Regional ozone pollution monitoring method and device based on power data

Abstract

The present invention discloses a method and device for monitoring regional ozone pollution based on electric power data, the method comprising: determining ozone impact factors, obtaining regional air quality data, meteorological data, and electric power data; constructing an electric power prediction model based on the historical electric power data of enterprises, and obtaining the predicted data of the electric power consumption of enterprises; obtaining the predicted data of ozone precursors based on the predicted data of the electric power consumption of enterprises, combined with the industry coefficient of ozone precursors; establishing an ozone analysis model, the model outputs the predicted results of the ozone pollution concentration in the region for a period of time in the future and the relative contribution prediction of each polluting industry; forming a list of governance enterprises based on the relative contribution of each polluting industry and the predicted proportion of the electric power consumption of enterprises. The present invention realizes the application of the electric power consumption of enterprises in combination with regional air data and meteorological data for analysis, predicting the recent ozone concentration in the region, effectively measuring the environmental pollution generated by various industries and enterprises from the perspective of electric power, and better achieving the effect of energy saving and pollution reduction.

Description

Technical Field

[0001] The present invention relates to the technical field of power data application, and in particular to a method and device for monitoring regional ozone pollution based on power data. Background Art

[0002] Research on the causes of ozone pollution shows that near-ground ozone is not a product of a single emission, but is produced by photochemical reactions of its precursors under the action of ultraviolet radiation. Therefore, the international analysis of the source of ozone starts with the analysis of its precursors. At present, the existing emergency measures for ozone pollution are mostly based on the monitoring data of monitoring stations, which need to rely on historical monitoring data and make certain predictions in combination with climate and meteorological conditions. Although such a technical path can achieve the effect of overall early warning, it cannot reflect the emission of pollution sources in a timely manner, and thus correspond to the corresponding polluting enterprises, and there is a problem that the emergency measures are not targeted. The electricity consumption data of industrial enterprises is closely related to production. At present, the power grid data has accumulated rich experience in monitoring the pollution discharge and pollution control equipment of enterprises, but no quantitative research has been carried out on the relationship between the electricity consumption data of enterprises and the emission gases of enterprises, resulting in the inability of environmental protection departments to accurately monitor the pollution discharge of enterprises. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device and storage medium for regional ozone pollution monitoring based on power data, which solves the problem that the prior art cannot timely reflect the emission of pollution sources, so as to correspond to the corresponding polluting enterprises, and the emergency measures are not targeted;

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions.

[0005] Regional ozone pollution monitoring methods based on power data include:

[0006] Obtain regional air quality data, meteorological data, and power data;

[0007] Based on the historical electricity consumption data of enterprises in the region, an electricity consumption forecast model is constructed to obtain the enterprise electricity consumption forecast data;

[0008] Based on the enterprise electricity consumption forecast data and the ozone precursor industry coefficient, the ozone precursor forecast data is obtained;

[0009] Establish an ozone analysis model, which outputs the predicted results of ozone pollution concentration in the region in the future and the relative contribution of each polluting industry;

[0010] Based on the relative contribution of each polluting industry and the predicted proportion of corporate electricity consumption, the contribution of companies to ozone pollution is analyzed, and a list of companies to be governed is compiled to assist the environmental protection department in formulating management plans.

[0011] In a preferred embodiment of the present invention, an electricity consumption prediction model is constructed based on the enterprise's historical electricity consumption data to obtain the enterprise's electricity consumption prediction data, and the enterprise's predicted electricity consumption y corresponding to the prediction time x is calculated. The calculation method is as follows:

[0012] ;

[0013] In the calculation formula, y is the enterprise's predicted electricity consumption, x is the time, and b is the 0 Historical node power, b 1 , ,.... ,b n To increase the power.

[0014] In a preferred embodiment of the present invention, based on the enterprise electricity consumption forecast data and combined with the ozone precursor industry coefficient, the industry ozone precursor forecast data is obtained as follows:

[0015] According to the industries to which the enterprises in the power grid data platform belong, the electricity consumption forecast data of key polluting enterprises are added together to obtain the electricity consumption forecast data of key polluting industries. The calculation method is as follows:

[0016] ;

[0017] In the calculation formula, z is the forecast data of electricity consumption of key polluting industries, X i Provide electricity consumption forecast data for major polluting enterprises;

[0018] Based on the industry's historical electricity consumption data and industry ozone precursor emission data, the ozone precursor industry coefficient is calculated as follows:

[0019] ;

[0020] In the calculation formula, w is the coefficient of the ozone precursor industry, n is the number of key polluting enterprises, and x is i is the ozone precursor emission of enterprise i, y i The electricity consumption of enterprise i;

[0021] Based on the electricity consumption forecast data of key enterprises and the ozone precursor industry coefficient, the industry ozone precursor forecast data is calculated: ;

[0022] In the calculation formula, t is the predicted data of industry ozone precursors, w is the ozone precursor industry coefficient, and z is the predicted data of electricity consumption in key polluting industries.

[0023] In a preferred embodiment of the present invention, an ozone analysis model is established, and the ozone analysis model outputs the predicted results of ozone pollution concentration in the region for a period of time in the future and the prediction of the relative contribution of each polluting industry;

[0024] An ozone analysis model is established, and the enterprise electricity consumption, enterprise information historical data, air quality, and meteorological historical data are cleaned and integrated and brought into the model as a training set; enterprise electricity consumption forecasts, meteorological forecasts, and ozone precursor forecasts are brought into the model as prediction sets; the model outputs the predicted results of ozone pollution concentration in the region in the future and the impact contribution of each related industry.

[0025] In a preferred embodiment of the present invention, the third-party library pyGAM based on Python language is used to implement modeling and regression prediction to analyze the ozone environment and form a complete research system. The calculation method is as follows:

[0026] ;

[0027] In the calculation formula, s i is a nonparametric smooth function, X i The dependent variables (industry electricity consumption, temperature, humidity, wind speed, wind direction, and ozone precursor emission concentration) were input into the model, and the regional ozone concentration prediction n was calculated to obtain the absolute contribution of the industry to ozone pollution.

[0028] In a preferred embodiment of the present invention, the contribution of enterprises to ozone pollution is analyzed according to the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, and a list of governance enterprises is formed to assist the environmental protection department in formulating a management plan. The calculation method is as follows:

[0029] ;

[0030] In the calculation formula, m is the enterprise contribution. For corporate electricity consumption, is the industry’s electricity consumption, and si is the industry’s absolute contribution to ozone pollution.

[0031] Regional ozone pollution monitoring device based on power data, including:

[0032] Determine ozone impact factor unit: used to determine ozone precursors, key polluting industries / enterprises, and meteorological impact factors based on ozone formation methods and ozone data sources;

[0033] Input unit: used to obtain regional meteorological data, air data, and electricity consumption data;

[0034] Enterprise power consumption prediction unit: used to determine the power consumption prediction model based on power data and obtain power consumption prediction data for key polluting enterprises;

[0035] Ozone precursor prediction unit: used to obtain industry ozone precursor prediction data based on the enterprise electricity consumption prediction data and the ozone precursor industry coefficient;

[0036] Ozone prediction model unit: used to establish an ozone analysis model. The model outputs the predicted results of ozone pollution concentration in the future region and the relative contribution of each polluting industry.

[0037] Output unit: used to analyze the contribution of enterprises to ozone pollution according to the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, form a list of governance enterprises, and assist the environmental protection department in formulating management plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a workflow diagram of a regional ozone pollution prevention and control monitoring method based on power big data of the present invention;

[0039] Figure 2 It is a principle block diagram of the regional ozone pollution monitoring device based on power data of the present invention;

[0040] Figure 3 This is a graph showing changes in ozone concentration in city 1 in Example 1 of the present invention;

[0041] Figure 4 This is a graph showing the influence of several factors on ozone in Example 1 of the present invention;

[0042] Figure 5 This is a graph showing the effect of relative humidity on ozone in Example 1 of the present invention;

[0043] Figure 6 This is a graph showing the effect of humidity on ozone in Example 1 of the present invention;

[0044] Figure 7 This is a graph showing the effect of wind speed on ozone in Example 1 of the present invention;

[0045] Figure 8 This is a graph showing the effect of wind direction on ozone in Example 1 of the present invention. DETAILED DESCRIPTION

[0046] The present invention is described in detail below in conjunction with the various embodiments shown in the accompanying drawings, but it should be noted that these embodiments are not limitations of the present invention, and any equivalent transformations or substitutions in functions, methods, or structures made by ordinary technicians in the field based on these embodiments are all within the scope of protection of the present invention. Example

[0047] The embodiment of the present invention provides a regional ozone pollution prevention and control monitoring method based on power big data, such as Figure 1 As shown, the method comprises the following steps:

[0048] Step S101: Determine the ozone impact factor and obtain regional air quality data, meteorological data, and electricity consumption data.

[0049] Ozone, as a secondary pollutant, mainly comes from NO 2 However, when only NO 2 When the reaction is complete, there will be a zero cycle, that is, the reaction process will not cause O 3 Increase, as shown in formula (1).

[0050] (1)

[0051] When the atmosphere contains O 3 When a more oxidizing free radical is present, it will 3 Reaction with NO terminates the cycle in equation (1) and results in O 3 Accumulation. VOC s Can produce oxidizing agents stronger than O 3 Peroxyalkyl (RO 2 ) free radicals, hindering and reducing O 3 The decomposition of , terminates the loop in formula (1), leading to O 3 Concentration accumulation, the specific reaction is shown in formula (2).

[0052] (2)

[0053] Analysis of actual data revealed that NO 2 and VOC s Strong correlation with ozone production:

[0054] When the ozone concentration in prefecture-level city 1 reaches its peak, the ozone concentration on that day is similar to NO 2 The concentration relationship is Figure 3 As shown by Figure 3 It can be seen that there is an overall negative correlation between the two, with a correlation coefficient of -0.74, that is, NO 2 The increase in concentration is conducive to reducing O 3 concentration, this phenomenon is consistent with the law of ozone formation mechanism, O 3 The accumulation itself is due to the more oxidizing VOCs s Replace O 3 Reacts chemically with NO. 2 When the concentration is higher, its photochemical reaction is enhanced, producing more NO, which is beneficial to O 3 consumption, thereby reducing O 3 concentration.

[0055] When the ozone concentration in prefecture-level city 1 reaches its peak, the ozone concentration and VOC s The concentration is generally positively correlated, that is, as VOC s The increase in concentration will promote O 3 The concentration increases. 3The production mechanism shows that when VOC reacts with NO, s With O 3 There is a direct "competitive" relationship between them, and VOC s Stronger oxidizing power than O 3 Therefore, VOC s The higher the concentration, the 3 The less chance of participating in chemical reactions, the 3 The more likely it is to accumulate, the more Figure 3 .

[0056] According to the data of a certain year, through the analysis of the ozone generation process, it is found that the following factors also have a certain impact on the generation of ozone, as follows: Figure 3 .

[0057] Humidity: Water vapor in the atmosphere affects the role of solar ultraviolet radiation in photochemical reactions, and high relative humidity is also an important factor in the formation of wet scavenging, that is, high relative humidity is not conducive to O 3 Accumulation. Actual data show that when the relative humidity is greater than 50, the increase in humidity is accompanied by O 3 reduction, such as Figure 4-8 .

[0058] Temperature: There is a close relationship between air temperature and light intensity. 3 The properties and chemical reactions of its precursors will also have a certain impact, so the O 3 Theoretically, the concentration is closely related to the temperature. Actual data shows that when the temperature is greater than 20°C, the concentration of O 3 Continue to increase until the temperature exceeds a critical point. 3 Decline, such as Figure 6 .

[0059] Wind speed and direction: Figure 7-8 Shows O 3 The relationship curve between concentration, wind speed and wind direction. The wind speed graph shows that the increase in wind speed leads to O 3 Decrease, when the wind speed reaches the critical value, O 3 As the wind speed increases, it increases, that is, higher wind speed is beneficial to O 3 The wind direction chart shows that when the wind direction is between 30-100 and 200-250, 3 The concentration is generally high. When the wind direction approaches 170 and 310, O 3 will reach a valley value. That is, the change in wind direction causes O 3 Changes in concentration, certain wind directions are conducive to the formation and accumulation of ozone, such as Figure 7-8 .

[0060] In summary, the factors affecting ozone formation are NO2 、VOC s (i.e. the ozone precursor is NO 2 and VOC s ), humidity, temperature, wind speed and wind direction.

[0061] It is internationally recognized that 14 industries in five major fields, including petrochemicals, chemicals, metal manufacturing, and printing and spraying, are VVOC s and NO x The emission sources and key polluting industries are as follows:

[0062]

[0063] Based on the above 14 industries and combined with the information of each enterprise on the power grid data platform, a detailed list of key polluting enterprises was drawn.

[0064] According to the above ozone influencing factors (NO 2 、VOC s (i.e. the ozone precursor is NO 2 and VOC s ), humidity, temperature, wind speed, wind direction, each influencing factor uses the single variable method, and establishes an exponential relationship with ozone changes when other conditions remain unchanged), obtains regional air quality data, meteorological data, and electricity consumption data, and cleans and integrates the data according to the correlation between regions, industries, and enterprises to form a unified data set.

[0065]

[0066] Step S102: Based on the historical electricity consumption data of key polluting enterprises, an electricity consumption prediction model is constructed to obtain enterprise electricity consumption prediction data. The method is as follows:

[0067] ;

[0068] In the calculation formula, y is the enterprise's predicted electricity consumption, x is the time, and b is the 0 Historical node power, b 1 , .... , b n The model can calculate the enterprise's predicted electricity consumption y corresponding to the predicted time x.

[0069] Step S103: Based on the enterprise electricity consumption forecast data and the ozone precursor industry coefficient, the industry ozone precursor forecast data is obtained. The method is as follows:

[0070] According to the industries to which the enterprises in the power grid data platform belong, the electricity consumption forecast data of key polluting enterprises are added together to obtain the electricity consumption forecast data of key polluting industries. The calculation method is as follows:

[0071] ;

[0072] In the calculation formula, z is the predicted electricity consumption data of key polluting industries, X I Provide electricity consumption forecast data for key polluting enterprises.

[0073] Based on the industry's historical electricity consumption data and the industry's ozone precursor emission data, the ozone precursor industry coefficient is calculated. The calculation method is as follows:

[0074] ;

[0075] In the calculation formula, w is the coefficient of the ozone precursor industry, n is the number of key polluting enterprises, and x is i is the ozone precursor emission of enterprise i (obtained from the enterprise pollutant emission report published by the Ministry of Ecology and Environment), y i The electricity consumption of enterprise i.

[0076] Based on the forecast data of electricity consumption of key enterprises and the industry coefficient of ozone precursors, the forecast data of ozone precursors in the industry are calculated.

[0077] ;

[0078] In the calculation formula, t is the predicted data of industry ozone precursors, w is the ozone precursor industry coefficient, and z is the predicted data of electricity consumption in key polluting industries.

[0079] Step S104: Establish an ozone analysis model, and the model outputs the predicted results of ozone pollution concentration in the region for a period of time in the future and the prediction of the relative contribution of each polluting industry.

[0080] Based on the python development language, the generalized additive model resource code library is introduced, the generalized additive model algorithm is used as the core data processing technology, the historical data of related influencing factors with a longer period is used as the basis for model training, and the data of short-term predicted influencing factors is used as the prediction sample, which together constitute the input variables of the model. Combined with the relevant data calculation and processing logic required for modeling, an ozone analysis model is established to output analysis results such as regional ozone concentration and industry impact contribution. The enterprise electricity consumption, enterprise information historical data, air quality, and meteorological historical data are cleaned and integrated, and brought into the model as a training set; the enterprise electricity consumption forecast, meteorological forecast, and ozone precursor forecast are brought into the model as a prediction set; the model outputs the predicted results of ozone pollution concentration in the region in the future and the impact contribution of each related industry.

[0081] Comprehensive consideration 3The concentration, air pollutants, meteorological elements and other influencing factors constitute a complex nonlinear dynamic system, and there are strong nonlinear interactions of feedback and regulation between the factors. Therefore, this study selected the generalized additive model (GAM, which has been widely used in most environmental research institutions and organizations around the world) and used the third-party library pyGAM based on the Python language to implement modeling and regression prediction to analyze the ozone environment and form a complete research system. The calculation method is as follows: ;

[0082] In the calculation formula, n is the prediction result set (ozone concentration, pollution contribution of each industry), S I is a nonparametric smooth function, X I Dependent variables (industry electricity, temperature, humidity, wind speed, wind direction, and ozone precursor emission concentrations) were input into the model.

[0083] The regional ozone pollution prediction result n is calculated.

[0084] The results of the model calculation are as follows:

[0085] Ozone concentration forecast for the next 3 days

[0086] ;

[0087] Step S105: Analyze the contribution of enterprises to ozone pollution based on the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, form a list of governance enterprises, and assist the environmental protection department in formulating a management plan. The calculation method is as follows:

[0088] ;

[0089] In the calculation formula, m is the enterprise contribution. For corporate electricity consumption, is the electricity consumption of the industry, and si is the industry contribution.

[0090] Table 1 Ozone impact ranking of various industries when pollution occurred in prefecture-level cities 1 and 2

[0091]

[0092] Table 2 Top 5 enterprises that have a major impact on ozone pollution in prefecture-level cities 1 and 2 in the past three days

[0093]

[0094] Embodiment 2:

[0095] Regional ozone pollution monitoring device based on power data, including:

[0096] Determine ozone impact factor unit: used to determine ozone precursors, key polluting industries / enterprises, and meteorological impact factors based on ozone formation methods and ozone data sources;

[0097] Input unit: used to obtain regional meteorological data, air data, and electricity consumption data;

[0098] Enterprise power consumption prediction unit: used to determine the power consumption prediction model based on power data and obtain power consumption prediction data for key polluting enterprises;

[0099] Ozone precursor prediction unit: used to obtain industry ozone precursor prediction data based on the enterprise electricity consumption prediction data and the ozone precursor industry coefficient;

[0100] Ozone prediction model unit: used to establish an ozone analysis model. The model outputs the predicted results of ozone pollution concentration in the future region and the relative contribution of each polluting industry.

[0101] Output unit: used to analyze the contribution of enterprises to ozone pollution according to the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, form a list of governance enterprises, and assist the environmental protection department in formulating management plans.

[0102] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.

[0103] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0104] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. Regional ozone pollution monitoring method based on power data, It is characterized in that include: Obtain regional air quality data, meteorological data, and power data; Based on the historical electricity consumption data of enterprises in the region, an electricity consumption forecast model is constructed to obtain the enterprise electricity consumption forecast data; Based on the enterprise electricity consumption forecast data and the ozone precursor industry coefficient, the ozone precursor forecast data is obtained; Establish an ozone analysis model, which outputs the predicted results of ozone pollution concentration in the region in the future and the relative contribution of each polluting industry; Analyze the contribution of enterprises to ozone pollution based on the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, form a list of governance enterprises, and assist the environmental protection department in formulating management plans; According to the historical electricity data of the enterprise, the electricity consumption forecast model is constructed to obtain the enterprise electricity consumption forecast data, and the enterprise forecast electricity consumption y corresponding to the forecast time x is calculated. The calculation method is as follows: ； In the calculation formula, y is the enterprise's predicted electricity consumption, x is the time, and b is the 0 Historical node power, To increase the power; Based on the enterprise electricity consumption forecast data and the ozone precursor industry coefficient, the industry ozone precursor forecast data is obtained as follows: According to the industries to which the enterprises in the power grid data platform belong, the electricity consumption forecast data of key polluting enterprises are added together to obtain the electricity consumption forecast data of key polluting industries. The calculation method is as follows: ； In the calculation formula, z is the forecast data of electricity consumption of key polluting industries, x is i Provide electricity consumption forecast data for major polluting enterprises; Based on the industry's historical electricity consumption data and industry ozone precursor emission data, the ozone precursor industry coefficient is calculated as follows: ； In the calculation formula, w is the coefficient of the ozone precursor industry, n is the number of key polluting enterprises, and x is i is the ozone precursor emission of enterprise i, y i The electricity consumption of enterprise i; Based on the electricity consumption forecast data of key enterprises and the ozone precursor industry coefficient, the industry ozone precursor forecast data is calculated: ; In the calculation formula, t is the predicted data of ozone precursors in the industry, w is the coefficient of ozone precursors in the industry, and z is the predicted data of electricity consumption in key polluting industries; Establish an ozone analysis model, which outputs the predicted results of ozone pollution concentration in the region in the future and the relative contribution of each polluting industry; An ozone analysis model is established, and the enterprise electricity consumption, enterprise information historical data, air quality, and meteorological historical data are cleaned and integrated and brought into the model as a training set; enterprise electricity consumption forecasts, meteorological forecasts, and ozone precursor forecasts are brought into the model as prediction sets; the model outputs the predicted results of ozone pollution concentration in the region in the future and the impact contribution of each related industry.

2. The method for monitoring regional ozone pollution based on power data according to claim 1, It is characterized in that The third-party library pyGAM based on Python language is used to implement modeling and regression prediction to analyze the ozone environment and form a complete research system. The calculation method is as follows: ; In the calculation formula, s i is a nonparametric smooth function, X i The model inputs dependent variables, including industry electricity consumption, temperature, humidity, wind speed, wind direction, and ozone precursor emission concentration, and calculates the regional ozone concentration prediction n to obtain the absolute contribution of the industry to ozone pollution.

3. The method for monitoring regional ozone pollution based on power data according to claim 1, It is characterized in that According to the relative contribution of each polluting industry and the predicted proportion of corporate electricity consumption, the contribution of enterprises to ozone pollution is analyzed to form a list of governance enterprises to assist the environmental protection department in formulating management plans. The calculation method is as follows: ; In the calculation formula, m is the enterprise contribution. For corporate electricity consumption, is the industry’s electricity consumption, and si is the industry’s absolute contribution to ozone pollution.

4. A regional ozone pollution monitoring device based on power data, used to implement the steps of the regional ozone pollution monitoring method based on power data according to any one of claims 1 to 3, It is characterized in that include: Determine ozone impact factor unit: used to determine ozone precursors, key polluting industries, enterprise scope, and meteorological impact factors based on ozone formation mode and ozone data source; Input unit: used to obtain regional meteorological data, air data, and electricity consumption data; Enterprise power consumption prediction unit: used to determine the power consumption prediction model based on power data and obtain power consumption prediction data for key polluting enterprises; Ozone precursor prediction unit: used to obtain industry ozone precursor prediction data based on the enterprise electricity consumption prediction data and the ozone precursor industry coefficient; Ozone prediction model unit: used to establish an ozone analysis model. The model outputs the predicted results of ozone pollution concentration in the future region and the relative contribution of each polluting industry. Output unit: used to analyze the contribution of enterprises to ozone pollution according to the relative contribution of each polluting industry and the predicted proportion of enterprise electricity consumption, form a list of governance enterprises, and assist the environmental protection department in formulating management plans.

Images