An operation evaluation method and device of an integrated energy system and a management and control system

Abstract

The application discloses a kind of operation evaluation method, device and management and control system of integrated energy system, method includes: obtaining the operation data of each subsystem in integrated energy system;Based on the integrated energy index library constructed in advance, the corresponding evaluation characteristics are filtered from the operation data of each subsystem;Using principal component analysis, the evaluation characteristics are analyzed, and the core characteristics are given;According to the similarity of each evaluation characteristic and core characteristic, determine the target evaluation characteristic and give the evaluation weight corresponding to the target evaluation characteristic;Based on the target evaluation characteristic of each subsystem in integrated energy system, the evaluation weight corresponding to the target evaluation characteristic is fused, and the operation evaluation data of integrated energy system is given.Through the operation data of integrated energy system, the data is extracted using principal component analysis and the target evaluation characteristic with high correlation is selected, and the evaluation weight is set by combining information entropy, to obtain operation evaluation data, improve the accuracy of integrated energy system evaluation.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of comprehensive energy system operation efficiency evaluation, and specifically relates to a comprehensive energy system operation evaluation method, device and management and control system. BACKGROUND

[0002] In today's energy field, comprehensive energy systems involve the production, conversion, storage and consumption of multiple energies, and their complexity is increasing.

[0003] Traditional evaluation methods have many limitations when dealing with comprehensive energy system data, such as difficulty in extracting key features from massive data, strong subjectivity in index selection, and lack of scientificity in setting index weights. These problems result in incomplete, inaccurate and inefficient evaluation of comprehensive energy systems, which cannot meet the needs of energy system optimization and sustainable development.

[0004] Patent application CN116227646A discloses a comprehensive energy system operation state evaluation method and system, characterized by establishing a comprehensive energy system operation state evaluation system and determining the weights of each index in the comprehensive energy system operation state evaluation system; constructing a multi-objective optimization scheduling model of the comprehensive energy system, and based on the weights of each index in the operation state evaluation system, establishing the coupling relationship of different forms of energy of each index in the operation state evaluation system; modeling the state probability of energy conversion equipment in multiple time periods, and according to the multi-objective optimization scheduling model of the comprehensive energy system and the coupling relationship of different forms of energy of each index in the operation state evaluation system, determining the importance of different energy conversion equipment in the comprehensive energy system; according to the importance of different energy conversion equipment in the comprehensive energy system, determining whether the operation state of the comprehensive energy system is at risk, which can be widely used in the field of operation scheduling control. The indexes in the evaluation system in this patent are set by humans, which is highly subjective, making the evaluation of the comprehensive energy system not comprehensive and accurate.

[0005] How to determine evaluation indexes under the premise of meeting the complexity and diversity of comprehensive energy systems to achieve scientific, comprehensive and accurate evaluation of comprehensive energy systems is a problem that needs to be solved. SUMMARY

[0006] In view of the defects in the prior art, the application provides a running evaluation method, device and management and control system of a comprehensive energy system, which comprises the following steps: obtaining running data of each subsystem in the comprehensive energy system; screening corresponding evaluation features from the running data of each subsystem based on a pre-constructed comprehensive energy index library; analyzing the evaluation features by using a principal component analysis method to give core features; determining target evaluation features and giving evaluation weights corresponding to the target evaluation features according to the similarity of each evaluation feature and the core features; and giving running evaluation data of the comprehensive energy system based on the target evaluation features of each subsystem in the comprehensive energy system and the evaluation weights corresponding to the target evaluation features. By collecting the running data of the comprehensive energy system, the principal component analysis method is used to extract features from the data and select target evaluation features with high correlation, and the evaluation weights are set in combination with information entropy, so that the running evaluation data is finally obtained, and the accuracy of the comprehensive energy system evaluation is improved.

[0007] In a first aspect, the application provides a running evaluation method of a comprehensive energy system, which specifically comprises the following steps:

[0008] Obtaining running data of each subsystem in the comprehensive energy system;

[0009] Screening corresponding evaluation features from the running data of each subsystem based on a pre-constructed comprehensive energy index library;

[0010] Analyzing the evaluation features by using a principal component analysis method to give core features;

[0011] Determining target evaluation features and giving evaluation weights corresponding to the target evaluation features according to the similarity of each evaluation feature and the core features;

[0012] Giving running evaluation data of the comprehensive energy system based on the target evaluation features of each subsystem in the comprehensive energy system and the evaluation weights corresponding to the target evaluation features.

[0013] Further, the running data of each subsystem in the comprehensive energy system is obtained, specifically comprising:

[0014] Obtaining initial running data of the comprehensive energy system;

[0015] Replacing or deleting abnormal values in the initial running data to complete data cleaning of the initial running data;

[0016] Standardizing the initial running data after the data cleaning to obtain the running data.

[0017] Further, the abnormal values in the initial running data are replaced or deleted to complete the data cleaning of the initial running data, specifically comprising:

[0018] obtaining historical operation data corresponding to the initial operation data;

[0019] According to the historical operation data, the standard deviation and mean value of the historical operation data are obtained, and the normal fluctuation range corresponding to the initial operation data is given;

[0020] According to the normal fluctuation range, the abnormal values in the initial operation data are identified, and the abnormal values are replaced or deleted, so as to complete the data cleaning of the initial operation data.

[0021] Further, the comprehensive energy index library includes supply indicators, consumption indicators, conversion indicators, equipment indicators and environmental indicators.

[0022] The pre-construction of the comprehensive energy index library is determined by the following steps:

[0023] Obtaining historical operation data of the comprehensive energy system, wherein the operation data is multi-parameter data, and the parameter dimension of each parameter is one of monitoring data of each subsystem, equipment operation log, energy conversion record and environmental monitoring data;

[0024] The historical operation data is normalized and an operation database with a multi-layer index structure is constructed, and the multi-layer index includes timestamp, subsystem and equipment in the subsystem;

[0025] By performing pattern mining on each parameter dimension in the operation database, key parameters in each parameter dimension are identified and determined as initial indicators, forming an initial indicator set of each parameter dimension;

[0026] The initial indicator set corresponding to the monitoring data of each subsystem is screened to give supply type initial indicators and consumption type initial indicators;

[0027] The supply type initial indicators and the consumption type initial indicators are subjected to correlation analysis, and according to the proportion of each combination of the supply type initial indicators and the consumption type initial indicators in the monitoring data of each subsystem, an index correlation network of supply and consumption is obtained, and supply indicators and consumption indicators are given based on the correlation conditions;

[0028] According to the supply indicators and the consumption indicators, the initial indicator set of each parameter dimension is updated to form an indicator set of each parameter dimension;

[0029] The index sensitivity of each index in the indicator set is analyzed by using a sliding time window, and each index is marked by using a dynamic weight distribution mechanism to construct a comprehensive energy index library.

[0030] Further, the index sensitivity of each index in the indicator set is analyzed by using a sliding time window, and each index is marked by using a dynamic weight distribution mechanism to construct a comprehensive energy index library, and the specific content includes:

[0031] based on the preset sliding step, moving the time window, analyzing the index sensitivity of each index in each time window, and obtaining index sensitivity data of each index;

[0032] substituting the index sensitivity data into the pre-constructed weight adjustment function to obtain the allocation weight of each index;

[0033] based on the allocation weight of each index, weighting and marking each index to construct a comprehensive energy index library.

[0034] Further, the principal component analysis method is used to analyze the evaluation characteristics and give the core characteristics, specifically including:

[0035] analyzing the linear correlation degree between each evaluation characteristic to construct a covariance matrix of the evaluation characteristics;

[0036] performing eigenvalue decomposition on the covariance matrix to give a plurality of eigenvalues;

[0037] According to the variance explanation proportion of each eigenvalue, combined with the preset explanation threshold, screening is performed among the plurality of eigenvalues to obtain the core characteristics.

[0038] Further, the linear correlation degree between each evaluation characteristic is analyzed to construct a covariance matrix of the evaluation characteristics, specifically including:

[0039] According to the elements in each evaluation characteristic, combined with the characteristic mean of the corresponding evaluation characteristic, the deviation characteristics of each evaluation characteristic are given;

[0040] Based on the deviation characteristics of any two evaluation characteristics, the mean of the product of the two deviation characteristics is given to obtain the linear correlation degree between the evaluation characteristics;

[0041] Fusion of the linear correlation degree between each evaluation characteristic, construct a covariance matrix of the evaluation characteristics.

[0042] Further, the plurality of eigenvalues are specifically represented as:

[0043] ;

[0044] wherein C is the covariance matrix of the evaluation characteristics, is a diagonal matrix, each element on the diagonal line of the diagonal matrix is an eigenvalue, is an identity matrix, is the transpose matrix of V, V is the eigenvector matrix, and the elements in the eigenvector matrix are the eigenvectors corresponding to the eigenvalues.

[0045] Further, according to the variance explanation proportion of each eigenvalue, combined with the preset explanation threshold, screening is performed among the plurality of eigenvalues to obtain the core characteristics, specifically including:

[0046] According to the variance explanation proportion of each characteristic value, the cumulative variance explanation proportion corresponding to each characteristic value is given;

[0047] The cumulative variance explanation proportion corresponding to each characteristic value is compared with the preset explanation threshold to obtain a comparison result;

[0048] According to the comparison result, the characteristic values are screened, and the characteristic vectors corresponding to the screened characteristic values are given;

[0049] The standard data matrix is projected into a vector matrix composed of the characteristic vectors corresponding to the screened characteristic values to obtain core features.

[0050] Further, according to the similarity between each evaluation feature and the core feature, the target evaluation feature is determined and the evaluation weight corresponding to the target evaluation feature is given, which specifically includes:

[0051] According to the similarity between the evaluation feature and the core feature, the evaluation feature is screened in combination with the preset similarity range, and the target evaluation feature is given;

[0052] In combination with the information amount of the target evaluation feature, the evaluation weight corresponding to the target evaluation feature is given.

[0053] Further, in combination with the information amount of the target evaluation feature, the evaluation weight corresponding to the target evaluation feature is given, which specifically includes:

[0054] According to the element values in the target evaluation feature, the information amount of the target evaluation feature is given;

[0055] In combination with the information amount of the target evaluation feature, the variation degree of the target evaluation feature is analyzed;

[0056] Based on the variation degrees of all target evaluation features, in combination with the variation degree of the target evaluation feature, the evaluation weight corresponding to the target evaluation feature is given.

[0057] Further, the evaluation weight corresponding to the target evaluation feature is specifically represented as:

[0058] ;

[0059] Wherein, is the evaluation weight corresponding to the jth target evaluation feature, is the information amount of the jth target feature weight, and m is the number of target evaluation features.

[0060] Further, based on the target evaluation features of each subsystem in the comprehensive energy system, the operation evaluation data of the comprehensive energy system is given by fusing the evaluation weights corresponding to the target evaluation features, which specifically includes:

[0061] The standard characteristic values are obtained by quantifying and / or standardizing the characteristic values in the target evaluation characteristics based on the target evaluation characteristics of each subsystem in the integrated energy system;

[0062] The running evaluation data is given by weighted summation of the standard characteristic values combined with the evaluation weights corresponding to the target evaluation characteristics.

[0063] In a second aspect, the present application further provides a running evaluation device of an integrated energy system, which adopts the running evaluation method of the integrated energy system according to any one of the above aspects, and comprises:

[0064] A data acquisition module is configured to acquire running data of each subsystem in the integrated energy system.

[0065] A characteristic screening module is configured to screen out corresponding evaluation characteristics from the running data of each subsystem based on a pre-constructed integrated energy index library.

[0066] A core determination module is configured to analyze the evaluation characteristics by principal component analysis and give core characteristics.

[0067] A weight determination module is configured to determine target evaluation characteristics and give evaluation weights corresponding to the target evaluation characteristics according to the similarity of each evaluation characteristic and the core characteristics.

[0068] A running evaluation module is configured to give running evaluation data of the integrated energy system based on the target evaluation characteristics of each subsystem in the integrated energy system and the evaluation weights corresponding to the target evaluation characteristics.

[0069] In a third aspect, the present application further provides a management and control system for an integrated energy system, which comprises a memory, a processor, and a computer program stored in the memory, and the computer program is executed by the processor to execute the instructions according to the above method.

[0070] The running evaluation method, device and management and control system of the integrated energy system provided by the present application have at least the following beneficial effects:

[0071] (1) By collecting the running data of the integrated energy system, the principal component analysis method is used to extract the characteristics of the data, the core characteristics obtained are analyzed for correlation with the pre-established integrated energy index library, the target evaluation characteristics with high correlation with the core characteristics are selected, the weights of the target evaluation characteristics are set in combination with the information entropy of the target evaluation characteristics, and finally the running evaluation data of the integrated energy system is obtained, thereby improving the accuracy of the running evaluation of the integrated energy system.

[0072] (2) Through the initial operation data of the comprehensive energy system collected, data cleaning and standardization operation are carried out, the noise interference in the data is effectively removed, the comparability and analyzability of the data are enhanced, and a solid foundation is laid for subsequent accurate evaluation.

[0073] (3) By adopting the combination of principal component analysis and correlation analysis, the target evaluation features with high correlation are screened out, the subjectivity and one-sidedness of the traditional method are avoided, the core features and operation nature of the comprehensive energy system can be accurately reflected, and the scientificity and pertinence of the evaluation index system are ensured.

[0074] (4) The evaluation weight is determined by the information entropy of the target evaluation feature, so that the weight distribution is completely based on the information characteristics of the data itself, the interference of human factors is avoided, the objectivity and scientificity of the weight setting are ensured, the evaluation result is more persuasive and reliable. BRIEF DESCRIPTION OF DRAWINGS

[0075] Figure 1 The flowchart of the operation evaluation method of the comprehensive energy system provided by the embodiment of the present application is provided.

[0076] Figure 2 The flowchart of determining the core feature provided by the embodiment of the present application is provided.

[0077] Figure 3 The flowchart of constructing the covariance matrix of the evaluation feature provided by the embodiment of the present application is provided.

[0078] Figure 4 The flowchart of screening the core feature from the plurality of feature values provided by the embodiment of the present application is provided.

[0079] Figure 5 The flowchart of determining the target evaluation feature and the evaluation weight provided by the embodiment of the present application is provided.

[0080] Figure 6 The flowchart of determining the evaluation weight provided by the embodiment of the present application is provided.

[0081] Figure 7 The structural block diagram of the operation evaluation device of the comprehensive energy system provided by the embodiment of the present application is provided.

[0082] Among them, 201, data acquisition module;202, feature screening module;203, core determination module;204, weight determination module;205, operation evaluation module. DETAILED DESCRIPTION

[0083] For better understanding of the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings of the specification and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor belong to the scope of protection of the present application.

[0084] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0085] It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the goods or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or also include elements inherent to such goods or devices. Without more limitations, the element defined by the sentence "including a" does not exclude the presence of other identical elements in the goods or devices including the element.

[0086] At present, the evaluation method of integrated energy system lacks data cleaning and standardization process, directly summarizes the data of different sources, different magnitudes and units, so that the data has noise interference and poor comparability. In the aspect of index selection, it mainly depends on experience judgment, and pays attention to some conventional indexes, which leads to the incompleteness of evaluation index system and the inability to accurately reflect the complex operation nature of integrated energy system. In the process of setting the weight of the index, subjective weighting is mostly used, which is greatly influenced by personal experience, leading to the lack of objectivity and consistency of weight distribution, and unable to provide strong support for the decision of energy system.

[0087] The application provides a method for evaluating operation of a comprehensive energy system, which comprises the following steps: obtaining operation data of each subsystem in the comprehensive energy system; screening corresponding evaluation features from the operation data of each subsystem based on a pre-constructed comprehensive energy index library; analyzing the evaluation features by using a principal component analysis method to give core features; giving evaluation weights corresponding to the evaluation features according to the similarity of each evaluation feature and the core features; and giving operation evaluation data of the comprehensive energy system based on the evaluation features of each subsystem in the comprehensive energy system and the evaluation weights corresponding to the evaluation features. By establishing a perfect data collection and preprocessing process, the principal component analysis (PCA) algorithm is used to extract key features, and the correlation analysis is used to screen out indicators closely related to the system performance, and then the entropy weight method is used to set objective weights based on the data information characteristics, so that the comprehensive energy system can be evaluated comprehensively, accurately and objectively, and a solid and reliable scientific basis is provided for the management and decision of the system, and the optimization development and efficient operation of the comprehensive energy system are promoted.

[0088] As shown in Figure 1 The application provides a method for evaluating operation of a comprehensive energy system, which comprises the following steps:

[0089] S101: obtaining operation data of each subsystem in the comprehensive energy system.

[0090] It can be understood that the comprehensive energy system mainly comprises an energy supply network, energy coupling devices, energy storage devices and users. Among them, four kinds of energy, i.e. electricity, gas, heat and cold, are transmitted to users by the energy supply network, and the exchange devices include combined heat and power (CHP), electric refrigerators, gas boilers, gas turbines and absorption refrigerators, etc. The energy storage devices include electric storage, gas storage, heat storage and cold storage, etc. That is, the comprehensive energy system comprises multiple subsystems such as an electric power subsystem, a heat subsystem, a natural gas subsystem and a cold subsystem. The original operation data of all subsystems and devices in the comprehensive energy system are collected, including but not limited to energy production data (such as the output of various energies and the operation parameters of production devices), energy consumption data (such as the energy consumption of different users or regions and the consumption mode), energy conversion data (such as the conversion efficiency of conversion devices and the loss), storage data (such as the storage capacity of energy storage devices and the charging and discharging parameters), and environmental data (such as the temperature and humidity of the environment). The collected original operation data come from various sensors, monitoring systems, metering devices and information management systems, so as to ensure the comprehensiveness and accuracy of the data.

[0091] The initial operation data are subjected to data cleaning, specifically including:

[0092] The initial operation data are subjected to data cleaning, specifically including: the historical operation data corresponding to the initial operation data are obtained;

[0093] Based on historical operating data, the standard deviation and mean of the historical operating data are obtained, and the normal fluctuation range corresponding to the initial operating data is given.

[0094] Based on the normal fluctuation range, identify outliers in the initial running data and replace or delete them.

[0095] In a specific example, statistical analysis and anomaly detection methods are used to remove outliers and erroneous data from the initial operating data. Taking energy data as an example, by analyzing the distribution and trends of historical data, combined with the standard deviation and mean of the data, the normal fluctuation range of the data is determined, and data exceeding the normal fluctuation range is identified and processed. Data exceeding the normal fluctuation range is marked as outliers, and these outliers are replaced or deleted based on neighboring data.

[0096] After cleaning the initial running data, data standardization is performed to scale the initial running data to an appropriate range, resulting in the running data, specifically represented as follows:

[0097] ;

[0098] ;

[0099] in, To Standardized operational data, Let j be the j-th feature value of the i-th initial set of running data. Let be the mean of the initial running data of the i-th group. is the standard deviation of the i-th initial running data, and n is the amount of data in the i-th initial running data.

[0100] Because the initial operational data of integrated energy systems comes from a wide range of sources and is diverse in type, this invention effectively solves the problems of data integration and unified scale by cleaning and standardizing the collected initial operational data, making the data analyzable and laying the foundation for subsequent evaluation. By using statistical analysis and anomaly detection methods to clean the data, noise interference is effectively removed. Data standardization unifies data of different magnitudes and units to the same scale, enhancing the comparability and analyzability of the data, facilitating subsequent model processing and analysis, and laying a solid foundation for accurate subsequent evaluation.

[0101] S102: Based on a pre-built comprehensive energy index library, corresponding evaluation features are selected from the operating data of each subsystem.

[0102] The comprehensive energy index library includes supply indexes, consumption indexes, conversion indexes, equipment indexes and environmental indexes. The pre-construction of the comprehensive energy index library is determined through the following steps:

[0103] The historical operation data of the comprehensive energy system is obtained, wherein the operation data is multi-parameter data, and the parameter dimension of each parameter is one of monitoring data of each subsystem, equipment operation log, energy conversion record and environmental monitoring data;

[0104] The historical operation data is normalized and an operation database with a multi-layer index structure is constructed. The multi-layer index includes a timestamp, a subsystem and equipment in the subsystem.

[0105] Each parameter dimension in the operation database is pattern-mined to identify key parameters in each parameter dimension and determine the initial indexes to form an initial index set of each parameter dimension.

[0106] The initial index set corresponding to the monitoring data of each subsystem is screened to give supply initial indexes and consumption initial indexes.

[0107] The supply initial indexes and the consumption initial indexes are associated analyzed. According to the proportion of the combination of each supply initial index and each consumption initial index in the monitoring data of each subsystem, the index association network of supply and consumption is obtained, and the supply indexes and the consumption indexes are given based on the association condition.

[0108] The initial index set of each parameter dimension is updated according to the supply indexes and the consumption indexes to form an index set of each parameter dimension.

[0109] The index sensitivity of each index in the index set is analyzed by using a sliding time window, and each index is weighted marked by combining a dynamic weight distribution mechanism to construct the comprehensive energy index library.

[0110] It can be understood that by normalizing the historical operation data, the historical operation data is scaled to a specific range, the dimensional difference between the historical operation data is reduced, and the historical operation data is compared and processed on the same scale. Based on the result of the normalization processing, an operation database with a multi-layer index structure is constructed. The multi-layer index includes a timestamp, a subsystem and equipment in the subsystem. Each piece of historical operation data includes at least three indexes. The corresponding historical operation data can be searched from the operation database through the three-layer index.

[0111] In the embodiments provided in the present application, the mode mining of each parameter dimension in the operation database specifically adopts a prototype clustering algorithm to cluster the parameters in the operation database, combines a preset minimum intra-cluster variance threshold and a maximum iteration number, obtains each clustering center, extracts the key parameters of each clustering center, and determines the initial indicators, thereby forming the initial indicator set of each parameter dimension. In the present example, the prototype clustering algorithm is implemented by using a K-prototypes clustering algorithm.

[0112] In a specific example, each parameter dimension in the operation database is input into the prototype clustering algorithm, and each parameter dimension is divided into different clusters according to the similarity of the parameters. The similarity of the parameters can be represented by the distance between the parameters, and samples with similar distances are divided into the same cluster. For example, the similarity between samples is calculated based on the Euclidean distance, and in the power system data, samples with similar voltage, current mode and device operating state are classified into one category. When the intra-cluster variance of each cluster is less than the minimum intra-cluster variance threshold or reaches the maximum iteration number, the clustering is completed, and the parameters in each cluster in the clustering result are analyzed to find the representative parameters in each cluster. The importance of the parameters can be measured by calculating the variance or information gain of each parameter in the cluster. For example, if the variance of voltage fluctuation is large in a certain cluster, and the variances of other parameters are relatively small, the voltage fluctuation parameter in this cluster can be a key parameter. The differences between parameters in different clusters can also be observed. If the values of a certain parameter differ significantly between different clusters, it can be an important parameter for distinguishing different operating states. For example, the device operating state code has different distributions between different clusters, which can indicate that it is critical for distinguishing between normal and abnormal device operating states and can be used as a key parameter.

[0113] According to the monitoring data of each subsystem and the corresponding relationship between the parameters in the initial indicator set, the parameters in the initial indicator set are classified and screened to give the supply type initial indicators and the consumption type initial indicators. It can be understood that whether the initial indicators in the initial indicator set are supply type initial indicators or consumption type initial indicators is determined by the monitoring data itself, for example, the monitoring data is energy intensity, and the corresponding initial indicator is a consumption type initial indicator, and for another example, the monitoring data is comprehensive energy consumption, and the corresponding initial indicator is a supply type initial indicator.

[0114] The supply type initial indicators and the consumption type initial indicators are subjected to correlation analysis, the indicator correlation network of supply and consumption is obtained according to the proportion of each combination of the supply type initial indicators and the consumption type initial indicators in the monitoring data of each subsystem, and the supply indicators and the consumption indicators are given based on the correlation conditions, specifically including:

[0115] According to the preset minimum support threshold and confidence threshold, the relationship between each supply class initial indicator and each consumption class initial indicator is analyzed by using association rule mining to obtain an indicator association network.

[0116] It should be understood that association rule mining is a method of finding relationships between variables in large databases. The Apriori algorithm is a classic algorithm for association rule mining, which generates association rules by finding frequent item sets. In the context of energy supply and consumption indicator analysis, this method can help understand the relationships between different energy indicators and build a multi-dimensional indicator system. In the embodiments provided in the present application, the minimum support threshold and the confidence threshold are first set. The minimum support represents the frequency of an item set appearing in all transactions. If the support of an item set is higher than the minimum support threshold, it is considered a frequent item set. Confidence represents the probability of the occurrence of the consequent given the antecedent. If the confidence of a rule is higher than the confidence threshold, it is considered a strong association rule.

[0117] The relationship between the supply class initial indicators and the consumption class initial indicators is analyzed, and the relationship between the proportion of each combination of the supply class initial indicators and the consumption class initial indicators in the monitoring data of each subsystem and the minimum support threshold is combined to construct the indicator association network. For example, there are multiple transaction data, each transaction data including a transaction number and consumption data of at least one of coal, oil, natural gas, and electricity. Using the Apriori algorithm, frequent item sets are found, i.e., when the proportion of a combination of a supply class initial indicator and a corresponding consumption class initial indicator in the monitoring data of a certain subsystem reaches the minimum support threshold, the combination is a frequent item set, for example: frequent item set {coal, electricity}: the frequency of the simultaneous occurrence of coal and electricity in all transaction data is higher than the minimum support threshold. Then, association rules are generated, for example: rule: if coal is supplied, then electricity is consumed (coal→electricity). If the confidence of the association rule is higher than the confidence threshold, the association rule is a strong association rule. The parameter group that meets the strong association condition is included in the indicator association network. For example, if the association rule between coal and electricity is a strong association, the connection between the two parameters is marked in the indicator association network. That is, multiple strong association rules constitute the indicator association network.

[0118] According to the supply indicators and the consumption indicators, the initial indicator set of each parameter dimension is updated to form an indicator set of each parameter dimension. Specifically, based on the supply indicators and the consumption indicators in the indicator association network, the initial indicators in the initial indicator set are screened, and if the initial indicator is included in the indicator association network, it is determined as an indicator in the indicator set.

[0119] Further, the index sensitivity of each index in the index set is analyzed by using a sliding time window, and each index is marked by a weighted mark by combining a dynamic weight distribution mechanism, and a comprehensive energy index library is constructed, including the following specific contents:

[0120] Based on the preset sliding step, the time window is moved, the index sensitivity of each index in each time window is analyzed, and index sensitivity data of each index is obtained;

[0121] The index sensitivity data is substituted into the weight adjustment function constructed in advance, and the distribution weight of each index is obtained;

[0122] Based on the distribution weight of each index, each index is marked by a weighted mark, and a comprehensive energy index library is constructed.

[0123] It can be understood that the sliding time window is a method for analyzing time series data, which analyzes the local characteristics of the data by sliding on a fixed size time window. In the embodiments provided by the present application, the size of the time window (such as one month or one quarter) and the time step of each sliding (such as one week) are first determined. In each time window, the sensitivity of each index, that is, the influence of the change of the index on the system energy efficiency, is analyzed.

[0124] For example, the monthly data of a power plant is analyzed, the size of the time window is one month, and the sliding step is one week. The relationship between the coal consumption and the power generation in each month is calculated.

[0125] The index sensitivity analysis refers to the evaluation of the influence degree of the change of the index on the system performance (such as energy efficiency).

[0126] The index sensitivity data is specifically represented as:

[0127] ;

[0128] Wherein, is the index of the index correlation network of the system energy efficiency Y, is the covariance of the index of the index correlation network and the system energy efficiency Y, is the standard deviation of the index of the index correlation network,

[0129] and the standard deviation of the system energy efficiency Y.

[0130] The dynamic weight distribution mechanism adjusts the weight of each parameter according to the index sensitivity of each index in the index correlation network and the system energy efficiency fluctuation.

[0131] The weight adjustment function is specifically represented as:

[0132] ;

[0133] wherein, is the distribution weight of the index in the index correlation network, and a and β are parameters for adjusting the distribution weight.

[0134] In a specific example, a = 2 and β = 0.5, and the distribution weight of coal consumption W1 = 2 x 0.5 + 0.5 = 1.5.

[0135] The indexes in the index correlation network that are significantly correlated with the system energy efficiency fluctuation are marked with weights. The indexes with higher distribution weights are considered to be significantly correlated with the system energy efficiency fluctuation. In a specific example, if the weights of coal consumption and natural gas consumption are 1.5 and 1.2 respectively, then coal consumption is marked as a more important index.

[0136] In a specific example, it is found that the increase in natural gas supply is significantly correlated with the decrease in power consumption in the past quarter. The distribution weight of the natural gas supply index can be increased to reflect its impact on the system energy efficiency. Finally, a comprehensive energy index library is constructed, which includes five dimensions of supply indexes, consumption indexes, conversion indexes, equipment indexes, and environmental indexes. The indexes in each dimension are weighted according to their correlation with the system energy efficiency fluctuation. In a specific example, the comprehensive energy index library includes:

[0137] Supply indexes: coal consumption (distribution weight 1.5), natural gas consumption (distribution weight 1.2); consumption indexes: power generation (distribution weight 1.0); conversion indexes: thermal efficiency (distribution weight 0.8); equipment indexes: equipment utilization rate (distribution weight 0.9); environmental indexes: temperature (distribution weight 0.7).

[0138] In other embodiments, the comprehensive energy index library can also be integrated with the mandatory monitoring parameters in industry specifications, and redundant indexes in the comprehensive energy index library can be further screened and removed.

[0139] ​The comprehensive energy index library helps better understand and manage the energy efficiency of the energy system. Through the construction process of the comprehensive energy index library, valuable information can be extracted from complex energy data using association rule mining technology, which can identify and label indicators that are significantly related to fluctuations in system energy efficiency, and build a comprehensive index library. The comprehensive energy index library can reflect the key performance indicators of the energy system and provide support for energy management and decision-making.

[0140] In a specific example, the comprehensive energy index library includes energy supply indicators, energy consumption indicators, energy conversion indicators, equipment operation indicators, and environmental indicators. Among them, the energy supply indicators include energy production, energy supply stability (comprehensively considering key factors such as energy supply interruption frequency (times / month), average interruption duration, and impact range proportion), energy self-sufficiency rate (percentage of local energy production to total energy consumption), etc.; energy consumption indicators include energy consumption (consumption quantity of different energy types at different time granularities, different regions (administrative regions, functional areas, etc.), and different user types (residents, businesses, industries, etc.)), energy consumption structure (proportion of each type of energy in total energy consumption), energy consumption elasticity coefficient (ratio of energy consumption growth rate to economic growth rate), etc.; energy conversion indicators include energy conversion efficiency (ratio of effective energy after conversion to input energy before conversion for different energy conversion equipment such as combined heat and power units, transformers, gas turbines, etc.), energy conversion loss rate (proportion of energy loss in the energy conversion process to total input energy), etc.; equipment operation indicators include equipment failure rate (ratio of equipment failure occurrence times to total equipment operation duration), equipment average failure-free time (average operation duration of equipment between adjacent two failures), equipment maintenance cost (periodic maintenance cost (materials, labor, etc.), fault repair cost, and equipment update and reconstruction allocation cost, etc.), etc.; environmental indicators include carbon emission intensity (carbon dioxide emissions per unit of energy consumption), pollutant emission indicators (monitoring of sulfur dioxide, nitrogen oxides, particulate matter, etc. pollutants emission amount and emission concentration), etc.

[0141] By constructing the comprehensive energy index library, the evaluation features related to the operation of the comprehensive energy system are preliminarily screened out from a large amount of operation data. Through preliminary screening, the computational intensity of subsequent core feature analysis is reduced, and the evaluation efficiency of the evaluation process is improved under the premise of ensuring the accuracy of the evaluation of the comprehensive energy system.

[0142] S103: Using principal component analysis, analyze the evaluation features and give the core features.

[0143] Specifically, referring to Figure 2 , including:

[0144] Analyzing the degree of linear correlation between each evaluation feature, constructing a covariance matrix of evaluation features;

[0145] performing eigen decomposition on the covariance matrix to obtain a plurality of eigenvalues;

[0146] According to the variance interpretation ratio of each eigenvalue, combined with the preset interpretation threshold, screening is performed among the plurality of eigenvalues to obtain the core features.

[0147] Further, referring to Figure 3 , a covariance matrix of the evaluation features is constructed, specifically including:

[0148] According to the elements in each evaluation feature, combined with the feature mean of the corresponding evaluation feature, the deviation feature of each evaluation feature is given;

[0149] Based on the deviation features of any two evaluation features, the mean of the product of the two deviation features is given to obtain the linear correlation degree between the evaluation features;

[0150] Fusion of the linear correlation degree between each evaluation feature, the covariance matrix of the evaluation features is constructed.

[0151] The linear correlation degree between each evaluation feature is specifically represented as:

[0152] ;

[0153] Wherein, is the linear correlation degree between the u-th evaluation feature and the v-th evaluation feature, m is the sample number, is the k-th eigenvalue in the u-th evaluation feature, is the feature mean of the u-th evaluation feature, is the k-th eigenvalue in the v-th evaluation feature, is the feature mean of the v-th evaluation feature.

[0154] The deviation feature refers to the difference between each eigenvalue in the evaluation feature and the feature mean.

[0155] The covariance matrix is specifically represented as:

[0156] ;

[0157] Wherein, C is the covariance matrix, is a matrix composed of normalized evaluation features, m is the sample number, is the transpose matrix.

[0158] Further, the plurality of eigenvalues is specifically represented as:

[0159] ;

[0160] Wherein, C is the covariance matrix of the evaluation features, Let be a diagonal matrix, where each element on the diagonal is an eigenvalue. It is the identity matrix. Let V be the transpose of V, where V is the eigenvector matrix, and the elements in the eigenvector matrix are the eigenvectors corresponding to the eigenvalues.

[0161] In one specific implementation, the covariance matrix C is decomposed into eigenvalues. and the corresponding feature vector The eigenvalue decomposition is specifically represented as... ,in, It is a diagonal matrix, and the elements on the diagonal are eigenvalues. And they are arranged in descending order. V is composed of eigenvectors. The matrix formed satisfies .

[0162] Furthermore, referring to Figure 4 Based on the variance explanation ratio of each feature value and combined with a preset explanation threshold, the core features are obtained by filtering from multiple feature values. These core features include:

[0163] Based on the variance explained by each eigenvalue, the cumulative variance explained by each eigenvalue is given.

[0164] The cumulative variance explained by each feature value is compared with the preset explanation threshold to obtain the comparison results;

[0165] Based on the comparison results, the feature values ​​are filtered, and the feature vectors corresponding to the filtered feature values ​​are given.

[0166] The core features are obtained by projecting the standard data matrix onto a vector matrix composed of the feature vectors corresponding to the filtered feature values.

[0167] In one specific implementation, the feature values ​​are arranged in descending order, and the core features are selected based on the cumulative variance interpretation ratio.

[0168] Calculate the proportion of cumulative variance explained for each eigenvalue:

[0169] ;

[0170] in, The proportion of cumulative variance explained by the k-th eigenvalue. Let be the proportion of variance explained by the i-th eigenvalue. Let be the i-th eigenvalue, and m be the number of eigenvalues.

[0171] In a specific example, the preset interpretation threshold is T, and the selected threshold satisfies... the minimum value k of the eigenvalues as the number of principal components.After selecting k principal components, the standardized data matrix is projected onto the matrix composed of the first k eigenvectors , to obtain the core features Y, which is specifically represented as:

[0172] ;

[0173] wherein, is the matrix composed of the first k eigenvectors , and the core features Y are the matrix composed of the first k eigenvectors , and the elements in the core features Y represent the score of the i-th sample on the j-th principal component.

[0174] S104: determining the target evaluation feature according to the similarity between each evaluation feature and the core feature, and giving the evaluation weight corresponding to the target evaluation feature.

[0175] Specifically, referring to Figure 5 , the method comprises:

[0176] screening the evaluation features according to the similarity between the evaluation features and the core features, in combination with a preset similarity range, to give the target evaluation feature;

[0177] in combination with the information amount of the target evaluation feature, to give the evaluation weight corresponding to the target evaluation feature.

[0178] In the embodiments provided in the present application, the similarity between each evaluation feature and the core feature is represented by the Pearson correlation coefficient, and in other embodiments, other ways can be used to determine the similarity between each evaluation feature and the core feature, which is not limited.

[0179] The similarity between each evaluation feature and the core feature is specifically represented as:

[0180] ;

[0181] wherein, is the similarity between the evaluation feature p and the core feature q, is the eigenvalue of the evaluation feature p in the i-th sample, is the eigenvalue of the core feature q in the i-th sample, is the eigenvalue of the core feature q in the i-th sample, is the eigenvalue of the core feature q in the i-th sample,

[0182] The value range of the Pearson correlation coefficient is between [-1, 1], and the closer the absolute value is to 1, the stronger the correlation between the evaluation feature p and the core feature q, and the positive sign indicates positive correlation and the negative sign indicates negative correlation.

[0183] In the embodiments provided by the present application, by setting a similarity range, it is judged whether the similarity is within the preset similarity range. If yes, the evaluation feature is taken as the target evaluation feature. Otherwise, if the similarity is not within the preset similarity range, the evaluation feature is excluded and is not taken as the target evaluation feature of the comprehensive energy system. In a specific example, the similarity range is 0.5-0.7, and the evaluation features with the absolute values of the similarities within the range are screened out as the target evaluation features. The target evaluation features obtained after screening are closely related to the core features and can deeply reflect the key features and operation nature of the comprehensive energy system, effectively avoid irrelevant or weakly related indicators interference, significantly improve the evaluation pertinence and effectiveness, and ensure that the evaluation focuses on the core elements and accurately understands the system performance.

[0184] It can be understood that the traditional evaluation method is too subjective in index selection, and generally selects common unified indexes, which is difficult to accurately screen out the core features that can actually reflect the operation nature of the comprehensive energy system. The present application screens out the key indicators (i.e. target evaluation features) with high correlation by using data mining, statistical analysis and index correlation analysis technology, and by combining principal component analysis and correlation analysis, avoids the subjectivity and one-sidedness of the traditional method, and can accurately reflect the core features and operation nature of the comprehensive energy system, and ensure the scientificity and pertinence of the evaluation index system.

[0185] Further, referring to Figure 6 , the evaluation weight corresponding to the target evaluation feature is given, specifically including:

[0186] According to the values of the elements in the target evaluation feature, the information amount of the target evaluation feature is given;

[0187] The variation degree of the target evaluation feature is analyzed in combination with the information amount of the target evaluation feature;

[0188] Based on the variation degrees of all target evaluation features, the evaluation weight corresponding to the target evaluation feature is given in combination with the variation degree of the target evaluation feature.

[0189] Further, the evaluation weight corresponding to the target evaluation feature is specifically expressed as:

[0190] ;

[0191] Wherein, is the evaluation weight corresponding to the jth target evaluation feature, is the information amount of the jth target feature weight, and m is the number of target evaluation features, is the variation degree of the target evaluation feature.

[0192] In the embodiments provided by the present invention, the entropy weight method is used to set the evaluation weights. The information entropy of each target evaluation feature is calculated to reflect the information content of each target evaluation feature. The weights are allocated entirely based on the inherent information features of the data, ensuring the objectivity and scientific nature of the weight setting.

[0193] In one specific implementation, for the target evaluation feature j, the information entropy is calculated, specifically expressed as:

[0194] ;

[0195] in, Let n be the information entropy corresponding to the target evaluation feature j, and n be the number of feature values ​​of the target evaluation feature j. The target evaluation feature j takes the value of The probability, Let be the feature value of target evaluation feature j in the i-th sample, and ln be the natural logarithm function.

[0196] Information entropy reflects the amount of information contained in the target evaluation features. The greater the information entropy of the target evaluation features, the smaller the degree of variation of the target evaluation features, the less information they provide, and the smaller their role in the comprehensive evaluation. Conversely, the smaller the information entropy of the target evaluation features, the greater the degree of variation of the target evaluation features, the more information they provide, and the greater their weight should be.

[0197] By determining the evaluation weights through the information entropy of the target evaluation features, the weight allocation is based entirely on the information features of the data itself, avoiding interference from human factors, ensuring the objectivity and scientific nature of the weight setting, and making the evaluation results more convincing and reliable.

[0198] S105: Based on the target evaluation characteristics of each subsystem in the integrated energy system, and by integrating the evaluation weights corresponding to the target evaluation characteristics, the operation evaluation data of the integrated energy system is given.

[0199] Specifically, based on the target evaluation characteristics of each subsystem in the integrated energy system, the characteristic values ​​in the target evaluation characteristics are quantified and / or standardized to obtain standard characteristic values;

[0200] The evaluation weights corresponding to the integrated target evaluation features are combined with the standard feature values ​​to provide operational evaluation data.

[0201] The performance evaluation data is specifically represented as follows:

[0202] ;

[0203] Where S represents the operational assessment data of the integrated energy system. The evaluation weights of target feature i are given. wherein k is the number of target evaluation features.

[0204] In a specific embodiment, the target evaluation features are quantified according to their respective characteristics and industry standards. For example, the target evaluation feature corresponding to energy supply stability can be obtained by calculating the number of energy supply interruptions, the duration of the interruptions, and the proportion of users affected within a certain period of time; the target evaluation feature corresponding to energy conversion efficiency can be determined according to the ratio of effective energy to input energy after conversion by different energy conversion equipment (such as combined heat and power units, gas turbines, etc.).

[0205] After the quantification of the target evaluation features, the quantified target evaluation features are standardized using the min-max standardization method to obtain the standard characteristic values.

[0206] The standard characteristic value is specifically represented as:

[0207] ;

[0208] wherein, is the standard characteristic value, x is the original characteristic value or the quantified original characteristic value, is the minimum value of the target evaluation feature, is the maximum value of the target evaluation feature,

[0209] After standardization, the value range of is [0, 1].

[0210] The evaluation weight corresponding to each target evaluation feature reflects the relative importance of the target evaluation feature in the comprehensive energy system evaluation. For example, in an energy system focusing on renewable energy development, the proportion of renewable energy production may be given a higher weight. By weighted summation, the information of each target evaluation feature is integrated into a single evaluation score, which intuitively reflects the overall performance of the comprehensive energy system.

[0211] According to the obtained operation evaluation data, the performance of the comprehensive energy system is divided into different levels. For example, excellent (operation evaluation data between 0.8 and 1), good (operation evaluation data between 0.6 and 0.8), medium (operation evaluation data between 0.4 and 0.6), poor (operation evaluation data between 0.2 and 0.4), and poor (operation evaluation data between 0 and 0.2) can be set as several levels. This level division helps to intuitively understand the relative position and performance level of the comprehensive energy system in the same type of system. The division of different levels can be adjusted according to the average level in the industry, the performance data of advanced benchmark systems, and relevant policy standards and specifications, etc. without limitation.

[0212] According to the performance level corresponding to the operation evaluation data, specific decision suggestions are provided for the optimization and development of the integrated energy system. In terms of energy supply, if the supply stability is insufficient, the standby energy supply equipment can be considered to be increased, the energy dispatching strategy can be optimized, or the interconnection and intercommunication with the surrounding energy system can be strengthened to improve the reliability of the supply. In terms of energy consumption, if the energy consumption structure is unreasonable and excessively relies on a kind of high-pollution or high-cost energy, policies can be formulated to encourage the transformation of energy consumption to clean energy, such as popularizing energy-saving equipment and implementing energy subsidy policies. For device operation, if the device failure rate is high, it is recommended to increase the device maintenance investment, establish a device full life cycle management system, and plan in advance for device replacement. In terms of environmental indicators, if the carbon emissions exceed the standard, renewable energy project construction can be promoted, and carbon capture and storage technology pilot measures can be implemented to reduce the environmental impact of the system and achieve sustainable development of the integrated energy system.

[0213] The application provides an operation evaluation method of an integrated energy system, and specifically comprises the following steps: obtaining operation data of each subsystem in the integrated energy system; screening corresponding evaluation features from the operation data of each subsystem based on a pre-constructed integrated energy index library; analyzing the evaluation features by using a principal component analysis method to give core features; determining target evaluation features according to the similarity of each evaluation feature and the core features and giving evaluation weights corresponding to the target evaluation features; and giving operation evaluation data of the integrated energy system based on the target evaluation features of each subsystem in the integrated energy system and the evaluation weights corresponding to the target evaluation features. By collecting the operation data of the integrated energy system, the principal component analysis algorithm is used to extract features from the data, the extracted features are analyzed in correlation with the pre-established integrated energy index library, the target evaluation features with high correlation are selected, the weights of the target evaluation features are set in combination with the information entropy of the features, and finally the operation evaluation data of the integrated energy system is obtained, thereby providing a scientific basis for the management and decision-making of the integrated energy system.

[0214] Reference Figure 7 The embodiment of the application provides an operation evaluation device of an integrated energy system, which comprises:

[0215] The data acquisition module 201 is used for acquiring operation data of each subsystem in the integrated energy system.

[0216] The feature screening module 202 is used for screening corresponding evaluation features from the operation data of each subsystem based on a pre-constructed integrated energy index library.

[0217] The core determination module 203 is used for analyzing the evaluation features by using a principal component analysis method to give core features.

[0218] The weight determination module 204 is configured to determine the target evaluation feature according to the similarity of each evaluation feature and the core feature, and give an evaluation weight corresponding to the target evaluation feature;

[0219] The operation evaluation module 205 is configured to give operation evaluation data of the comprehensive energy system based on the target evaluation features of each subsystem in the comprehensive energy system and the evaluation weights corresponding to the target evaluation features.

[0220] In addition, the present application also provides a management and control system for a comprehensive energy system, which comprises a memory, a processor, and a computer program stored in the memory, and when the computer program is executed by the processor, the instructions according to the above method are executed.

[0221] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0222] It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or instrument, or any combination of the above. More specific examples of computer readable storage medium can include, but are not limited to, electrical connection with one or more conductors, portable computer disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or instrument. In the present disclosure, the computer readable signal medium can include a data signal propagating in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagating data signal can take various forms, including but not limited to electromagnetic signals, optical signals or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or instrument. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to: wire, cable, RF (radio frequency), etc., or any suitable combination of the above.

[0223] The computer readable medium described above can be included in the electronic device described above; alternatively, it can exist separately from the electronic device.

[0224] Computer program code for carrying out operations of the present disclosure can be written in any of one or more programming languages, including object oriented programming languages such as Java, Smalltalk, C++, or conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0225] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the opposite order, depending on the functionality involved. It will also be noted that each block and combination of blocks in the block diagrams and / or flow diagrams can be implemented by a dedicated hardware-based system that carries out specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0226] The units involved in the embodiments of the present disclosure can be implemented in the form of software, or can be implemented in the form of hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.

[0227] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims include all such variations and modifications as fall within the scope of the present application. It is apparent that those skilled in the art can modify and adapt the present application in various ways without departing from the spirit and scope of the present application. It is therefore intended that the present application encompass all such modifications and variations as fall within the scope of the claims and their equivalents.

Claims

1. A method for operation evaluation of an integrated energy system, characterized in that, The method comprises the following steps: obtaining operation data of each subsystem in the comprehensive energy system; based on the pre-constructed comprehensive energy index library, the corresponding evaluation features are screened from the operation data of each subsystem; the comprehensive energy index library includes supply indicators, consumption indicators, conversion indicators, equipment indicators and environmental indicators; the pre-construction of the comprehensive energy index library is determined by the following steps: obtaining the historical operation data of the comprehensive energy system, wherein the operation data is multi-parameter data, and the parameter dimension of each parameter is one of the monitoring data of each subsystem, the equipment operation log, the energy conversion record and the environmental monitoring data; the historical operation data is normalized and an operation database with a multi-layer index structure is constructed, the multi-layer index includes a timestamp, a subsystem and equipment within the subsystem; by performing pattern mining on each parameter dimension in the operation database, key parameters in each parameter dimension are identified and determined as initial indicators to form an initial indicator set of each parameter dimension; the initial indicator set corresponding to the monitoring data of each subsystem is screened to give supply-type initial indicators and consumption-type initial indicators; the supply-type initial indicators and the consumption-type initial indicators are subjected to correlation analysis, and based on the proportion of each combination of the supply-type initial indicators and the consumption-type initial indicators in the monitoring data of each subsystem, an index correlation network of supply and consumption is obtained, and based on the correlation conditions, supply indicators and consumption indicators are given; based on the supply indicators and the consumption indicators, the initial indicator set of each parameter dimension is updated to form an indicator set of each parameter dimension; based on a preset sliding step, a time window is moved, the index sensitivity of each indicator in each time window is analyzed, and index sensitivity data of each indicator is obtained; the index sensitivity data is substituted into a pre-constructed weight adjustment function to obtain the distribution weight of each indicator; based on the distribution weight of each indicator, each indicator is weighted and labeled to construct the comprehensive energy index library; using principal component analysis, the evaluation features are analyzed to give core features; based on the similarity of the evaluation features and the core features, and in combination with a preset similarity range, the evaluation features are screened to give target evaluation features; in combination with the information amount of the target evaluation features, evaluation weights corresponding to the target evaluation features are given; based on the target evaluation features of each subsystem in the comprehensive energy system, the evaluation weights corresponding to the target evaluation features are fused to give operation evaluation data of the comprehensive energy system.

2. The operation evaluation method of the integrated energy system according to claim 1, wherein The operation data of each subsystem in the comprehensive energy system is obtained, specifically including: obtaining initial operation data of the comprehensive energy system; replacing or deleting abnormal values in the initial operation data to complete data cleaning of the initial operation data; standardizing the initial operation data after data cleaning to obtain the operation data.

3. The method for operating assessment of an integrated energy system according to claim 2, wherein, The abnormal values in the initial operation data are replaced or deleted to complete the data cleaning of the initial operation data, specifically including: obtaining historical operation data corresponding to the initial operation data; based on the historical operation data, the standard deviation and mean value of the historical operation data are obtained to give a normal fluctuation range corresponding to the initial operation data; According to the normal fluctuation range, the abnormal values in the initial operation data are identified, and the abnormal values are replaced or deleted, so as to complete the data cleaning of the initial operation data.

4. The method for operating assessment of an integrated energy system according to claim 1, wherein, The principal component analysis method is used to analyze the evaluation characteristics, and the core characteristics are given, including: The linear correlation degree between each evaluation characteristic is analyzed, and the covariance matrix of the evaluation characteristics is constructed. The covariance matrix is decomposed to give a plurality of characteristic values. According to the variance explanation proportion of each characteristic value, combined with the preset explanation threshold, the core characteristics are obtained by screening from the plurality of characteristic values.

5. The method for operating assessment of an integrated energy system according to claim 4, wherein, The linear correlation degree between each evaluation characteristic is analyzed, and the covariance matrix of the evaluation characteristics is constructed, including: According to the elements in each evaluation characteristic, combined with the characteristic mean of the corresponding evaluation characteristic, the deviation characteristics of each evaluation characteristic are given. Based on the deviation characteristics of any two evaluation characteristics, the mean of the product of the two deviation characteristics is given, and the linear correlation degree between the evaluation characteristics is obtained. The linear correlation degree between each evaluation characteristic is fused to construct the covariance matrix of the evaluation characteristics.

6. The method for operating assessment of an integrated energy system according to claim 4, wherein, The plurality of characteristic values are specifically represented as: ； wherein C is a covariance matrix of the evaluation features, is a diagonal matrix, each element on the diagonal of the diagonal matrix being an eigenvalue, is an identity matrix, is is a transpose matrix of, is an eigenvector matrix, an element in the eigenvector matrix being an eigenvector corresponding to an eigenvalue.

7. The method for operating assessment of an integrated energy system according to claim 4, wherein, According to the variance explanation proportion of each characteristic value, combined with the preset explanation threshold, the core characteristics are obtained by screening from the plurality of characteristic values, including: According to the variance explanation proportion of each characteristic value, the corresponding cumulative variance explanation proportion of each characteristic value is given. The cumulative variance explanation proportion corresponding to each characteristic value is compared with the preset explanation threshold to obtain a comparison result. According to the comparison result, the characteristic values are screened, and the characteristic vectors corresponding to the screened characteristic values are given. The standard data matrix is projected into the vector matrix composed of the characteristic vectors corresponding to the screened characteristic values to obtain the core characteristics.

8. The method for operating assessment of an integrated energy system according to claim 1, wherein, Combined with the information amount of the target evaluation characteristic, the evaluation weight corresponding to the target evaluation characteristic is given, including: According to the element values in the target evaluation characteristic, the information amount of the target evaluation characteristic is given. Combined with the information amount of the target evaluation characteristic, the variation degree of the target evaluation characteristic is analyzed. Based on the variation degrees of all target evaluation characteristics, the evaluation weight corresponding to the target evaluation characteristic is given.

9. The method for operating assessment of an integrated energy system according to claim 8, wherein, The evaluation weight corresponding to the target evaluation characteristic is specifically represented as: ; wherein w j is the evaluation weight corresponding to the jth target evaluation feature, E j is the information quantity of the jth target evaluation feature, m is the number of target evaluation features, and 1-E j is the variation degree of the jth target evaluation feature.

10. The method for operating assessment of an integrated energy system according to claim 1, wherein, Based on the target evaluation characteristics of each subsystem in the comprehensive energy system, the evaluation weight corresponding to the target evaluation characteristic is fused, and the operation evaluation data of the comprehensive energy system is given, including: Based on the target evaluation characteristics of each subsystem in the comprehensive energy system, the characteristic values in the target evaluation characteristics are quantized and / or standardized to obtain standard characteristic values. The evaluation weight corresponding to the target evaluation characteristic is fused, and the standard characteristic values are weighted and summed to give the operation evaluation data.

11. An operation evaluation device of an integrated energy system, characterized by, The operation evaluation method of the comprehensive energy system as claimed in any one of claims 1-10 is adopted, including: A data acquisition module is configured to acquire operation data of each subsystem in the comprehensive energy system. The feature screening module is configured to screen corresponding evaluation features from the operation data of each subsystem based on a pre-constructed comprehensive energy index library; the comprehensive energy index library includes supply indexes, consumption indexes, conversion indexes, equipment indexes, and environmental indexes; the pre-construction of the comprehensive energy index library is determined by the following steps: obtaining historical operation data of the comprehensive energy system, wherein the operation data is multi-parameter data, and the parameter dimension of each parameter is one of monitoring data of each subsystem, equipment operation logs, energy conversion records, and environmental monitoring data; performing normalization processing on the historical operation data and constructing a multi-layer index structure operation database, wherein the multi-layer index includes timestamps, subsystems, and equipment within the subsystems; performing pattern mining on each parameter dimension in the operation database to identify key parameters in each parameter dimension and determine the key parameters as initial indexes to form an initial index set of each parameter dimension; screening the initial index set corresponding to the monitoring data of each subsystem to give supply-type initial indexes and consumption-type initial indexes; performing correlation analysis on the supply-type initial indexes and the consumption-type initial indexes, obtaining an index correlation network of supply and consumption according to the proportion of the combination of each supply-type initial index and each consumption-type initial index in the monitoring data of each subsystem, and giving supply indexes and consumption indexes based on correlation conditions; updating the initial index set of each parameter dimension based on the supply indexes and the consumption indexes to form an index set of each parameter dimension; moving a time window based on a pre-set sliding step, analyzing the index sensitivity of each index in each time window to obtain index sensitivity data of each index; substituting the index sensitivity data into a pre-constructed weight adjustment function to obtain the distribution weight of each index; weighting and marking each index based on the distribution weight of each index to construct the comprehensive energy index library; The core determination module is configured to analyze the evaluation features by principal component analysis to give core features; The weight determination module is configured to screen the evaluation features based on the similarity of the evaluation features and the core features and in combination with a pre-set similarity range to give target evaluation features; and give evaluation weights corresponding to the target evaluation features in combination with the information amount of the target evaluation features; The operation evaluation module is configured to give operation evaluation data of the comprehensive energy system based on the target evaluation features of each subsystem in the comprehensive energy system and in combination with the evaluation weights corresponding to the target evaluation features. 12.A management and control system for an integrated energy system, comprising a memory, a processor, and a computer program stored on the memory, wherein, The computer program is run by a processor to execute instructions of the method according to any one of claims 1-10.

Images