graph establishment unit and a feature record extraction unit; Carbon content line graph establishment unit: used to deploy carbon content sensors at the pollutant discharge outlets of power companies, randomly extract a time period F in the power generation process corresponding to a certain historical carbon emission record; obtain the collection frequency of the carbon content sensor, obtain the interval length g between collecting two adjacent carbon content data, and collect the carbon content data of the carbon content sensor in the time period F according to the interval length g, the number of carbon content data is m=F / g, and transmit it to the computer program to establish a carbon content line graph; Power generation line graph establishing unit: used to deploy a power generation sensor for monitoring the power generation during the power generation process at the generator outlet, obtain the collection frequency of the power generation sensor, obtain the interval time h between collecting two adjacent power generation data, and collect the power generation data of the power generation sensor in the time period F according to the interval time h. The number of power generation data is n=F / h, and is transmitted to the computer program to establish a power generation line graph.

3. The green value-coordinated power market operation simulation and deduction system according to claim 2 is characterized in that: The feature record extraction unit is used to obtain the DTW distance between the two line graphs based on the values ​​of each element in the carbon content line graph and the power generation line graph using a dynamic time warping method. If the DTW distance is less than a preset distance threshold and the values ​​of each element in the carbon content line graph and the power generation line graph are greater than 0, then the carbon emission record is used as a feature record, thereby obtaining all feature records.

4. The green value-coordinated power market operation simulation and deduction system according to claim 1 is characterized in that: The deviation range calculation module includes a feature record analysis unit and a deviation range calculation unit; Feature record analysis unit: used to obtain the carbon emission line graph L corresponding to a feature record c And power generation line chart L e , line chart L c and L e The corresponding total time period is F; Q moments are randomly obtained from the time period F, and the ratio of carbon content to power generation corresponding to each moment is obtained, and a total of Q ratios are obtained, and the minimum and maximum ratios are extracted; then the minimum and maximum ratios corresponding to each feature record are obtained.

5. The green value-coordinated power market operation simulation and deduction system according to claim 4 is characterized in that: The deviation range calculation unit is used to take the total number of feature records as D, extract the recording time corresponding to each feature record, and sort the feature records from 1 to D in the order of the recording time from front to back, and add all the sequence numbers to obtain the total sequence number S D , and then the weight of the feature record with sequence number d is W d =d / S D , where 1≤d≤D; according to the minimum ratio, maximum ratio and weight corresponding to each feature record, the first deviation coefficient is obtained as , where R min d is the minimum value of the ratio of the feature record with serial number d, and the second deviation coefficient is , where R max d The maximum value of the ratio of the feature record with serial number d is obtained, and the deviation range is [R1, R2].

6. The green value-coordinated power market operation simulation and deduction system according to claim 1 is characterized in that: The data correction module includes a to-be-detected set determination unit, an objective function establishment unit and a data correction unit; The unit for determining the set to be detected is used to extract the carbon content and power generation at each moment in the current carbon emission record; wherein, the next moment of a moment a is b, if the carbon content difference between moment a and moment b is greater than a preset difference threshold, or the ratio of the carbon content to the power generation at moment a is not within the deviation range, then moment a is marked; All marked moments are obtained, and all adjacent marked moments are taken as a set to be detected, thereby obtaining several sets to be detected.

7. The green value-coordinated power market operation simulation and deduction system according to claim 6 is characterized in that: The objective function establishment unit is used to take the previous moment of the earliest moment in a certain set to be detected as T1, the next moment of the latest moment as T2, and a certain moment in a certain set to be detected as T x ; Set time T1, time T2 and time T x The actual carbon content corresponding to C1, C2 and C x ; Establish an objective function of carbon content changing with time, and mark the position point (T1, C1) and the position point (T2, C2) in the objective function, and connect the two position points to obtain the line segment S.

8. The green value-coordinated power market operation simulation and deduction system according to claim 7 is characterized in that: The data correction unit is used to obtain the time T x When the carbon content C corresponding to line segment S is x 、 ; Set the time as T x The actual power generation at that time is taken as E x , and according to the carbon content C x and C x 、 , if C is satisfied x Divide by E x The ratio is outside the deviation range and C x 、 Divide by E x If the ratio is within the deviation range, the actual carbon content C x as abnormal data; and then all abnormal data are obtained, all abnormal data are corrected according to the data correction technology, and the corrected values ​​are used as virtual carbon content.

9. The green value-coordinated power market operation simulation and deduction system according to claim 1 is characterized in that: The early warning prompt module includes an early warning prompt unit; Early warning prompt unit: used to obtain a corrected virtual carbon content y0, and the carbon contents y1 and y2 adjacent to the time before and after the virtual carbon content y0, obtain the power generation z0, z1 and z2 at the time corresponding to the carbon contents y0, y1 and y2 respectively, obtain vector Y=(y1, y0, y2) and vector Z=(z1, z0, z2), and obtain the cosine similarity between vector Y and vector Z as the eigenvalue corresponding to the carbon content y0, and then obtain the eigenvalues ​​corresponding to several virtual carbon contents, and add and calculate the average value as the early warning coefficient of the data correction technology. If the early warning coefficient is less than the preset coefficient threshold, the current data correction technology is warned and the relevant personnel are prompted to make corrections again.

Images