A power assessment method and system based on participation of multiple flexibility resources

Abstract

The present invention belongs to the technical field of power systems and energy management. The present invention discloses a power evaluation method and system based on the participation of multiple flexible resources, including obtaining power evaluation heterogeneous data; preprocessing the obtained power evaluation heterogeneous data to obtain a heterogeneous feature data set; constructing a multiple flexible resource model through the heterogeneous feature data set, and predicting the power generation output of different resources through the multiple flexible resource model; formulating and executing a resource scheduling strategy based on the power generation output of different resources; through the comprehensive scheduling of multiple flexible resources, it is possible to adjust the input of resources according to real-time changes in demand and power production, making the power system more adaptable and stable; and helping to improve the utilization efficiency of various types of power generating sets and reduce resource waste.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems and energy management, and more specifically, to a power evaluation method and system based on the participation of multiple flexibility resources. Background Art

[0002] Patent announcement number CN117543713A discloses a method and system for evaluating the flexibility of a power system. The present invention introduces the theory of portfolio high-order moment analysis to characterize the flexibility of the power system in order to reveal the regulatory potential and risk of system flexibility. A flexibility unit probability model that considers spatial correlation is constructed through a multivariate Copula function. A flexibility evaluation index based on high-order moments is established, and an index calculation method based on kernel density estimation and Monte Carlo simulation is given. The proposed index can not only reflect the average level and stability of the system's flexibility regulation capability, but also its potential and risk; it can quantitatively evaluate the impact of the types of flexibility resources and investment areas on system flexibility. Moreover, the calculation of the proposed index only requires the regulation capability distribution and installed capacity of each flexibility unit, without the need for long-term time series simulation calculations, which improves the calculation speed.

[0003] Existing power assessment methods and systems have the following major problems:

[0004] Traditional outlier detection methods often use fixed thresholds or static models to identify abnormal data. However, this approach cannot flexibly adapt to different scenarios based on changes in data distribution. If the data distribution changes, the fixed threshold may not be able to accurately distinguish between normal and abnormal data, resulting in incorrect recognition results.

[0005] Relying on manual selection of the number of Gaussian distributions may result in the selected number of distributions not being appropriate for the actual characteristics of the data. Different data sets may require different numbers of Gaussian distributions for accurate modeling, and manual selection may not accurately capture the complexity of the data, resulting in the model failing to fully capture the distribution characteristics of the data or oversimplifying the data. Failure to use the Bayesian Information Criterion to optimize the complexity of the model may result in inadequate model fit.

[0006] Lack of diversified resource integration may cause the power system to rely on a single or a few energy sources, resulting in inefficient dispatching during peak or trough loads. Without the integration of diversified flexible resources, the power system may not be able to fully utilize the advantages of various power generation resources.

[0007] Without the support of demand response and load regulation models, the power system may lack the ability to flexibly respond to demand fluctuations, resulting in increased load fluctuations; the power grid will face greater stability challenges, and may encounter problems such as excessive load peaks or inability to meet demand during low load periods, increasing the complexity of power grid operation; the lack of modeling of the power characteristics and operating characteristics of DC interconnection lines will restrict cross-regional power dispatching; in the case of uneven power demand, power cannot be allocated quickly and flexibly, resulting in an imbalance in power supply between different regions within the power grid, increasing losses in long-distance power transmission, and affecting the timely supply of electricity; the lack of regulatory support for energy storage and flexibility resources may require reliance on more traditional power equipment for system regulation, increasing the maintenance cost and complexity of the power grid.

[0008] In view of this, the present invention proposes a power evaluation method and system based on the participation of multiple flexibility resources to solve the above problems. Summary of the Invention

[0009] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned objectives, the present invention provides the following technical solution: a power assessment method based on the participation of multiple flexibility resources, comprising:

[0010] S1. Obtaining heterogeneous data for power assessment;

[0011] S2. Preprocess the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set;

[0012] S3. Construct a multivariate flexibility resource model using heterogeneous feature datasets, and predict the power generation output of different resources using the multivariate flexibility resource model.

[0013] S4. Develop and implement resource scheduling strategies based on the power generation output of different resources.

[0014] Furthermore, the heterogeneous data for power evaluation includes power generation side data, energy storage side data, demand side data and grid side data; the power generation side data includes photovoltaic power generation data, wind power generation data, thermal power unit data and hydropower data;

[0015] Photovoltaic power generation data includes solar radiation intensity, photovoltaic panel temperature, and installation angle; wind power generation data includes wind turbine power generation, wind turbine cut-in and cut-out wind speeds; thermal power unit data includes unit power upper and lower limits and unit start and stop status; hydropower data includes water flow rate through the unit and generating head;

[0016] The energy storage side data includes the charging and discharging power, efficiency, state of charge of battery energy storage and the upper and lower reservoir capacities of pumped storage; the demand side data includes the user's electricity load and electricity price data; the grid side data includes the real-time load of the grid, peak and valley load, frequency fluctuations of the grid, voltage level of the grid and load of the transmission lines.

[0017] Furthermore, the method of preprocessing the acquired power evaluation heterogeneous data to obtain a heterogeneous feature data set includes:

[0018] By improving the Gaussian mixture model, outliers in the power assessment heterogeneous data are identified, the identified outliers are eliminated, the missing values in the power assessment heterogeneous data are processed, and the duplicate data in the power assessment heterogeneous data are removed; the non-numeric data in the power assessment heterogeneous data are encoded and converted into numerical data to obtain a processed heterogeneous feature data set; the processed heterogeneous feature data set is normalized by standard deviation and converted into a standard normal distribution to obtain a normalized heterogeneous feature data set.

[0019] Furthermore, the method of identifying outliers in the power evaluation heterogeneous data by improving the Gaussian mixture model and removing the identified outliers includes:

[0020] S41. Combine the power generation side data, energy storage side data, demand side data and power generation side data in the power evaluation heterogeneous data into a multidimensional feature matrix ;in, ' is the number of samples, that is, the number of data points in the multidimensional feature matrix; is the number of feature dimensions, that is, the number of features of each sample;

[0021] S42, preset the distribution of power generation side data, energy storage side data, demand side data and power generation side data as follows: The mixture of Gaussian distributions is represented by the Gaussian mixture model, which is: ;in, For data points In all The probability density value in the Gaussian mixture model; For the The weights of the Gaussian distribution; For the The probability density function of a Gaussian distribution; For the The mean vector of the Gaussian distribution; For the The covariance matrix of a Gaussian distribution; is the number of Gaussian distribution; is the index of each individual Gaussian distribution component in the Gaussian mixture model;

[0022] S43. Dynamically determine the optimal number of Gaussian distributions through the Bayesian Information Criterion; estimate the parameters of the Gaussian mixture model through the expectation maximization algorithm, and randomly initialize the mean vector, covariance matrix and weight of each Gaussian distribution; use the posterior probability calculation formula to calculate the probability that each data point in the multidimensional feature matrix belongs to the first The posterior probability of a Gaussian distribution is given by The probability of a Gaussian distribution being generated; the posterior probability calculation formula is: ;in, For data points Belong to The probability of a Gaussian distribution being generated; is the first data points; is the index of the data point; For the The weights of the Gaussian distribution; The index for traversing all Gaussian distributions;

[0023] S44. For each data point in the multidimensional feature data , calculate its probability density in the Gaussian mixture model , the preset probability density threshold is , the preset probability density threshold is dynamically adjusted through the probability density threshold adjustment formula, and the probability density threshold adjustment formula is: ;in, is the probability density threshold after dynamic adjustment; is the proportionality coefficient; is the average probability density of the data; is the target outlier;

[0024] S45, if , then determine the data point is an abnormal value; if , then determine the data point is a normal value, which will satisfy The data points are removed from the heterogeneous data of power evaluation.

[0025] Furthermore, the method for dynamically determining the optimal number of Gaussian distributions by using the Bayesian Information Criterion includes:

[0026] Preset number of Gaussian distributions The candidate range of ' is ;in, is the minimum value of the Gaussian distribution number; is the maximum value of the Gaussian distribution number; for the preset Gaussian distribution number The number of each Gaussian distribution within the candidate range , train the Gaussian mixture model and calculate the corresponding maximum likelihood value through the maximum likelihood estimation formula; the maximum likelihood estimation formula is: ;in, For each Gaussian distribution number The corresponding maximum likelihood value;

[0027] According to the number of each Gaussian distribution , calculate its Bayesian information criterion value through the Bayesian information criterion calculation formula; the Bayesian information criterion calculation formula is: ;in, is the Bayesian information criterion value; is the log-likelihood of the Gaussian mixture model; is the number of Gaussian mixture model parameters, including mean vector, covariance matrix and weights;

[0028] By comparing the number of different Gaussian distributions The corresponding Bayesian Information Criterion value BIC, select the number of Gaussian distributions that minimizes the Bayesian Information Criterion value BIC , which is the optimal number of Gaussian distributions.

[0029] Furthermore, the method of constructing a multivariate flexibility resource model through heterogeneous feature data sets includes:

[0030] The multivariate flexibility resource model includes a photovoltaic power generation output model, a wind power generation output model, a thermal power unit fuel cost model, a hydropower unit output model, a pumped storage unit model, an IBDR cost calculation model, a PSDR cost calculation model, an electrochemical energy storage model, a DC tie line power characteristic model, and a DC tie line operation characteristic model;

[0031] Constructing a photovoltaic power generation power evaluation model: ;in, For photovoltaic systems in daily Output power at any moment; is the rated power of the photovoltaic; The actual light intensity at the moment; is the rated light intensity of the photovoltaic system; For a certain moment in the day;

[0032] Use temperature linear function to describe its influence on photovoltaic power generation output; the preset photovoltaic panel temperature is , photovoltaic power generation output is , the temperature linear function is: ;in, At the reference temperature Photovoltaic power generation output under is the reference temperature; is a constant, which represents the rate at which temperature affects photovoltaic power output;

[0033] The cosine law is used to calculate the incident angle of sunlight, and the photoelectric conversion efficiency of the photovoltaic panel is considered to estimate the power generation. The output model is: ;in, The contribution of the installation angle and orientation of solar panels to photovoltaic power generation output; is the rated output power of the photovoltaic panel; is the conversion efficiency of the photovoltaic cell; is the angle between the sunlight and the normal of the photovoltaic panel;

[0034] Taking into account the solar radiation intensity, photovoltaic panel temperature, and the installation angle and orientation of the solar panel, the photovoltaic power generation output model is obtained using the weighted average method. The photovoltaic power generation output model is: ;in, The contribution weight of solar radiation intensity to photovoltaic power generation output; is the contribution weight of photovoltaic panel temperature to photovoltaic power generation output; The contribution weight of the solar panel installation angle and orientation to photovoltaic power output.

[0035] Furthermore, the wind power generation output model includes: ;in, The power generated by the wind turbine; is the actual wind speed; is the cut-in wind speed; To cut out wind speed; is the rated wind speed; is the rated output power of the fan;

[0036] The output power of thermal power units is subject to upper and lower limits, and the constraint expressions are: ;in, For thermal power plant model Thermal power units Output power; and Represent thermal power units Upper and lower limits of output; for Thermal power units A binary variable for the running status, Indicates shutdown. Indicates running;

[0037] The fuel cost model of thermal power units is constructed by coal consumption cost and start-up and shutdown cost. The fuel cost model of thermal power units is: ;in, is the total fuel cost of thermal power units; is the coal consumption cost of thermal power units; is the start-up and shutdown cost of thermal power units;

[0038] The coal consumption cost expression of thermal power units is: ;in, For thermal power units Total running time; is the total number of thermal power units; 、 Thermal power units Coal consumption cost coefficient; for Thermal power units Active power;

[0039] The start-up and shutdown cost expression of thermal power units is: ;in, For thermal power units The start-stop cost of Thermal power units A binary variable for the operating status;

[0040] Hydropower units include run-of-river hydropower stations and pumped storage units; the output model of hydropower units is: ;in, For the The output power of a run-of-river hydropower station at time t; is the density of water; is the acceleration due to gravity; For power generation efficiency; is the power generation flow; The power generation head;

[0041] The flow constraint formula is used to constrain the power generation flow of the run-of-river hydropower station. The flow constraint formula is: ;in, are the maximum and minimum power generation flows of the lth run-of-river hydropower station, ; is the number of run-of-river hydropower stations;

[0042] The pumped storage unit is composed of units in turbine working condition and units in pump working condition. The actual output power of the unit in power generation condition is measured by the turbine working condition output formula. The turbine working condition output formula is: ;in, for The number of units in power generation condition at all times; for The output of the pumped storage unit turbine under operating conditions at all times; and It is the upper and lower limits of the output of the pumped storage unit under power generation conditions;

[0043] The actual output power of the unit under pumping conditions is measured by the water pump working condition output formula; the water pump working condition output formula is: ;in, for The number of units in pumping operation at all times; for The output of the pumped storage unit under the working condition of the water pump at all times; and It is the upper and lower limits of the output of the pumped storage unit under the working condition of the water pump;

[0044] An IBDR cost calculation model is established based on the changes in the power company's revenue from demand-side users with IBDR capabilities;

[0045] Assuming that users do not participate in IBDR, the power company's income is: ;in, The income of the power company before the user participates in IBDR; for Fixed electricity price on the retail side at the time; Before the implementation of the demand response project IBDRs in The load of the moment;

[0046] The cost of IBDR is the power outage loss caused by load reduction. When the load is on, the compensation provided by the power company is: ;in, Reduce for users through IBDR When the load is on, the power company compensates it; and Respectively The degree of the quadratic term and the linear coefficient of the IBDR compensation amount; For the IBDR at the moment load shedding;

[0047] After users participate in IBDR, the power company's income is: ;in, The income of the power company after the users participate in IBDR;

[0048] The IBDR cost calculation model is: Where: ; ;

[0049] Assuming that users do not participate in PSDR, the power company's revenue is: ;in, Before the implementation of the demand response project PSDR in The load at the moment; after the user participates in PSDR, the power company’s income is: ;in, The proportion of preferential electricity prices given by power companies to users in order to increase their enthusiasm for participation; for The amount of increase in electricity prices at any given moment; For the PSDR in The amount of load reduction at a given time;

[0050] According to the price elasticity coefficient of demand available: ; Then the PSDR cost calculation model is: ;in, ; ; ;

[0051] The electrochemical energy storage model is: ;in, is the discharge efficiency of the energy storage system; Charging efficiency for energy storage systems; Energy storage device Charging power at all times; Energy storage device Discharge power at all times; Energy storage device The amount of electricity stored at any moment; Energy storage device The amount of electricity released at any moment;

[0052] The charging and discharging power constraint formula is used to constrain the charging and discharging power of the energy storage at each moment. The charging and discharging power constraint formula is: ;in, It is a 0-1 variable. When the energy storage is charged is 1, when the energy storage is discharged is 0;

[0053] Each stepped power of the DC tie line is regarded as a feasible state of the DC tie line power. If the DC tie line is in operation, the power of the DC tie line is and can only be in the feasible state set, that is, ;in, DC tie line exist Active power at the moment; DC tie line In a feasible state The power value; DC tie line The number of feasible states;

[0054] The power characteristic model of the DC tie line is: ;in, is the power of the DC tie line; is a 0-1 variable, indicating the DC tie line Is it in a feasible state at time t? ;

[0055] The operating characteristic model of the DC tie line is: ;in, and DC tie lines The minimum and maximum power that can be transmitted; DC tie line exist Operating power at all times;

[0056] Based on data from the power generation side, energy storage side, grid side and demand side, simulation technology analysis is run to quantitatively evaluate the impact of different flexibility resources on total costs by comparing the cost effects of different flexibility resources when participating in power assessment.

[0057] Furthermore, the method of running simulation technology analysis based on power generation data, energy storage data, grid data, and demand side data to quantitatively evaluate the impact of different flexibility resources on total costs by comparing the cost effects of different flexibility resources when participating in power assessment includes:

[0058] Taking the minimization of the total cost of power system operation with the participation of multiple flexible resources as the goal, the optimal economic benefit objective function of the system joint operation model is constructed. The optimal economic benefit objective function is: ;in, 、 、 and Represent the power generation side cost, demand side cost, energy storage side cost and environmental cost respectively;

[0059] The power generation cost is expressed as: ;in, is the total operating cost of thermal power units; is the total operating cost of the hydropower unit; is the total operating cost of the pumped storage unit; is the number of thermal power units that have undergone flexibility modifications;

[0060] The demand side cost is expressed as: The energy storage cost is expressed as: The environmental cost refers to the carbon emission cost. Carbon emissions come from thermal power generation units. The carbon emissions are expressed as:

[0061] ;in, 、 、 Calculation parameters for carbon emissions from thermal power units;

[0062] Carbon emission quota is expressed as: ;in, is the carbon emission quota per unit of power generation of thermal power units; the carbon emission cost is expressed as: ;in, The price per unit of carbon emissions is used; by comparing the cost effects of different flexibility resources when participating in electricity assessment, the impact of different flexibility resources on the total cost is quantitatively evaluated.

[0063] Furthermore, the method for formulating and executing resource scheduling strategies based on the power generation output of different resources includes collecting the power generation output data and operating status of different resources in real time through the power assessment intelligent management terminal, and feeding back to the scheduling center; the scheduling center specifies the corresponding resource scheduling strategies based on the collected power generation output data and operating status of different resources, and sends resource adjustment instructions to each generator set to control the operating status of each generator set.

[0064] An electric power assessment system based on the participation of multiple flexibility resources includes:

[0065] Data acquisition module, used to obtain heterogeneous data for power evaluation;

[0066] A data processing module is used to pre-process the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set;

[0067] Multivariate flexibility resource modeling module, which is used to construct a multivariate flexibility resource model based on heterogeneous feature data sets and predict the power generation output of different resources through the multivariate flexibility resource model;

[0068] The scheduling decision execution module is used to formulate and execute resource scheduling strategies based on the power generation output of different resources; each module is connected via wired and / or wireless means.

[0069] The technical effects and advantages of the power assessment method and system based on the participation of multiple flexibility resources of the present invention are as follows:

[0070] The Gaussian mixture model can efficiently identify data points in power assessment data that do not conform to the normal distribution. These outliers may be caused by data collection errors, equipment failures, or other external factors. Accurately identifying and eliminating these outliers helps improve data quality and ensure the accuracy of subsequent analysis and decision-making. The Bayesian Information Criterion dynamically determines the optimal number of Gaussian distributions, and the probability density threshold adjustment formula dynamically adjusts the threshold for outlier detection. This allows for flexible adaptation to outlier identification needs in different scenarios based on changes in data distribution, thereby avoiding overly strict or overly loose threshold settings and improving the robustness of the method.

[0071] The Bayesian Information Criterion dynamically selects the optimal number of Gaussian distributions, eliminating the need for manual configuration. The Bayesian Information Criterion considers both the model's fit and its complexity, selecting a model that fits the data well while remaining reasonably complex. This makes the entire process more automated and adaptable to varying data characteristics.

[0072] By integrating multiple flexible resources, including photovoltaics, wind power, thermal power, hydropower, and energy storage, a comprehensive power assessment model has been constructed. Diversified resource utilization comprehensively considers the advantages, disadvantages, and characteristics of different types of power generation, providing diverse solutions for the power system and achieving optimal resource allocation and scheduling. By integrating multiple flexible resources, including wind power, thermal power, hydropower, energy storage, and DC interconnections, optimized power production scheduling can be achieved, ensuring that the power system meets demand while minimizing system operating costs.

[0073] Through IBDR (demand response) and PSDR (load regulation) models, electricity demand can be adjusted, system load fluctuations can be reduced, and grid operation can be optimized. Furthermore, electrochemical energy storage models help regulate power flows between peaks and valleys, provide backup power, and improve system stability and anti-interference capabilities. By modeling the power and operating characteristics of DC interconnection lines, rapid cross-regional power dispatch can be achieved, improving power supply flexibility and reducing losses during long-distance transmission. By achieving efficient dispatch and cost optimization of flexible resources, power companies can better adapt to market changes, support government carbon reduction targets and sustainable energy policies, and quantify the cost-effectiveness of flexible resources to provide a basis for policy formulation and market design. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of a power assessment method based on the participation of multiple flexibility resources according to the present invention;

[0075] Figure 2 This is a schematic diagram of the structure of an electric power assessment system based on the participation of multiple flexibility resources of the present invention. DETAILED DESCRIPTION

[0076] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0077] Example 1

[0078] See also Figure 1 As shown, this embodiment provides a power assessment method based on the participation of multiple flexibility resources, including:

[0079] S1. Obtaining heterogeneous data for power assessment;

[0080] S2. Preprocess the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set;

[0081] S3. Construct a multivariate flexibility resource model using heterogeneous feature datasets, and predict the power generation output of different resources using the multivariate flexibility resource model.

[0082] S4. Develop and implement resource scheduling strategies based on the power generation output of different resources.

[0083] Heterogeneous data for power assessment includes power generation data, energy storage data, demand data, and grid data. Power generation data includes photovoltaic power generation data, wind power generation data, thermal power unit data, and hydropower data.

[0084] Photovoltaic power generation data includes solar radiation intensity, photovoltaic panel temperature, and installation angle; wind power generation data includes wind turbine power generation, wind turbine cut-in and cut-out wind speeds; thermal power unit data includes unit power upper and lower limits and unit start and stop status; hydropower data includes water flow rate through the unit and generating head;

[0085] The energy storage side data includes the charging and discharging power, efficiency, state of charge of battery energy storage and the upper and lower reservoir capacities of pumped storage; the demand side data includes the user's electricity load and electricity price data; the grid side data includes the real-time load of the grid, peak and valley load, frequency fluctuations of the grid, voltage level of the grid and load of the transmission lines.

[0086] The method for preprocessing the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set includes:

[0087] By improving the Gaussian mixture model, outliers in the power assessment heterogeneous data are identified, the identified outliers are eliminated, the missing values in the power assessment heterogeneous data are processed, and the duplicate data in the power assessment heterogeneous data are removed; the non-numeric data in the power assessment heterogeneous data are encoded and converted into numerical data to obtain a processed heterogeneous feature data set; the processed heterogeneous feature data set is normalized by standard deviation and converted into a standard normal distribution to obtain a normalized heterogeneous feature data set.

[0088] The improved Gaussian mixture model is used to identify outliers in the heterogeneous data of power assessment. The methods for removing the identified outliers include:

[0089] S41. Combine the power generation side data, energy storage side data, demand side data and power generation side data in the power evaluation heterogeneous data into a multidimensional feature matrix ;in, ' is the number of samples, that is, the number of data points in the multidimensional feature matrix; is the number of feature dimensions, that is, the number of features of each sample;

[0090] S42, preset the distribution of power generation side data, energy storage side data, demand side data and power generation side data as follows: The mixture of Gaussian distributions is represented by the Gaussian mixture model, which is: ;in, For data points In all The probability density value in the Gaussian mixture model; For the The weights of the Gaussian distribution; For the The probability density function of a Gaussian distribution; For the The mean vector of the Gaussian distribution; For the The covariance matrix of a Gaussian distribution; is the number of Gaussian distribution; is the index of each individual Gaussian distribution component in the Gaussian mixture model;

[0091] S43. Dynamically determine the optimal number of Gaussian distributions through the Bayesian Information Criterion; estimate the parameters of the Gaussian mixture model through the expectation maximization algorithm, and randomly initialize the mean vector, covariance matrix and weight of each Gaussian distribution; use the posterior probability calculation formula to calculate the probability that each data point in the multidimensional feature matrix belongs to the first The posterior probability of a Gaussian distribution is given by The probability of a Gaussian distribution being generated; the posterior probability calculation formula is: ;in, For data points Belong to The probability of a Gaussian distribution being generated; is the first data points; is the index of the data point; For the The weights of the Gaussian distribution; To traverse the index of all Gaussian distributions;

[0092] S44. For each data point in the multidimensional feature data , calculate its probability density in the Gaussian mixture model , the preset probability density threshold is , the preset probability density threshold is dynamically adjusted through the probability density threshold adjustment formula, and the probability density threshold adjustment formula is: ;in, is the probability density threshold after dynamic adjustment; is the proportionality coefficient; is the average probability density of the data; is the target outlier;

[0093] For example, if the scale factor is 2, the average probability density of the data is 0.2, the number of feature dimensions is 5, the number of Gaussian distributions is 10, the number of data points in the multidimensional feature matrix is 50, the preset probability density threshold is 0.8, and the target outlier value is 0.01, then the dynamically adjusted probability density threshold is 0.32.

[0094] S45, if , then determine the data point is an abnormal value; if , then determine the data point is a normal value, which will satisfy The data points are removed from the heterogeneous data of power evaluation.

[0095] Methods for dynamically determining the optimal number of Gaussian distributions using the Bayesian Information Criterion include:

[0096] Preset number of Gaussian distributions The candidate range of ' is ;in, is the minimum value of the Gaussian distribution number; is the maximum value of the Gaussian distribution number; for the preset Gaussian distribution number The number of each Gaussian distribution within the candidate range , train the Gaussian mixture model and calculate the corresponding maximum likelihood value through the maximum likelihood estimation formula; the maximum likelihood estimation formula is: ;in, For each Gaussian distribution number The corresponding maximum likelihood value;

[0097] According to the number of each Gaussian distribution , calculate its Bayesian information criterion value through the Bayesian information criterion calculation formula; the Bayesian information criterion calculation formula is: ;in, is the Bayesian information criterion value; is the log-likelihood of the Gaussian mixture model; is the number of Gaussian mixture model parameters, including mean vector, covariance matrix and weights;

[0098] By comparing the number of different Gaussian distributions The corresponding Bayesian Information Criterion value BIC, select the number of Gaussian distributions that minimizes the Bayesian Information Criterion value BIC , which is the optimal number of Gaussian distributions.

[0099] Methods for constructing multivariate flexibility resource models using heterogeneous feature datasets include;

[0100] The multivariate flexibility resource model includes a photovoltaic power generation output model, a wind power generation output model, a thermal power unit fuel cost model, a hydropower unit output model, a pumped storage unit model, an IBDR cost calculation model, a PSDR cost calculation model, an electrochemical energy storage model, a DC tie line power characteristic model, and a DC tie line operation characteristic model;

[0101] Photovoltaic power generation, as a clean and renewable energy technology, is gaining increasing popularity and development worldwide. However, its power generation efficiency is highly dependent on solar irradiance and is therefore significantly affected by meteorological conditions. During periods of good sunshine, photovoltaic panels effectively absorb sunlight and achieve high power generation efficiency. Conversely, adverse weather conditions such as rainy or cloudy skies can significantly reduce power generation, leading to a sudden drop in output. This creates significant uncertainty in the output of photovoltaic power generation systems.

[0102] Constructing a photovoltaic power generation power evaluation model: ;in, For photovoltaic systems in daily Output power at any moment; is the rated power of the photovoltaic; The actual light intensity at the moment; is the rated light intensity of the photovoltaic system; For a certain moment in the day;

[0103] The influence of photovoltaic panel temperature on photovoltaic power generation output is studied, and the temperature linear function is used to describe its influence on photovoltaic power generation output; the photovoltaic panel temperature is preset to be , photovoltaic power generation output is , the temperature linear function is: ;in, At the reference temperature Photovoltaic power generation output under is the reference temperature; is a constant, which represents the rate at which temperature affects photovoltaic power output;

[0104] Photovoltaic power generation is affected by the installation angle and orientation of solar panels. The cosine law is used to calculate the incident angle of sunlight, and the photoelectric conversion efficiency of photovoltaic panels is considered to estimate the power generation. The output model is: ;in, The contribution of the installation angle and orientation of solar panels to photovoltaic power generation output; is the rated output power of the photovoltaic panel; is the conversion efficiency of the photovoltaic cell; It is the angle between the sun's rays and the normal of the photovoltaic panel, which can be calculated based on the solar altitude angle, solar azimuth angle and photovoltaic panel inclination angle;

[0105] Taking into account the solar radiation intensity, photovoltaic panel temperature, and the installation angle and orientation of the solar panel, the photovoltaic power generation output model is obtained using the weighted average method. The photovoltaic power generation output model is: ;in, The contribution weight of solar radiation intensity to photovoltaic power generation output; is the contribution weight of photovoltaic panel temperature to photovoltaic power generation output; The contribution weight of the solar panel installation angle and orientation to photovoltaic power output.

[0106] Research shows that the output power of a wind turbine is mainly related to the rated wind speed, cut-in wind speed, and cut-out wind speed, and is specifically divided into the following three situations: If the actual wind speed is smaller than the cut-in wind speed, or if the actual wind speed is larger than the cut-out wind speed, the wind turbine will not work and the output power will be 0; If the actual wind speed is between the cut-in wind speed and the rated wind speed, the output power of the wind turbine is proportional to the actual wind speed; If the actual wind speed is between the rated wind speed and the cut-out wind speed, the output power of the wind turbine is the rated power.

[0107] Wind power generation output models include: ;in, The power generated by the wind turbine; is the actual wind speed; is the cut-in wind speed; To cut out wind speed; is the rated wind speed; is the rated output power of the fan;

[0108] The output power of thermal power units is subject to upper and lower limits, and the constraint expressions are: ;in, For thermal power plant model Thermal power units Output power; and Represent thermal power units Upper and lower limits of output; for Thermal power units A binary variable for the running status, Indicates shutdown. Indicates running;

[0109] The fuel cost model of thermal power units is constructed by coal consumption cost and start-up and shutdown cost. The fuel cost model of thermal power units is: ;in, is the total fuel cost of thermal power units; is the coal consumption cost of thermal power units; is the start-up and shutdown cost of thermal power units;

[0110] The coal consumption cost expression of thermal power units is: ;in, For thermal power units Total running time; is the total number of thermal power units; 、 Thermal power units Coal consumption cost coefficient; for Thermal power units Active power;

[0111] The start-up and shutdown cost expression of thermal power units is: ;in, For thermal power units The start-stop cost of Thermal power units A binary variable for the operating status;

[0112] Hydropower units offer the advantages of short start-up and shutdown times, rapid load ramping, wide load adjustment range, and strong ability to cope with rapid load changes, making them ideal flexible power sources. They can be started up to full power in minutes, with load adjustment rates exceeding 30% of rated capacity and achieving 100% peak regulation. Run-of-the-river hydropower stations are those that utilize the natural flow of a river directly for power generation without a regulating reservoir. Their output is primarily influenced by factors such as inflow flow, unit performance, and operating head.

[0113] Hydropower units include run-of-river hydropower stations and pumped storage units; the output model of hydropower units is: ;in, For the The output power of a run-of-river hydropower station at time t; is the density of water; is the acceleration due to gravity; For power generation efficiency; is the power generation flow; The power generation head;

[0114] A pumped storage unit is a special type of hydropower station with operating characteristics similar to those of a conventional hydropower station. It also has two operating modes: turbine operating mode and pump operating mode.

[0115] Physical characteristic model: Based on the operating characteristics and modes of the pumped storage unit, the main consideration is to establish its turbine operating condition and pump operating condition operation model, upper and lower reservoir capacity model and operating condition selection constraints.

[0116] The flow constraint formula is used to constrain the power generation flow of the run-of-river hydropower station. The flow constraint formula is: ;in, are the maximum and minimum power generation flows of the lth run-of-river hydropower station, ; is the number of run-of-river hydropower stations;

[0117] The pumped storage unit is composed of units in turbine working condition and units in pump working condition. The actual output power of the unit in power generation condition is measured by the turbine working condition output formula. The turbine working condition output formula is: ;in, for The number of units in power generation condition at all times; for The output of the pumped storage unit turbine under operating conditions at all times; and It is the upper and lower limits of the output of the pumped storage unit under power generation conditions;

[0118] The actual output power of the unit under pumping conditions is measured by the water pump working condition output formula; the water pump working condition output formula is: ;in, for The number of units in pumping operation at all times; for The output of the pumped storage unit under the working condition of the water pump at all times; and It is the upper and lower limits of the output of the pumped storage unit under the working condition of the water pump;

[0119] Demand response refers to the response of electricity users to electricity prices or incentive signals, which optimizes their own electricity consumption and the comprehensive optimization of power system resources by changing their normal electricity consumption patterns. Demand response in competitive electricity markets can be divided into price-based demand response (PSDR) and incentive-based demand response (IBDR) according to different user response methods.

[0120] An IBDR cost calculation model is developed based on the change in revenue a power company receives from demand-side customers with IBDR capabilities. Power companies earn electricity revenue by supplying power to demand-side customers with IBDR capabilities. When load reduction occurs, these customers are financially compensated, and this reduction in load also reduces electricity revenue. Therefore, the cost of IBDR is the change in power company revenue before and after load reduction.

[0121] Assuming that users do not participate in IBDR, the power company's income is: ;in, The income of the power company before the user participates in IBDR; for Fixed electricity price on the retail side at the time; Before the implementation of the demand response project IBDRs in The load of the moment;

[0122] The cost of IBDR is the power outage loss caused by load reduction. When the load is on, the compensation provided by the power company is: ;in, Reduce for users through IBDR When the load is on, the power company compensates it; and Respectively The degree of the quadratic term and the linear coefficient of the IBDR compensation amount; For the IBDRs at the moment load shedding;

[0123] After users participate in IBDR, the power company's income is: ;in, The income of the power company after the users participate in IBDR;

[0124] The IBDR cost calculation model is: Where: ; ;

[0125] PSDR allows users to respond to changes in retail electricity prices and adjust their electricity demand accordingly, described by the demand price elasticity coefficient. Dispatch optimization yields load reductions, and the actual retail electricity price delivered to users is calculated based on the elasticity coefficient. The cost of PSDR is the change in electricity company revenue before and after the price change, which is also the benefit users receive from participating in the demand response program.

[0126] Assuming that users do not participate in PSDR, the power company's revenue is: ;in, Before the implementation of the demand response project PSDR in The load at the moment; after the user participates in PSDR, the power company’s income is: ;in, The proportion of preferential electricity prices given by power companies to users in order to increase their enthusiasm for participation; for The amount of increase in electricity prices at any given moment; For the PSDR in The load reduction at the time; Since PSDR users can not only reduce load demand when electricity prices rise, but also increase load demand when electricity prices fall, and May be negative.

[0127] According to the price elasticity coefficient of demand available: ; Then the PSDR cost calculation model is: ;in, ; ; ;

[0128] The electrochemical energy storage model is: ;in, is the discharge efficiency of the energy storage system; Charging efficiency for energy storage systems; Energy storage device Charging power at all times; Energy storage device Discharge power at all times; Energy storage device The amount of electricity stored at any moment; Energy storage device The amount of electricity released at any moment;

[0129] The charging and discharging power constraint formula is used to constrain the charging and discharging power of the energy storage at each moment. The charging and discharging power constraint formula is: ;in, It is a 0-1 variable. When the energy storage is charged is 1, when the energy storage is discharged is 0;

[0130] Charge and discharge cycle limits: Excessive charge and discharge during operation can lead to a sharp decline in the energy storage lifespan, making this an uneconomical operation mode. Similarly, frequent charge and discharge also shortens the energy storage lifespan. To prevent excessive charge and discharge cycles from damaging the battery, the number of charge and discharge cycles must be limited, meaning that the daily discharge capacity must be less than the rated capacity of the energy storage.

[0131] High-voltage DC converter equipment is not suitable for frequent adjustment, and power coordination with the receiving grid is difficult. Therefore, current HVDC interconnection lines mostly operate in a stepped, segmented mode, ensuring relatively stable power transmission within each segment. Fluctuations in renewable energy output from the sending grid are smoothed by the bundled thermal power units, ensuring relatively stable DC transmission power. The difficulty of DC interconnection line modeling lies in the stepped operation of the exchanged power. To more accurately model this operational characteristic, each stepped power level of the DC interconnection line is considered a feasible state of the DC interconnection line power. If the DC interconnection line is in operation, the DC interconnection line power is, and can only be, concentrated within this feasible state.

[0132] Each stepped power of the DC tie line is regarded as a feasible state of the DC tie line power. If the DC tie line is in operation, the power of the DC tie line is and can only be in the feasible state set, that is, ;in, DC tie line exist Active power at the moment; DC tie line In a feasible state The power value; DC tie line The number of feasible states;

[0133] The power characteristic model of the DC tie line is: ;in, is the power of the DC tie line; is a 0-1 variable, indicating the DC tie line Is it in a feasible state at time t? ;

[0134] The operating characteristic model of the DC tie line is: ;in, and DC tie lines The minimum and maximum power that can be transmitted; DC tie line exist Operating power at all times;

[0135] The feasible step power of a DC tie-line during operation is dependent on its operating characteristics and dispatching method, and generally remains constant over extended periods. However, the upper and lower limits of the DC tie-line power are affected by factors such as system load, the status of generators on the sending grid, the receiving grid's capacity, and the DC tie-line's operation. These limits can fluctuate frequently, even within a single day. By incorporating the on / off status of the DC tie-line, only the upper and lower limits of the DC power can be modified without changing the feasible step power, thus increasing the model's flexibility and engineering adaptability.

[0136] Based on data from the power generation side, energy storage side, grid side and demand side, simulation technology analysis is run to quantitatively evaluate the impact of different flexibility resources on total costs by comparing the cost effects of different flexibility resources when participating in power assessment.

[0137] Based on data from the generation, storage, grid, and demand sides of the grid, simulations were run to analyze the cost effects of different flexibility resources when participating in power assessments. Methods for quantifying the impact of different flexibility resources on total costs include:

[0138] Given the relatively low unit cost of renewable energy generation, its large-scale integration can reduce dependence on traditional energy resources by increasing the proportion of renewable energy consumption, thereby reducing overall fuel consumption and energy costs. However, when a variety of flexibility resources are included in the scope of power system scheduling, although this enhances the flexibility of the system, it may also lead to an increase in the complexity of power system operation and an increase in additional costs such as unit adaptive transformation. The objective function described above serves as an analysis benchmark. By comparing and analyzing the cost effects of different flexibility resources when participating in power system operation, it quantitatively evaluates the impact of these resources on the total system cost, thereby scientifically measuring the economic performance of the power system under the conditions of large-scale integration of renewable energy.

[0139] Taking the minimization of the total cost of power system operation with the participation of multiple flexible resources as the goal, the optimal economic benefit objective function of the system joint operation model is constructed. The optimal economic benefit objective function is: ;in, 、 、 and Represent the power generation side cost, demand side cost, energy storage side cost and environmental cost respectively;

[0140] The power generation cost is expressed as: ;in, is the total operating cost of thermal power units; is the total operating cost of the hydropower unit; is the total operating cost of the pumped storage unit; is the number of thermal power units that have undergone flexibility modifications;

[0141] The demand side cost is expressed as: The energy storage cost is expressed as: The environmental cost refers to the carbon emission cost. Carbon emissions come from thermal power generation units. The carbon emissions are expressed as:

[0142] ;in, 、 、 Calculation parameters for carbon emissions from thermal power units;

[0143] Carbon emission quota is expressed as: ;in, is the carbon emission quota per unit of power generation of thermal power units; the carbon emission cost is expressed as: ;in, The price per unit of carbon emissions is used; by comparing the cost effects of different flexibility resources when participating in electricity assessment, the impact of different flexibility resources on the total cost is quantitatively evaluated.

[0144] The carbon trading mechanism is a market mechanism that treats CO2 emission rights as commodities for free trade, thereby achieving low-carbon environmental goals. It uses economic means to drive the power industry toward a low-carbon economy. Carbon emission rights buyers purchase a specified amount of carbon emission quotas from sellers, thereby fulfilling their greenhouse gas reduction targets. This creates a mutually beneficial situation for both parties, while increasing the seller's economic benefits. As a quota-based trading mechanism, the carbon trading mechanism operates through the buying and selling of carbon emission rights. The government sets a certain limit on the total amount of carbon emission rights and, based on analysis, allocates certain carbon emission quotas to certain power generation companies. Power generation companies that exceed these limits are fined according to the extent of the excess, in an effort to achieve energy conservation and emission reduction. The carbon trading market, born from this, provides power generation companies that exceed their carbon emission limits with the opportunity to purchase carbon emission quotas, minimizing penalties and minimizing operating costs.

[0145] The method for formulating and implementing resource scheduling strategies based on the power generation output of different resources includes collecting the power generation output data and operating status of different resources in real time through the power assessment intelligent management terminal, and feeding it back to the scheduling center; the scheduling center specifies the corresponding resource scheduling strategy based on the collected power generation output data and operating status of different resources, and sends resource adjustment instructions to each generator set to control the operating status of each generator set.

[0146] This embodiment uses a Gaussian mixture model to efficiently identify data points in power assessment data that do not conform to the normal distribution. These outliers may be caused by data collection errors, equipment failures, or other external factors. Accurately identifying and eliminating these outliers helps improve data quality and ensure the accuracy of subsequent analysis and decision-making. The optimal number of Gaussian distributions is dynamically determined through the Bayesian Information Criterion, and the threshold for outlier detection is dynamically adjusted through the probability density threshold adjustment formula. This allows for flexible adaptation to outlier identification requirements in different scenarios based on changes in data distribution, thereby avoiding overly strict or overly loose threshold settings and improving the robustness of the method.

[0147] The Bayesian Information Criterion dynamically selects the optimal number of Gaussian distributions, eliminating the need for manual configuration. The Bayesian Information Criterion considers both the model's fit and its complexity, selecting a model that fits the data well while remaining reasonably complex. This makes the entire process more automated and adaptable to varying data characteristics.

[0148] By integrating multiple flexible resources, including photovoltaics, wind power, thermal power, hydropower, and energy storage, a comprehensive power assessment model has been constructed. This diversified resource utilization comprehensively considers the advantages and disadvantages and characteristics of different types of power generation, providing diverse solutions for the power system, thereby achieving optimal resource allocation and scheduling. By integrating multiple flexible resources, such as wind power, thermal power, hydropower, energy storage, and DC interconnections, it is possible to achieve optimized scheduling of power production, ensuring that the power system meets demand while minimizing system operating costs.

[0149] Through IBDR (demand response) and PSDR (load regulation) models, electricity demand can be adjusted, system load fluctuations can be reduced, and grid operation can be optimized. Furthermore, electrochemical energy storage models help regulate power flows between peaks and valleys, provide backup power, and improve system stability and anti-interference capabilities. By modeling the power and operating characteristics of DC interconnection lines, rapid cross-regional power dispatch can be achieved, improving power supply flexibility and reducing losses during long-distance transmission. By achieving efficient dispatch and cost optimization of flexible resources, power companies can better adapt to market changes, support government carbon reduction targets and sustainable energy policies, and quantify the cost-effectiveness of flexible resources to provide a basis for policy formulation and market design.

[0150] Example 2

[0151] See also Figure 2 As shown, this embodiment provides a power assessment system based on the participation of multiple flexibility resources, including:

[0152] Data acquisition module, used to obtain heterogeneous data for power evaluation;

[0153] A data processing module is used to pre-process the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set;

[0154] Multivariate flexibility resource modeling module, which is used to construct a multivariate flexibility resource model based on heterogeneous feature data sets and predict the power generation output of different resources through the multivariate flexibility resource model;

[0155] The scheduling decision execution module is used to formulate and execute resource scheduling strategies based on the power generation output of different resources; each module is connected via wired and / or wireless means.

[0156] Since the electronic device introduced in this embodiment is an electronic device used to implement the power evaluation method and system based on the participation of multiple flexible resources in the embodiment of this application, based on the power evaluation method and system based on the participation of multiple flexible resources introduced in the embodiment of this application, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be introduced in detail here. As long as technical personnel in this field implement the electronic device used in the power evaluation method and system based on the participation of multiple flexible resources in the embodiment of this application, they all fall within the scope of protection of this application.

[0157] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0158] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that for users of ordinary skill in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A power assessment method based on the participation of multiple flexibility resources, characterized in that: include: S1. Obtaining heterogeneous data for power assessment; S2. Preprocess the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set; The method for preprocessing the acquired power evaluation heterogeneous data to obtain a heterogeneous feature data set includes: identifying outliers in the power evaluation heterogeneous data by improving the Gaussian mixture model, and removing the identified outliers; the method for identifying outliers in the power evaluation heterogeneous data by improving the Gaussian mixture model and removing the identified outliers includes: S41. Combine the power generation side data, energy storage side data, demand side data and grid side data in the power evaluation heterogeneous data into a multidimensional feature matrix ;in, ' is the number of samples, that is, the number of data points in the multidimensional feature matrix; is the number of feature dimensions, that is, the number of features of each sample; S42, preset the distribution of power generation side data, energy storage side data, demand side data and power generation side data as follows: A mixture of Gaussian distributions, represented by a Gaussian mixture model; S43. Dynamically determine the optimal number of Gaussian distributions through the Bayesian Information Criterion; estimate the parameters of the Gaussian mixture model through the expectation maximization algorithm, and randomly initialize the mean vector, covariance matrix and weight of each Gaussian distribution; use the posterior probability calculation formula to calculate the probability that each data point in the multidimensional feature matrix belongs to the first The posterior probability of a Gaussian distribution is given by The probability of a Gaussian distribution being generated; S44. For each data point in the multidimensional feature data , calculate its probability density in the Gaussian mixture model , the preset probability density threshold is , the preset probability density threshold is dynamically adjusted through the probability density threshold adjustment formula, and the probability density threshold adjustment formula is: ;in, is the probability density threshold after dynamic adjustment; is the proportionality coefficient; is the average probability density of the data; is the target outlier; S45, if , then determine the data point is an abnormal value; if , then determine the data point is a normal value, which will satisfy The data points are removed from the heterogeneous data of power assessment; S3. Construct a multivariate flexibility resource model using heterogeneous feature datasets, and predict the power generation output of different resources using the multivariate flexibility resource model. S4. Develop and implement resource scheduling strategies based on the power generation output of different resources.

2. The power assessment method based on the participation of multiple flexibility resources according to claim 1 is characterized in that: The heterogeneous data for power evaluation includes power generation side data, energy storage side data, demand side data and grid side data; the power generation side data includes photovoltaic power generation data, wind power generation data, thermal power unit data and hydropower data; Photovoltaic power generation data includes solar radiation intensity, photovoltaic panel temperature, and installation angle; wind power generation data includes wind turbine power generation, wind turbine cut-in and cut-out wind speeds; thermal power unit data includes unit power upper and lower limits and unit start and stop status; hydropower data includes water flow rate through the unit and generating head; The energy storage side data includes the charging and discharging power, efficiency, state of charge of battery energy storage and the upper and lower reservoir capacities of pumped storage; the demand side data includes the user's electricity load and electricity price data; the grid side data includes the real-time load of the grid, peak and valley load, frequency fluctuations of the grid, voltage level of the grid and load of the transmission lines.

3. The power evaluation method based on the participation of multiple flexibility resources according to claim 2 is characterized in that: The method of preprocessing the acquired power evaluation heterogeneous data to obtain a heterogeneous feature data set further includes: Process missing values in the power assessment heterogeneous data and remove duplicate data in the power assessment heterogeneous data; encode the non-numeric data in the power assessment heterogeneous data and convert it into numerical data to obtain a processed heterogeneous feature data set; perform standard deviation normalization on the processed heterogeneous feature data set and convert it into a standard normal distribution to obtain a normalized heterogeneous feature data set.

4. The power assessment method based on the participation of multiple flexibility resources according to claim 3 is characterized in that: The method of identifying outliers in the heterogeneous data of power evaluation by improving the Gaussian mixture model and removing the identified outliers also includes: The Gaussian mixture model is: ;in, For data points In all The probability density value in the Gaussian mixture model; For the The weights of the Gaussian distribution; For the The probability density function of a Gaussian distribution; For the The mean vector of the Gaussian distribution; For the The covariance matrix of a Gaussian distribution; is the number of Gaussian distribution; is the index of each individual Gaussian distribution component in the Gaussian mixture model; The formula for calculating the posterior probability is: ;in, For data points Belong to The probability of a Gaussian distribution being generated; is the first data points; is the index of the data point; For the The weights of the Gaussian distribution; The index for traversing all Gaussian distributions.

5. The power evaluation method based on the participation of multiple flexibility resources according to claim 4 is characterized in that: The method for dynamically determining the optimal number of Gaussian distributions by using the Bayesian Information Criterion includes: Preset number of Gaussian distributions The candidate range of ' is ;in, is the minimum value of the Gaussian distribution number; is the maximum value of the Gaussian distribution number; for the preset Gaussian distribution number The number of each Gaussian distribution within the candidate range , train the Gaussian mixture model and calculate the corresponding maximum likelihood value through the maximum likelihood estimation formula; the maximum likelihood estimation formula is: ;in, For each Gaussian distribution number The corresponding maximum likelihood value; According to the number of each Gaussian distribution , calculate its Bayesian information criterion value through the Bayesian information criterion calculation formula; the Bayesian information criterion calculation formula is: ;in, is the Bayesian information criterion value; is the log-likelihood of the Gaussian mixture model; is the number of Gaussian mixture model parameters, including mean vector, covariance matrix and weights; By comparing the number of different Gaussian distributions The corresponding Bayesian Information Criterion value BIC, select the number of Gaussian distributions that minimizes the Bayesian Information Criterion value BIC , which is the optimal number of Gaussian distributions.

6. The power assessment method based on the participation of multiple flexibility resources according to claim 5 is characterized in that: The method for constructing a multivariate flexibility resource model through heterogeneous feature data sets includes: The multivariate flexibility resource model includes a photovoltaic power generation output model, a wind power generation output model, a thermal power unit fuel cost model, a hydropower unit output model, a pumped storage unit model, an IBDR cost calculation model, a PSDR cost calculation model, an electrochemical energy storage model, a DC tie line power characteristic model, and a DC tie line operation characteristic model; Constructing a photovoltaic power generation power evaluation model: ;in, For photovoltaic systems in daily Output power at any moment; is the rated power of the photovoltaic; The actual light intensity at the moment; is the rated light intensity of the photovoltaic system; For a certain moment in the day; Use temperature linear function to describe its influence on photovoltaic power generation output; the preset photovoltaic panel temperature is , photovoltaic power generation output is , the temperature linear function is: ;in, At the reference temperature Photovoltaic power generation output under is the reference temperature; is a constant, which represents the rate at which temperature affects photovoltaic power output; The cosine law is used to calculate the incident angle of sunlight, and the photoelectric conversion efficiency of the photovoltaic panel is considered to estimate the power generation. The output model is: ;in, The contribution of the installation angle and orientation of solar panels to photovoltaic power generation output; is the rated output power of the photovoltaic panel; is the conversion efficiency of the photovoltaic cell; is the angle between the sunlight and the normal of the photovoltaic panel; Taking into account the solar radiation intensity, photovoltaic panel temperature, and the installation angle and orientation of the solar panel, the photovoltaic power generation output model is obtained using the weighted average method. The photovoltaic power generation output model is: ;in, The contribution weight of solar radiation intensity to photovoltaic power generation output; is the contribution weight of photovoltaic panel temperature to photovoltaic power generation output; The contribution weight of the solar panel installation angle and orientation to photovoltaic power output.

7. The power evaluation method based on the participation of multiple flexibility resources according to claim 6 is characterized in that: The wind power generation output model includes: ;in, The power generated by the wind turbine; is the actual wind speed; is the cut-in wind speed; To cut out wind speed; is the rated wind speed; is the rated output power of the fan; The output power of thermal power units is subject to upper and lower limits, and the constraint expressions are: ;in, For thermal power plant model Thermal power units Output power; and Represent thermal power units Upper and lower limits of output; for Thermal power units A binary variable for the running status, Indicates shutdown. Indicates running; The fuel cost model of thermal power units is constructed by coal consumption cost and start-up and shutdown cost. The fuel cost model of thermal power units is: ;in, is the total fuel cost of thermal power units; is the coal consumption cost of thermal power units; is the start-up and shutdown cost of thermal power units; The coal consumption cost expression of thermal power units is: ;in, For thermal power units Total running time; is the total number of thermal power units; 、 Thermal power units Coal consumption cost coefficient; for Thermal power units Active power; The start-up and shutdown cost expression of thermal power units is: ;in, For thermal power units The start-stop cost of Thermal power units A binary variable for the operating status; Hydropower units include run-of-river hydropower stations and pumped storage units; the output model of hydropower units is: ;in, For the The output power of a run-of-river hydropower station at time t; is the density of water; is the acceleration due to gravity; For power generation efficiency; is the power generation flow; The power generation head; The flow constraint formula is used to constrain the power generation flow of the run-of-river hydropower station. The flow constraint formula is: ;in, are the maximum and minimum power generation flows of the lth run-of-river hydropower station, ; is the number of run-of-river hydropower stations; The pumped storage unit is composed of units in turbine working condition and units in pump working condition. The actual output power of the unit in power generation condition is measured by the turbine working condition output formula. The turbine working condition output formula is: ;in, for The number of units in power generation condition at all times; for The output of the pumped storage unit turbine under operating conditions at all times; and It is the upper and lower limits of the output of the pumped storage unit under power generation conditions; The actual output power of the unit under pumping conditions is measured by the water pump working condition output formula; the water pump working condition output formula is: ;in, for The number of units in pumping operation at all times; for The output of the pumped storage unit under the working condition of the water pump at all times; and It is the upper and lower limits of the output of the pumped storage unit under the working condition of the water pump; An IBDR cost calculation model is established based on the changes in the power company's revenue from demand-side users with IBDR capabilities; Assuming that users do not participate in IBDR, the power company's income is: ;in, The income of the power company before the user participates in IBDR; for Fixed electricity price on the retail side at the time; Before the implementation of the demand response project IBDRs in The load of the moment; The cost of IBDR is the power outage loss caused by load reduction. When the load is on, the compensation provided by the power company is: ;in, Reduce for users through IBDR When the load is on, the power company compensates it; and Respectively The degree of the quadratic term and the linear coefficient of the IBDR compensation amount; For the IBDRs at the moment load shedding; After users participate in IBDR, the power company's income is: ;in, The income of the power company after the users participate in IBDR; The IBDR cost calculation model is: Where: ; ; Assuming that users do not participate in PSDR, the power company's revenue is: ;in, Before the implementation of the demand response project PSDR in The load at the moment; after the user participates in PSDR, the power company’s income is: ;in, The proportion of preferential electricity prices given by power companies to users in order to increase their enthusiasm for participation; for The amount of increase in electricity prices at any given moment; For the PSDR in The amount of load reduction at a given time; According to the price elasticity coefficient of demand available: ; Then the PSDR cost calculation model is: ;in, ; ; ; The electrochemical energy storage model is: ;in, is the discharge efficiency of the energy storage system; Charging efficiency for energy storage systems; Energy storage device Charging power at all times; Energy storage device Discharge power at all times; Energy storage device The amount of electricity stored at any moment; Energy storage device The amount of electricity released at any moment; The charging and discharging power constraint formula is used to constrain the charging and discharging power of the energy storage at each moment. The charging and discharging power constraint formula is: ;in, It is a 0-1 variable. When the energy storage is charged is 1, when the energy storage is discharged is 0; Each stepped power of the DC tie line is regarded as a feasible state of the DC tie line power. If the DC tie line is in operation, the power of the DC tie line is and can only be in the feasible state set, that is, ;in, DC tie line exist Active power at the moment; DC tie line In a feasible state The power value; DC tie line The number of feasible states; The power characteristic model of the DC tie line is: ;in, is the power of the DC tie line; is a 0-1 variable, indicating the DC tie line Is it in a feasible state at time t? ; The operating characteristic model of the DC tie line is: ;in, and DC tie lines The minimum and maximum power that can be transmitted; DC tie line exist Operating power at all times; Based on data from the power generation side, energy storage side, grid side and demand side, simulation technology analysis is run to quantitatively evaluate the impact of different flexibility resources on total costs by comparing the cost effects of different flexibility resources when participating in power assessment.

8. The power assessment method based on the participation of multiple flexibility resources according to claim 7 is characterized in that: The method of running simulation technology analysis based on power generation data, energy storage data, grid data, and demand data to quantitatively evaluate the impact of different flexibility resources on total costs by comparing the cost effects of different flexibility resources when participating in power assessment includes: Taking the minimization of the total cost of power system operation with the participation of multiple flexible resources as the goal, the optimal economic benefit objective function of the system joint operation model is constructed. The optimal economic benefit objective function is: ;in, 、 、 and Represent the power generation side cost, demand side cost, energy storage side cost and environmental cost respectively; The power generation cost is expressed as: ;in, represents the total operating cost of the photovoltaic unit, represents the total operating cost of the wind turbine, is the total operating cost of thermal power units; is the total operating cost of the hydropower unit; is the total operating cost of the pumped storage unit; is the number of thermal power units that have undergone flexibility transformation, represents the start-up and shutdown loss cost of the pumped storage unit; Indicates the operation and maintenance cost of the pumped storage unit with flexible adjustment. represents the peak shaving cost; The demand side cost is expressed as: The energy storage cost is expressed as: ,in, represents the operation and maintenance cost of electrochemical energy storage; Represents the operation and maintenance cost of P2G; the environmental cost refers to the carbon emission cost, which comes from thermal power generation units. The carbon emission amount is expressed as: ;in, 、 、 Calculation parameters for carbon emissions from thermal power units; Carbon emission quota is expressed as: ;in, is the carbon emission quota per unit of power generation of thermal power units; the carbon emission cost is expressed as: ;in, The price per unit of carbon emissions is used; by comparing the cost effects of different flexibility resources when participating in electricity assessment, the impact of different flexibility resources on the total cost is quantitatively evaluated.

9. The power evaluation method based on the participation of multiple flexibility resources according to claim 8, characterized in that: The method for formulating and executing resource scheduling strategies based on the power generation output of different resources includes collecting the power generation output data and operating status of different resources in real time through the power assessment intelligent management terminal, and feeding back the data to the scheduling center; the scheduling center specifies the corresponding resource scheduling strategies based on the collected power generation output data and operating status of different resources, and sends resource adjustment instructions to each generator set to control the operating status of each generator set.

10. An electric power evaluation system based on the participation of multiple flexible resources, used to implement the electric power evaluation method based on the participation of multiple flexible resources according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, used to obtain heterogeneous data for power evaluation; A data processing module is used to pre-process the acquired power assessment heterogeneous data to obtain a heterogeneous feature data set; Multivariate flexibility resource modeling module, which is used to construct a multivariate flexibility resource model based on heterogeneous feature data sets and predict the power generation output of different resources through the multivariate flexibility resource model; The scheduling decision execution module is used to formulate and execute resource scheduling strategies based on the power generation output of different resources; each module is connected via wired and / or wireless means.

Images