Digital park carbon emission trend deduction method and system and electronic equipment

Abstract

The invention discloses a digital park carbon emission trend deduction method and system and electronic equipment, and relates to the technical field of carbon emission dynamic optimization, and the method comprises the steps: predicting an energy consumption sequence of continuous P time points through combining a production plan and climate characteristics of an industrial park in a future time period, predicting an output power sequence of the multi-source energy based on a historical power generation record; and on this basis, the energy power supply proportion is analyzed, a power supply proportion sequence is generated, finally, the energy consumption sequence and the power supply proportion sequence are integrated by using the unit energy carbon emission factor, the carbon emission in the future time zone is calculated, and accurate deduction of the carbon emission trend is realized. The technical problems that multi-source energy collaborative modeling is insufficient and dynamic power supply proportion optimization lags behind in existing park carbon emission prediction are solved, and the technical effects of reducing the carbon emission prediction error rate and improving the new energy power supply proportion dynamic optimization response speed are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of dynamic optimization of carbon emissions, and in particular to a method, system and electronic equipment for deducing carbon emission trends in a digital park. Background Art

[0002] Existing industrial park carbon emission management generally relies on static historical data and a single energy model, which makes it difficult to cope with the complex challenges brought about by dynamic adjustment of production plans, climate fluctuations and coordinated supply of multi-source energy. Traditional forecasting methods lack refined modeling of production intensity, ambient temperature and energy supply and demand linkage, resulting in low carbon emission forecasting accuracy and inability to respond to changes in energy structure in real time. In addition, existing technologies lack the ability to dynamically optimize the proportion of new energy power supply, making it difficult to balance power supply reliability and low-carbon goals. How to achieve high-precision carbon emission deduction and dynamic energy scheduling under multi-factor coupling has become a technical problem that needs to be solved urgently.

[0003] At the current stage, relevant technologies have technical problems such as insufficient collaborative modeling of multi-source energy in park carbon emission forecasting and lagging optimization of dynamic power supply ratio. Summary of the invention

[0004] This application solves the technical problems of insufficient multi-source energy collaborative modeling and lagging dynamic power supply ratio optimization in existing park carbon emission forecasts by providing a digital park carbon emission trend deduction method, system and electronic equipment.

[0005] This application provides a digital park carbon emission trend deduction method, including: According to the production plan and climate characteristics of the industrial park in the predetermined future time zone, energy consumption is predicted at P consecutive time points to generate a predicted energy consumption sequence; according to the historical power generation records, multi-energy output power is predicted at P consecutive time points to generate multiple predicted energy output power sequences; based on the predicted energy consumption sequence and multiple predicted energy output power sequences, energy power supply ratio analysis is performed to generate a predicted energy power supply ratio sequence; based on the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply ratio sequence, carbon emissions are calculated for the predetermined future time zone, and predicted carbon emissions are obtained as the carbon emission trend deduction result.

[0006] This application provides a digital park carbon emission trend deduction system, including: A predicted energy consumption sequence generation module, the predicted energy consumption sequence generation module is used to predict the energy consumption at P consecutive time points according to the production plan and climate characteristics of the industrial park in a predetermined future time zone, and generate a predicted energy consumption sequence; a predicted energy output power sequence generation module, the predicted energy output power sequence generation module is used to predict the multi-energy output power at P consecutive time points according to historical power generation records, and generate multiple predicted energy output power sequences; an energy power supply proportion analysis module, the energy power supply proportion analysis module is used to perform energy power supply proportion analysis based on the predicted energy consumption sequence and multiple predicted energy output power sequences, and generate a predicted energy power supply proportion sequence; a carbon emission calculation module, the carbon emission calculation module is used to calculate the carbon emissions in the predetermined future time zone according to the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply proportion sequence, and obtain the predicted carbon emissions as the carbon emission trend deduction result.

[0007] The present application also provides an electronic device, including: A memory is used to store executable instructions; a processor is used to implement a digital park carbon emission trend deduction method when executing the executable instructions stored in the memory.

[0008] The digital park carbon emission trend deduction method, system and electronic equipment proposed in this application are intended to first predict the energy consumption sequence of P consecutive time points by combining the production plan and climate characteristics of the industrial park in the future period, and predict the output power sequence of multi-source energy based on historical power generation records; on this basis, analyze the proportion of energy supply and generate a power supply ratio sequence, and finally use the unit energy carbon emission factor to integrate the energy consumption sequence and the power supply ratio sequence, calculate the carbon emissions in the future time zone, and realize the accurate deduction of carbon emission trends, thereby achieving the technical effect of reducing the error rate of carbon emission prediction and improving the dynamic optimization response speed of the new energy power supply ratio. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0010] Figure 1 A flowchart of a method for deriving carbon emission trends in a digital park provided in an embodiment of the present application; Figure 2A schematic diagram of the structure of a digital park carbon emission trend deduction system provided in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0011] Explanation of the accompanying drawings: predicted energy consumption sequence generation module 10, predicted energy output power sequence generation module 20, energy supply proportion analysis module 30, carbon emission calculation module 40, input device 201, processor 202, memory 203, output device 204. DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides a method for deriving carbon emission trends in a digital park, such as Figure 1 As shown, the method includes: Step S100, according to the production plan and climate characteristics of the industrial park in the predetermined future time zone, the energy consumption at P consecutive time points is predicted to generate a predicted energy consumption sequence. Specifically, first, the production plan in the predetermined future time zone is obtained from the industrial park management department, such as the expected output of the product, the equipment operation arrangement, etc., and the climate characteristic data is mastered with the help of the meteorological department or professional model. P consecutive (P>30) time points are set in the time zone at specific intervals and P time intervals are divided. For each interval, the production plan and the climate characteristics are divided and combined based on the differences in energy consumption of the product production process and the impact of the climate on the equipment operation, and P energy consumption related data are determined. By collecting past production records to construct a sample energy consumption related data set and a sample energy consumption set, machine learning is used to configure K (K≥3) prediction operators, supervised training and verification are carried out, and after the loss function converges, an energy consumption prediction plug-in is integrated to construct the energy consumption prediction plug-in, which is used to predict the energy consumption according to the P energy consumption related data, convert it into the power mean, and generate a predicted energy consumption sequence in chronological order, laying the foundation for energy consumption data for carbon emission trend deduction.

[0016] In a possible implementation, according to the production plan and climate characteristics of the industrial park in the predetermined future time zone, the energy consumption at P consecutive time points is predicted to generate a predicted energy consumption sequence. Step S100 further includes step S110, obtaining the production plan and climate characteristics of the industrial park in the predetermined future time zone, wherein the production plan is the expected product output and the climate characteristics are the expected ambient temperature. Specifically, obtaining the production plan (expected product output) and climate characteristics (expected ambient temperature) in the predetermined future time zone of the industrial park requires a multi-pronged approach. In terms of production plan acquisition, on the one hand, it is necessary to connect with the production management departments of various enterprises in the park and the park management agency to collect information such as the expected output, time distribution and production capacity adjustment plan of each product in the future predetermined time period, and then cross-check and verify the data, and judge the rationality in combination with past production data; in terms of climate feature acquisition, it is necessary to cooperate with the Meteorological Bureau or meteorological service company to sign a data service agreement to obtain refined temperature forecasts, and at the same time use the data of the park's own meteorological monitoring station, and temporarily deploy simple equipment to assist when necessary, and finally integrate the two types of data, use tools for statistical analysis and correlation with production plans, and lay a solid data foundation for subsequent energy consumption and other analyses.

[0017] Step S120, set P consecutive time points in the predetermined future time zone according to the predetermined time interval, and divide and obtain P time intervals, where P is an integer greater than 30. Specifically, the determination of the time interval requires a comprehensive analysis of the purpose, data characteristics and collection and processing capabilities. For scenes such as chemical production with large fluctuations in energy consumption, minute-level intervals may be selected, while stable production activities such as textiles can be selected at the hour level. After determining the interval, in the predetermined future time zone, starting from the starting time, set P consecutive (P>30) time points in sequence according to the interval, such as setting 168 points at intervals of 1 hour in the next week. Based on these time points, a time interval is formed between two adjacent points. For example, 168 time intervals are divided in the above example. Each interval can determine energy consumption-related data in combination with production plans, climate conditions, etc. Because P is large enough, it can fully reflect the changes of various factors in different time periods, thereby improving the reliability of the analysis results.

[0018] Step S130, divide and combine the production plan and climate characteristics according to the P time intervals to determine P energy consumption related data. Specifically, after determining the P time intervals, divide and combine the production plan and climate characteristics to determine the energy consumption related data. As far as the production plan is concerned, the expected product output is subdivided by time interval, such as the electronic product manufacturing park allocates the monthly output by day, and at the same time associates the energy consumption characteristics of each production link, considering the change of equipment operation status, such as the impact of equipment maintenance shutdown on energy consumption. In terms of climate characteristics, the ambient temperature is obtained according to the time interval, such as the daily average, maximum and minimum temperatures are counted from the hourly temperature data, the impact of temperature on equipment and production is analyzed, and seasonal factors are combined. Finally, an energy consumption related data calculation model that comprehensively considers the production plan and climate characteristics is established, and the total energy consumption corresponding to each time interval, the unit product energy consumption and other data are calculated according to the model, so as to determine P energy consumption related data, and lay a solid data foundation for subsequent energy consumption prediction and analysis.

[0019] Step S140, using the energy consumption prediction plug-in, according to the P energy consumption related data, respectively predict, output P predicted energy consumption, calculate P predicted energy consumption power means, and construct the predicted energy consumption sequence. Specifically, when using the energy consumption prediction plug-in to construct the predicted energy consumption sequence, first comprehensively check and debug the plug-in trained based on a large amount of historical energy consumption and related influencing factors data. After that, the energy consumption related data of P comprehensive production plans and climate characteristics and other factors are input into the plug-in in turn, and the algorithm model in the plug-in parses the data, and weights each factor according to the weight distribution method obtained by training, and outputs P predicted energy consumption after complex calculations. Then, use the formula "predicted energy consumption power mean = predicted energy consumption ÷ corresponding time interval duration" to calculate P predicted energy consumption power means. Finally, arrange these means according to the order of time intervals, and construct a predicted energy consumption sequence that can intuitively show the predicted trend of energy consumption power changes in the predetermined future time zone, providing strong support for park energy planning and other work.

[0020] In a possible implementation, an energy consumption prediction plug-in is used to predict the P energy consumption related data, output P predicted energy consumptions, calculate the P predicted energy consumption power means, and construct the predicted energy consumption sequence. Step S140 further includes step S141, based on the historical production records of the industrial park, a sample energy consumption related data set is collected, and the energy consumption corresponding to different energy consumption related data is counted according to the historical electricity consumption records, which is set as the sample energy consumption, and a sample energy consumption set is constructed. Specifically, collaborate with the data management and power management departments of the industrial park to clarify the database location and access rights of the historical production records, and obtain historical electricity consumption records from the power management system or supplier. Samples are extracted from the historical production records at certain time intervals, and data such as product production, equipment operation, and production process are collected. Factors affecting energy consumption such as the production workshop environment and logistics transportation are considered to integrate and form a sample energy consumption related data set. Then, using time as the matching dimension, the associated data is matched with the historical electricity consumption records, and the energy consumption corresponding to each set of associated data is counted according to the power circuit identification of the production device, which is set as the sample energy consumption. After checking and correcting the abnormal data, a reliable sample energy consumption set is constructed according to the order of the associated data to provide high-quality data support for subsequent model training.

[0021] Step S142, using the sample energy consumption associated data set and the sample energy consumption set as training data, respectively train multiple prediction operators, and harvest multiple energy consumption prediction branches. Specifically, when constructing an energy consumption prediction model, first screen a variety of prediction operators such as linear regression, decision tree, neural network, etc., determine K (K ≥ 3) and initialize them respectively, such as initializing the coefficient vector for linear regression, setting the maximum depth and other parameters for the decision tree, and determining the structure of the neural network and initializing the weights and biases. Then pre-process the sample energy consumption associated data set and the sample energy consumption set, standardize the numerical data, process the missing values, and then divide them into training sets and validation sets at a ratio of 70%-80% and 20%-30%. Then start the training cycle for each prediction operator, the neural network calculates the loss of the predicted value and the true value through forward propagation, and updates the parameters through back propagation; the linear regression minimizes the loss function to solve the coefficient; the decision tree selects features and split points to build a tree. During training, the validation set is regularly used for evaluation, and timely adjustments are made when problems such as overfitting occur, such as reducing the learning rate of the neural network, improving the linear regression model, and pruning the decision tree. When the prediction operator meets the performance requirements in the validation set and the training converges, the trained operator is saved to form an energy consumption prediction branch. Finally, K different prediction branches are obtained for subsequent plug-in integration.

[0022] Step S143, construct the energy consumption prediction plug-in according to the integration of the multiple energy consumption prediction branches, wherein the output of the energy consumption prediction plug-in is the mean of the outputs of the multiple energy consumption prediction branches. Specifically, to construct the energy consumption prediction plug-in to integrate multiple energy consumption prediction branches, it is necessary to first clarify the characteristics of each branch, such as the linear regression branch is good at processing linear trend data, the decision tree branch can deal with discrete data and complex decision logic, and the neural network branch has a strong nonlinear fitting ability. Then design the integrated architecture, build the main program framework with modular programming, and be responsible for the adaptation and distribution of input data and the collection of prediction results of each branch. After the new energy consumption related data is input into the plug-in, the main program converts the data according to the requirements of each branch and distributes it in parallel using multi-threading or distributed technology. Each branch receives data to complete the calculation, and the linear regression, decision tree, neural network and other branches output the predicted value according to their own model algorithm. The main program collects the results and calculates the arithmetic mean according to the setting. For example, the outputs of the three branches are 100, 120, and 110 kWh respectively, and the final output is (100+120+110)÷3=110 kWh for subsequent work such as energy planning.

[0023] In a possible implementation, the sample energy consumption associated data set and the sample energy consumption amount set are used as training data to train multiple prediction operators respectively, and multiple energy consumption prediction branches are obtained. Step S142 further includes step S1421, configuring K prediction operators based on machine learning, where K is greater than or equal to 3. Specifically, when configuring K (K ≥ 3) prediction operators based on machine learning, first clarify the business requirements of energy consumption prediction, such as prediction duration, object scope, etc., and deeply analyze the data characteristics of the sample energy consumption associated data set and the sample energy consumption amount set, covering scale, type, distribution and feature correlation. According to the analysis results, select the appropriate operator type. Linear regression is suitable for linear relationship scenarios, decision trees can handle complex data and nonlinear relationships, neural networks are good at capturing complex patterns, support vector machines perform well in small sample high-dimensional data, and random forests can improve stability. After determining the type, set key parameters for each operator, such as regularization parameters for linear regression, depth, number of samples and splitting criteria for decision trees, network structure, activation function and other parameters for neural networks, kernel functions and other parameters for support vector machines, and number of decision trees for random forests. For complex models such as neural networks and random forests, a reasonable architecture is designed. The former determines the number of neurons in the input, hidden, and output layers, and the latter controls the decision tree generation process. Finally, the mean square error and other indicators are used to evaluate the operator performance through cross-validation. Based on the results, the optimization parameters are adjusted using methods such as grid search to lay a solid foundation for the training and integration of energy consumption prediction models.

[0024] Step S1422, the training data is divided into K parts, and the K prediction operators are supervised trained and verified respectively until the loss function converges, and multiple energy consumption prediction branches are obtained. Specifically, in the process of constructing the energy consumption prediction branch, first ensure that the training data is accurate and complete, and use algorithms such as stratified random sampling to divide the sample energy consumption association data set and the sample energy consumption set into K parts to ensure that the feature distribution of each data is similar. Then, for each piece of data, supervised training is carried out for the K prediction operators respectively, the linear regression coefficient is adjusted by the least squares method, the decision tree is constructed according to the information gain and other criteria, the neural network updates the parameters with the help of the back propagation algorithm, and the small batch gradient descent method is mostly used during training. During training, 10%-20% of the training data is reserved as a verification set, and the performance is evaluated by indicators such as the mean absolute error. The regularization parameter can be adjusted for linear regression, the decision tree can be pruned and optimized, and the learning rate can be changed for the neural network. Continue training and verification until the loss functions of the K prediction operators converge. At this time, each operator forms an energy consumption prediction branch. They are based on different algorithms and training data, and subsequently work together to improve the prediction accuracy in the energy consumption prediction plug-in integration.

[0025] Step S200, based on the historical power generation records, multi-energy output power prediction is performed at P consecutive time points to generate multiple predicted energy output power sequences. Specifically, when performing multi-energy output power prediction and generating prediction sequences, it is necessary to first connect with relevant institutions, obtain historical power generation records covering multiple energy power generation facilities, comprehensively check data integrity, unify the format and pre-process, such as repairing missing values, processing outliers and standardizing data. Then, the prediction time range is set according to actual needs, such as predicting the next week for arranging power dispatch, and then selecting the time point interval according to the energy fluctuation characteristics and accuracy requirements. If the hourly interval is selected, the prediction for one week is 168. Then select models for different energy characteristics, such as the Holt-Winters model for thermal power generation, neural networks for wind power and photovoltaics, and a combination of physics and data for hydropower, which can also be optimized through model integration. After preparing 70%-80% training sets and 20%-30% validation sets, train the model, continuously adjust the parameters and use the validation set to prevent overfitting. After the model is trained, future data predictions are input, and finally the prediction results are sorted out, stored by energy and time, and the predicted output power series of each energy source are generated and visualized to provide an intuitive reference for decision-making.

[0026] In a possible implementation, according to the historical power generation records, the multi-energy output power prediction at P consecutive time points is performed to generate multiple predicted energy output power sequences. Step S200 further includes step S210, obtaining the multi-source power supply mode of the industrial park and multiple historical power generation records of the multi-source power supply mode. Specifically, to obtain the multi-source power supply mode of the industrial park and its historical power generation records, it is necessary to first clarify the power supply types such as photovoltaic, wind power, and energy storage and the time range of data collection. If it is used for short-term scheduling, high-frequency data from the past few months to one year is collected, and for long-term planning, several years of data are collected. Then, a data acquisition channel is constructed, and the operation and maintenance management team of the photovoltaic power station, wind farm, and energy storage facility is connected internally. The power generation power, charging and discharging data, and equipment parameters of different time periods are extracted from their monitoring system or energy management system. Externally, meteorological data such as light and wind speed are obtained from the meteorological department, and power market data is obtained from the power trading platform. Finally, the data format is unified, the power generation unit, time format, etc. are standardized, the data is verified and cleaned, missing values ​​are filled, abnormal values ​​are corrected, and compared with the actual equipment operation and physical laws to ensure that the data is accurate and reliable.

[0027] Step S220, obtain P power generation impact data sets of the multi-source power supply mode within P time intervals. Specifically, to obtain P power generation impact data sets of the multi-source power supply mode within P time intervals, the time interval should be determined according to the analysis purpose, business, and data characteristics. The short-term scheduling is in hours or minutes, and the long-term planning is in days, weeks, or months. It is set in combination with the production operation of the park and the data acquisition storage capacity. Then identify the influencing factors. Photovoltaic is affected by light intensity, ambient temperature, and air quality. Wind power depends on wind speed, wind direction, and air density. Energy storage is related to charging and discharging strategies, remaining power, and equipment aging. Then establish a data acquisition system. Meteorological factors rely on meteorological monitoring stations. Energy storage data is obtained from energy management systems. Air quality data is collected in cooperation with environmental protection departments or with professional equipment. The acquisition frequency is set according to the time interval and the equipment time synchronization is ensured. Finally, clean the preprocessed data, remove outliers, process missing values, and standardize them. Then, divide them into P power generation impact data sets containing various influencing factor data of multi-source power supply modes according to the time interval, and provide input for the subsequent construction of an integrated power predictor.

[0028] Step S230, according to the historical power generation records, an integrated power predictor is constructed based on machine learning, and multi-energy output power is predicted according to the P power generation impact data sets, and multiple predicted energy output power sequences are generated. Specifically, the historical power generation records of photovoltaic, wind power, energy storage and other multi-source power supply are first collected from multiple channels to ensure integrity and accuracy, clean the data, fill in missing values, correct abnormal values, and extract relevant features such as light duration, and standardize or normalize after encoding conversion. Then, an integrated power predictor is constructed based on machine learning, and algorithms such as RNN, LSTM, SVM, random forest regression, etc. are selected to determine the model structure parameters, and the model is optimized by grid search and other methods, and the training set, validation set and test set are divided. The model is trained and adjusted according to the validation set to prevent overfitting, and the generalization ability is evaluated with the test set. Finally, the P power generation impact data sets are preprocessed to make them consistent with the training set and then input into the model. The model predicts the multi-energy output power of each time interval based on the learned pattern, and generates multiple predicted energy output power sequences such as photovoltaic, wind power, energy storage, etc. according to time arrangement, providing a decision basis for park energy planning, etc.

[0029] Step S300, based on the predicted energy consumption sequence and multiple predicted energy output power sequences, perform energy power supply ratio analysis and generate a predicted energy power supply ratio sequence. Specifically, when performing energy power supply ratio analysis and generating a predicted energy power supply ratio sequence based on the predicted energy consumption sequence and multiple predicted energy output power sequences, it is necessary to first carefully check the data, correct the abnormal values, ensure the timestamp matching, obtain the unit energy carbon emission factor from the authoritative channel and unify the dimension. Then, the power supply of each power supply mode at each time point is calculated based on the predicted energy output power and the time interval, and the total power supply is added to obtain the power supply ratio of each power supply mode, and then the power supply ratio of each power supply mode is calculated. Then, the power supply ratio is combined with the unit energy carbon emission factor to analyze the carbon emission contribution ratio of each power supply mode. Finally, the power supply ratio of each time point is arranged by time to generate a predicted energy power supply ratio sequence, which can intuitively present the changes in the power supply ratio of each power supply mode at different times, provide a reference for energy planners, and help optimize energy supply strategies.

[0030] In a possible implementation, based on the predicted energy consumption sequence and multiple predicted energy output power sequences, an energy power supply ratio analysis is performed to generate a predicted energy power supply ratio sequence. Step S300 further includes step S310, selecting the first predicted energy consumption power mean value and the first predicted energy output power set at the first time point. Specifically, when selecting the first time point, it is necessary to select the analysis purpose, such as optimizing the peak energy dispatching of electricity consumption, which can be selected at 10 am on weekdays, and focusing on the utilization of new energy at night, which can be selected at 3 am. It may also be affected by specific production processes such as factory equipment maintenance. After determining the time point, data is extracted from the predicted energy consumption sequence. If there are multiple predicted values, the first predicted energy consumption power mean value is calculated by arithmetic mean method, such as 5 predicted values ​​are calculated to obtain the mean value. Then, for the predicted energy output power sequences of multiple power supply modes such as photovoltaic, wind power, and energy storage, the predicted values ​​at the first time point are extracted respectively, such as photovoltaic according to the illumination model, wind power according to the wind speed model, and energy storage from the charge and discharge sequence. These values ​​are integrated into the first predicted energy output power set to provide key data for the subsequent energy power supply ratio analysis.

[0031] Step S320, configure the first power demand index according to the first product output and the first ambient temperature in the first time interval. Specifically, when configuring the first power demand index, first define the first time interval according to the energy analysis time scale and target, extract the first product output data in the interval from the production record database, and obtain the first ambient temperature data from the meteorological monitoring equipment or related platforms, and process the data of multiple monitoring points by arithmetic or weighted average method according to the demand. Then analyze the relationship between product output and power demand, establish a correlation model by linear regression and other methods, and modify the model by considering factors such as production process; then study the relationship between ambient temperature and power demand, establish a temperature-power demand function, pay attention to the impact of temperature fluctuations and determine the fluctuation impact coefficient. Finally, determine the weight according to the importance of the impact of product output and ambient temperature on power demand, calculate the first power demand index by weighted sum, and compare and verify with the actual power consumption data. If the deviation is large, check the data, model and weight setting, and adjust it to the index to accurately reflect the power demand in the interval.

[0032] Step S330, taking the first electricity demand index as a constraint, taking the maximum proportion of new energy power generation as a goal, analyzing the energy power supply ratio according to the first predicted energy consumption power mean and the first predicted energy output power set, outputting the first predicted energy power supply ratio, and adding it to the predicted energy power supply ratio sequence. Specifically, in order to achieve the goal of maximum proportion of new energy power generation and meet the first electricity demand index constraint at the same time, an optimization model needs to be constructed. The proportion of new energy power supply such as photovoltaic, wind power, and energy storage is set as a decision variable, with a value between 0 and 1 and a sum of 1. The objective function is to maximize the sum of the proportion of new energy power supply, with the first electricity demand index, the output power of each power supply mode and its own physical limitations as constraints. A linear programming algorithm such as the simplex method is selected, the model is converted into a standard form and then solved, and the variable value is adjusted iteratively until the optimality condition is met, and a group of new energy power supply ratios such as photovoltaic 30% and wind power 40% are obtained. This result is sorted into the first predicted energy power supply ratio output, and added to the predicted energy power supply ratio sequence in chronological order to provide dynamic data support for energy planning.

[0033] In a possible implementation, the first power demand indicator is configured according to the first product output and the first ambient temperature in the first time interval, and step S320 further includes step S321, calculating the ratio of the first product output to the average product output in the historical time interval, and setting it as the first production intensity. Specifically, to calculate the first production intensity, the historical time interval must be determined according to the analysis purpose and data characteristics. If the impact of short-term production fluctuations on energy demand is concerned, a similar period in the recent period can be selected, such as the hour period that is the same as the first time interval every day in the past week; if a long-term trend analysis is performed, a wider period is covered, such as the same week in the same month of the past quarter. When selecting an interval, ensure that the data is available and stable, and avoid interference periods such as equipment maintenance. Then, collect product output data for the historical time interval from the production management system, unify the format and clean it, and select arithmetic mean, weighted mean or median according to the data distribution to calculate the product output mean. Finally, obtain the product output of the first time interval, divide it by the mean to obtain the first production intensity, which can reflect the change of the production intensity of the first time interval relative to the historical average level.

[0034] Step S322, calculate the ratio of the first ambient temperature to the average ambient temperature in the historical time interval, and set it as the first ambient intensity. Specifically, when calculating the first ambient intensity, first determine the historical time interval according to the analysis target. If you focus on short-term impacts, select similar time periods. If you study long-term trends, cover long periods, and avoid periods of abnormal temperature fluctuations to ensure stable and reliable data acquisition. Then collect data from multiple channels such as official meteorological monitoring stations, the park's own equipment, and professional data service providers, and check and clean abnormal values ​​and missing values. After that, select methods such as arithmetic mean or weighted mean to calculate the mean based on the characteristics of the data, and verify and adjust it with historical climate data. Finally, obtain the first ambient temperature from the same reliable source, and divide it by the mean to obtain the first ambient intensity, which reflects the degree of deviation of the ambient temperature in the first time interval from the historical average level.

[0035] Step S323, calculate the first power intensity according to the first production intensity and the first environmental intensity, and set the first power supply reliability coefficient according to the first power intensity as the first power demand indicator, wherein the power supply reliability coefficient and the power intensity are positively correlated. Specifically, the first power intensity is calculated by first analyzing the correlation of historical power consumption, production and environmental temperature data, and combining expert experience to determine the weights of the first production intensity and the first environmental intensity, such as setting them to 0.6 and 0.4 respectively. A weighted sum model is used, that is, , substitute the obtained intensity value to calculate the first power intensity, and get 1.122. Since the power supply reliability coefficient is positively correlated with the power intensity, a linear function is constructed , through regression analysis of historical data, k and b values ​​are determined, such as k=0.8 and b=0.1. The first power consumption intensity is substituted into the function to calculate the first power supply reliability coefficient, such as 0.9976, which is used as the first power demand indicator to provide a key basis for energy decision-making.

[0036] In a possible implementation, the first electricity demand index is used as a constraint, the maximum proportion of new energy power generation is used as a goal, and the energy power supply ratio is analyzed according to the first predicted energy consumption power mean and the first predicted energy output power set, and the first predicted energy power supply ratio is output, which is added to the predicted energy power supply ratio sequence. Step S330 further includes step S331, according to the historical power generation records, the stable power supply ratio of each power supply mode in the multi-source power supply mode in the predetermined historical time zone is respectively counted, and set as the historical power supply reliability coefficient, and multiple historical power supply reliability coefficients are obtained. Specifically, in order to calculate the historical power supply reliability coefficient, the power generation records of each multi-source power supply mode (such as photovoltaic, wind power, energy storage) in the predetermined historical time zone are first collected from multiple channels such as energy management system and power generation equipment log, and the errors, anomalies and missing values ​​are cleaned and corrected. Then, a stable power supply state is defined for different power supply modes, such as photovoltaic power generation power within the rated power ±10% fluctuation range, wind power within the normal operating power range, and energy storage charging and discharging power within a safe range and can be stably output. Then, according to this standard, the data is traversed at each time point, and the stable power supply time is accumulated, such as 6,000 hours for photovoltaic power, 5,000 hours for wind power, and 4,000 hours for energy storage in the past year. Finally, the stable power supply time of each power supply mode is divided by the total time to obtain the historical power supply reliability coefficient, such as about 0.685 for photovoltaic power, about 0.571 for wind power, and about 0.457 for energy storage. The coefficient is subsequently used for energy supply plan analysis.

[0037] Step S332, with the goal of meeting the first predicted energy consumption power mean, randomly generate the first initial energy power supply plan according to the predicted energy output power set, wherein the initial energy power supply plan includes the energy power supply ratio. Specifically, when generating the first initial energy power supply plan, with the goal of meeting the first predicted energy consumption power mean, work is carried out based on a set of predicted output powers of multiple power supply methods including photovoltaic, wind power, energy storage, etc. Through a random number generation algorithm, the energy power supply ratio is randomly assigned to each power supply method in the range of 0 to 1, and it is ensured that the sum of all ratios is 1, during which the rationality of the ratio is generated and verified multiple times. Based on the generated ratio and predicted output power, the power supply power of each power supply method is calculated, such as the photovoltaic power supply power is the product of its predicted output power and the ratio. Then, the power supply power of each power supply method is added to obtain the total power supply power, which is compared with the first predicted energy consumption power mean. If it is not satisfied, the ratio is adjusted and recalculated until the total power supply power meets the target requirements.

[0038] Step S333, taking the energy power supply proportion as the weight, based on the multiple historical power supply reliability coefficients, calculate the first overall power supply reliability coefficient of the first initial energy power supply scheme. Specifically, to calculate the first overall power supply reliability coefficient, first clarify the energy power supply proportion corresponding to each power supply mode from the first initial energy power supply scheme. For example, there are three power supply modes in the scheme: photovoltaic, wind power, and energy storage, and their respective power supply proportions are 0.3, 0.4, and 0.3, respectively. At the same time, we need to review the historical power supply reliability coefficients of each power supply mode obtained based on historical power generation records, just like the historical power supply reliability coefficient of photovoltaic is 0.685, wind power is 0.75, and energy storage is 0.8. Next, according to the weighted calculation method, the energy power supply proportion of each power supply mode is multiplied by its corresponding historical power supply reliability coefficient. Taking photovoltaic as an example, the energy power supply proportion of photovoltaic 0.3 is multiplied by its historical power supply reliability coefficient of 0.685 to obtain 0.2055. Similarly, wind power is 0.4 multiplied by 0.75, the result is 0.3; energy storage is 0.3 multiplied by 0.8, which is equal to 0.24. Finally, add up all these product results, that is, 0.2055 plus 0.3 plus 0.24, and the total of 0.7455 is the first overall power supply reliability coefficient. This coefficient reflects the overall power supply reliability level of the first initial energy power supply scheme, taking into account the power supply proportion of each power supply mode and their historical power supply reliability.

[0039] Step S334, if the first overall power supply reliability coefficient is greater than or equal to the first power demand index, the first initial energy supply scheme is retained, and the first new energy power generation ratio is calculated. Specifically, when evaluating the first initial energy supply scheme, the specific values ​​of the first overall power supply reliability coefficient and the first power demand index are first determined. The former is calculated by the ratio of each power supply mode in the scheme and the historical reliability coefficient, such as 0.8, and the latter is obtained by combining factors such as production and environmental intensity, assuming to be 0.75. Comparing the two, when the first overall power supply reliability coefficient is greater than or equal to the first power demand index, in this case 0.8≥0.75, the scheme meets the requirements and is retained, and the scheme contains information on the ratio of various power supply modes. Then it is clarified that photovoltaic power, wind power, etc. are new energy power supply modes, and their ratios are extracted from the retained schemes, such as photovoltaic power 0.3, wind power 0.4, and the first new energy power generation ratio is calculated to be 0.7 by adding them together. This ratio reflects the ratio of new energy in the power supply scheme under the reliability of power demand, which is of great significance for evaluating energy structure and sustainability.

[0040] Step S335, if the first overall power supply reliability coefficient is less than the first electricity demand index, it is discarded. Specifically, in the evaluation of energy power supply schemes, it is necessary to first clarify the first overall power supply reliability coefficient and the first electricity demand index. The former, such as a scheme containing photovoltaics, wind power, and energy storage, accounts for 0.3, 0.4, and 0.3 respectively, and the corresponding historical reliability coefficients are 0.6, 0.7, and 0.8, which are weighted calculated to be 0.69; the latter takes into account production and environmental intensity factors and is set to 0.75. Comparing the two, in this example, 0.69 is less than 0.75, indicating that the first initial energy power supply scheme cannot meet the power supply reliability requirements and is immediately discarded. After abandonment, the initial energy power supply scheme needs to be regenerated, and the energy power supply ratio is randomly generated again and combined with the predicted energy output power set, and the whole process is repeated until a scheme that meets the requirements is found.

[0041] Step S336, iterative selection, screening and calculation of the proportion of new energy power generation are performed until the predetermined number of selections is reached, and the energy power supply proportion corresponding to the maximum proportion of new energy power generation is output as the first predicted energy power supply proportion. Specifically, in the optimization of the energy power supply scheme, a predetermined number of selections is first set, such as 100 times, and the variables used to record the proportion of new energy power generation and the corresponding energy power supply proportion are initialized. In each iteration, the target is to meet the first predicted energy consumption power mean, and the initial energy power supply scheme is randomly generated according to the predicted energy output power set, assuming that the proportions of photovoltaic, wind power, and energy storage power supply are 0.25, 0.35, and 0.4 respectively. Then, the energy power supply proportion of this scheme is used as the weight, and the first overall power supply reliability coefficient is calculated in combination with the historical power supply reliability coefficient, such as 0.7325. Compared with the first electricity demand index (set to 0.7), if the requirements are met, the scheme is retained and the proportion of new energy power generation (0.6 in this case) is calculated, and the relevant data is recorded; if not, it is discarded. Repeatedly, until the predetermined number of selections is reached. After the completion, find out the largest proportion of renewable energy power generation in the record, such as 0.7, and its corresponding energy power supply proportion, and set it as the first predicted energy power supply proportion output, providing a key basis for energy planning decisions.

[0042] Step S400, calculate the carbon emissions of the predetermined future time zone according to the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply ratio sequence, and obtain the predicted carbon emissions as the carbon emission trend deduction result. Specifically, when calculating the carbon emissions of the predetermined future time zone, it is necessary to first collect data comprehensively. Clarify the unit energy carbon emission factors corresponding to different power supply methods, such as thermal power is assumed to be 0.8 tons of carbon dioxide / MWh, hydropower is 0.05 tons of carbon dioxide / MWh, wind power is 0.02 tons of carbon dioxide / MWh, etc. These data can be obtained from energy industry reports, etc. At the same time, obtain the predicted energy consumption sequence, for example, with hourly intervals, and the predicted values ​​for the next 24 hours are such as [100,120,110,…,90] MWh. There is also a predicted energy power supply ratio sequence obtained through previous iterative screening, which is assumed to be a two-dimensional array to present the proportions of each power supply method. Then, the carbon emissions are calculated. For each time node, the energy supply of each power supply mode is calculated based on the predicted energy consumption and power supply ratio, and then the carbon emissions are calculated by combining the unit energy carbon emission factor. The total carbon emissions at the time node are accumulated to generate the predicted carbon emissions sequence. Finally, this sequence is output as the result of carbon emission trend deduction, which can be displayed in charts or data tables to provide decision-making basis for energy planning and carbon emission management.

[0043] The embodiment of the present application adopts a method of combining the production plan and climate characteristics of the industrial park in the future period to predict the energy consumption sequence of P consecutive time points, and predicts the output power sequence of multi-source energy based on the historical power generation records; on this basis, the energy supply ratio is analyzed and the power supply ratio sequence is generated, and finally the energy consumption sequence and the power supply ratio sequence are integrated using the unit energy carbon emission factor to calculate the carbon emissions in the future time zone, so as to realize the accurate deduction of the carbon emission trend, and achieve the technical effect of reducing the error rate of carbon emission prediction and improving the dynamic optimization response speed of the new energy power supply ratio.

[0044] In the above, refer to Figure 1 The carbon emission trend deduction method of a digital park according to an embodiment of the present invention is described in detail. Figure 2 A digital park carbon emission trend deduction system according to an embodiment of the present invention is described.

[0045] The digital park carbon emission trend deduction system according to the embodiment of the present invention is used to solve the technical problems of insufficient multi-source energy collaborative modeling and lagging dynamic power supply ratio optimization in the existing park carbon emission prediction, and achieves the technical effect of reducing the carbon emission prediction error rate and improving the dynamic optimization response speed of the new energy power supply ratio. The digital park carbon emission trend deduction system includes: a predicted energy consumption sequence generation module 10, a predicted energy output power sequence generation module 20, an energy power supply ratio analysis module 30, and a carbon emission calculation module 40.

[0046] The predicted energy consumption sequence generation module 10 is used to perform energy consumption forecasting at P consecutive time points according to the production plan and climate characteristics of the industrial park in a predetermined future time zone, and generate a predicted energy consumption sequence.

[0047] The predicted energy output power sequence generation module 20 is used to perform multi-energy output power prediction at P consecutive time points according to historical power generation records, and generate multiple predicted energy output power sequences.

[0048] The energy supply proportion analysis module 30 is used to perform energy supply proportion analysis based on the predicted energy consumption sequence and multiple predicted energy output power sequences to generate a predicted energy supply proportion sequence.

[0049] The carbon emission calculation module 40 is used to calculate the carbon emissions in the predetermined future time zone according to the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply ratio sequence, and obtain the predicted carbon emissions as the carbon emission trend deduction result.

[0050] Next, the specific configuration of the predicted energy consumption sequence generation module 10 will be described in detail. As described above, according to the production plan and climate characteristics of the industrial park in the predetermined future time zone, energy consumption is predicted at P consecutive time points to generate a predicted energy consumption sequence. The predicted energy consumption sequence generation module 10 further includes: a climate characteristic acquisition unit, the climate characteristic acquisition unit is used to acquire the production plan and climate characteristics of the industrial park in the predetermined future time zone, wherein the production plan is the expected product output and the climate characteristic is the expected ambient temperature; a time interval division unit, the time interval division unit is used to set P consecutive time points in the predetermined future time zone according to a predetermined time interval, and divide and obtain P time intervals, wherein P is an integer greater than 30; an energy consumption related data determination unit, the energy consumption related data determination unit is used to divide and combine the production plan and climate characteristics according to the P time intervals, and determine P energy consumption related data; a power mean calculation unit, the power mean calculation unit is used to use the energy consumption prediction plug-in to predict according to the P energy consumption related data respectively, output P predicted energy consumption amounts, calculate P predicted energy consumption power means, and construct the predicted energy consumption sequence.

[0051] Among them, using the energy consumption prediction plug-in, predictions are made according to the P energy consumption related data respectively, P predicted energy consumptions are output, and the P predicted energy consumption power means are calculated to construct the predicted energy consumption sequence. The power mean calculation unit further includes: an associated data set acquisition subunit, the associated data set acquisition subunit is used to collect sample energy consumption related data sets based on the historical production records of the industrial park, and count the energy consumption corresponding to different energy consumption related data according to the historical electricity consumption records, set it as the sample energy consumption, and construct a sample energy consumption set; an energy consumption prediction branch acquisition subunit, the energy consumption prediction branch acquisition subunit is used to use the sample energy consumption related data set and the sample energy consumption set as training data, respectively train multiple prediction operators, and harvest multiple energy consumption prediction branches; an energy consumption prediction plug-in construction subunit, the energy consumption prediction plug-in construction subunit is used to integrate and construct the energy consumption prediction plug-in according to the multiple energy consumption prediction branches, wherein the output of the energy consumption prediction plug-in is the mean of the outputs of the multiple energy consumption prediction branches.

[0052] Among them, the sample energy consumption associated data set and the sample energy consumption amount set are used as training data, and multiple prediction operators are trained respectively to obtain multiple energy consumption prediction branches. The energy consumption prediction branch acquisition subunit further includes: a prediction operator configuration microunit, which is used to configure K prediction operators based on machine learning, where K is greater than or equal to 3; a loss function convergence microunit, which is used to divide the training data into K equal parts, and perform supervised training and verification on the K prediction operators respectively until the loss function converges to obtain multiple energy consumption prediction branches.

[0053] The specific configuration of the predicted energy output power sequence generation module 20 will be described in detail below. As described above, based on the historical power generation records, the multi-energy output power is predicted at P consecutive time points to generate multiple predicted energy output power sequences. The predicted energy output power sequence generation module 20 further includes: a power supply mode acquisition unit, the power supply mode acquisition unit is used to acquire the multi-source power supply mode of the industrial park, and multiple historical power generation records of the multi-source power supply mode; a power generation impact data set acquisition unit, the power generation impact data set acquisition unit is used to acquire P power generation impact data sets of the multi-source power supply mode within P time intervals; an integrated power predictor construction unit, the integrated power predictor construction unit is used to construct an integrated power predictor based on machine learning according to historical power generation records, and perform multi-energy output power predictions according to the P power generation impact data sets to generate multiple predicted energy output power sequences.

[0054] The specific configuration of the energy supply ratio analysis module 30 will be described in detail below. As described above, based on the predicted energy consumption sequence and multiple predicted energy output power sequences, an energy supply ratio analysis is performed to generate a predicted energy supply ratio sequence, and the energy supply ratio analysis module 30 further includes: a first time point selection unit, the first time point selection unit is used to select the first predicted energy consumption power mean and the first predicted energy output power set at the first time point; a demand index configuration unit, the demand index configuration unit is used to configure the first electricity demand index according to the first product output and the first ambient temperature in the first time interval; a first predicted energy supply ratio output unit, the first predicted energy supply ratio output unit is used to take the first electricity demand index as a constraint, take the maximum proportion of new energy power generation as a goal, perform energy supply ratio analysis according to the first predicted energy consumption power mean and the first predicted energy output power set, output the first predicted energy supply ratio, and add it to the predicted energy supply ratio sequence.

[0055] Among them, the first electricity demand index is configured according to the first product output and the first ambient temperature in the first time interval, and the demand index configuration unit further includes: a product output mean ratio calculation subunit, the product output mean ratio calculation subunit is used to calculate the ratio of the first product output to the average product output in the historical time interval, and set it as the first production intensity; a first environmental intensity setting subunit, the first environmental intensity setting subunit is used to calculate the ratio of the first ambient temperature to the average ambient temperature in the historical time interval, and set it as the first environmental intensity; a first electricity intensity calculation subunit, the first electricity intensity calculation subunit is used to calculate the first electricity intensity according to the first production intensity and the first environmental intensity, and set the first power supply reliability coefficient according to the first electricity intensity as the first electricity demand index, wherein the power supply reliability coefficient is positively correlated with the electricity intensity.

[0056] Among them, taking the first electricity demand indicator as a constraint and the maximum proportion of new energy power generation as a goal, an energy supply ratio analysis is performed according to the first predicted energy consumption power mean and the first predicted energy output power set, and the first predicted energy supply ratio is output and added to the predicted energy supply ratio sequence. The first predicted energy supply ratio output unit further includes: a stable power supply ratio statistical subunit, the stable power supply ratio statistical subunit is used to count the stable power supply ratio of each power supply mode in the multi-source power supply mode within a predetermined historical time zone according to historical power generation records, set it as a historical power supply reliability coefficient, and obtain multiple historical power supply reliability coefficients; a first initial energy power supply plan generation subunit, the first initial energy power supply plan generation subunit is used to randomly generate a first initial energy power supply plan according to the predicted energy output power set with the goal of meeting the first predicted energy consumption power mean, wherein the initial energy power supply plan includes energy power proportion; a reliability coefficient calculation subunit, the reliability coefficient calculation subunit is used to calculate the first overall power supply reliability coefficient of the first initial energy power supply scheme based on the multiple historical power supply reliability coefficients with the energy power supply proportion as a weight; a first new energy power generation proportion calculation subunit, the first new energy power generation proportion calculation subunit is used to retain the first initial energy power supply scheme and calculate the first new energy power generation proportion if the first overall power supply reliability coefficient is greater than or equal to the first electricity demand index; an electricity demand index determination subunit, the electricity demand index determination subunit is used to discard if the first overall power supply reliability coefficient is less than the first electricity demand index; a predetermined selection number determination subunit, the predetermined selection number determination subunit is used to perform iterative selection, screening and new energy power generation proportion calculation until the predetermined selection number is reached, and the energy power supply proportion corresponding to the maximum new energy power generation proportion is output as the first predicted energy power supply proportion.

[0057] The digital park carbon emission trend deduction system provided in the embodiment of the present invention can execute the digital park carbon emission trend deduction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0058] Based on the foregoing embodiments, an embodiment of the present application further provides an electronic device, which, when executing a processor of the electronic device, can implement the method described in any of the foregoing embodiments.

[0059] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an implementation of the present invention. Figure 3The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The electronic device is in the form of a general computing device, and its components may include but are not limited to an input device 201, a processor 202, a memory 203, and an output device 204. Among them, the processor 202 may be one or more; the processor 202 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 203, that is, realizing the above-mentioned digital park carbon emission trend deduction method.

[0060] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0061] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A digital park carbon emission trend deduction method, characterized in that: Methods include: According to the production plan and climate characteristics of the industrial park in the predetermined future time zone, the energy consumption at P consecutive time points is predicted to generate a predicted energy consumption sequence; According to the historical power generation records, multiple energy output power forecasts are carried out at P consecutive time points to generate multiple predicted energy output power sequences; Based on the predicted energy consumption sequence and multiple predicted energy output power sequences, energy power supply ratio analysis is performed to generate a predicted energy power supply ratio sequence; The carbon emissions in the predetermined future time zone are calculated according to the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply ratio sequence, and the predicted carbon emissions are obtained as the carbon emission trend deduction result.

2. The digital park carbon emission trend deduction method according to claim 1 is characterized in that: According to the production plan and climate characteristics of the industrial park in the predetermined future time zone, the energy consumption at P consecutive time points is predicted to generate a predicted energy consumption sequence, including: Obtain the production plan and climate characteristics of the industrial park in a predetermined future time zone, where the production plan is the expected product output and the climate characteristics are the expected ambient temperature; Setting P consecutive time points in the predetermined future time zone at predetermined time intervals, and dividing and obtaining P time intervals, where P is an integer greater than 30; Dividing and combining the production plan and climate characteristics according to the P time intervals to determine P energy consumption related data; By using the energy consumption prediction plug-in, predictions are made according to the P energy consumption related data respectively, P predicted energy consumption amounts are output, the P predicted energy consumption power means are calculated, and the predicted energy consumption sequence is constructed.

3. The digital park carbon emission trend deduction method according to claim 2 is characterized in that: Build an energy consumption forecast plugin, including: Based on the historical production records of the industrial park, a sample energy consumption related data set is collected, and the energy consumption corresponding to different energy consumption related data is counted according to the historical electricity consumption records, which is set as the sample energy consumption, and a sample energy consumption set is constructed; The sample energy consumption associated data set and the sample energy consumption amount set are used as training data to train multiple prediction operators respectively, and multiple energy consumption prediction branches are obtained; The energy consumption prediction plug-in is constructed based on the integration of the multiple energy consumption prediction branches, wherein the output of the energy consumption prediction plug-in is the average of the outputs of the multiple energy consumption prediction branches.

4. The digital park carbon emission trend deduction method according to claim 3 is characterized in that: Train multiple prediction operators separately to obtain multiple energy consumption prediction branches, including: Configure K prediction operators based on machine learning, where K is greater than or equal to 3; The training data is equally divided into K parts, and supervised training and verification are performed on the K prediction operators respectively until the loss function converges, thereby obtaining a plurality of energy consumption prediction branches.

5. The digital park carbon emission trend deduction method according to claim 2 is characterized in that: According to the historical power generation records, the multi-energy output power forecast is carried out at P consecutive time points to generate multiple predicted energy output power sequences, including: Obtain the multi-source power supply mode of the industrial park and multiple historical power generation records of the multi-source power supply mode; Acquire P power generation impact data sets of the multi-source power supply mode within P time intervals; According to historical power generation records, an integrated power predictor is constructed based on machine learning, and multi-energy output power predictions are performed separately according to the P power generation impact data sets to generate multiple predicted energy output power sequences.

6. The method for deriving carbon emission trends of a digital park according to claim 2 is characterized in that: Based on the predicted energy consumption sequence and multiple predicted energy output power sequences, energy power supply ratio analysis is performed to generate a predicted energy power supply ratio sequence, including: Selecting a first predicted energy consumption power mean value and a first predicted energy output power set at a first time point; configuring a first electricity demand indicator according to a first product output and a first ambient temperature in a first time interval; Taking the first electricity demand indicator as a constraint and the maximum proportion of new energy power generation as the goal, an energy supply ratio analysis is performed based on the first predicted energy consumption power mean and the first predicted energy output power set, and the first predicted energy supply ratio is output and added to the predicted energy supply ratio sequence.

7. The method for deriving carbon emission trends of a digital park according to claim 6 is characterized in that: Configuring a first power demand indicator according to a first product output and a first ambient temperature in a first time interval includes: Calculate the ratio of the output of the first product to the average output of the product in the historical time interval, and set it as the first production intensity; Calculate the ratio of the first ambient temperature to the average ambient temperature in a historical time interval, and set it as the first ambient intensity; A first power consumption intensity is calculated according to the first production intensity and the first environmental intensity, and a first power supply reliability coefficient is set according to the first power consumption intensity as a first power demand indicator, wherein the power supply reliability coefficient is positively correlated with the power consumption intensity.

8. The method for deriving carbon emission trends of a digital park according to claim 7 is characterized in that: Output the first predicted energy supply ratio, including: According to the historical power generation records, the stable power supply ratio of each power supply mode in the multi-source power supply mode within the predetermined historical time zone is counted respectively, which is set as the historical power supply reliability coefficient, and multiple historical power supply reliability coefficients are obtained; With the first predicted energy consumption power mean as the goal, a first initial energy power supply plan is randomly generated according to the predicted energy output power set, wherein the initial energy power supply plan includes an energy power supply ratio; Taking the energy power supply proportion as a weight and based on the multiple historical power supply reliability coefficients, a first overall power supply reliability coefficient of the first initial energy power supply scheme is calculated; If the first overall power supply reliability coefficient is greater than or equal to the first power demand index, the first initial energy power supply plan is retained, and the first new energy power generation ratio is calculated; If the first overall power supply reliability coefficient is less than the first power demand index, then discard it; Iterative selection, screening and calculation of the proportion of new energy power generation are performed until the predetermined number of selections is reached, and the energy supply proportion corresponding to the maximum proportion of new energy power generation is output as the first predicted energy supply proportion.

9. The digital park carbon emission trend deduction system is characterized by: The system is used to implement the digital park carbon emission trend deduction method according to any one of claims 1 to 8, and the system includes: A predicted energy consumption sequence generation module, wherein the predicted energy consumption sequence generation module is used to perform energy consumption forecasting at P consecutive time points according to the production plan and climate characteristics of the industrial park in a predetermined future time zone, and generate a predicted energy consumption sequence; A predicted energy output power sequence generation module, wherein the predicted energy output power sequence generation module is used to perform multi-energy output power prediction at P consecutive time points according to historical power generation records, and generate multiple predicted energy output power sequences; An energy supply ratio analysis module, the energy supply ratio analysis module is used to perform energy supply ratio analysis based on the predicted energy consumption sequence and multiple predicted energy output power sequences, and generate a predicted energy supply ratio sequence; A carbon emission calculation module is used to calculate the carbon emissions in the predetermined future time zone according to the unit energy carbon emission factor, the predicted energy consumption sequence and the predicted energy power supply ratio sequence, and obtain the predicted carbon emissions as the carbon emission trend deduction result.

10. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the digital park carbon emission trend deduction method described in any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images