A power spot market settlement and diagnosis analysis system and method

Abstract

The present invention discloses a system and method for settlement and diagnosis and analysis of the electric power spot market, wherein the system includes a transaction settlement terminal and a diagnosis and analysis terminal, wherein the transaction settlement terminal includes: a settlement parameter and rule setting module for setting parameters and rules for market settlement; a settlement unit management module for counting unit information of market members for transaction settlement; a settlement data management module for managing various transaction data, and preprocessing the transaction data, constructing a knowledge graph based on the preprocessed data, and after receiving the user's query instruction, performing a multi-dimensional query on the settlement data according to the query instruction; the diagnosis and analysis terminal includes a market operation analysis module, and the market operation analysis module is used to analyze the overall operating efficiency of the electric power spot market, price formation fluctuations, and the power purchase profit and loss of the power grid company according to the settlement data. The system can process and analyze the transaction data of the electric power spot market, and provide an effective data basis for market settlement.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity spot market settlement, and in particular to an electricity spot market settlement and diagnosis and analysis system and method. Background Art

[0002] With the advancement of power market reform, power spot market transactions are becoming increasingly complex, with many participants and a variety of transactions, such as day-ahead spot transactions, real-time spot transactions, capacity market transactions, ancillary service market transactions, etc. Each transaction has its own specific settlement rules. These rules involve multiple aspects such as electricity metering, electricity price formation, compensation mechanism, default handling, etc., and there may be differences in different regions and markets. Traditional settlement and analysis methods can no longer meet the dynamic changes in the current power market. In view of this, a power spot market settlement and diagnostic analysis system is needed. Summary of the invention

[0003] The present invention aims to provide a system and method for electricity spot market settlement and diagnosis and analysis to solve the technical problems existing in the prior art.

[0004] The present invention is achieved through the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a power spot market settlement and diagnostic analysis system, comprising: a transaction settlement end and a diagnostic analysis end, the transaction settlement end comprising: a settlement parameter and rule setting module, a settlement unit management module and a settlement data management module, the diagnostic analysis end comprising a market operation analysis module, and the settlement parameter and rule setting module is used to set parameters and rules for market settlement;

[0006] The settlement unit management module is used to collect statistics on unit information of market members for transaction settlement;

[0007] The settlement data management module is used to manage various transaction data, pre-process the transaction data to obtain pre-processed data, build a knowledge graph based on the pre-processed data, and perform multi-dimensional query on the settlement data according to the query instruction after receiving the user's query instruction;

[0008] The market operation analysis module is used to analyze the overall operation efficiency, price fluctuations and power purchase profit and loss of the power grid company based on the settlement data.

[0009] Furthermore, the transaction settlement end also includes a market member management module, and the diagnostic analysis end also includes a market entity analysis module. The market member management module is used to manage the transaction information of various market members, and the market entity analysis module is used to analyze the structure, profit and loss situation and bidding strategy of various entities participating in the electricity spot market based on the transaction information of the market members of the transaction settlement end.

[0010] Further, the settlement parameter and rule setting module includes an acquisition unit, a screening unit, a determination unit, a configuration unit and a rule setting unit, wherein the acquisition unit is used to acquire business requirements and a settlement list of the power spot market;

[0011] The screening unit is used to screen the codes and names of settlement parameters according to business requirements and the settlement list;

[0012] The determining unit determines the target parameter type based on the code and name of the settlement parameter;

[0013] The configuration unit is used to configure the settlement parameters according to the target parameter type, and the settlement parameters include parameter code, parameter name, parameter type, data source type, data source field and parameter default value;

[0014] The rule setting unit is used to determine the settlement objects according to different types of power generation enterprises, power sales companies and users, calculate the electricity volume according to the settlement objects, and formulate the basic electricity price, market electricity price and electricity price adjustment method according to the electricity volume, and set the settlement period and settlement rules of the electricity fee according to the basic electricity price, market electricity price and electricity price adjustment method.

[0015] Furthermore, the rule setting unit includes a fuzzy model subunit, which takes the basic electricity price, the market electricity price and the electricity price adjustment method as input variables, and fuzzifies the input variables to obtain fuzzy results, establishes a fuzzy rule base according to the operating rules of the electricity market and expert knowledge, performs fuzzy reasoning on the fuzzified results of the input variables and the fuzzy rule base to obtain fuzzy output, and converts the fuzzy output into clear settlement cycles and settlement rules.

[0016] Furthermore, the settlement data management module includes a data monitoring unit, a data preprocessing unit and a knowledge graph unit, wherein the data monitoring unit is used to monitor the acquired contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data and assessment compensation data in real time;

[0017] The data preprocessing unit is used to clean, update and correct the acquired data to obtain preprocessed data;

[0018] The knowledge graph unit is used to identify entities in the settlement data based on the preprocessed data, determine the relationships between entities and entity attributes, build a knowledge graph based on entities, entity attributes and entity relationships, select a graph database of the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

[0019] Furthermore, the market operation analysis module includes an operation efficiency analysis unit, which is used to calculate the resource allocation efficiency and transaction efficiency based on the settlement data of the transaction settlement end, and analyze the overall operation efficiency of the electricity spot market through the resource allocation efficiency and transaction efficiency. The resource allocation efficiency includes the evaluation of the utilization degree of power generation resources and the optimal allocation of electricity resources. The transaction efficiency includes transaction cost, transaction speed and transaction smoothness.

[0020] In a second aspect, an embodiment of the present invention provides a method for settlement and diagnosis analysis in a power spot market, including:

[0021] Obtain various transaction data, set settlement parameters and rules;

[0022] Preprocessing the transaction data to obtain preprocessed data;

[0023] Build a knowledge graph based on the preprocessed data, receive user query instructions, and perform multi-dimensional queries on settlement data based on the user's query instructions;

[0024] Based on the settlement data, the overall operating efficiency of the electricity spot market, price fluctuations, and the profit and loss of power grid companies purchasing electricity are analyzed.

[0025] Furthermore, the method also includes: obtaining transaction information of various market members, and analyzing the structure, profit and loss situation and bidding strategy of various entities participating in the electricity spot market based on the transaction information of market members.

[0026] Furthermore, the specific methods for obtaining various transaction data and setting settlement parameters and rules include:

[0027] Obtain business requirements and settlement lists for the electricity spot market;

[0028] Filter the codes and names of settlement parameters according to business requirements and calculation lists;

[0029] Determine the target parameter type based on the code and name of the settlement parameter;

[0030] Settlement parameter configuration is performed according to the target parameter type, wherein the settlement parameter includes parameter code, parameter name, parameter type, data source type, data source field, and parameter default value;

[0031] Determine the settlement objects according to different types of power generation enterprises, power sales companies and users, calculate the electricity volume according to the settlement objects, formulate the basic electricity price, market electricity price and electricity price adjustment method according to the electricity volume, and set the settlement cycle and settlement rules of electricity charges according to the basic electricity price, market electricity price and electricity price adjustment method;

[0032] The basic electricity price, market electricity price and electricity price adjustment method are taken as input variables, and the input variables are fuzzified to obtain fuzzy results. A fuzzy rule base is established according to the operating rules of the electricity market and expert knowledge. The fuzzy results of the input variables and the fuzzy rule base are fuzzy inferred to obtain fuzzy outputs, and the fuzzy outputs are converted into clear settlement cycles and settlement rules.

[0033] Furthermore, the transaction data includes contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data, and assessment compensation data;

[0034] Conduct real-time monitoring of the contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data, and assessment compensation data;

[0035] Clean, update and correct transaction data to obtain pre-processed data;

[0036] Identify entities in the settlement data based on the preprocessed data, determine the relationships and attributes between entities, build a knowledge graph based on entities, entity attributes, and entity relationships, select the graph database of the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] The embodiment of the present invention provides a power spot market settlement and diagnostic analysis system, which establishes a data connection through a transaction settlement terminal and a diagnostic analysis terminal. The transaction settlement terminal accurately records and processes each transaction data, and the diagnostic analysis terminal comprehensively and deeply analyzes the operation status of the power spot market based on these high-quality data. From the perspectives of the overall market operation efficiency, price formation and fluctuation analysis, and the power purchase profit and loss of the power grid company, it provides accurate and comprehensive data basis for the settlement of the power spot market. The system also provides strong data support and decision-making basis for market participants and regulators from the perspectives of various market entities, profit and loss status calculations, and bidding strategies.

[0039] An electricity spot market settlement and diagnosis analysis method provided by an embodiment of the present invention has the same inventive concept as an electricity spot market settlement and diagnosis analysis system and has the same beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0041] Figure 1 A structural block diagram of a power spot market settlement and diagnostic analysis system provided by the first embodiment of the present invention;

[0042] Figure 2 It is a structural block diagram of a settlement parameter and rule setting module in an embodiment of the present invention;

[0043] Figure 3 is a structural block diagram of a settlement data management module in an embodiment of the present invention;

[0044] Figure 4 An overall flow chart of a power spot market settlement and diagnostic analysis method provided by an embodiment of the present invention;

[0045] Figure 5 is a specific flow chart of step S1 in an embodiment of the present invention;

[0046] Figure 6 is a specific flow chart of step S13 in an embodiment of the present invention;

[0047] Figure 7 is a specific flow chart of step S136 in an embodiment of the present invention;

[0048] Figure 8 This is a specific flow chart of step S2 in an embodiment of the present invention;

[0049] Fig. 9 4 is a specific flow chart of step S23 in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary implementation modes of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0051] Example 1

[0052] like Figure 1As shown, an embodiment of the present invention provides a power spot market settlement and diagnostic analysis system, including a transaction settlement terminal 1 and a diagnostic analysis terminal 2, wherein the transaction settlement terminal 1 and the diagnostic analysis terminal 2 are communicatively connected. The transaction settlement terminal 1 includes a market member management module 11, a settlement unit management module 12, a settlement parameter and rule setting module 13, and a settlement data management module 14; the market member management module 11 is used to manage the information of transactions of various market members, the settlement unit management module 12 is used to count the unit information of market members for transaction settlement, the settlement parameter and rule setting module 13 is used to set the parameters and rules of market settlement, and the settlement data management module 14 is used to manage the various transaction data accessed, and pre-process the transaction data to obtain pre-processed data, build a knowledge graph based on the pre-processed data, and after receiving the user's query instruction, perform multi-dimensional query on the settlement data according to the query instruction. The diagnostic analysis terminal 2 includes a market operation analysis module 21 and a market subject analysis module 22. The market operation analysis module 21 is used to analyze the overall operating efficiency, price fluctuations and power grid company's power purchase profit and loss situation of the electricity spot market based on settlement data. The market subject analysis module 22 is used to analyze the structure, profit and loss situation and bidding strategy of various entities participating in the electricity spot market based on the transaction information of market members.

[0053] The above-mentioned embodiment processes and analyzes the transaction data of the power market by establishing a data interactive connection between the transaction settlement terminal and the diagnosis and analysis terminal, thereby providing an effective data basis for market settlement.

[0054] like Figure 2As shown, the settlement parameter and rule setting module 13 includes an acquisition unit 131, a screening unit 132, a determination unit 133, a configuration unit 134 and a rule setting unit 135. The acquisition unit 131 is used to acquire the business needs and settlement list of the power spot market. The business needs of the power spot market include clarifying whether to configure the settlement parameters for medium- and long-term transactions or spot transactions, as well as the specific requirements of different types of power generation enterprises, power sales companies, users, etc. in terms of settlement. According to the business objectives, the effect to be achieved by the settlement parameter configuration is determined. The settlement list includes relevant parameters of special transaction varieties, market power monitoring parameters, loss allocation adjustment coefficients, etc. Each parameter is described in detail to clarify its meaning, function, relationship with other parameters and specific application methods in the settlement process. The screening unit 132 is used to screen the codes and names of the settlement parameters according to the business needs and the settlement list. According to the meaning of the parameters and business habits, a clear, accurate and unique name is determined for each parameter. The name should be concise and easy to understand and identify, and avoid using vague or ambiguous words. A corresponding code is compiled for each parameter, and the code should be unique and systematic to facilitate identification, storage, query and management in the system. Adopt certain coding rules, such as classifying and coding parameters according to the business module and type to which they belong, to ensure the standardization and readability of the coding.

[0055] The determination unit 133 determines the target parameter type based on the code and name of the settlement parameter. The determination unit constructs a decision tree model based on the features of the codes and names of all historical settlement parameters, and uses the decision tree model to predict the parameter type to obtain the target parameter type. First, the information gain of all attributes is calculated, and the attribute with the largest information gain is selected as the partition attribute of the root node. Then, according to the different values ​​of the attribute, the data set is divided into multiple subsets. For each subset, if the samples therein belong to the same type of parameter type, the subset is marked as a leaf node, and its category is the type of parameter; if the subset also contains samples of different categories, the partition attribute is recursively selected for the subset and a subtree is constructed until all subsets are marked as leaf nodes or the preset stop condition is reached.

[0056] The configuration unit 134 is used to configure the settlement parameters according to the target parameter type. The settlement parameters include parameter code, parameter name, parameter type, data source type, data source field and parameter default value. Determine the data source channel of each parameter, that is, the data source type. Common data source types include manual entry, system automatic collection, external interface import, etc. Set reasonable default values ​​for parameters according to business rules and historical data. The default value should be representative and universal to a certain extent, so that the settlement system can run normally and give reasonable results without clear input values. The determined parameter name, code, type, data source type, default value and constraint conditions are configured and developed according to the technical requirements and data structure of the settlement system. During the system implementation process, sufficient testing and verification should be carried out to ensure the accuracy of parameter configuration and the stability of the system.

[0057] The rule setting unit 135 is used to determine the settlement objects according to different types of power generation enterprises, power sales companies and users, calculate the electricity volume according to the settlement objects, and formulate the basic electricity price, market electricity price and electricity price adjustment method according to the electricity volume, and set the settlement period and settlement rules of the electricity fee according to the basic electricity price, market electricity price and electricity price adjustment method.

[0058] The rule setting unit 135 includes a fuzzy model sub-unit, which takes the basic electricity price, the market electricity price and the electricity price adjustment method as input variables, and fuzzifies the input variables to obtain fuzzy results, establishes a fuzzy rule base according to the operating rules of the electricity market and expert knowledge, performs fuzzy reasoning on the fuzzified results of the input variables and the fuzzy rule base to obtain fuzzy outputs, and converts the fuzzy outputs into clear settlement cycles and settlement rules.

[0059] The basic electricity price, market electricity price and electricity price adjustment method in the electricity market often have a certain degree of ambiguity. For example, concepts such as "high electricity price" and "large electricity price fluctuations" have no clear boundaries. Fuzzy logic algorithms can process this fuzzy information and determine the appropriate settlement period and rules by establishing fuzzy rules. Fuzzify input variables such as basic electricity price, market electricity price and electricity price adjustment range. For example, define fuzzy sets such as "low basic electricity price", "medium basic electricity price", "high basic electricity price" and their membership functions. For market electricity prices, fuzzy sets such as "stable market electricity price", "small fluctuations in market electricity price" and "large fluctuations in market electricity price" can also be defined similarly, and the parameters of the membership function can be determined based on historical data and expert experience. For electricity price adjustment methods, fuzzy concepts such as "frequent adjustment", "moderate adjustment" and "rare adjustment" can be defined. Establish a fuzzy rule base based on the operating laws of the electricity market and expert knowledge. For example, the rule could be “If the base electricity price is high and the market electricity price fluctuates greatly and the electricity price is adjusted frequently, then choose a shorter settlement period and flexible settlement rules”; or “If the base electricity price is medium and the market electricity price is stable and the electricity price is adjusted moderately, choose a quarterly settlement period and a settlement rule that proportionally combines the base electricity price and the market electricity price”, etc.

[0060] The fuzzy model subunit calculates the activation strength of each rule through fuzzy logic operations, and then integrates the results of these rules to obtain a fuzzy output, which represents the fuzzy suggestions for settlement cycles and rules.

[0061] Assume that there are n rules in the fuzzy rule base, and the form of the i-th rule is:

[0062] If x is A i And y is B i , then z is C i , where x and y are input variables, A i , B i and C i is the corresponding fuzzy set. It is known that the input variable x is related to the fuzzy set A. i The membership degree is μ Ai (x), y for fuzzy set B i The membership degree is μ Bi (y), then the activation strength of the rule is α i for:

[0063] α i =min(μ Ai (x),μ Bi (y))

[0064] It is obtained by synthesizing the activation strength of all rules and the membership function of the corresponding output fuzzy set:

[0065] μC(z)=m i＝a1x(min(α i ,μC i (z)))

[0066] Where: μ C (z) is the membership degree of the fuzzy set C of the output variable z, α i is the activation strength of the rule, μ Ci (z) is the membership degree of the i-th rule.

[0067] like Figure 3 As shown, the settlement data management module 14 includes a data monitoring unit 141, a data preprocessing unit 142 and a knowledge graph unit 143. The data monitoring unit 141 is used to monitor the acquired contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, metering data and assessment compensation data in real time. Real-time tracking of contract signing between power generation enterprises, power sales companies and users; continuous monitoring of contract execution progress, including indicators such as completed electricity transactions and remaining contract electricity; setting up a contract abnormality warning mechanism, and issuing an alarm in time when there is a large deviation in contract execution or abnormal fluctuations in contract prices. Pay close attention to the transaction dynamics of the inter-provincial spot market, and obtain real-time information such as transaction prices, transaction electricity, and transaction periods; monitor the available capacity and actual transmission power of inter-provincial transmission channels to ensure the smooth progress of inter-provincial spot transactions; conduct compliance checks on inter-provincial spot transactions to ensure that transactions comply with relevant laws and regulations and market rules. Real-time grasp of the supply and demand situation and price trends of the provincial spot market; for the distributed energy in the province, special attention is paid to its participation in spot transactions; after the provincial spot transaction is completed, the system automatically verifies the transaction settlement data to ensure the accuracy of the settlement. Real-time verification of the connected metering data is carried out to ensure the accuracy and reliability of the data. The implementation of the assessment and compensation mechanism is monitored to ensure the reasonable allocation and use of compensation funds.

[0068] The data preprocessing unit 142 is used to clean, update and correct the acquired data to obtain preprocessed data. The knowledge graph unit is used to identify entities in the settlement data based on the preprocessed data, determine the relationship between entities and entity attributes, build a knowledge graph based on entities, entity attributes and entity relationships, select a graph database for the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

[0069] The knowledge graph unit 143 extracts relevant entity and relationship information from contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, metering data, assessment compensation data, etc., to prepare for the construction of the knowledge graph. Identify various entities in the settlement data, such as power generation enterprises, power sales companies, users, contracts, transactions, metering equipment, assessment indicators, etc. Determine the relationship between entities, such as the contractual relationship between power generation enterprises and power sales companies, the transaction relationship between users and power sales companies, the metering relationship between metering equipment and users, and the assessment relationship between assessment indicators and market participants. Select a graph database suitable for storing knowledge graphs. This embodiment uses Neo4j to store the identified entity and relationship information in the graph database. Construct a knowledge graph based on entities, entity attributes, and entity relationships, and select a graph database of the knowledge graph to establish a real-time connection between the knowledge graph and the data source. Establish a real-time connection between the knowledge graph and the data source to ensure that the knowledge graph can promptly feedback changes in settlement data, and regularly perform consistency checks on the data in the knowledge graph to ensure that the knowledge graph is consistent with the data in the data source. Users can query characteristic entities in the knowledge graph by entering entity names or attribute information, or query the direct relationship between two entities, query the shortest path between two entities, or combine multiple query conditions for complex queries. By building a knowledge graph, multi-dimensional queries on settlement data can be realized, helping users quickly and accurately obtain the required information, and providing strong support for settlement management and decision-making analysis in the power market.

[0070] The market operation analysis module 21 includes an operation efficiency analysis unit 211, which is used to calculate the resource allocation efficiency and transaction efficiency according to the settlement data of the transaction settlement terminal, and analyze the overall operation efficiency of the power spot market through resource allocation efficiency and transaction efficiency. Resource allocation efficiency includes the evaluation of the utilization degree of power generation resources and the optimal configuration of power consumption resources. The transaction efficiency includes transaction costs, transaction speed and transaction fluency. Price formation fluctuations include market clearing models, analysis of the impact of cost factors on prices, price fluctuation amplitude and frequency, and price peak and trough analysis; the power purchase profit and loss of the power grid company includes the power purchase source and price of the power sales company, power purchase cost structure analysis, power sales revenue and power purchase profit and loss evaluation.

[0071] The market subject analysis module 22 is used to analyze the structure, profit and loss situation and bidding strategy of various subjects participating in the power spot market according to the transaction information of market members. Among them, the structure of various subjects participating in the power spot market includes power generation enterprises, power sales companies and large, medium and small users, the profit and loss situation includes the profit and loss analysis of various subject structures, and the bidding strategy includes the bidding strategy analysis of various subject structures.

[0072] The market operation analysis module 21 accurately presents the resource allocation efficiency and clearly displays the transaction efficiency, including transaction costs and transaction speed, by analyzing the overall operating efficiency of the spot market. In the price formation and fluctuation analysis, the price formation mechanism and fluctuation factors are explained in detail to make the price change pattern clear. The analysis of the power grid company's power purchase profit and loss comprehensively covers the power purchase cost, power sales revenue and related profit and loss calculation and influencing factors. In terms of structural analysis, the market subject analysis module 22 can carefully sort out the types, scales, distribution and other characteristics of power generation enterprises, power sales companies and users; in the profit and loss analysis, the income, cost and break-even point of each subject are accurately calculated, and the key influencing factors are found through sensitivity analysis; in the bidding strategy analysis, the bidding strategies of each subject based on cost, market forecast and other factors are comprehensively analyzed, from the cost addition and competition response of power generation enterprises, to the strategies of power sales companies on the power purchase and sales side, to the minimization of power consumption costs and trading strategies of large users, providing strong data support and decision-making basis for market participants and regulators.

[0073] The embodiment of the present invention provides a power spot market settlement and diagnostic analysis system, which establishes a data connection through a transaction settlement terminal and a diagnostic analysis terminal. The transaction settlement terminal accurately records and processes each transaction data, and the diagnostic analysis terminal comprehensively and deeply analyzes the operation status of the power spot market based on these high-quality data. From the perspectives of the overall market operation efficiency, price formation and fluctuation analysis, and the power purchase profit and loss of the power grid company, it provides accurate and comprehensive data basis for the settlement of the power spot market. The system also provides strong data support and decision-making basis for market participants and regulators from the perspectives of various market entities, profit and loss status calculations, and bidding strategies.

[0074] like Figure 4 As shown, another embodiment of the present invention provides a method for settlement and diagnosis analysis of a power spot market, comprising:

[0075] S1: Obtain various transaction data, set settlement parameters and rules;

[0076] S2: preprocessing the transaction data to obtain preprocessed data;

[0077] S3: Build a knowledge graph based on the preprocessed data, receive the user's query instructions, and perform multi-dimensional queries on the settlement data according to the user's query instructions;

[0078] S4: Analyze the overall operating efficiency, price fluctuations and power purchase profit and loss of the power grid company based on the settlement data.

[0079] S5: Obtain the transaction information of various market members, and analyze the structure, profit and loss situation and bidding strategy of various entities participating in the electricity spot market based on the transaction information of market members.

[0080] like Figure 5 As shown, obtaining various transaction data and setting settlement parameters and rules include the following steps:

[0081] S11. Obtain business requirements and settlement lists of the electricity spot market.

[0082] Obtaining business needs for the electricity spot market includes clarifying whether to configure settlement parameters for medium- and long-term transactions or spot transactions, as well as specific settlement requirements for different types of power generation companies, power sales companies, and users. Determine the effects to be achieved by the settlement parameter configuration based on business objectives. The settlement list includes relevant parameters for special transaction products, market power monitoring parameters, loss allocation adjustment coefficients, etc. Describe each parameter in detail to clarify its meaning, function, relationship with other parameters, and specific application methods in the settlement process.

[0083] S12. Filter the codes and names of settlement parameters according to business requirements and calculation lists.

[0084] Determine a clear, accurate, and unique name for each parameter based on the meaning of the parameter and business practices. The name should be concise, easy to understand and identify, and avoid using vague or ambiguous words. Compile a corresponding code for each parameter. The code should be unique and systematic to facilitate identification, storage, query, and management in the system. Certain coding rules can be adopted, such as classifying and coding according to the business module and type to which the parameter belongs, to ensure the standardization and readability of the code.

[0085] S13. Determine the target parameter type based on the code and name of the settlement parameter;

[0086] like Figure 6 As shown, step S13 also includes the following:

[0087] S131. Construct a decision tree model based on the features of the codes and names of all historical settlement parameters, and use the decision tree model to predict the parameter type to obtain the target parameter type.

[0088] Specifically, first calculate the information gain of all attributes, and select the attribute with the largest information gain as the partition attribute of the root node. Then, divide the data set into multiple subsets according to the different values ​​of the attribute. For each subset, if the samples in it belong to the same parameter type, the subset is marked as a leaf node, and its category is the parameter type; if the subset also contains samples of different categories, recursively continue to select partition attributes for the subset and build subtrees until all subsets are marked as leaf nodes or the preset stop condition is reached.

[0089] S132. Configure settlement parameters according to the target parameter type. The settlement parameters include parameter code, parameter name, parameter type, data source type, data source field and parameter default value.

[0090] Determine the data source channel for each parameter, that is, the data source type. Common data source types include manual entry, system automatic collection, external interface import, etc. Set reasonable default values ​​for parameters based on business rules and historical data. The default value should be representative and universal, and enable the settlement system to operate normally and give reasonable results without clear input values. The determined parameter name, code, type, data source type, default value, and constraint conditions should be configured and developed according to the technical requirements and data structure of the settlement system. During the system implementation process, sufficient testing and verification should be carried out to ensure the accuracy of parameter configuration and the stability of the system.

[0091] S133. Determine the settlement objects according to different types of power generation enterprises, power sales companies and users;

[0092] S134. Calculate the power based on the settlement object;

[0093] S135. Formulate basic electricity price, market electricity price and electricity price adjustment method based on the calculated electricity quantity;

[0094] S136. Use the established basic electricity price, market electricity price and electricity price adjustment method to set the electricity bill settlement cycle and settlement rules.

[0095] The basic electricity price, market electricity price and electricity price adjustment method in the electricity market are often vague. For example, concepts such as "high electricity price" and "large electricity price fluctuations" have no clear boundaries. Fuzzy logic algorithms can process this fuzzy information and determine the appropriate settlement period and rules by establishing fuzzy rules.

[0096] like Figure 7 As shown, step S136 also includes the following steps:

[0097] S1361. Take the basic electricity price, market electricity price and electricity price adjustment method as input variables, and fuzzify the input variables;

[0098] Fuzzify input variables such as basic electricity price, market electricity price and electricity price adjustment range. For example, define fuzzy sets such as "low basic electricity price", "medium basic electricity price", "high basic electricity price", and their membership functions. For market electricity price, fuzzy sets such as "stable market electricity price", "small fluctuations in market electricity price", and "large fluctuations in market electricity price" can also be similarly defined, and the parameters of the membership function can be determined based on historical data and expert experience. For the electricity price adjustment method, fuzzy concepts such as "frequent adjustment", "moderate adjustment", and "rare adjustment" can be defined.

[0099] S1362. Establish a fuzzy rule base based on the operating rules of the power market and expert knowledge;

[0100] A fuzzy rule base is established based on the operating rules of the power market and expert knowledge. For example, the rule can be "If the basic electricity price is high and the market electricity price fluctuates greatly and the electricity price is adjusted frequently, then choose a shorter settlement period and flexible settlement rules"; or "If the basic electricity price is medium and the market electricity price is stable and the electricity price is adjusted moderately, choose a quarterly settlement period and a settlement rule that combines the basic electricity price and the market electricity price in proportion", etc.

[0101] S1363. Perform fuzzy reasoning on the fuzzification results of the input variables and the fuzzy rule base;

[0102] Fuzzy reasoning is performed based on the fuzzification results of the input variables and the fuzzy rule base. The activation strength of each rule is calculated through fuzzy logic operations, and then the results of these rules are combined to obtain a fuzzy output, which represents the fuzzy suggestions for settlement cycles and rules.

[0103] Assume that there are n rules in the fuzzy rule base, and the form of the i-th rule is:

[0104] If x is A i And y is B i , then z is C i , where x and y are input variables, A i , B i and C i is the corresponding fuzzy set. It is known that the input variable x is related to the fuzzy set A. i The membership degree is μ Ai (x), y for fuzzy set B i The membership degree is μ Bi (y), then the activation strength of the rule is α i for:

[0105] α i =min(μ Ai (x),μ Bi (y))

[0106] It is obtained by synthesizing the activation strength of all rules and the membership function of the corresponding output fuzzy set:

[0107] μC(z)=m i＝ a1x(min(α i ,μC i (z)))

[0108] Where: μ C (z) is the membership degree of the fuzzy set C of the output variable z, α i is the activation strength of the rule, μCi (z) is the membership degree of the i-th rule.

[0109] S1364. Convert fuzzy output into clear settlement cycles and settlement rules.

[0110] Convert fuzzy output into clear settlement cycles and rules. Here, defuzzification methods such as centroid method and maximum membership method are used to convert the fuzzy set obtained by fuzzy reasoning into specific settlement cycles and rule parameter values.

[0111] like Figure 8 As shown, S2 includes the following steps:

[0112] S21. Real-time monitoring of the accessed contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data, and assessment compensation data;

[0113] Track the signing of contracts between power generation companies, power sales companies and users in real time; continuously monitor the progress of contract execution, including indicators such as completed power transactions and remaining contract power; set up a contract abnormality warning mechanism to issue an alarm in time when there is a large deviation in contract execution or abnormal fluctuations in contract prices. Pay close attention to the trading dynamics of the inter-provincial spot market, and obtain information such as transaction prices, transaction power, and transaction time periods in real time; monitor the available capacity and actual transmission power of inter-provincial transmission channels to ensure the smooth progress of inter-provincial spot transactions; conduct compliance checks on inter-provincial spot transactions to ensure that transactions comply with relevant laws and regulations and market rules. Understand the supply and demand situation and price trends of the provincial spot market in real time; pay special attention to the participation of distributed energy in the province in spot transactions; after the completion of the provincial spot transaction, the system automatically checks the transaction settlement data to ensure the accuracy of the settlement. Verify the accessed metering data in real time to ensure the accuracy and reliability of the data. Monitor the implementation of the assessment and compensation mechanism to ensure the reasonable allocation and use of compensation funds.

[0114] S22. preprocessing the received data, including data cleaning, updating and correction;

[0115] S23. Construct a knowledge graph based on the preprocessed data, and store the constructed knowledge graph in the database. When receiving the user's query instruction, perform multi-dimensional data query according to the query instruction.

[0116] like Fig. 9 As shown, step S23 specifically includes:

[0117] S231. Identify entities in the settlement data based on the preprocessed data, and determine the relationships between entities and entity attributes.

[0118] Extract relevant entity and relationship information from contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, metering data, assessment compensation data, etc. to prepare for the construction of the knowledge graph. Identify various entities in the settlement data, such as power generation companies, power sales companies, users, contracts, transactions, metering equipment, assessment indicators, etc. Determine the relationship between entities, such as the contractual relationship between power generation companies and power sales companies, the transaction relationship between users and power sales companies, the metering relationship between metering equipment and users, and the assessment relationship between assessment indicators and market participants. Select a graph database suitable for storing knowledge graphs. Neo4j is used here to store the identified entity and relationship information in the graph database.

[0119] S232. Build a knowledge graph based on entities, entity attributes, and entity relationships, select a graph database for the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

[0120] Establish a real-time connection between the knowledge graph and the data source to ensure that the knowledge graph can reflect changes in settlement data in a timely manner. Regularly check the consistency of the data in the knowledge graph to ensure that the knowledge graph is consistent with the data source.

[0121] S233. After receiving the user's query instruction, perform entity query, relationship query, path query and combination query according to the query instruction.

[0122] Users can query specific entities in the knowledge graph by entering entity names or attribute information; they can also query the direct relationship between two entities; they can query the shortest path between two entities; they can also combine multiple query conditions for complex queries. By building a knowledge graph, multi-dimensional queries on settlement data can be realized, helping users to quickly and accurately obtain the required information, and providing strong support for settlement management and decision-making analysis in the power market.

[0123] The analysis of the overall operating efficiency of the electricity spot market, price fluctuations, and the power purchase profit and loss of power grid companies based on settlement data includes:

[0124] The overall operating efficiency of the electricity spot market is analyzed by analyzing resource allocation efficiency and transaction efficiency. Resource allocation efficiency includes the evaluation of the utilization degree of power generation resources and the optimal allocation of electricity resources. The transaction efficiency includes transaction costs, transaction speed and transaction smoothness. Price formation fluctuations include market clearing models, analysis of the impact of cost factors on prices, price fluctuation range and frequency, and price peak and trough analysis. The power purchase profit and loss situation of power grid companies includes the power purchase sources and prices of power sales companies, power purchase cost structure analysis, power sales revenue and power purchase profit and loss evaluation.

[0125] Obtain the transaction information of various market members, and analyze the structure, profit and loss situation, and bidding strategy of various entities participating in the electricity spot market based on the transaction information of market members. The structure of various entities participating in the electricity spot market includes power generation enterprises, power sales companies, and large, medium and small users; the profit and loss situation includes the profit and loss analysis of various entity structures; the bidding strategy includes the bidding strategy analysis of various entity structures.

[0126] Market operation analysis accurately presents resource allocation efficiency and clearly displays transaction efficiency, including transaction costs and transaction speed, by analyzing the overall operating efficiency of the spot market. In price formation and fluctuation analysis, the price formation mechanism and fluctuation factors are explained in detail to make the price change pattern clear. The analysis of the power grid company's power purchase profit and loss comprehensively covers the power purchase cost, power sales revenue, and related profit and loss calculations and influencing factors. In terms of structural analysis, the market subject analysis can carefully sort out the types, scales, distribution and other characteristics of power generation companies, power sales companies and users; in the profit and loss analysis, the revenue, cost and break-even point of each subject are accurately calculated, and the key influencing factors are found through sensitivity analysis; in the bidding strategy analysis, the bidding strategies of each subject based on cost, market forecast and other factors are comprehensively analyzed, from the cost addition and competitive response of power generation companies, to the strategies of power sales companies on the power purchase and sales side, to the minimization of power consumption costs and trading strategies of large users, providing strong data support and decision-making basis for market participants and regulators.

[0127] The embodiment of the present invention provides a method for settlement and diagnostic analysis of the electricity spot market. By acquiring the transaction data of the transaction settlement terminal, preprocessing the transaction data, and constructing a knowledge graph, a multi-dimensional query of the settlement data is realized by constructing the knowledge graph, which helps users to quickly and accurately obtain the required information, and provides strong support for the settlement management and decision-making analysis of the electricity market. According to the settlement data, the overall market operation efficiency, price formation and fluctuation analysis, and the power purchase profit and loss of the power grid company are analyzed from multiple aspects, providing accurate and comprehensive data basis for the settlement of the electricity spot market. It can also analyze from multiple aspects such as various market entities, profit and loss situation calculation and bidding strategy of the overall market, providing strong data support and decision-making basis for market participants and regulators.

[0128] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0129] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0131] It can be understood that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A power spot market settlement and diagnostic analysis system, characterized in that: include: A transaction settlement terminal and a diagnosis and analysis terminal, wherein the transaction settlement terminal includes: a settlement unit management module, a settlement parameter and rule setting module and a settlement data management module, and the diagnosis and analysis terminal includes a market operation analysis module. The settlement unit management module is used to count the unit information of market members for transaction settlement; The settlement parameter and rule setting module is used to set the parameters and rules of market settlement; The settlement data management module is used to manage various transaction data, pre-process the transaction data to obtain pre-processed data, build a knowledge graph based on the pre-processed data, and perform multi-dimensional query on the settlement data according to the query instruction after receiving the user's query instruction; The market operation analysis module is used to analyze the overall operating efficiency of the power spot market, price fluctuations, and the power purchase profit and loss of the power grid company based on settlement data.

2. The system according to claim 1, characterized in that The transaction settlement end also includes a market member management module, and the diagnostic analysis end also includes a market entity analysis module. The market member management module is used to manage the transaction information of various market members, and the market entity analysis module is used to analyze the structure, profit and loss situation and bidding strategy of various entities participating in the electricity spot market based on the transaction information of market members.

3. The system according to claim 1, characterized in that The settlement parameter and rule setting module includes an acquisition unit, a screening unit, a determination unit, a configuration unit and a rule setting unit, wherein the acquisition unit is used to acquire the business requirements and settlement list of the power spot market; The screening unit is used to screen the codes and names of settlement parameters according to business requirements and the settlement list; The determining unit determines the target parameter type based on the code and name of the settlement parameter; The configuration unit is used to configure the settlement parameters according to the target parameter type, and the settlement parameters include parameter code, parameter name, parameter type, data source type, data source field and parameter default value; The rule setting unit is used to determine the settlement objects according to different types of power generation enterprises, power sales companies and users, calculate the electricity volume according to the settlement objects, and formulate the basic electricity price, market electricity price and electricity price adjustment method according to the electricity volume, and set the settlement period and settlement rules of the electricity fee according to the basic electricity price, market electricity price and electricity price adjustment method.

4. The system according to claim 3, characterized in that The rule setting unit includes a fuzzy model subunit, which takes the basic electricity price, the market electricity price and the electricity price adjustment method as input variables, and fuzzifies the input variables to obtain fuzzy results, establishes a fuzzy rule base according to the operating rules of the electricity market and expert knowledge, performs fuzzy reasoning on the fuzzified results of the input variables and the fuzzy rule base to obtain fuzzy output, and converts the fuzzy output into clear settlement cycles and settlement rules.

5. The system according to claim 1, characterized in that The settlement data management module includes a data monitoring unit, a data preprocessing unit and a knowledge graph unit, wherein the data monitoring unit is used to monitor the acquired contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data and assessment compensation data in real time; The data preprocessing unit is used to clean, update and correct the acquired data to obtain preprocessed data; The knowledge graph unit is used to identify entities in the settlement data based on the preprocessed data, determine the relationships between entities and entity attributes, build a knowledge graph based on entities, entity attributes and entity relationships, select a graph database of the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

6. The system according to claim 1, characterized in that The market operation analysis module includes an operation efficiency analysis unit, which is used to calculate resource allocation efficiency and transaction efficiency based on the settlement data of the transaction settlement end, and analyze the overall operation efficiency of the electricity spot market through resource allocation efficiency and transaction efficiency. The resource allocation efficiency includes the evaluation of the utilization degree of power generation resources and the optimal configuration of electricity resources. The transaction efficiency includes transaction cost, transaction speed and transaction smoothness.

7. A method for electricity spot market settlement and diagnostic analysis, characterized in that: include: Obtain various transaction data, set settlement parameters and rules; Preprocessing the transaction data to obtain preprocessed data; Build a knowledge graph based on the preprocessed data, receive user query instructions, and perform multi-dimensional queries on settlement data based on the user's query instructions; Based on the settlement data, the overall operating efficiency of the electricity spot market, price fluctuations, and the profit and loss of power grid companies purchasing electricity are analyzed.

8. The method according to claim 7, characterized in that The method also includes: obtaining transaction information of various market members, and analyzing the structure, profit and loss status and bidding strategy of various entities participating in the power spot market based on the transaction information of the market members.

9. The method according to claim 7, characterized in that: The specific methods for obtaining various transaction data and setting settlement parameters and rules include: Obtain business requirements and settlement lists for the electricity spot market; Filter the codes and names of settlement parameters according to business requirements and calculation lists; Determine the target parameter type based on the code and name of the settlement parameter; Settlement parameter configuration is performed according to the target parameter type, wherein the settlement parameter includes parameter code, parameter name, parameter type, data source type, data source field, and parameter default value; Determine the settlement objects according to different types of power generation enterprises, power sales companies and users, calculate the electricity volume according to the settlement objects, formulate the basic electricity price, market electricity price and electricity price adjustment method according to the electricity volume, and set the settlement cycle and settlement rules of electricity charges according to the basic electricity price, market electricity price and electricity price adjustment method; The basic electricity price, market electricity price and electricity price adjustment method are taken as input variables, and the input variables are fuzzified to obtain fuzzy results. A fuzzy rule base is established according to the operating rules of the electricity market and expert knowledge. The fuzzy results of the input variables and the fuzzy rule base are fuzzy inferred to obtain fuzzy outputs, and the fuzzy outputs are converted into clear settlement cycles and settlement rules.

10. The method according to claim 7, characterized in that The transaction data includes contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data, and assessment compensation data; Conduct real-time monitoring of the contract data, inter-provincial spot transaction data, intra-provincial spot transaction data, measurement data, and assessment compensation data; Clean, update and correct transaction data to obtain pre-processed data; Identify entities in the settlement data based on the preprocessed data, determine the relationships and attributes between entities, build a knowledge graph based on entities, entity attributes, and entity relationships, select the graph database of the knowledge graph, and establish a real-time connection between the knowledge graph and the data source.

Images