Coal-fired unit group comprehensive energy consumption curve generation method based on kernel principal component analysis

Abstract

The application provides a method for generating a comprehensive energy consumption curve of a coal-fired unit group based on kernel principal component analysis. The method for generating the comprehensive energy consumption curve of the coal-fired unit group based on kernel principal component analysis can more accurately reflect the real energy consumption characteristics of a pure condensing coal-fired unit group, improve the stability and reliability of the comprehensive energy consumption curve, and effectively support scientific calculation of variable costs and market mechanism design in an electricity market.

Description

Technical Field

[0001] This invention relates to the field of energy consumption characteristic modeling and cost parameter calculation technology for coal-fired power generating units, and in particular to a method for generating comprehensive energy consumption curves for coal-fired power generating unit groups based on kernel principal component analysis. Background Technology

[0002] With the deepening of power market reform, the scientific calculation of variable costs for coal-fired power units has become a key foundation for building a multi-tiered power market system. Against the backdrop of the coordinated development of the electricity spot market, capacity market, and ancillary service market, the modeling and weighted fitting technology of energy consumption characteristic curves for coal-fired power units serves as an important supporting tool for power economic operation analysis and is widely used in areas such as market power monitoring, price mechanism design, and dispatch optimization. In related technologies, the least squares method is typically used to perform quadratic polynomial fitting on measured data from a single unit to construct the energy consumption characteristic curve of that unit, and then combined with a capacity-weighted method to generate a comprehensive curve for the entire unit group. Specifically, this technical system covers the entire process from data acquisition and curve fitting to weighted fusion, involving multi-dimensional collaboration between statistical modeling, machine learning, and power system operation.

[0003] However, existing capacity-weighted methods directly use installed capacity as the weighting criterion, failing to fully consider the actual operating efficiency, individual characteristics, and state differences of the units. This can lead to distortion of the composite curve, making it unable to accurately reflect the true energy consumption level of the unit group. In particular, traditional Principal Component Analysis (PCA), limited by linear assumptions, struggles to capture the nonlinear correlation characteristics between units and is prone to losing local features and exhibiting insufficient overall stability when dealing with heterogeneous unit groups. Therefore, existing technologies have significant limitations in dynamic cost analysis, market mechanism support, and scheduling strategy optimization. There is an urgent need for a weighted fitting method that can balance the commonalities and individual characteristics of units and possess nonlinear modeling capabilities to improve the reliability and applicability of the composite curve. Summary of the Invention

[0004] The present invention aims to at least partially solve one of the technical problems in the related art.

[0005] Therefore, the first objective of this invention is to propose a method for generating a comprehensive energy consumption curve for a coal-fired power unit group based on kernel principal component analysis.

[0006] The second objective of this invention is to propose a device for generating comprehensive energy consumption curves for coal-fired power unit groups based on kernel principal component analysis.

[0007] The third objective of this invention is to provide an electronic device.

[0008] The fourth objective of this invention is to provide a computer-readable storage medium.

[0009] The fifth objective of this invention is to provide a computer program product.

[0010] To achieve the above objectives, a first aspect of the present invention proposes a method for generating a comprehensive energy consumption curve for a coal-fired power unit group based on kernel principal component analysis, comprising: S1, acquiring data pairs of power supply coal consumption and load points for each unit in a pure condensing coal-fired power unit group, wherein the number of data pairs is not less than 3, and determining the common load output range of the unit group; S2, based on the data pairs, performing quadratic polynomial fitting on each unit using the least squares method to generate a corresponding single-unit energy consumption characteristic curve; S3, based on the single-unit energy consumption characteristic curve, performing quadratic polynomial fitting on the common load point of the unit group. S4. Select no less than 500 load points within the load output range, calculate the energy consumption of each unit at the corresponding load point, and standardize the load output and energy consumption; S5. Use kernel principal component analysis to train the standardized data, calculate the principal component contribution of each unit in the feature space, determine the initial weights based on the contribution, and normalize the initial weights; S6. Based on the normalized weights, perform weighted fitting on the energy consumption characteristic curve of the single unit to generate a comprehensive energy consumption characteristic curve representing the unit group.

[0011] In one embodiment of the present invention, the step of obtaining power supply coal consumption and load point data pairs of each unit in a pure condensing coal-fired power unit group, wherein the number of data pairs is not less than 3, and determining the common load output range of the unit group, further includes: S11, the power supply coal consumption and load point data pairs are derived from unit performance test reports or power plant platform systems, and each data pair has been verified for reliability to ensure the accuracy and representativeness of the data; S12, the common load output range is the intersection of the output ranges of all units in the unit group, the maximum value of which is the maximum output value in the intersection, the minimum value of which is 0, and the range covers at least 80% of the operating range of the unit group.

[0012] In one embodiment of the present invention, the step of performing a quadratic polynomial fitting on each unit using the least squares method based on the data pair to generate a corresponding single-unit energy consumption characteristic curve further includes: S21, wherein the quadratic polynomial fitting function is y = ax 2 +bx+c, where a, b, and c are parameters to be determined, and the parameters are estimated by minimizing the sum of squared errors between the observed and predicted values; S22, the energy consumption is obtained by multiplying the load output by the corresponding coal consumption for power supply, and is corrected by combining the plant power consumption rate to improve the fitting accuracy of the fitted curve to the actual energy consumption.

[0013] In one embodiment of the present invention, the step of training the standardized data using kernel principal component analysis, calculating the principal component contribution of each unit in the feature space, determining the initial weights based on the contribution, and normalizing the initial weights further includes: S41, the kernel principal component analysis preferentially selects the RBF kernel function, sets the initial gamma value to 0.001, and initially sets the number of principal components n_components to 2; S42, if the cumulative explanatory power of the principal components is less than 80%, the gamma value is adjusted to 0.01 or 0.0001, or the number of principal components is increased to 3, so as to improve the comprehensiveness and robustness of feature extraction.

[0014] In one embodiment of the present invention, the method further includes: dynamically updating the generated integrated energy consumption characteristic curve; when the power supply coal consumption data of any unit in the unit group changes significantly or a new unit is added, steps S1 to S5 are re-executed to generate an updated integrated energy consumption characteristic curve.

[0015] To achieve the above objectives, a second aspect of the present invention proposes a device for generating a comprehensive energy consumption curve for a coal-fired power unit group based on kernel principal component analysis, comprising: a data acquisition module for acquiring power supply coal consumption and load point data pairs for each unit in a pure condensing coal-fired power unit group, wherein the number of data pairs is not less than three, and determining the common load output range of the unit group; a curve fitting module for performing quadratic polynomial fitting on each unit using the least squares method based on the data pairs to generate a corresponding single-unit energy consumption characteristic curve; and an energy consumption calculation and standardization module for calculating the common load output... At least 500 load points are selected within the range, and the energy consumption of each unit at the corresponding load point is calculated. The load output and energy consumption are then standardized. A kernel principal component analysis module is used to train the standardized data using kernel principal component analysis, calculate the principal component contribution of each unit in the feature space, determine the initial weights based on the contribution, and normalize the initial weights. A comprehensive curve generation module is used to perform weighted fitting on the energy consumption characteristic curve of the single unit based on the normalized weights to generate a comprehensive energy consumption characteristic curve representing the unit group.

[0016] In one embodiment of the present invention, the data acquisition module is further configured to: the power supply coal consumption and load point data pairs are derived from unit performance test reports or power plant platform systems, and each data pair is verified for reliability to ensure the accuracy and representativeness of the data; the common load output range is the intersection of the output ranges of all units in the unit group, the maximum value of which is the maximum output value in the intersection, the minimum value of which is 0, and the range covers at least 80% of the operating range in the unit group.

[0017] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0018] The memory stores computer-executed instructions;

[0019] The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0020] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0021] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product that, when executed by a processor, implements the method described in any one of the first aspects.

[0022] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects: effectively solving the problem that the traditional capacity-weighted method ignores the actual efficiency and individual characteristics of the generating units, improving the stability and accuracy of the comprehensive energy consumption characteristic curve, and providing reliable data support for the calculation of variable costs in the electricity market.

[0023] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0024] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0025] Figure 1 This is a flowchart of a method for generating a comprehensive energy consumption curve of a coal-fired power unit group based on kernel principal component analysis, according to an embodiment of the present invention.

[0026] Figure 2 This is a schematic diagram of the structure of a device for generating integrated energy consumption curves of coal-fired power unit groups based on kernel principal component analysis, according to an embodiment of the present invention. Detailed Implementation

[0027] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0028] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0030] Figure 1 This is a flowchart of a method for generating a comprehensive energy consumption curve for a coal-fired power unit group based on kernel principal component analysis, according to an embodiment of the present invention.

[0031] like Figure 1 As shown, the method for generating the comprehensive energy consumption curve of a coal-fired power unit group based on kernel principal component analysis includes the following steps:

[0032] S1, acquire power supply coal consumption and load point data pairs for each unit in the pure condensing coal-fired unit group, the number of data pairs shall not be less than 3 sets, and determine the common load output range of the unit group.

[0033] Specifically, this step aims to obtain power supply coal consumption and load point data pairs for each unit in a pure condensing coal-fired power unit group, and to determine the common load output range of the unit group. This is a fundamental step in constructing the comprehensive energy consumption characteristic curve. In some implementations, this step ensures the integrity and reliability of the data by collecting at least three representative power supply coal consumption and load point data pairs for each unit. The data source is usually the unit performance test report or the power plant operation platform system, complying with the technical requirements for energy consumption data collection and management in DL / T1052-2016 "Regulations for Supervision and Management of Energy Conservation Technology in Thermal Power Plants". Furthermore, the common load output range is the intersection of the output ranges of all units in the unit group, with its maximum value being the maximum output value in this intersection and its minimum value being 0. This range covers at least 80% of the operating range of the unit group. This step plays a crucial role in this invention, aiming to construct a representative load range for subsequent weighted fitting of the multi-unit energy consumption characteristic curves, thereby improving the accuracy and applicability of the comprehensive curve.

[0034] At the technical implementation level, the acquisition of power supply coal consumption (unit: g / kWh) and load point (unit: MW) data pairs must meet the requirements of time synchronization and operating condition consistency, meaning the data should reflect the performance of the units under the same or similar operating conditions. Furthermore, to ensure the accuracy of subsequent fitting and weighted calculations, the load points of each unit need to be cross-compared to select the portion of the load range that is covered by data for all units, which is then used as the common load output range. This range typically uses the minimum load point as the lower limit and the maximum load point as the upper limit, forming a continuous load range for subsequent unified energy consumption characteristic curve fitting and weighted calculations.

[0035] Regarding parameter indicators, the number of load point data pairs should be no less than three sets to meet the basic requirements of least squares fitting of quadratic polynomial curves. The selection of load points should cover the typical operating range of the units, such as key nodes like 50%, 75%, and 100% of rated load. The determination of the common load output range needs to consider the differences in rated capacity of the units, and is usually done by taking the intersection method to ensure that all units have valid data support within this range.

[0036] In practical applications, this step is suitable for modeling the energy consumption of coal-fired power plant groups under specific analysis dimensions (such as coal type, unit type, and operating years). By unifying the load range, fitting biases caused by differences in unit capacity can be eliminated, improving the representativeness and applicability of the comprehensive curve.

[0037] The technical effect of this step is that it provides a standardized and comparable data foundation for subsequent weight calculation and curve weighted fitting based on kernel principal component analysis (KPCA), thereby improving the fitting accuracy and generalization ability of the comprehensive energy consumption characteristic curve and providing reliable support for variable cost calculation and electricity market analysis.

[0038] S2. Based on the data pairs, the least squares method is used to perform quadratic polynomial fitting on each unit to generate the corresponding single-unit energy consumption characteristic curve.

[0039] Specifically, in this step, for each pure condensing coal-fired unit, the measured coal consumption for power supply and load point data are fitted using the least squares method to perform a quadratic polynomial fit, thereby generating the unit's energy consumption characteristic curve. This step is the fundamental link in building the single-unit model in the entire method, and its fitting accuracy directly affects the reliability and representativeness of the subsequent weighted composite curve.

[0040] At the technical implementation level, it is first necessary to ensure that each unit has at least three (preferably five) representative load-power supply coal consumption data pairs. This data typically originates from unit performance test reports or the power plant's operation platform system, ensuring high reliability. The fitting function adopts a standard quadratic polynomial form:

[0041] y = ax2 +bx+c

[0042] Where x represents the unit load output (unit: MW), y represents the corresponding energy consumption (unit: gce / kWh or tce / GWh), and a, b, and c are fitting coefficients. The energy consumption y is usually obtained by multiplying the coal consumption for power supply by the load output, and can also be corrected by combining the plant power consumption rate to more accurately reflect the actual power generation energy consumption.

[0043] At the parameter level, the least squares method minimizes the measured value Y. i with fitted value The sum of squared residuals between them, that is, the residuals for each unit's measured energy consumption point (xi, yi), are:

[0044]

[0045] The objective function is:

[0046]

[0047] Taking the partial derivatives of a, b, and c and setting them to zero yields a system of linear equations, which can be solved to obtain the optimal parameters. The partial derivatives of the quadratic coefficient a, the linear coefficient b, and the constant coefficient c are all zero. These three equations can be solved simultaneously using algebraic elimination or determinant expansion to calculate the specific values ​​of a, b, and c.

[0048] At the application level, this step is suitable for modeling the variable costs of coal-fired power units in the electricity market. In particular, before generating the comprehensive curve for a regional unit group, each unit needs to be modeled independently. By using quadratic polynomial fitting, the energy consumption variation trend of the unit under different load levels can be effectively characterized, providing a mathematical basis for subsequent weighted calculations.

[0049] In terms of technical effectiveness, this step enables accurate modeling of the energy consumption characteristics of a single unit, providing a standardized and comparable curve expression for subsequent weight calculation based on kernel principal component analysis, thereby improving the scientific nature and traceability of the overall curve of the entire unit group.

[0050] S3. Based on the single-unit energy consumption characteristic curve, select no less than 500 load points within the common load output range, calculate the energy consumption of each unit at the corresponding load point, and standardize the load output and energy consumption.

[0051] Specifically, in this step, based on the energy consumption characteristic curves of individual units, no fewer than 500 load points are selected within the common load output range of the unit group, and the energy consumption of each unit at the corresponding load point is calculated. Subsequently, the load output and energy consumption are standardized. This step is a crucial step in constructing the comprehensive energy consumption characteristic curve. Its technical implementation principle is based on statistical sampling and data preprocessing methods, aiming to provide structured and highly comparable input data for subsequent kernel principal component analysis (KPCA).

[0052] In some implementations, the determination of the common load output range needs to be based on the intersection of the output capabilities of all units. Typically, the minimum full-load capacity in the unit group is used as the upper limit, and the lower limit is set to 0 MW, to ensure that all units have operational data to support their calculations within this range. At least 500 load points are selected, using either equal-interval sampling or a non-uniform sampling strategy based on load distribution density to cover typical operating conditions. Each load point x i Substitute (i = 1, 2, ..., 500) into the quadratic polynomial energy consumption characteristic curve of each unit (in the form y = ax) 2 Given (bx + c), calculate the corresponding energy consumption y. i This allows for the construction of (x) for each unit. i ,y i Data pairs.

[0053] Furthermore, to eliminate dimensional differences in load scale and energy consumption levels among different units, it is necessary to standardize the load output x and energy consumption y. The standardization method typically employs Z-score standardization, which involves subtracting the mean from each variable and then dividing by the standard deviation to make the data distribution approximate a standard normal distribution. Standardized data can improve the convergence efficiency of kernel principal component analysis and the accuracy of weight calculation.

[0054] In practical applications, this step is suitable for analyzing regional power grids or coal-fired power unit groups based on specific analytical dimensions (such as unit type, year of commissioning, etc.). Through high-density load point sampling and standardization, it can effectively reflect the energy consumption behavior of units under different load levels, providing a reliable data foundation for subsequent weight allocation based on kernel principal component analysis.

[0055] From a technical perspective, this step, through systematic data sampling and standardization, enhances the comparability and consistency of data from different units, thereby improving the accuracy and robustness of the integrated curve fitting. Simultaneously, the selection of no fewer than 500 load points meets the statistical requirements for sample size, ensuring the representativeness and generalization ability of the fitting results.

[0056] S4. The standardized data is trained using kernel principal component analysis to calculate the principal component contribution of each unit in the feature space, and the initial weights are determined based on the contribution. The initial weights are then normalized.

[0057] Specifically, this step uses kernel principal component analysis to train the standardized data, calculates the principal component contribution of each pure condensing coal-fired unit in the feature space, determines the initial weights accordingly, and finally normalizes the weights. This is the key step in realizing the weighted fitting of the integrated energy consumption characteristic curve of the unit group in this invention.

[0058] At the technical implementation level, KPCA is a nonlinear dimensionality reduction method that maps the original data to a high-dimensional feature space using a kernel function, and then performs principal component analysis in that space. In this invention, the load output x and energy consumption y data pairs for each unit have already formed a dataset within a unified range in step III. These data are then standardized to eliminate dimensional differences and ensure the comparability of data from different units in the feature space. Standardization typically employs the Z-score method, which involves subtracting the mean from each feature and dividing by its standard deviation to make the data distribution approximate a standard normal distribution.

[0059] At the parameter level, this invention preferentially selects the radial basis function (RBF) as the kernel function, with its kernel parameter gamma initially set to 0.001. During training, the number of principal components, n_components, is set to 2. If the cumulative explanatory power of the principal components is less than 80%, the gamma parameter needs to be adjusted (e.g., increased to 0.01 or decreased to 0.0001), or the number of principal components needs to be increased to 3 to ensure that the extracted features are sufficiently representative. The principal component contribution reflects the magnitude of each unit's projection onto the principal components in the feature space. A higher contribution indicates that the unit has stronger representativeness or nonlinear characteristics within the unit group.

[0060] At the application level, this step is suitable for comprehensive energy consumption modeling of coal-fired power unit groups in the electricity market, especially in scenarios requiring dynamic, scientific, and traceable variable cost calculations. By extracting and weighting nonlinear features from the energy consumption data of multiple units, it can more accurately reflect the overall operating efficiency and energy consumption level of a regional or dimensional power unit group.

[0061] From a technical perspective, this step extracts the nonlinear common characteristics of the unit group using KPCA and determines its weight in the composite curve by combining the principal component contribution of each unit. Compared with the traditional capacity-weighted method, this better reflects the operating characteristics and individual differences of the units. Normalization ensures that the sum of the weights is 1, meeting the mathematical requirements of weighted fitting, thereby improving the stability and prediction accuracy of the composite curve and providing reliable data support for the design of electricity market mechanisms and cost calculation.

[0062] S5. Based on the normalized weights, the energy consumption characteristic curves of the individual units are weighted and fitted to generate a comprehensive energy consumption characteristic curve representing the group of units.

[0063] Specifically, in this step, the energy consumption characteristic curves of each individual unit are weighted and fitted based on the normalized weights to generate a comprehensive energy consumption characteristic curve representing the unit group. This is a key step in realizing unit group energy consumption modeling and variable cost calculation in this invention. This step overcomes the shortcomings of traditional capacity-weighted methods that ignore differences in unit efficiency and operating characteristics by introducing the contribution of unit principal components extracted by kernel principal component analysis as a weighting factor, thereby improving the fitting accuracy and representativeness of the comprehensive curve.

[0064] In some implementations, this step first normalizes the calculated principal component contributions of each unit, typically using L1 normalization. This involves summing the contribution vectors of all units and then dividing the contribution of each unit by the sum, resulting in a total weight of 1. The normalized weights reflect the contribution of each unit to the overall energy consumption pattern within the unit group, possess nonlinear feature extraction capabilities, and effectively preserve local differences and common characteristics among units.

[0065] Furthermore, the weighted fitting process employs the weighted least squares method. Specifically, the energy consumption data corresponding to more than 500 load points within the common output range of each unit are weighted and summed according to their normalized weights to form a weighted set of data points. Subsequently, these weighted data points are fitted using a quadratic polynomial. By minimizing the sum of squared weighted residuals, the optimal fitting parameters can be obtained, thereby generating the comprehensive energy consumption characteristic curve.

[0066] In practical applications, this step is suitable for modeling coal-fired power unit groups under regional power grids, dispatch areas, or specific technical dimensions, and is particularly valuable in scenarios such as electricity market variable cost calculation, market power analysis, and dispatch optimization. By introducing a nonlinear weighting mechanism, the composite curve can more realistically reflect the energy consumption behavior of the unit group, improve the accuracy and traceability of cost calculation, and provide reliable data support for the design of electricity market mechanisms.

[0067] The method for generating comprehensive energy consumption curves of coal-fired power unit groups based on kernel principal component analysis in this invention extracts the common and individual characteristics of the power unit group through kernel principal component analysis, determines the weight of each unit in the comprehensive curve, and thus generates more stable and reliable comprehensive energy consumption characteristic curves of regional or dimensional power unit groups, improving the accuracy and applicability of variable cost calculation.

[0068] In addition, the present invention dynamically updates the generated comprehensive energy consumption characteristic curve. When the coal consumption data for power supply of any unit in the unit group changes significantly or a new unit is added, steps S1 to S5 are re-executed to generate an updated comprehensive energy consumption characteristic curve.

[0069] Specifically, this step involves a dynamic update mechanism for the comprehensive energy consumption characteristic curve. Its core technology lies in monitoring whether the coal consumption data for power supply of any unit in the unit group has changed significantly or whether a new unit has been added. This triggers a re-execution of the entire curve generation process, ensuring the timeliness and accuracy of the comprehensive curve. In some implementations, significant changes in coal consumption data for power supply can be determined by setting a threshold. For example, if the coal consumption for power supply of a unit changes by more than ±2% within three consecutive statistical periods, the system will automatically identify it as an abnormal fluctuation and trigger the update process. Furthermore, when a new pure condensing coal-fired unit is added to the unit group, the performance data of this unit must meet the requirement of collecting data from at least three complete load-coal consumption points to comply with the data integrity standard of step S1.

[0070] From a technical implementation perspective, this step achieves real-time response and processing of raw data by constructing a data monitoring module and process control logic. When the triggering condition is met, the system will re-call steps S1 to S5, sequentially completing data acquisition, single-machine curve fitting, data point expansion, kernel principal component analysis (KPCA) weight calculation, and comprehensive curve generation. Regarding parameter settings, the KPCA algorithm preferentially uses a radial basis function (RBF) kernel, with an initial gamma value set to 0.001 and the number of principal components n_components set to 2, to extract the nonlinear common features of the unit group. If the cumulative explanatory power of the principal components is less than 80%, the gamma value needs to be adjusted (e.g., between 0.0001 and 0.01) or the number of principal components increased to 3 to improve the model's fitting accuracy and robustness.

[0071] This step is widely applicable in practical scenarios such as variable cost calculation in the electricity market, unit group performance evaluation, and market power monitoring. Especially in the context of large-scale grid integration of new energy sources, coal-fired units need to dynamically adjust their market participation methods, and timely updates to the comprehensive energy consumption curve help improve the scientific nature and fairness of the market mechanism. This step effectively avoids distortion of the comprehensive curve caused by changes in unit performance or structure, thereby improving the accuracy and traceability of variable cost calculation and providing solid data support for the operation of the electricity market.

[0072] The method for generating comprehensive energy consumption curves of coal-fired power unit groups based on kernel principal component analysis in this invention responds in real time to significant changes in coal consumption for power supply or the addition of new units through a dynamic update mechanism, ensuring that the comprehensive energy consumption characteristic curves continuously reflect the latest operating characteristics of the power unit group, and further improving the timeliness, accuracy and adaptability of variable cost calculation.

[0073] To achieve the above embodiments, the present invention also proposes a device for generating comprehensive energy consumption curves of coal-fired power unit groups based on kernel principal component analysis. Figure 2 This is a schematic diagram of a device for generating comprehensive energy consumption curves for a coal-fired power unit group based on kernel principal component analysis, provided as an embodiment of the present invention. Figure 2 As shown, the device includes:

[0074] The data acquisition module 100 is used to acquire power supply coal consumption and load point data pairs of each unit in the pure condensing coal-fired unit group, the number of data pairs is not less than 3 sets, and to determine the common load output range of the unit group.

[0075] The curve fitting module 200 is used to perform quadratic polynomial fitting on each unit based on the data pair using the least squares method to generate the corresponding single-unit energy consumption characteristic curve.

[0076] The energy consumption calculation and standardization module 300 is used to select no less than 500 load points within the common load output range, calculate the energy consumption of each unit at the corresponding load point, and standardize the load output and energy consumption.

[0077] The kernel principal component analysis module 400 is used to train the standardized data using the kernel principal component analysis method, calculate the principal component contribution of each unit in the feature space, determine the initial weights based on the contribution, and normalize the initial weights.

[0078] The comprehensive curve generation module 500 is used to perform weighted fitting on the single-unit energy consumption characteristic curve based on the normalized weights to generate a comprehensive energy consumption characteristic curve representing the unit group.

[0079] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0080] To implement the above embodiments, the present invention also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0081] To implement the above embodiments, the present invention also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0082] To implement the above embodiments, the present invention also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0083] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0084] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0085] This invention is intended to provide implementation schemes for users to selectively prevent the use or access to personal information data. That is, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0086] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0087] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0088] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0090] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0091] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0092] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0093] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0094] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0095] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating comprehensive energy consumption curves for a coal-fired power unit group based on kernel principal component analysis, characterized in that, include: S1, acquire power supply coal consumption and load point data pairs for each unit in the pure condensing coal-fired unit group, the number of data pairs shall not be less than 3 sets, and determine the common load output range of the unit group; S2, Based on the data pairs, the least squares method is used to perform quadratic polynomial fitting on each unit to generate the corresponding single-unit energy consumption characteristic curve; S3. Based on the single-unit energy consumption characteristic curve, select no less than 500 load points within the common load output range, calculate the energy consumption of each unit at the corresponding load point, and standardize the load output and energy consumption. S4. The standardized data is trained using kernel principal component analysis to calculate the principal component contribution of each unit in the feature space, and the initial weights are determined based on the contribution. The initial weights are then normalized. Specifically, the calculated principal component contribution of each unit is normalized using the L1 normalization method. After summing the contribution vectors of all units, the contribution of each unit is divided by the sum to make the total weight equal to 1. The normalized weights reflect the degree of contribution of each unit to the overall energy consumption pattern in the unit group. S5. Based on the normalized weights, the energy consumption characteristic curves of the individual units are weighted and fitted to generate a comprehensive energy consumption characteristic curve representing the group of units.

2. The method as described in claim 1, characterized in that, The acquisition of power supply coal consumption and load point data pairs for each unit in a pure condensing coal-fired power unit group, wherein the number of data pairs is not less than 3, and the determination of the common load output range of the unit group, further includes: S11, the power supply coal consumption and load point data pairs are derived from unit performance test reports or power plant platform systems, and each data pair has been verified for reliability to ensure the accuracy and representativeness of the data; S12, the common load output range is the intersection of the output ranges of all units in the unit group, the maximum value of which is the maximum output value in the intersection, the minimum value of which is 0, and the range covers at least 80% of the operating range in the unit group.

3. The method as described in claim 1, characterized in that, The step of performing quadratic polynomial fitting on each unit using the least squares method based on the data pairs to generate the corresponding single-unit energy consumption characteristic curve also includes: S21, the quadratic polynomial fitting function is: , where a, b, and c are parameters to be determined. The optimal fitting parameters are calculated by minimizing the sum of squared errors between the observed and predicted values. S22, the energy consumption is obtained by multiplying the load output by the corresponding coal consumption for power supply, and is corrected in combination with the plant power consumption rate to improve the fitting accuracy of the fitting curve to the actual energy consumption.

4. The method as described in claim 1, characterized in that, The method of training the standardized data using kernel principal component analysis to calculate the principal component contribution of each unit in the feature space, determining initial weights based on the contribution, and normalizing the initial weights further includes: S41, the kernel principal component analysis method preferentially selects the RBF kernel function, the initial gamma value is set to 0.001, and the number of principal components n_components is initially set to 2; S42. If the cumulative explanation rate of the principal components is less than 80%, adjust the gamma value to 0.01 or 0.0001, or increase the number of principal components to 3 to improve the comprehensiveness and robustness of feature extraction.

5. The method as described in claim 1, characterized in that, Also includes: The generated integrated energy consumption characteristic curve is dynamically updated. When the coal consumption data for power supply of any unit in the unit group changes significantly or a new unit is added, steps S1 to S5 are re-executed to generate an updated integrated energy consumption characteristic curve.

6. A device for generating comprehensive energy consumption curves for coal-fired power unit groups based on kernel principal component analysis, characterized in that, include: The data acquisition module is used to acquire power supply coal consumption and load point data pairs of each unit in the pure condensing coal-fired unit group. The number of data pairs is not less than 3 sets, and the common load output range of the unit group is determined. The curve fitting module is used to perform quadratic polynomial fitting on each unit based on the data pairs using the least squares method, and generate the corresponding single-unit energy consumption characteristic curve. The energy consumption calculation and standardization module is used to select no less than 500 load points within the common load output range, calculate the energy consumption of each unit at the corresponding load point, and standardize the load output and energy consumption. The kernel principal component analysis module is used to train the standardized data using the kernel principal component analysis method, calculate the principal component contribution of each unit in the feature space, determine the initial weights based on the contribution, and normalize the initial weights. Specifically, the calculated principal component contribution of each unit is normalized using the L1 normalization method. After summing the contribution vectors of all units, the contribution of each unit is divided by the sum, so that the total weight is 1. The normalized weights reflect the degree of contribution of each unit to the overall energy consumption pattern in the unit group. The comprehensive curve generation module is used to perform weighted fitting on the energy consumption characteristic curves of the individual units based on the normalized weights, and generate a comprehensive energy consumption characteristic curve representing the group of units.

7. The apparatus as claimed in claim 6, characterized in that, The data acquisition module is also used for: The power supply coal consumption and load point data pairs are derived from unit performance test reports or power plant platform systems, and each data pair has been verified for reliability to ensure the accuracy and representativeness of the data. The common load output range is the intersection of the output ranges of all units in the unit group. Its maximum value is the maximum output value in the intersection, and its minimum value is 0. This range covers at least 80% of the operating range of the unit group.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-5.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-5.

Images