Green power consumption traceability method and system based on block chain technology

Abstract

The invention is suitable for the technical field of green power consumption traceability, and provides a green power consumption traceability method and system based on a block chain technology, and the method comprises the steps: obtaining initial data of a power generation link, a power transmission link, a power distribution link and a user side; constructing a power generation model, a power transmission model, a power distribution model and a user side model based on the initial data; extracting historical data related to green power consumption from the historical database, constructing a statistical model, and calibrating and optimizing the power generation model, the power transmission model, the power distribution model and the user side model by using the statistical model; respectively performing uncertainty analysis on the models to obtain a comprehensive evaluation result; performing encryption processing on the comprehensive evaluation result, the initial data, the model parameters and the data processing timestamp information through a block chain encryption technology, and storing the data to a block chain; and according to the query request of the user, a corresponding green power consumption traceability visualization result is generated, so that the green power consumption traceability depth and precision are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of green electricity consumption traceability technology, and in particular to a green electricity consumption traceability method and system based on blockchain technology. Background Art

[0002] Blockchain is a distributed ledger maintained by multiple nodes. In the green power consumption traceability, all participants, including power generation companies, transmission companies, distribution companies, power sales companies and users, can serve as a node in the blockchain network. The data in the blockchain is encrypted and linked through cryptographic technology to form blocks, each of which contains the hash value of the previous block. A smart contract is an automatically executed contract condition deployed on the blockchain in the form of code. In the green power consumption traceability process, smart contracts can define various rules, such as the settlement rules for green power transactions, data update and verification rules, etc.

[0003] In the existing technology, in the process of tracing the source of green electricity consumption, it is impossible to accurately obtain the detailed information of each power generation unit or consumption terminal, as well as the volatility of information. This results in insufficient data granularity, leading to problems of low traceability depth and accuracy. Summary of the invention

[0004] The embodiments of the present application provide a green electricity consumption traceability method and system based on blockchain technology, which is used to solve the problem of low traceability depth and accuracy.

[0005] The first aspect of the embodiment of the present application provides a green electricity consumption tracing method based on blockchain technology, including:

[0006] Obtain initial data from power generation, transmission, distribution and user end;

[0007] Constructing a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data;

[0008] Extracting historical data related to green electricity consumption from a historical database, building a statistical model based on the characteristics of the historical data, and using the statistical model to calibrate and optimize the power generation model, transmission model, distribution model, and user-end model;

[0009] Perform uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and perform uncertainty analysis on the statistical model at the same time to obtain a comprehensive evaluation result;

[0010] The comprehensive evaluation results, initial data, model parameters and data processing timestamp information are encrypted and stored on the blockchain through blockchain encryption technology;

[0011] Generate corresponding green electricity consumption traceability visualization results based on the user's query request.

[0012] Furthermore, the constructing of a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data includes:

[0013] Power generation model:

[0014]

[0015] Where: P solar is the output power of solar power generation, P STC is the power generated under standard test conditions, G and G STC are the actual light intensity and the light intensity under standard test conditions, respectively; k is the power temperature coefficient; T and T STC are the actual temperature of the solar panel and the temperature of the solar panel under standard test conditions, P wind is the output power of wind power generation, v is the wind speed at the hub height of the wind turbine, v r is the rated wind speed, v ci and v co are the cut-in and cut-out wind speeds, ρ is the air density, A is the swept area of ​​the fan blade, C p is the wind energy utilization coefficient, P r is the rated power;

[0016] Transmission Model:

[0017]

[0018] Where: Δ is the power loss of the transmission line, I, R, P, and U are the line current, resistance, transmission power, and transmission voltage, respectively. is the power factor, ΔU is the voltage drop, Q is the reactive power, and C is the line reactance;

[0019] Power distribution model:

[0020]

[0021] S1=P1+jQ1,S2=P2+jQ2

[0022] Where: P i is the injected active power of node i, Q i is the injected reactive power of node i, U i is the voltage at node i, Y ij is the element of the node admittance matrix, n is the number of distribution network nodes, and is the conjugate complex number, j is the imaginary unit, j 2=1, U1 and U2 are the voltages on the primary and secondary sides of the transformer, N1 and N2 are the turns on the primary and secondary sides of the transformer, P1 and Q1 are the active power and reactive power on the primary side of the transformer, P2 and Q2 are the active power and reactive power on the secondary side of the transformer, S1 and S2 are the apparent power on the primary and secondary sides of the transformer;

[0023] User-side model:

[0024]

[0025] Among them: P' is the power of the electrical equipment, U' is the voltage across the equipment, I' is the current of the equipment, R' is the resistance of the equipment, P total is the total power load of users, P i ′ is the power of the ith electrical device, and n′ is the number of electrical devices of the user.

[0026] Furthermore, the historical data related to green electricity consumption is extracted from the historical database, a statistical model is constructed according to the characteristics of the historical data, and the statistical model is used to calibrate and optimize the power generation model, the transmission model, the distribution model and the user-end model, including:

[0027] Filtering characteristic variables that meet correlation conditions based on the historical data;

[0028] Inputting the characteristic variables into the constructed multiple linear regression model for model training to obtain a trained statistical model;

[0029] Based on the trained statistical model, the future green electricity consumption indicators are predicted and the impact of different factors on green electricity consumption is analyzed.

[0030] Furthermore, the historical data related to green electricity consumption is extracted from the historical database, a statistical model is constructed according to the characteristics of the historical data, and the statistical model is used to calibrate and optimize the power generation model, the transmission model, the distribution model and the user-end model, including:

[0031] Determining calibration parameters in the power generation model, the power transmission model, the power distribution model and the user-end model;

[0032] Calculating the difference between the results of the power generation model, the power transmission model, the power distribution model and the user-end model and the result of the statistical model;

[0033] The calibration parameters are adjusted based on the calculated differences.

[0034] Furthermore, the adjusting the calibration parameters according to the calculated differences includes:

[0035]

[0036] Where: X is the calibration parameter, X new To adjust the updated parameters, X old is the current parameter, α is the learning rate, is the partial derivative of the difference index with respect to X.

[0037] Furthermore, the uncertainty analysis is performed on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and the uncertainty analysis is performed on the statistical model at the same time, to obtain a comprehensive evaluation result, including:

[0038] Determining the uncertainty distribution of the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and calculating the probability distribution of the model based on the uncertainty distribution of the input parameters;

[0039] Calculating a probability distribution of a model based on the uncertainty distribution of the statistical model;

[0040] A comprehensive probability distribution is determined according to the probability distributions of the power generation model, the power transmission model, the power distribution model and the user-end model and the probability distribution of the statistical model.

[0041] Furthermore, the determining the uncertainty distribution of the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and calculating the probability distribution of the model based on the uncertainty distribution of the input parameters, includes:

[0042] Determining the uncertainty distribution of input parameters of the power generation model, the power transmission model, the power distribution model and the user-end model respectively;

[0043] The Monte Carlo algorithm is used to perform parameter sampling based on the uncertain distribution of the input parameters of the power generation model, the power transmission model, the power distribution model and the user-end model, and the extracted parameters are substituted into the power generation model, the power transmission model, the power distribution model and the user-end model respectively to obtain the corresponding probability distribution.

[0044] Furthermore, the probability distribution of the uncertainty distribution calculation model based on the statistical model includes:

[0045] Confidence intervals of parameters of the statistical model are determined, and a probability distribution of the statistical model is calculated based on the confidence intervals of the parameters of the statistical model.

[0046] Furthermore, determining the comprehensive probability distribution according to the probability distributions of the power generation model, the power transmission model, the power distribution model and the user-end model and the probability distribution of the statistical model includes:

[0047] Calculate the comprehensive probability distribution corresponding to the probability distribution of the power generation model, the power transmission model, the power distribution model and the user-end model and the probability distribution of the statistical model according to the Bayesian theorem;

[0048] The mean, standard deviation and confidence interval of the comprehensive probability distribution are calculated to obtain the uncertainty result of the comprehensive assessment.

[0049] The second aspect of the embodiment of the present application provides a green electricity consumption traceability system based on blockchain technology, including:

[0050] An initial data acquisition unit, used to acquire initial data of power generation, transmission, distribution and user ends;

[0051] A model building unit, used to build a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data;

[0052] Model calibration and oiler unit, used to extract historical data related to green power consumption from the historical database, build a statistical model according to the characteristics of the historical data, and use the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model;

[0053] A comprehensive evaluation result determination unit is used to perform uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and to perform uncertainty analysis on the statistical model at the same time, to obtain a comprehensive evaluation result;

[0054] A blockchain on-chain unit, used to encrypt and store the comprehensive evaluation results, initial data, model parameters and data processing timestamp information on the blockchain through blockchain encryption technology;

[0055] The traceability result generation unit is used to generate corresponding green electricity consumption traceability visualization results according to the user's query request.

[0056] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0057] The present invention obtains the initial data of the power generation link, the power transmission link, the power distribution link and the user end, which can lay a solid data foundation for the entire green power consumption analysis system; constructs the power generation model, the power transmission model, the power distribution model and the user end model based on the initial data, which can accurately describe the flow and change process of green power in each link from the physical principle level; extracts historical data related to green power consumption from the historical database, constructs a statistical model according to the characteristics of the historical data, and uses the statistical model to calibrate and optimize the power generation model, the power transmission model, the power distribution model and the user end model, which can dig out the hidden relationship between the green power consumption and various factors such as meteorology, economy, time, etc. and the long-term change trend; performs uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user end model respectively, and performs uncertainty analysis on the statistical model at the same time. Qualitative analysis can obtain comprehensive assessment results, which can comprehensively identify the risks that may be faced in the process of green electricity consumption. The results obtained through comprehensive assessment show the degree and scope of uncertainty in each link in a quantitative form; the comprehensive assessment results, initial data, model parameters and data processing timestamp information are encrypted and stored on the blockchain through blockchain encryption technology, and the corresponding green electricity consumption traceability visualization results are generated according to the user's query request. The chain structure and timestamp function of the blockchain enable the source, processing process and changes of the data to be clearly recorded and traced. The intuitive visualization form presents complex green electricity consumption-related data and analysis results, allowing users to quickly and clearly understand the entire process from green electricity generation to consumption and the key information of each link, effectively improving the depth and accuracy of green electricity consumption traceability.

[0058] Other advantages, objectives, and features of the present invention will be set forth in part in the following description, and in part will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a schematic diagram of an embodiment of a green electricity consumption traceability method based on blockchain technology in the present invention. DETAILED DESCRIPTION

[0060] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "corresponding to" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] Embodiment 1

[0062] The implementation method in this embodiment can be implemented in the system, can be implemented in the server, and can also be implemented in the terminal, without explicit limitation. The following will introduce the green power consumption traceability method based on blockchain technology in this application from the perspective of system implementation. Figure 1 , the method provided in the embodiment of the present application comprises the following steps:

[0063] S11. Obtaining initial data of power generation, transmission, distribution and user terminals;

[0064] The initial data of the power generation link includes basic equipment information data, operating status data, and resource-related data. The basic equipment information data includes equipment type and specifications, equipment location and layout data; the operating status data includes real-time power generation, voltage and current data, equipment health indicators and other data; resource-related data includes meteorological data, fuel data, etc. The transmission link includes line physical parameter data, operating electrical parameter data, and topological structure data. The line physical parameters include line length, material and cross-sectional area, tower information, etc. The operating electrical parameter data includes current and voltage, power and power factor, line temperature, etc. The topological structure data includes substation location and connection relationship related data. The distribution link includes distribution network parameter data, operating status data, and user access data. The distribution network parameter data includes distribution line parameters, distribution transformer parameters, and switchgear parameters; the operating status data includes node voltage and current, power and power factor, transformer load rate and oil temperature, etc.; user access data includes user location and access method, user capacity and electricity type, etc. The user end includes power equipment data, user behavior data, and user basic information data.

[0065] S12. Constructing a power generation model, a transmission model, a distribution model and a user-end model based on the initial data;

[0066] Power generation model:

[0067]

[0068]

[0069] Where: P solar is the output power of solar power generation, P STC is the power generated under standard test conditions, G and G STC are the actual light intensity and the light intensity under standard test conditions, respectively; k is the power temperature coefficient; T and T STC are the actual temperature of the solar panel and the temperature of the solar panel under standard test conditions, P wind is the output power of wind power generation, v is the wind speed at the hub height of the wind turbine, v r is the rated wind speed, v ci and v co are the cut-in and cut-out wind speeds, ρ is the air density, A is the swept area of ​​the fan blade, C p is the wind energy utilization coefficient, P r is the rated power;

[0070] Transmission Model:

[0071]

[0072] Where: ΔP is the power loss of the transmission line, I, R, P, and U are the line current, resistance, transmission power, and transmission voltage, respectively. is the power factor, ΔU is the voltage drop, Q is the reactive power, and C is the line reactance;

[0073] Power distribution model:

[0074]

[0075] S1=P1+jQ1,S2=P2+jQ2

[0076] Where: P i is the injected active power of node i, Q i is the injected reactive power of node i, U i is the voltage at node i, Y ij is the element of the node admittance matrix, n is the number of distribution network nodes, and is the conjugate complex number, j is the imaginary unit, j 2=1, U1 and U2 are the voltages on the primary and secondary sides of the transformer, N1 and N2 are the turns on the primary and secondary sides of the transformer, P1 and Q1 are the active power and reactive power on the primary side of the transformer, P2 and Q2 are the active power and reactive power on the secondary side of the transformer, S1 and S2 are the apparent power on the primary and secondary sides of the transformer;

[0077] User-side model:

[0078]

[0079] Among them: P' is the power of the electrical equipment, U' is the voltage across the equipment, I' is the current of the equipment, R' is the resistance of the equipment, P total is the total power load of users, P i ′ is the power of the ith electrical device, and n′ is the number of electrical devices of the user.

[0080] S13. Extract historical data related to green power consumption from the historical database, build a statistical model based on the characteristics of the historical data, and use the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model;

[0081] In this embodiment, historical data related to green power consumption is extracted from the historical database, and a statistical model is constructed according to the characteristics of the historical data, including the following:

[0082] 1. Screening feature variables that meet the correlation conditions based on historical data;

[0083] Collect historical data covering all aspects of green power consumption from relevant databases, including power generation, such as power generation and power generation of different types of power generation equipment, transmission, such as transmission loss and voltage level, distribution, such as distribution line parameters and node voltage, user, such as power consumption and power consumption time, and external influencing factors, such as meteorological data, economic data, and policy implementation. Clean the collected data, process missing values ​​and outliers, and ensure data quality and integrity.

[0084] Here, the Pearson correlation coefficient is used to measure the degree of linear correlation between two variables. The correlation threshold is set according to business experience and data analysis requirements. Finally, the characteristic variables that pass the correlation test and do not have serious multicollinearity problems are screened out as input variables for the subsequent construction of the multiple linear regression model.

[0085] 2. Input the characteristic variables into the constructed multiple linear regression model for model training to obtain a trained statistical model;

[0086] The expression of the multiple linear regression model is set as:

[0087] y=β0+β1x1+β2x2+…+β p x p +∈

[0088] Among them: y is the green power consumption index, x1, x2,…, x p are the p selected characteristic variables, β0 is the intercept term, β1, β2,…, β p is the regression coefficient to be estimated, ∈ is the random error term, which is assumed to have a mean of 0 and a variance of σ 2 The normal distribution of .

[0089] The sorted and screened historical data set is divided into a training set and a test set according to a certain ratio. The least squares method is used to find a set of regression coefficients so that the sum of squared errors between the predicted value and the actual observed value is minimized. By taking partial derivatives of the squared errors with respect to the regression coefficients and setting the partial derivatives equal to 0, the normal equations can be obtained, and then the estimated values ​​of the regression coefficients can be solved. The trained model is used to predict the test set data, and the evaluation indicators are calculated to measure the performance of the model. If the model performance is not ideal, the model is adjusted and retrained and evaluated until satisfactory model performance is obtained, and a trained statistical model is obtained.

[0090] 3. Predict future green electricity consumption indicators based on the trained statistical model and analyze the impact of different factors on green electricity consumption.

[0091] According to the forecasting needs, collect the characteristic variable data related to green power consumption in the future. For example, if the characteristic variable includes meteorological factors, the future weather forecast data of the meteorological department can be obtained; for economic-related variables, the data of economic forecasting agencies can be referred to or reasonable estimates can be made based on economic development trends. Ensure that the format and range of the acquired data are consistent with the characteristic variables used in model training. Substitute the acquired future characteristic variable data into the trained multivariate linear regression model, and calculate the predicted value of the green power consumption index according to the model formula. Determine the size and sign of the regression coefficient corresponding to each characteristic variable in the model. The sign of the coefficient indicates the direction of influence. A positive value indicates that the characteristic variable is positively correlated with the green power consumption index, that is, when the variable increases, the green power consumption index will increase; a negative value indicates a negative correlation, and an increase in the variable will cause the green power consumption index to decrease. For example, if the regression coefficient corresponding to a certain meteorological factor is positive, it means that the better the meteorological conditions are, the more conducive it is to green power consumption. The absolute value of the coefficient reflects the degree of influence. The larger the absolute value, the more significant the influence of the variable on the green power consumption index.

[0092] In addition, statistical models are used to calibrate and optimize the power generation model, transmission model, distribution model and user-side model, including the following:

[0093] 1. Determine the calibration parameters in the power generation model, transmission model, distribution model and user-side model;

[0094] For solar power generation models, key calibration parameters include power generation under standard test conditions and power temperature coefficient. In addition, if dust coverage, shadowing and other factors are taken into account, a comprehensive efficiency correction factor is also involved. For wind power generation models, calibration objects include wind energy utilization factor, air density, wind turbine blade swept area, cut-in wind speed, rated wind speed, cut-out wind speed and rated power.

[0095] The line resistance of the power loss calculation model is the main calibration parameter, and the power factor also needs to be calibrated, because the load conditions in the actual power grid are complex and the power factor may be inconsistent with the theoretical calculation. In the voltage drop calculation model, the line resistance and line reactance are the key calibration parameters. In addition, the transmission power and reactive power also need to be calibrated according to the actual situation.

[0096] The elements of the node admittance matrix and the injected power of the node in the distribution network power flow calculation model are calibration parameters. In the distribution transformer model, the apparent power and the loss parameters of the transformer in the power conservation formula are calibration parameters.

[0097] In the user's electrical equipment power model, the equipment resistance is the main calibration parameter. For non-resistive loads, the inductance, capacitance and other parameters as well as the change of power factor also need to be considered. The power of each electrical equipment in the user's total load model is the focus of calibration, and the number of equipment also needs to be adjusted according to actual conditions.

[0098] 2. Calculate the difference between the results of the power generation model, the power transmission model, the power distribution model and the user-end model and the results of the statistical model;

[0099] It should be noted that the physical model and the statistical model should be calculated under the same input conditions. For example, for the power generation model, the same meteorological data, equipment parameters, etc. are used as inputs; for the transmission model, the same transmission power, line parameters, etc. are used as inputs. Choose an appropriate time range or sample point for comparison. It can be continuous data within a specific time period, or a number of representative sample data points.

[0100] Difference calculation includes calculating mean square error, average decision error and relative error. According to the selected difference calculation method, the difference indicators between the power generation model, transmission model, distribution model and user-end model and the statistical model are calculated respectively. For example, for the power generation model, under a given set of light intensity and temperature data, the power generation power is calculated using the physical power generation model and the statistical model respectively, and then the difference indicators such as MSE, MAE or RE between them are calculated.

[0101] 3. Adjust the calibration parameters based on the calculated differences.

[0102] According to the description in step 2 above, the gradient descent method is used for optimization. Taking the above MSE as an example, taking the power temperature coefficient k in the power generation model as an example, assuming that the difference index is MSE(k), the update formula is:

[0103]

[0104] Where: k new is the updated parameter value, k old is the current parameter, α is the learning rate, is the partial derivative of MSE with respect to k.

[0105] Based on the above MSE calculation, the calibration parameters are optimized, and the partial derivatives of the power generation model, transmission model, distribution model and user-end model are solved by using the above mean square error, average decision error and relative error, which can be expressed by the following formula:

[0106]

[0107] Where: X is the calibration parameter, X new To adjust the updated parameters, X old is the current parameter, α is the learning rate, is the partial derivative of the difference index with respect to X.

[0108] Set the initial parameter value and the iteration stop condition, and update the parameters according to the selected optimization algorithm. In each iteration, calculate the difference index to the calibration parameter, and then update the parameter. After each parameter update, check whether the stop condition is met. If not, continue to the next round of iteration until the condition is met. The calibration parameters obtained at this time can make the results of the physical model and the statistical model closer, thereby improving the accuracy of the physical model.

[0109] S14. Perform uncertainty analysis on the power generation model, transmission model, distribution model and user-end model respectively, and perform uncertainty analysis on the statistical model at the same time to obtain a comprehensive evaluation result;

[0110] In this embodiment, step S14 includes the following:

[0111] 1. Determine the uncertainty distribution of the power generation model, transmission model, distribution model and user-end model respectively, and calculate the probability distribution of the model based on the uncertainty distribution of the input parameters;

[0112] Specifically, the step includes:

[0113] Determine the uncertainty distribution of input parameters of the power generation model, the power transmission model, the power distribution model and the user-side model respectively;

[0114] The Monte Carlo algorithm is used to perform parameter sampling based on the uncertain distribution of input parameters of the power generation model, transmission model, distribution model and user-side model. The extracted parameters are substituted into the power generation model, transmission model, distribution model and user-side model respectively to obtain the corresponding probability distribution.

[0115] Determining the uncertainty distribution of input parameters: For solar power generation models Light intensity G follows a normal distribution Temperature T follows a normal distribution where μ G , μ T , It can be obtained through historical meteorological data statistics. The power temperature coefficient k has a certain fluctuation range due to factors such as equipment differences and aging, and it obeys the uniform distribution k~U(k min ,k max ).

[0116] Perform Monte Carlo simulation to randomly generate a large number of light intensities G that conform to the above distribution i , Temperature T i And the power temperature coefficient k i Substitute these samples into the power generation formula to calculate the power generation for each simulation:

[0117]

[0118] Perform statistical analysis on the N generated power samples to obtain the probability distribution of the generated power. For example, calculate the mean value of the generated power Standard Deviation The probability density function of the generated power can be obtained by drawing a histogram or using the kernel density estimation method. The uncertainty range of the generated power can be expressed as an interval at a certain confidence level.

[0119] In the power transmission model, for the power loss formula, the line resistance R fluctuates due to the change of temperature T. Assuming that the temperature T follows a normal distribution, the relationship between the line resistance and the temperature is R = R0 (1 + α (T-T0)), then the distribution of R can be obtained by converting the distribution of. The transmission power, voltage and power factor may also fluctuate to a certain extent. Their probability distribution is determined based on the actual operation data. For example, if the transmission power follows a normal distribution, Similarly, Monte Carlo simulation is performed to randomly generate a large number of samples of temperature, transmission power, voltage, and power factor that conform to the above distribution. For each sample, the line resistance is calculated first, and then substituted into the power loss formula to calculate the power loss. The obtained power loss samples are statistically analyzed to calculate the mean and standard deviation of the power loss, and the probability density function of the power loss is obtained by drawing a histogram or kernel density estimation. The uncertainty range of the power loss can also be expressed as an interval under a certain confidence level.

[0120] The above lists the process of uncertainty analysis for solar energy model and transmission model. Other models are similar and will not be repeated here. The uncertainty of physical models of power generation, transmission, distribution and user end mainly comes from the uncertainty of model input parameters, such as meteorological conditions and equipment performance parameters in the power generation link; line parameters in the transmission link are affected by temperature; load fluctuations in the distribution link; changes in parameters of power equipment at the user end, etc., as well as the complexity and randomness of the physical process itself, such as the intermittent nature of renewable energy generation. By analyzing the probability distribution and variation range of these input parameters, and using physical models for multiple simulation calculations, the probability distribution and uncertainty range of output power parameters, such as power generation power, transmission loss, distribution voltage, user power consumption, etc., are obtained to quantify the uncertainty of the physical model.

[0121] 2. Probability distribution of the uncertain distribution calculation model based on the statistical model;

[0122] Specifically, the step includes:

[0123] Determine the confidence intervals for the parameters of the statistical model and calculate the probability distribution of the statistical model based on the confidence intervals for the parameters of the statistical model.

[0124] For the statistical model y = β0 + β1x1 + β2x2 + ... + β n x n +∈, assuming the error term follows a normal distribution The regression coefficients were estimated by the least squares method. Calculate the covariance matrix of the regression coefficients Where X is a matrix containing samples of the independent variables. The confidence interval for where t α / 2 (n-p-1) is the quantile of a distribution with n-p-1 degrees of freedom, where n is the number of samples and p is the number of independent variables. is the covariance matrix The confidence interval reflects the uncertainty in the model parameter estimates.

[0125] When using a statistical model for prediction, the mean square error between the predicted value and the actual value is calculated. The mean square error can be decomposed into the sum of the squared deviation and the sum of the variance. Through methods such as cross-validation, the mean square error on different data sets is obtained to evaluate the uncertainty of the prediction results.

[0126] 3. Determine the comprehensive probability distribution based on the probability distribution of the power generation model, transmission model, distribution model and user-end model and the probability distribution of the statistical model.

[0127] Specifically, the step includes:

[0128] Calculate the comprehensive probability distribution corresponding to the probability distribution of the power generation model, transmission model, distribution model and user-end model and the probability distribution of the statistical model according to the Bayesian theorem;

[0129] The mean, standard deviation and confidence interval of the comprehensive probability distribution are calculated to obtain the uncertainty results of the comprehensive assessment.

[0130] Assume that the probability distribution of power generation calculated by the physical model is f phy (P), the probability distribution of power generation predicted by the statistical model is f stat (P), according to Bayes' theorem, the combined probability distribution f combined (P) can be expressed as:

[0131]

[0132] By calculating the mean, standard deviation, confidence interval and other statistics of the above-mentioned comprehensive probability distribution, the uncertainty results of the comprehensive evaluation are obtained. This result comprehensively considers the calculation results of the physical model based on physical principles and actual parameter uncertainties, as well as the uncertainty factors mined from the data perspective by the statistical model, and more comprehensively reflects the uncertainty of power generation in the process of green power consumption. Similar methods can also be used for comprehensive evaluation of other indicators such as transmission loss, distribution parameters, and user power consumption.

[0133] S15. Encrypt the comprehensive evaluation results, initial data, model parameters and data processing timestamp information through blockchain encryption technology and store them on the blockchain;

[0134] In this embodiment, the above steps are summarized to obtain comprehensive evaluation results after uncertainty analysis of power generation model, transmission model, distribution model, user-end model and statistical model. Various initial data collected from power generation, transmission, distribution and user-end are integrated, covering equipment parameters, operation status data, resource data, topology data and other aspects to ensure the integrity and accuracy of the data, and are sorted according to a unified data format specification. All parameter information involved in the process of constructing power generation model, transmission model, distribution model, user-end model and statistical model, including various parameters such as performance parameters of power generation equipment, resistance and reactance values ​​of lines in physical models, and regression coefficients in statistical models, are also recorded and saved in a clear structure. The corresponding timestamps are recorded for each data collection, model calculation, evaluation and analysis operation, accurate to the specific year, month, day, hour, minute, second or even finer time granularity. These timestamps can clearly show the order of data in the entire processing process and the time nodes of each stage, providing a basis for the time dimension for subsequent data tracing. The prepared comprehensive evaluation results, initial data, model parameters and data processing timestamp information are combined into a complete data set according to certain logical relationships.

[0135] Select a suitable blockchain platform based on actual needs and application scenarios. Use the public key of the selected asymmetric encryption algorithm to encrypt the constructed data set, apply the selected hash function to the unencrypted data set for hash calculation, and obtain a fixed-length hash summary. On the selected blockchain platform, construct transaction information containing encrypted data and hash summaries, broadcast the constructed transaction information to the entire blockchain network through blockchain nodes, and after verification by nodes in the network, once the verification is passed, the transaction will be packaged into a new block and added to the blockchain in sequence according to the chain structure of the blockchain to achieve distributed storage of data.

[0136] S16. Generate corresponding green electricity consumption traceability visualization results according to the user's query request.

[0137] Develop user-oriented query interfaces, including web form pages, mobile APP interfaces, or API interfaces for other systems to call. On the backend server side, parse the query requests submitted by users and extract key query condition information, such as the time range of the query, the area involved, the specific links of concern, and the indicators expected to be viewed. According to the parsed query conditions, use the query function provided by the blockchain platform to retrieve data records that meet the requirements from the encrypted data stored on the blockchain. Extract the data content directly related to the query request from the decrypted data set and organize it according to a certain logic. According to the data characteristics and display requirements, select the appropriate visualization tool, select the appropriate chart type for display according to different query indicators and data relationships, and finally display the generated green power consumption traceability visualization results to users through appropriate channels.

[0138] Embodiment 2

[0139] An embodiment of a green electricity consumption traceability system based on blockchain technology in the present invention includes the following steps:

[0140] An initial data acquisition unit, used to acquire initial data of power generation, transmission, distribution and user ends;

[0141] A model building unit, used for building a power generation model, a transmission model, a distribution model and a user-end model based on initial data;

[0142] Model calibration and oiler unit, used to extract historical data related to green power consumption from the historical database, build a statistical model according to the characteristics of the historical data, and use the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model;

[0143] A comprehensive evaluation result determination unit is used to perform uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and to perform uncertainty analysis on the statistical model at the same time, to obtain a comprehensive evaluation result;

[0144] The blockchain on-chain unit is used to encrypt and store the comprehensive evaluation results, initial data, model parameters and data processing timestamp information on the blockchain through blockchain encryption technology;

[0145] The traceability result generation unit is used to generate corresponding green electricity consumption traceability visualization results according to the user's query request.

[0146] For the specific definition of the system, please refer to the definition of the method above, which will not be repeated here. Each module in the above system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0147] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0148] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0150] It can be understood that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A green electricity consumption tracing method based on blockchain technology, characterized in that: include: Obtain initial data from power generation, transmission, distribution and user end; Constructing a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data; Extracting historical data related to green electricity consumption from a historical database, building a statistical model based on the characteristics of the historical data, and using the statistical model to calibrate and optimize the power generation model, transmission model, distribution model, and user-end model; Perform uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and perform uncertainty analysis on the statistical model at the same time to obtain a comprehensive evaluation result; The comprehensive evaluation results, initial data, model parameters and data processing timestamp information are encrypted and stored on the blockchain through blockchain encryption technology; Generate corresponding green electricity consumption traceability visualization results based on the user's query request.

2. The green electricity consumption tracing method based on blockchain technology according to claim 1 is characterized in that: The constructing of a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data includes: Power generation model: Where: P solar is the output power of solar power generation, P STC is the power generated under standard test conditions, G and G STC are the actual light intensity and the light intensity under standard test conditions, respectively, k is the power temperature coefficient, T and T STC are the actual temperature of the solar panel and the temperature of the solar panel under standard test conditions, P wind is the output power of wind power generation, v is the wind speed at the hub height of the wind turbine, v r is the rated wind speed, v ci and v co are the cut-in and cut-out wind speeds, ρ is the air density, A is the swept area of ​​the fan blade, C p is the wind energy utilization coefficient, P r is the rated power; Transmission Model: Where: ΔP is the power loss of the transmission line, I, R, P, and U are the line current, resistance, transmission power, and transmission voltage, respectively. is the power factor, ΔU is the voltage drop, Q is the reactive power, and C is the line reactance; Power distribution model: S1=P1+jQ1,S2=P2+jQ2 Where: P i is the injected active power of node i, Q i is the injected reactive power of node i, U i is the voltage at node i, Y ij is the element of the node admittance matrix, n is the number of distribution network nodes, and is the conjugate complex number, j is the imaginary unit, j 2 =1, U1 and U2 are the voltages on the primary and secondary sides of the transformer, N1 and N2 are the turns on the primary and secondary sides of the transformer, P1 and Q1 are the active power and reactive power on the primary side of the transformer, P2 and Q2 are the active power and reactive power on the secondary side of the transformer, S1 and S2 are the apparent power on the primary and secondary sides of the transformer; User-side model: Among them: P' is the power of the electrical equipment, U' is the voltage across the equipment, I' is the current of the equipment, R' is the resistance of the equipment, P total is the total power load of users, P i ′ is the power of the ith electrical device, and n′ is the number of electrical devices of the user.

3. The green electricity consumption tracing method based on blockchain technology according to claim 1 is characterized in that: The extracting historical data related to green power consumption from the historical database, building a statistical model according to the characteristics of the historical data, and using the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model include: Filtering characteristic variables that meet correlation conditions based on the historical data; Inputting the characteristic variables into the constructed multiple linear regression model for model training to obtain a trained statistical model; Based on the trained statistical model, the future green electricity consumption indicators are predicted and the impact of different factors on green electricity consumption is analyzed.

4. The green electricity consumption tracing method based on blockchain technology according to claim 3 is characterized in that: The extracting historical data related to green power consumption from the historical database, building a statistical model according to the characteristics of the historical data, and using the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model include: Determining calibration parameters in the power generation model, the power transmission model, the power distribution model and the user-end model; Calculating the difference between the results of the power generation model, the power transmission model, the power distribution model and the user-end model and the result of the statistical model; The calibration parameters are adjusted based on the calculated differences.

5. The green electricity consumption tracing method based on blockchain technology according to claim 4 is characterized in that: The step of adjusting the calibration parameters according to the calculated differences comprises: Where: X is the calibration parameter, X new To adjust the updated parameters, X old is the current parameter, α is the learning rate, is the partial derivative of the difference index with respect to X.

6. The green electricity consumption tracing method based on blockchain technology according to claim 1 is characterized in that: The uncertainty analysis is performed on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and the uncertainty analysis is performed on the statistical model at the same time, to obtain a comprehensive evaluation result, including: Determining the uncertainty distribution of the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and calculating the probability distribution of the model based on the uncertainty distribution of the input parameters; Calculating a probability distribution of a model based on the uncertainty distribution of the statistical model; A comprehensive probability distribution is determined according to the probability distributions of the power generation model, the power transmission model, the power distribution model and the user-end model and the probability distribution of the statistical model.

7. The green electricity consumption tracing method based on blockchain technology according to claim 6 is characterized in that: The step of respectively determining the uncertainty distribution of the power generation model, the power transmission model, the power distribution model, and the user-end model, and calculating the probability distribution of the model based on the uncertainty distribution of the input parameters includes: Determining the uncertainty distribution of input parameters of the power generation model, the power transmission model, the power distribution model and the user-end model respectively; The Monte Carlo algorithm is used to perform parameter sampling based on the uncertain distribution of the input parameters of the power generation model, the power transmission model, the power distribution model and the user-end model, and the extracted parameters are substituted into the power generation model, the power transmission model, the power distribution model and the user-end model respectively to obtain the corresponding probability distribution.

8. The green electricity consumption tracing method based on blockchain technology according to claim 7 is characterized in that: The probability distribution of the uncertain distribution calculation model based on the statistical model includes: Confidence intervals of parameters of the statistical model are determined, and a probability distribution of the statistical model is calculated based on the confidence intervals of the parameters of the statistical model.

9. The green electricity consumption tracing method based on blockchain technology according to claim 8 is characterized in that: Determining the comprehensive probability distribution according to the probability distributions of the power generation model, the power transmission model, the power distribution model, and the user-end model and the probability distribution of the statistical model includes: Calculate the comprehensive probability distribution corresponding to the probability distribution of the power generation model, the power transmission model, the power distribution model and the user-end model and the probability distribution of the statistical model according to the Bayesian theorem; The mean, standard deviation and confidence interval of the comprehensive probability distribution are calculated to obtain the uncertainty result of the comprehensive assessment.

10. A green electricity consumption traceability system based on blockchain technology, characterized in that: include An initial data acquisition unit, used to acquire initial data of power generation, transmission, distribution and user ends; A model building unit, used to build a power generation model, a power transmission model, a power distribution model and a user-end model based on the initial data; Model calibration and oiler unit, used to extract historical data related to green power consumption from the historical database, build a statistical model according to the characteristics of the historical data, and use the statistical model to calibrate and optimize the power generation model, transmission model, distribution model and user-end model; A comprehensive evaluation result determination unit is used to perform uncertainty analysis on the power generation model, the power transmission model, the power distribution model and the user-end model respectively, and to perform uncertainty analysis on the statistical model at the same time, to obtain a comprehensive evaluation result; A blockchain on-chain unit, used to encrypt and store the comprehensive evaluation results, initial data, model parameters and data processing timestamp information on the blockchain through blockchain encryption technology; The traceability result generation unit is used to generate corresponding green electricity consumption traceability visualization results according to the user's query request.

Images