Cross-regional power transaction risk identification method and device, and storage medium
Through the combination of hierarchical analysis method and entropy weight method, cross-regional power transaction risk types and indicator weights are given, cross-regional power transaction risks are identified, and cross-regional power transaction risks are solved, and the problem of insufficient identification of cross-regional power transaction risks in the existing technology is achieved. Accurately identify and reduce.
Patent Information
- Application Number
- CN202411044271.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology lacks effective cross-regional power transaction risk identification methods, which leads to the inability to pre-perceive cross-regional power transaction risks, affecting the optimal allocation of power grid resources and the consumption of new energy.
Using a combination of hierarchical analysis method and entropy weight method, we determine the transaction risk type and the target weight of the risk indicators of cross-regional power transactions. By obtaining the scoring results of multiple transaction risk types and risk indicators, we construct a comparison matrix and judgment matrix, and give it Each risk type and indicator correspond to the weights, thereby identifying cross-regional power trading risks.
It realizes accurate identification of cross-regional power transaction risks, reduces risks, improves transaction efficiency, and solves the problem of insufficient identification of power transaction risks in the region.
Smart Images

Figure CN118966772A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing, and in particular to a method, device and storage medium for identifying risks in cross-regional power trading. Background Art
[0002] Real-time cross-regional power trading is of great significance for optimizing grid resource allocation, absorbing new energy, and complementing surplus and shortage. However, with the increase in the number of members in the power trading market and the further increase in source-load uncertainty, cross-regional power trading faces a series of risks, such as the risk of tight supply and demand under extreme weather conditions, the risk of price gouging by market members, and the risk of regulatory regulation. At present, the risk assessment of power market transactions is mainly focused on the risk assessment of transactions within the region, and there is a lack of risk assessment of cross-regional power transactions, resulting in high risks in cross-regional power transactions.
[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0004] The embodiments of the present invention provide a method, device and storage medium for identifying cross-regional electricity trading risks, so as to at least solve the technical problem that the related technology mainly focuses on the identification of intra-regional electricity trading risks, lacks consideration of the identification of cross-regional electricity trading risks, and thus leads to the inability to pre-perceive cross-regional electricity trading risks.
[0005] According to one aspect of an embodiment of the present invention, a method for identifying risks in cross-regional power transactions is provided, comprising: obtaining a plurality of transaction risk types corresponding to cross-regional power transactions, and a plurality of risk indicator sets corresponding to the plurality of transaction risk types, wherein the plurality of transaction risk types correspond one-to-one to the plurality of risk indicator sets; determining target weights corresponding to the plurality of transaction risk types, and target weights corresponding to the risk indicators included in the plurality of risk indicator sets; determining target power transaction data of the cross-regional power transaction, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the plurality of risk indicator sets; and determining a risk identification result of the cross-regional power transaction based on the target power transaction data, the target weights corresponding to the plurality of transaction risk types, and the target weights corresponding to the risk indicators included in the plurality of risk indicator sets.
[0006] Optionally, determining the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, includes: taking the risk identification result of the cross-regional power transaction as the target layer, the multiple transaction risk types as the criterion layer, and the risk indicators included in the multiple risk indicator sets as the decision layer, and using the hierarchical analysis method to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets; obtaining multiple groups of power transaction data of the cross-regional power transaction, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; based on the multiple groups of power transaction data, using the entropy weight method to determine the second weights corresponding to the multiple transaction risk types, and the second weights corresponding to the risk indicators included in the multiple risk indicator sets; based on the first weights and the second weights corresponding to the multiple transaction risk types, obtaining the target weights corresponding to the multiple transaction risk types; based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets, obtaining the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0007] Optionally, the risk identification result of the cross-regional electricity transaction is used as the target layer, the multiple transaction risk types are used as the criterion layer, and the risk indicators included in the multiple risk indicator sets are used as the decision layer, and the hierarchical analysis method is used to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets, including: obtaining the scoring results of each transaction risk type in the multiple transaction risk types relative to other transaction risk types, and the scoring results of each risk indicator in the multiple risk indicator sets relative to other risk indicators; based on the scoring results of each transaction risk type relative to other transaction risk types, constructing a criterion layer comparison matrix, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on each risk A decision-making layer comparison matrix is constructed based on the scoring results of the indicators relative to other risk indicators, wherein the rows and columns of the decision-making layer comparison matrix are risk indicators included in a plurality of risk indicator sets, respectively, and the elements in the decision-making layer comparison matrix are the scoring results of the corresponding risk indicators relative to another risk indicator; based on the criterion layer comparison matrix and a preset first comparison factor, a criterion layer judgment matrix is constructed, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; based on the decision-making layer comparison matrix and a preset second comparison factor, a decision-making layer judgment matrix is constructed, wherein the elements included in the decision-making layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; based on the criterion layer judgment matrix, the first weights corresponding to the multiple transaction risk types are determined; based on the decision-making layer judgment matrix, the first weights corresponding to the risk indicators included in the plurality of risk indicator sets are determined.
[0008] Optionally, the determining, based on the criterion layer judgment matrix, first weights respectively corresponding to the multiple transaction risk types; and the determining, based on the decision layer judgment matrix, first weights respectively corresponding to the risk indicators included in the multiple risk indicator sets include: obtaining the first weight corresponding to any transaction risk type among the multiple transaction risk types by:
[0009]
[0010] Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij(j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of the multiple transaction risk types; based on the criterion layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the multiple transaction risk types respectively; based on the decision layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively.
[0011] Optionally, after determining the first weights corresponding to the multiple transaction risk types respectively based on the criterion layer judgment matrix; and determining the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively based on the decision layer judgment matrix, the method further includes: performing a consistency check on the first weights corresponding to the multiple transaction risk types respectively, and performing a consistency check on the first weights corresponding to the risk indicators included in the multiple risk indicator sets; if the consistency check on the first weights corresponding to the multiple transaction risk types respectively fails, and / or the consistency check on the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively fails, updating the criterion layer judgment matrix and / or the decision layer judgment matrix; determining new first weights corresponding to the multiple transaction risk types respectively based on the updated criterion layer judgment matrix; and / or determining new first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively based on the decision layer judgment matrix.
[0012] Optionally, obtaining target weights corresponding to the multiple transaction risk types based on the first weights and the second weights corresponding to the multiple transaction risk types respectively; obtaining target weights corresponding to the risk indicators included in the multiple risk indicator sets based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets respectively, includes: obtaining the target weight corresponding to any transaction risk type among the multiple transaction risk types by:
[0013]
[0014] Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η srepresents the second weight corresponding to any one of the transaction risk types, d1 and d2 represent the linear combination coefficients to be solved, d1' represents the result obtained by normalizing d1, and d'2 represents the result obtained by normalizing d2; based on the first weights and the second weights respectively corresponding to the multiple transaction risk types, a method of obtaining the target weight corresponding to any one of the transaction risk types is adopted to obtain the target weights respectively corresponding to the multiple transaction risk types; based on the first weights and the second weights respectively corresponding to the risk indicators included in the multiple risk indicator sets, a method of obtaining the target weight corresponding to any one of the transaction risk types is adopted to obtain the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets.
[0015] Optionally, the risk identification result of the cross-regional power transaction is determined based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, including: obtaining the risk scores corresponding to the multiple transaction risk types based on the target power transaction data and the target weights of the risk indicators corresponding to the multiple transaction risk types; obtaining the total risk score of the cross-regional power transaction based on the risk scores corresponding to the multiple transaction risk types and the target weights of the risk indicators corresponding to the multiple transaction risk types; and using the risk scores corresponding to the multiple transaction risk types and / or the total risk score as the risk identification result of the cross-regional power transaction.
[0016] According to another aspect of an embodiment of the present invention, a cross-regional power transaction risk identification device is also provided, including: an indicator acquisition module, used to obtain multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond one-to-one to the multiple risk indicator sets; a weight determination module, used to determine the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets; a data determination module, used to determine the target power transaction data of the cross-regional power transaction, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; a risk identification module, used to determine the risk identification result of the cross-regional power transaction based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0017] Optionally, the weight determination module includes: a first determination module, which uses the risk identification result of the cross-regional power transaction as the target layer, the multiple transaction risk types as the criterion layer, and the risk indicators included in the multiple risk indicator sets as the decision layer, and adopts a hierarchical analysis method to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets; a first acquisition module, which is used to acquire multiple groups of power transaction data of the cross-regional power transaction, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; a second determination module, which uses an entropy weight method to determine, based on the multiple groups of power transaction data, the second weights corresponding to the multiple transaction risk types, and the second weights corresponding to the risk indicators included in the multiple risk indicator sets; a second acquisition module, which is used to obtain the target weights corresponding to the multiple transaction risk types based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets; and obtain the target weights corresponding to the risk indicators included in the multiple risk indicator sets based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0018] Optionally, the first determination module includes: a first acquisition submodule, used to obtain the scoring results of each transaction risk type in the multiple transaction risk types relative to other transaction risk types, and the scoring results of each risk indicator in the multiple risk indicator sets relative to other risk indicators; a first construction submodule, used to construct a criterion layer comparison matrix based on the scoring results of each transaction risk type relative to other transaction risk types, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on the scoring results of each risk indicator relative to other risk indicators, a decision layer comparison matrix is constructed, wherein the rows and columns of the decision layer comparison matrix are respectively included in the multiple risk indicator sets risk indicator, the elements in the decision-making layer comparison matrix are the scoring results of the corresponding risk indicator relative to another risk indicator; a second construction submodule is used to construct a criterion layer judgment matrix based on the criterion layer comparison matrix and a preset first comparison factor, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; based on the decision-making layer comparison matrix and the preset second comparison factor, a decision-making layer judgment matrix is constructed, wherein the elements included in the decision-making layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; a first determination submodule is used to determine the first weights corresponding to the multiple transaction risk types respectively based on the criterion layer judgment matrix; based on the decision-making layer judgment matrix, determine the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively.
[0019] Optionally, the first determining submodule is further used to obtain a first weight corresponding to any transaction risk type among the multiple transaction risk types by:
[0020]
[0021] Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij (j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of the multiple transaction risk types; based on the criterion layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the multiple transaction risk types respectively; based on the decision layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively.
[0022] Optionally, the device also includes: a first verification module, used to perform consistency verification on the first weights corresponding to the multiple transaction risk types, and to perform consistency verification on the first weights corresponding to the risk indicators included in the multiple risk indicator sets; a first updating module, used to update the criterion layer judgment matrix and / or the decision layer judgment matrix when the consistency verification on the first weights corresponding to the multiple transaction risk types fails and / or the consistency verification on the first weights corresponding to the risk indicators included in the multiple risk indicator sets fails; a third determination module, used to determine new first weights corresponding to the multiple transaction risk types based on the updated criterion layer judgment matrix; and / or to determine new first weights corresponding to the risk indicators included in the multiple risk indicator sets based on the decision layer judgment matrix.
[0023] Optionally, the second acquisition module is further used to obtain a target weight corresponding to any transaction risk type among the multiple transaction risk types by:
[0024]
[0025] Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η s represents the second weight corresponding to any one of the transaction risk types, d1 and d2 represent the linear combination coefficients to be solved, d1' represents the result obtained by normalizing d1, and d'2 represents the result obtained by normalizing d2; based on the first weights and the second weights respectively corresponding to the multiple transaction risk types, a method of obtaining the target weight corresponding to any one of the transaction risk types is adopted to obtain the target weights respectively corresponding to the multiple transaction risk types; based on the first weights and the second weights respectively corresponding to the risk indicators included in the multiple risk indicator sets, a method of obtaining the target weight corresponding to any one of the transaction risk types is adopted to obtain the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets.
[0026] Optionally, the risk identification module includes: a first scoring module, used to obtain the risk scores corresponding to the multiple transaction risk types based on the target power transaction data and the target weights of the risk indicators corresponding to the multiple transaction risk types; a second scoring module, used to obtain the total risk score of the cross-regional power transaction based on the risk scores corresponding to the multiple transaction risk types and the target weights of the risk indicators corresponding to the multiple transaction risk types; and a third scoring module, used to use the risk scores corresponding to the multiple transaction risk types and / or the total risk score as the risk identification result of the cross-regional power transaction.
[0027] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing any one of the cross-regional electricity trading risk identification methods.
[0028] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the cross-regional electricity trading risk identification methods.
[0029] In an embodiment of the present invention, by obtaining multiple transaction risk types corresponding to cross-regional power transactions and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond to the multiple risk indicator sets one by one; determining the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets; determining the target power transaction data of the cross-regional power transaction, wherein the target power transaction data at least includes the indicator values corresponding to the risk indicators included in the multiple risk indicator sets; based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, determining the risk identification result of the cross-regional power transaction, achieving the purpose of assigning corresponding weights from the two levels of transaction risk type and risk indicator, and performing risk identification of cross-regional power transactions based on the obtained weights and the corresponding power transaction data, thereby achieving the technical effect of accurately identifying cross-regional power transaction risks to reduce cross-regional power transaction risks, thereby solving the technical problem that the related technology mainly focuses on the identification of intra-regional power transaction risks, lacks consideration of cross-regional power transaction risk identification, and thus cannot pre-perceive the risk of cross-regional power transactions. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0031] Figure 1 is a flow chart of a method for identifying risks in cross-regional power transactions according to an embodiment of the present invention;
[0032] Figure 2 is a flow chart of an optional cross-regional power transaction risk identification method according to an embodiment of the present invention;
[0033] Figure 3 It is a schematic diagram of a device for identifying risks in cross-regional power transactions according to an embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0036] According to an embodiment of the present invention, a method embodiment for identifying cross-regional electricity trading risks is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.
[0037] Figure 1 is a flow chart of a method for identifying risks of cross-regional power transactions according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:
[0038] Step S102, obtaining multiple transaction risk types corresponding to cross-regional power transactions and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond to the multiple risk indicator sets one-to-one;
[0039] Optionally, the types of cross-regional power market transaction risks may include, but are not limited to, market transaction volume risk A1, market price risk A2, and market power risk A3. Among them, market transaction volume risk A1 refers to the risks of volume that may occur in the early, middle, and late stages of power transactions, such as insufficient volume, and the inability to reach a transaction volume due to transmission channel blockage; market price risk A2 refers to the risks of market prices that may occur in the early, middle, and late stages of transactions due to abnormal supply and demand changes, violation of transaction procedures, and anti-market behavior; market power risk A3 refers to the risks of market power that may occur in the early and middle stages of transactions, such as alliances of market members driving up electricity prices and using their own advantages in scale and scope to conduct unfair transactions.
[0040] Optionally, each of the multiple transaction risk types corresponds to a transaction risk indicator set, and each transaction risk indicator set includes multiple transaction risk indicators corresponding to the corresponding transaction risk type.
[0041] The above-mentioned market transaction electricity risk A1 can be quantitatively analyzed by the following transaction risk indicators: the proportion of declared clean energy electricity B1, the proportion of thermal power reserve capacity B2, the utilization rate of transmission channels / interconnection lines B3, the ratio of intraday transaction electricity on the previous day B4, and the difference ratio between the converted electricity of the buyer's node and the actual electricity emitted by the seller's node (i.e. the electricity purchasing area and the electricity selling area) B5.
[0042] Among them, the proportion of clean energy electricity reported B1 reflects the risk of electricity transmission not meeting the standard due to weather factors, changes in predicted output and actual output. The greater the proportion of clean energy electricity, the greater the risk. The proportion of thermal power reserve capacity B2 reflects the ability of the subject to adjust the transmission electricity when the output of new energy is insufficient. The larger the value, the greater the amount of electricity that the reporting subject can use for adjustment, that is, the corresponding risk of insufficient electricity is smaller. The utilization rate of the transmission channel / interconnection line B3 reflects the probability of blockage of transactions occurring in the transmission channel / interconnection line. The higher the utilization rate, the greater the risk of electricity blockage. The ratio of intraday transaction electricity B4 reflects the activity of transaction electricity. The higher the proportion of intraday transaction electricity, the weaker the stability and the higher the risk. The difference ratio B5 between the converted electricity of the buyer's node and the actual electricity emitted by the seller's node reflects the ability of the seller's node to perform the contract after the buyer and the seller reach a transaction. It can be used to judge the ability of the seller's node to perform the contract. The larger the difference ratio, the greater the risk.
[0043] The reported clean energy electricity proportion B1 can be obtained in the following way:
[0044]
[0045] The thermal power reserve capacity ratio B2 can be obtained as follows:
[0046]
[0047] Among them, Q r represents the clean electricity declared by the seller node, Q0 represents the total electricity declared by the seller node, Q fire Represents the thermal power reserve capacity of the seller's node.
[0048] The previous day's intraday transaction volume ratio B4 can be obtained as follows:
[0049]
[0050] Among them, Power 日内 Indicates the amount of electricity traded during the day, Power 日前 Indicates the day-ahead transaction electricity.
[0051] The difference ratio B5 between the converted power of the buyer node and the actual power sent by the seller node can be obtained as follows:
[0052]
[0053] Among them, power 卖电 The actual generation of electricity for the seller market entity, The electricity reported by the buyer market entity is converted to the electricity of the seller market entity, coe l is the conversion parameter.
[0054] Market price risk A2 can be quantified by the following transaction risk indicators: the difference between transaction price and quotation B6, the peak-to-valley difference between transaction electricity prices B7, the difference between the maximum and average transaction electricity prices B8, the difference between the declared electricity price and the average declared electricity price B9, the demand elasticity index B10, the growth rate of thermal power cost B11, and the Lerner index B12.
[0055] Among them, the difference between the transaction price and the quotation B6 represents the difference between the final seller's quotation and the converted transaction price, that is, the size of the profit that the seller can obtain, reflecting the market liquidity risk and execution risk in power trading. The larger the difference, the greater the risk. The peak-to-valley difference of the transaction electricity price B7 represents the extreme difference of the transaction electricity price, reflecting the market transparency. When the extreme difference is too large, there may be ultra-low prices or ultra-high prices for purchasing electricity, which will affect market stability. The larger the peak-to-valley difference, the greater the risk. The difference between the maximum and average transaction electricity prices B8 reflects the volatility and supply-demand relationship of the transaction electricity price. The larger the difference, the greater the risk. The difference between the declared electricity price and the average declared electricity price B9 reflects the market transparency. A large difference indicates asymmetric market information. The larger the difference, the greater the risk. The growth rate of thermal power cost B11, the cost of thermal power will be directly reflected in the price. The higher the cost, the greater the risk of price increases. Among them, the growth rate of thermal power cost B11 can be obtained as follows:
[0056]
[0057] Among them, Price ct Indicates the current cost of thermal power generation, Price c0 It indicates the thermal power generation cost in the previous year or can be defined by the market administrator based on the market power generation cost forecast.
[0058] The Lerner Index B12 represents the ratio of electricity price to marginal cost of power generation, reflecting market power. The higher the Lerner Index, the greater the risk. The Lerner Index B12 can be obtained as follows:
[0059] B12=(Price-MC) / Price
[0060] Among them, Price represents the declared price and MC represents the marginal cost of the transaction.
[0061] The demand elasticity index B10 represents the ratio of the rate of change of electricity prices to the rate of change of demand, reflecting the effective reflection of prices on market supply and demand. The greater the demand elasticity index, the greater the risk. The demand elasticity index B10 can be obtained as follows:
[0062]
[0063] Among them, Q represents the reported electricity quantity, and ΔQ represents the change value of the reported electricity quantity.
[0064] Market power risk A3 can be quantified through the following transaction risk indicators: electricity price limit rate B13, market player participation B14, maximum bid difference B15, retention ratio B16, power purchase acceptance rate B17, ratio of market player income to regional average annual income B18, ratio of market reported sales volume to medium- and long-term contract purchase volume B19, market concentration on the power generation side B20, market concentration on the power sales side B21, and power purchaser's high reported bid winning rate B22.
[0065] Among them, the power price limit rate B13, the ratio of the number of periods with power prices close to the maximum price limit to the total number of bidding periods, reflects the risk of price gouging on the power generation side of the market. The lower the ratio, the greater the risk. The market subject participation B14, which indicates the ratio of the subjects participating in power trading in the power trading market to the total market subjects that can participate in power spot trading, reflects the activeness of the trading market subjects in participating in the transaction and the health of the rules. The smaller the ratio, the lower the participation and the greater the risk. The maximum bid difference B15, which indicates the largest bid difference in a single power transaction, reflects the extreme behavior in a certain power transaction, including the extreme behavior of the buyer, such as the behavior of purchasing power at an ultra-low price by violating market rules, and the extreme behavior of the seller, such as the seller's price gouging when the buyer urgently needs to purchase power due to sudden accidents, extreme weather, etc. The larger the maximum bid difference, the greater the risk. The retention ratio B16 indicates the ratio of the power reported by the seller node to the predicted surplus power, reflecting the buyer's node's control over the power sold in the market. The higher the retention ratio, the greater the risk. The power purchase acceptance rate B17 indicates the ratio of the transaction power of the buyer node to the actual power accepted, which reflects the rationality of the power purchase of the buyer node and the acceptance capacity of the purchased power. The lower the power purchase acceptance rate, the greater the risk. The ratio of the market entity's income to the regional annual average income B18 reflects whether the profit of the buyer node is much higher than the regional average income, thus resulting in its monopoly position. The higher the ratio, the greater the risk. The ratio of the market's declared sales power to the medium- and long-term contracted power purchases B19 reflects the improper behavior of market entities in reselling power. The larger the ratio, the greater the risk. The market concentration on the power purchase side B20 indicates the proportion of the number of power purchasers to the total number of parties involved in the transaction, reflecting the power purchase side's ability to control the market. The higher the concentration, the larger the ratio, the greater the risk. The market concentration on the power sales side B21 indicates the proportion of the number of power sellers to the total number of parties involved in the transaction, reflecting the power sales side's ability to control the market and the degree of monopoly. The higher the concentration, the larger the ratio, the greater the risk. The winning rate of the electricity purchaser with a high bid price B22 indicates the transaction completion rate when the electricity purchaser purchases electricity at the highest price, reflecting the principle of market fairness. The lower the winning rate, the higher the risk.
[0066] Among them, the correlation between each risk indicator and the risk identification result (such as positive correlation or negative correlation) is shown in the following table.
[0067] Table 1 Risk assessment system for cross-regional power trading
[0068] Decision-making level Risk Correlation Reported clean energy electricity ratio B1 Positive correlation Thermal power reserve capacity ratio B2 Negative correlation Transmission channel / tie line utilization rate B3 Positive correlation The ratio of the amount of electricity traded on the previous day B4 Positive correlation The difference between the converted power of the buyer's node and the actual power sent by the seller's node is B5 Positive correlation Difference between transaction price and quotation B6 Positive correlation Peak-valley difference of transaction electricity price B7 Positive correlation The difference between the maximum and average transaction price B8 Positive correlation Difference between declared electricity price and average declared electricity price B9 Positive correlation Demand elasticity coefficient B10 Positive correlation Thermal power cost growth rate B11 Positive correlation Lerner Index B12 Positive correlation Electricity price limit rate B13 Negative correlation Market player participation B14 Negative correlation Maximum quote difference B15 Positive correlation Retention rate B16 Positive correlation Electricity purchase acceptance rate B17 Negative correlation Ratio of market entity income to social annual average income B18 Positive correlation Ratio of electricity sold in the spot market to electricity purchased under medium- and long-term contracts B19 Positive correlation Market concentration on power generation side B20 Positive correlation Market concentration of electricity sales side B21 Positive correlation The winning rate of the power purchaser with high bid price is B22 Negative correlation
[0069] Step S104, determining target weights corresponding to a plurality of transaction risk types, and target weights corresponding to risk indicators included in a plurality of risk indicator sets;
[0070] Optionally, each transaction risk type and risk indicator has a corresponding target weight. By assigning different weights to each transaction risk type and risk indicator, the importance of each transaction risk type and risk indicator for the transaction risk identification result can be better measured to avoid the influence of relatively low-importance transaction risk types or risk indicators on the transaction risk identification result, thereby causing the cross-regional power transaction risk identification result to be determined to be low in accuracy. Among them, the larger the target weight value, the greater the influence of the corresponding transaction risk type or risk indicator on the transaction risk identification result.
[0071] In an optional embodiment, target weights corresponding to multiple transaction risk types and target weights corresponding to risk indicators included in multiple risk indicator sets are determined, including: taking the risk identification results of cross-regional power transactions as the target layer, multiple transaction risk types as the criterion layer, and risk indicators included in multiple risk indicator sets as the decision layer, and using a hierarchical analysis method to determine first weights corresponding to multiple transaction risk types and first weights corresponding to risk indicators included in multiple risk indicator sets; obtaining multiple groups of power transaction data of cross-regional power transactions, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to risk indicators included in multiple risk indicator sets; based on the multiple groups of power transaction data, using an entropy weight method to determine second weights corresponding to multiple transaction risk types and second weights corresponding to risk indicators included in multiple risk indicator sets; based on the first weights and second weights corresponding to the multiple transaction risk types, target weights corresponding to the multiple transaction risk types are obtained; based on the first weights and second weights corresponding to the risk indicators included in the multiple risk indicator sets, target weights corresponding to the risk indicators included in the multiple risk indicator sets are obtained.
[0072] Optionally, the target weight corresponding to each transaction risk type and risk indicator can be comprehensively determined based on multiple methods such as the analytic hierarchy process and the entropy weight method. The above method considers factors more comprehensively, and the target weight calculated on this basis is more accurate and reliable. Specifically, the risk identification result can be used as the target layer, the transaction risk type as the criterion layer, and the risk indicator as the decision layer. The analytic hierarchy process is used to determine the first weight corresponding to each transaction risk type and risk indicator; further based on multiple groups of power transaction data, the entropy weight method is combined to determine the second weight corresponding to each transaction risk type and risk indicator. According to the calculated first weight and second weight, the target weight corresponding to each transaction risk type and risk indicator is comprehensively determined. In the process of determining the risk weight by the above method, the importance of different risk types and risk indicators is comprehensively considered, the influence of subjective factors on the weight is avoided, and the scientificity and accuracy of the decision are improved. At the same time, through the combined application of the analytic hierarchy process and the entropy weight method, the correlation between the indicators can be better considered, and the accuracy and reliability of the weight can be further improved. The target weight and risk indicator weight finally obtained can provide decision makers with a more objective and accurate decision-making basis, which helps to reduce the risk of cross-regional power transactions and improve transaction efficiency.
[0073] In an optional embodiment, the risk identification results of cross-regional electricity transactions are used as the target layer, multiple transaction risk types are used as the criterion layer, and the risk indicators included in multiple risk indicator sets are used as the decision layer. The hierarchical analysis method is used to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets, including: obtaining the scoring results of each transaction risk type in the multiple transaction risk types relative to other transaction risk types, and the scoring results of each risk indicator in the multiple risk indicator sets relative to other risk indicators; based on the scoring results of each transaction risk type relative to other transaction risk types, constructing a criterion layer comparison matrix, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on each risk Based on the scoring results of the indicators relative to other risk indicators, a decision-making layer comparison matrix is constructed, wherein the rows and columns of the decision-making layer comparison matrix are the risk indicators included in the multiple risk indicator sets, and the elements in the decision-making layer comparison matrix are the scoring results of the corresponding risk indicators relative to another risk indicator; based on the criterion layer comparison matrix and the preset first comparison factor, a criterion layer judgment matrix is constructed, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; based on the decision-making layer comparison matrix and the preset second comparison factor, a decision-making layer judgment matrix is constructed, wherein the elements included in the decision-making layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; based on the criterion layer judgment matrix, the first weights corresponding to the multiple transaction risk types are determined; based on the decision-making layer judgment matrix, the first weights corresponding to the risk indicators included in the multiple risk indicator sets are determined.
[0074] Optionally, the multiple transaction risk types in the criterion layer can be scored in pairs based on the expert scoring method, and all risk indicators included in the multiple risk indicator sets in the decision layer can be scored in pairs using the expert scoring method. By taking the average score of multiple expert scoring results, using the three-scale method, the scores of 0-3 points are marked as 0, the scores of 4-6 points are marked as 0.5, and the scores of 7-10 points are marked as 1. Based on the scoring results, a comparison matrix (i.e., a criterion layer comparison matrix and a decision layer comparison matrix) is determined, wherein the total number of rows and the total number of columns of the criterion layer comparison matrix are the total number of multiple transaction risk types, and the total number of rows and the total number of columns of the decision layer comparison matrix are the total number of risk indicators included in the multiple risk indicator sets. By performing corresponding operations on the elements included in the constructed comparison matrix, a judgment matrix (i.e., a criterion layer judgment matrix and a decision layer judgment matrix) for characterizing the importance of each transaction risk type or risk indicator is obtained; and the first weight of each transaction risk type or risk indicator is further determined by the judgment matrix. Among them, the method of obtaining the judgment matrix at the criterion layer is the same as the method of obtaining the judgment matrix at the decision layer. The following takes the transaction risk type as an example to illustrate the specific method of obtaining the judgment matrix.
[0075] For example, the criterion layer comparison matrix can be constructed as follows:
[0076]
[0077] Among them, A is the criterion layer comparison matrix, a ij The value of is {0,0.5,1}, which indicates the importance of the score of the i-column element compared with the j-row element. 0 indicates that the i-column element is less important than the j-row element. A value of 0.5 indicates that the row and column elements are equally important. A value of 1 indicates that the i-column element is more important than the j-row element. The row and column elements in A both represent transaction risk types, and n represents the total number of multiple transaction risk types.
[0078] Based on the elements included in the criterion layer comparison matrix, the criterion layer judgment matrix is constructed in the following way:
[0079]
[0080] Where c represents the comparison factor, s i represents the sum of the i-column-by-row sum of the criterion layer comparison matrix, E represents the criterion layer judgment matrix, and the e in the matrix ij satisfy e ii =e jj =1, the structure of the criterion level comparison matrix is the same as that of the criterion level comparison matrix, and the number of rows and columns of the criterion level comparison matrix are the same as those of the criterion level judgment matrix.
[0081] The construction method of the decision-level comparison matrix and the decision-level judgment matrix is the same as that of the criterion layer comparison matrix and the criterion layer judgment matrix. The difference is that the decision-level comparison matrix and the decision-level judgment matrix are determined based on the risk indicators included in the risk indicator sets corresponding to multiple transaction risk types, which will not be repeated here.
[0082] Optionally, the method for obtaining the first weight corresponding to each transaction risk type is the same as the first weight of the risk indicator. The specific method for obtaining the first weight is described below using the transaction risk type as an example.
[0083] In an optional embodiment, based on the criterion layer judgment matrix, determining first weights corresponding to the plurality of transaction risk types respectively; based on the decision layer judgment matrix, determining first weights corresponding to the risk indicators included in the plurality of risk indicator sets respectively, including: obtaining the first weight corresponding to any transaction risk type among the plurality of transaction risk types by the following method:
[0084]
[0085] Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij (j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of multiple transaction risk types; based on the criterion layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the multiple transaction risk types; based on the decision layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0086] In the above method, the first weights of the multiple transaction risk types of the corresponding criterion layer are calculated by introducing the feature vector, η c =[η1,η2,η3,...,η n ] T That is, it represents a feature vector composed of first weights corresponding to multiple transaction risk types.
[0087] It should be noted that each element of the criterion layer judgment matrix is used to indicate the importance of a certain transaction risk type relative to other transaction risk types in the criterion layer; for example, ij It can be understood as the importance of the i-th transaction risk type relative to the j-th transaction risk type among multiple transaction risk types. The cumulative multiplication of the importance of each transaction risk type relative to other transaction risk types in the criterion layer judgment matrix can be obtained to determine the average importance of each transaction risk type relative to other transaction risk types. The average importance of all transaction risk types can be obtained. The first weight obtained by calculating the ratio of the two can accurately reflect the relative importance of each transaction risk type among all transaction risk types.
[0088] In an optional embodiment, after determining the first weights corresponding to the multiple transaction risk types respectively based on the criterion layer judgment matrix; and determining the first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively based on the decision layer judgment matrix, the method also includes: performing a consistency check on the first weights corresponding to the multiple transaction risk types respectively, and performing a consistency check on the first weights corresponding to the risk indicators included in the multiple risk indicator sets; if the consistency check on the first weights corresponding to the multiple transaction risk types fails, and / or the consistency check on the first weights corresponding to the risk indicators included in the multiple risk indicator sets fails, updating the criterion layer judgment matrix and / or the decision layer judgment matrix; determining new first weights corresponding to the multiple transaction risk types respectively based on the updated criterion layer judgment matrix; and / or determining new first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively based on the decision layer judgment matrix.
[0089] Optionally, after obtaining the first weight of each transaction risk type or risk indicator, the obtained first weight can be further checked for consistency, thereby improving the accuracy of obtaining the first weight, so that the obtained first weight can more truly reflect the importance of the corresponding transaction risk type or risk indicator. If the consistency check passes, the calculated first weights corresponding to the various transaction risk types, or the first weights corresponding to the risk indicators included in the multiple risk indicator sets, can be used for subsequent cross-regional power transaction risk identification; otherwise, the corresponding comparison matrix (i.e., the criterion layer comparison matrix or the decision layer comparison matrix) is adjusted, and the corresponding first weight is recalculated to ensure that the calculated first weight is more accurate and reliable.
[0090] Optionally, the consistency check of the first weights corresponding to the various transaction risk types may be performed in the following manner, but is not limited to the following manner. The consistency check index CI value may be obtained in the following manner, but is not limited to the following manner:
[0091]
[0092] Among them, η max represents the maximum value of the first weights corresponding to the multiple transaction risk types, and n represents the total number of the multiple transaction risk types;
[0093] Find the average random consistency index RI value corresponding to the calculated CI by querying the average random consistency index RI table;
[0094] Based on the CI value and the RI value, the consistency ratio CR is calculated as follows:
[0095]
[0096] Among them, when CR<0.1, it can be considered that the criterion layer judgment matrix meets the consistency, that is, the first weights corresponding to various transaction risk types have passed the consistency test; otherwise, it is necessary to readjust the criterion layer comparison matrix.
[0097] It should be noted that the consistency check method of the first weights corresponding to the risk indicators included in the multiple risk indicator sets is the same as the consistency check method of the first weights corresponding to the multiple transaction risk types, which will not be repeated here.
[0098] Optionally, based on multiple groups of electricity trading data, the entropy weight method can be used to determine the second weights corresponding to multiple trading risk types, and the second weights corresponding to the risk indicators included in multiple risk indicator sets. Each group of electricity trading data in the multiple groups of electricity trading data corresponds to an evaluation scheme, and each group of electricity trading data includes indicator values of risk indicators included in multiple risk indicator sets, and scoring values corresponding to multiple trading risk types, wherein the scoring value can be determined based on the indicator value of the risk indicator included in the corresponding risk indicator set. For example, it can be a comprehensive evaluation made by experts in advance based on the indicator values of each indicator in each group of electricity trading data, and is used to evaluate the possibility of trading risks in the electricity trading data caused by the corresponding trading risk type.
[0099] Specifically, based on multiple groups of power transaction data, the entropy weight method can be used to determine the second weights corresponding to the various transaction risk types in the following manner:
[0100] The scoring values corresponding to the various transaction risk types can be determined from the multiple sets of power transaction data to obtain multiple sets of transaction risk type scoring data. Based on the multiple sets of transaction risk type scoring data, an evaluation matrix in the following form is constructed:
[0101]
[0102] Among them, T * represents the evaluation matrix. The total number of rows in the evaluation matrix, m, is the total number of groups of transaction risk type scoring data (i.e., the total number of evaluation schemes). The total number of columns in the evaluation matrix, n, is the total number of multiple transaction risk types. xy(x=1,2,3...,m,y=1,2,3...,n) represents the score value of the xth transaction risk type in the yth group of transaction risk type score data (i.e., the yth evaluation scheme); the evaluation matrix is standardized in the following form:
[0103]
[0104] The evaluation matrix after the standard is calculated by the above formula is T = (r xy ) n×m , the second weight η corresponding to any transaction risk type among multiple transaction risk types is further calculated by the following formula: x :
[0105]
[0106] η s =[η1,η2,η3,...,η n ] T
[0107] Among them, H x is entropy, η x is the entropy weight corresponding to the transaction risk type x, that is, the second weight corresponding to the transaction risk type x, η x satisfy The size of the entropy weight reflects the importance of the corresponding indicator. The closer it is to 1, the more important the transaction risk type is. On the contrary, the closer it is to 0, the less important the transaction risk type is.
[0108] It should be noted that the method for obtaining the second weights corresponding to the risk indicators included in the multiple risk indicator sets is the same as the method for obtaining the second weights corresponding to the multiple transaction risk types. The difference lies in the different application data, which will not be repeated here.
[0109] In an optional embodiment, based on the first weights and the second weights corresponding to the multiple transaction risk types, target weights corresponding to the multiple transaction risk types are obtained; based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets, target weights corresponding to the risk indicators included in the multiple risk indicator sets are obtained, including: obtaining the target weight corresponding to any transaction risk type among the multiple transaction risk types by:
[0110]
[0111] Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η srepresents the second weight corresponding to any transaction risk type, d1 and d2 represent the linear combination coefficients to be solved, d1' represents the result obtained by normalizing d1, and d'2 represents the result obtained by normalizing d2; based on the first weights and second weights corresponding to a plurality of transaction risk types, respectively, a method of obtaining the target weight corresponding to any transaction risk type is adopted to obtain the target weights corresponding to the plurality of transaction risk types; based on the first weights and second weights corresponding to the risk indicators included in a plurality of risk indicator sets, respectively, a method of obtaining the target weight corresponding to any transaction risk type is adopted to obtain the target weights corresponding to the risk indicators included in a plurality of risk indicator sets.
[0112] Optionally, the above method for calculating the target weight based on the first weight and the second weight can be understood as a game theory comprehensive weighting method, through which the first weight of each transaction risk type (or risk indicator) is first combined with the corresponding second weight, and the target weight obtained is the comprehensive weight. In the above method, the weights obtained by combining the analytic hierarchy process and the entropy weight method are obtained by the game theory comprehensive weighting method to obtain a comprehensive weight, thereby achieving a balance between the subjective and objective.
[0113] Step S106, determining target power transaction data for cross-regional power transaction;
[0114] Optionally, the target power transaction data includes at least indicator values corresponding to the risk indicators included in multiple risk indicator sets.
[0115] Step S108, determining the risk identification result of the cross-regional power transaction based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0116] Optionally, each transaction risk type and risk indicator corresponds to a corresponding target weight. By assigning different weights to each transaction risk type and risk indicator, the importance of each transaction risk type and risk indicator to the transaction risk identification results can be better measured. The risk identification results of cross-regional power transactions calculated on this basis are also more accurate and reliable.
[0117] In an optional embodiment, based on target power trading data, target weights corresponding to multiple trading risk types, and target weights corresponding to risk indicators included in multiple risk indicator sets, the risk identification result of cross-regional power trading is determined, including: based on target power trading data and the target weights of risk indicators corresponding to multiple trading risk types, obtaining risk scores corresponding to multiple trading risk types; based on the risk scores corresponding to multiple trading risk types, and the target weights of risk indicators corresponding to multiple trading risk types, obtaining a total risk score for cross-regional power trading; using the risk scores corresponding to multiple trading risk types and / or the total risk score as the risk identification result for cross-regional power trading.
[0118] Optionally, based on the target weights corresponding to the various transaction risk types and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, the indicator values included in the target power transaction data are weighted and calculated, and the weighted calculation results are used as the risk identification results of cross-regional power transactions. Specifically, weighted calculations can be first performed based on the target weights of each indicator value and the corresponding risk indicator in the target power transaction data to obtain the risk scores corresponding to the various transaction risk types. Through the risk scores corresponding to the various transaction risk types, the possibility of each transaction risk type in cross-regional power transactions can be measured; further, based on the target weights of each transaction risk type, the risk scores corresponding to the various transaction risk types are weighted and calculated to obtain the total risk score of cross-regional power transactions. The risk scores corresponding to the various transaction risk types and / or the total risk score can be used together as the risk identification results of cross-regional power transactions. According to the above risk identification results, not only can it be identified whether there is a transaction risk in cross-regional power transactions, but also the main cause of the transaction risk can be further determined.
[0119] Optionally, before determining the total risk score of cross-regional electricity transactions, it is necessary to normalize some risk indicator values in the target electricity transaction data so as to determine the total risk score of cross-regional electricity transactions based on the normalized data, so as to avoid interference in the calculation of the total risk score due to numerical differences in different transaction indicators.
[0120] Optionally, the index values corresponding to the aforementioned indicators such as the difference ratio between the converted power of the buyer node and the actual power sent by the seller node B5, the difference between the transaction price and the quotation B6, the peak-to-valley difference of the transaction price B7, the difference between the maximum transaction price and the average transaction price B8, the difference between the declared power price and the average declared power price B9, the growth rate of thermal power cost B11, and the maximum quotation difference B15 can be normalized. For the difference data, the 3-scaling method can be used to perform normalization in the following way:
[0121]
[0122] Among them, Bi (i = 5, 6, 7, 8, 9, 11, 15) represents the index value of the corresponding risk index, and D5 is the actual power value of power 卖电 , D6 is the reported value, D7 is the lowest transaction price, D8 is the average transaction price, D9 is the average reported electricity value, D11 is 1, and D15 is the highest reported value.
[0123] The negative correlation indicators mentioned above are standardized using the following formula.
[0124] Bi=|1-Bi|
[0125] Optionally, after determining the total risk score of cross-regional power transactions, the transaction risk level of cross-regional power transactions can be further determined according to the total risk score of cross-regional power transactions (i.e., the cross-regional power transaction risk value F), and the obtained transaction risk level can be used as the risk identification result of cross-regional power transactions. Specifically, the risk level of regional power transactions can be divided as follows: when 1>F≥0.7, the risk level is high and a red warning appears; when 0.7>F≥0.4, the risk level is medium and a yellow warning appears; when 0.4>F≥0, the risk level is low and no warning appears.
[0126] Through the above steps S102 to S108, it is possible to assign corresponding weights from the two levels of transaction risk type and risk indicator, and identify the risks of cross-regional power transactions based on the obtained weights and the corresponding power transaction data, thereby achieving the technical effect of accurately identifying the risks of cross-regional power transactions and reducing the risks of cross-regional power transactions, thereby solving the technical problem that the relevant technologies mainly focus on the identification of risks in regional power transactions, lack consideration of the identification of risks in cross-regional power transactions, and thus cannot perceive the risks of cross-regional power transactions in advance.
[0127] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode: Figure 2 is a flow chart of an optional cross-regional power transaction risk identification method according to an embodiment of the present invention, such as Figure 2 As shown, the method includes:
[0128] S1: Clarify the risk indicators in cross-regional power market transactions, provide the evaluation criteria for each risk indicator, and define the calculation method of risk indicators;
[0129] S2: Based on the analytic hierarchy process, the target layer, criterion layer, and decision layer are constructed. The target layer is used to measure the risk identification results of cross-regional power market transactions. The criterion layer is divided into market transaction volume risk, market price risk, and market power risk according to the risk type. The decision layer is a series of specific risk indicators for data quantification of the risk type of the criterion layer;
[0130] S3: Using a full score of 10, experts compare each other to score the indicators of the criterion layer and the corresponding decision-making layer. By taking the average score and using the three-scale method, the scores of 0-3 points are marked as 0, 4-6 points are marked as 0.5, and 7-10 points are marked as 1, and the judgment matrix of the criterion layer and the judgment matrix of the decision-making layer are obtained;
[0131] S4: Calculate the weight of each indicator according to the eigenvalue method and perform consistency check. If the judgment matrix meets the definition of the consistency matrix, the weight allocation is successful, otherwise return to step S3 to re-score;
[0132] S5: Use the entropy weight method to calculate the corresponding objective weights of each indicator at the criterion layer and the decision layer;
[0133] S6: linearly combine the weight obtained in step S4 and the weight obtained in step S5 by using a comprehensive weighting method based on game theory to obtain a comprehensive weight;
[0134] S7: Input the target transaction data to obtain the original data of each indicator of the decision-making layer and obtain the normalized data. Use the comprehensive weight obtained in step S6 to calculate the cross-regional electricity market transaction risk value F. It is stipulated that when 1>F≥0.7, the risk level is high and a red warning appears; when 0.7>F≥0.4, the risk level is medium and a yellow warning appears; when 0.4>F≥0, the risk level is low and no warning appears.
[0135] This embodiment provides a data-driven comprehensive assessment method for cross-regional power market transaction risks. The method establishes a cross-regional power market transaction data set, and uses a combination of a three-scale analytic hierarchy process and an entropy weight method to assess cross-regional power market risks, including establishing a cross-regional power market risk assessment index system, establishing an improved analytic hierarchy process (IAHP) model, and realizing a comprehensive assessment of cross-regional power market transaction risks. This embodiment solves the problem of different risk indicators caused by different transaction modes, processes, and market entities in cross-regional power transactions, and forms a comprehensive and feasible risk assessment index system that adapts to new cross-regional power market transaction risks. At the same time, the improved analytic hierarchy process is used to achieve a comprehensive assessment of cross-regional power market transaction risks, and provide risk warnings for cross-regional power market transactions.
[0136] It should be noted that in this embodiment, the differences in cross-regional power transactions are fully considered, and new evaluation indicators with strong correlation, such as market power, are proposed, which reduces indicators with weak correlation or irrelevant indicators such as prediction accuracy and system backup capacity, thereby improving the accuracy and rapidity of risk assessment. Compared with a single evaluation method, the subjective and objective comprehensive evaluation algorithm of the combined hierarchical analysis method and entropy weight method adopted in this embodiment can reflect the relationship between subjective value judgment and objective risk, overcome one-sidedness, and improve the practical usability of cross-regional power transaction risk assessment.
[0137] In this embodiment, a cross-regional power trading risk identification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0138] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing the above-mentioned cross-regional power transaction risk identification method. Figure 3 is a schematic diagram of the structure of a device for identifying risks of cross-regional power transactions according to an embodiment of the present invention. Figure 3 As shown, the above-mentioned cross-regional power transaction risk identification device includes: an indicator acquisition module 300, a weight determination module 302, a data determination module 304, and a risk identification module 306, wherein:
[0139] The indicator acquisition module 300 is used to acquire multiple transaction risk types corresponding to cross-regional power transactions and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond to the multiple risk indicator sets one by one;
[0140] The weight determination module 302 is connected to the indicator acquisition module 300 and is used to determine the target weights corresponding to the multiple transaction risk types and the target weights corresponding to the risk indicators included in the multiple risk indicator sets;
[0141] The data determination module 304 is connected to the weight determination module 302 and is used to determine the target power transaction data of the cross-regional power transaction, wherein the target power transaction data at least includes the indicator values corresponding to the risk indicators included in the plurality of risk indicator sets;
[0142] The risk identification module 306 is connected to the data determination module 304, and is used to determine the risk identification results of cross-regional power transactions based on the target power transaction data, the target weights corresponding to multiple transaction risk types, and the target weights corresponding to the risk indicators included in multiple risk indicator sets.
[0143] In an embodiment of the present invention, an indicator acquisition module 300 is set to obtain multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond one-to-one to the multiple risk indicator sets; a weight determination module 302 is connected to the indicator acquisition module 300, and is used to determine the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets; a data determination module 304 is connected to the weight determination module 302, and is used to determine the target power transaction data of the cross-regional power transaction, wherein the target power transaction data at least includes the indicator values corresponding to the risk indicators included in the multiple risk indicator sets; a risk identification module 306 ... It is connected to the data determination module 304, and is used to determine the risk identification result of cross-regional power trading based on the target power trading data, the target weights corresponding to the multiple trading risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, so as to achieve the purpose of assigning corresponding weights from the two levels of trading risk type and risk indicator, and identifying the risks of cross-regional power trading based on the obtained weights and the corresponding power trading data, thereby achieving the technical effect of accurately identifying the risks of cross-regional power trading to reduce the risks of cross-regional power trading, and further solves the technical problem that the related technology mainly focuses on the risk identification of power trading within the region, lacks consideration of the risk identification of cross-regional power trading, and thus cannot perceive the risks of cross-regional power trading in advance.
[0144] Optionally, the weight determination module includes: a first determination module, which uses the risk identification results of cross-regional power transactions as the target layer, multiple transaction risk types as the criterion layer, and the risk indicators included in multiple risk indicator sets as the decision layer, and adopts the hierarchical analysis method to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets; a first acquisition module, which is used to obtain multiple groups of power transaction data of cross-regional power transactions, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; a second determination module, which is used to determine the second weights corresponding to the multiple transaction risk types, and the second weights corresponding to the risk indicators included in the multiple risk indicator sets based on the multiple groups of power transaction data by using the entropy weight method; a second acquisition module, which is used to obtain the target weights corresponding to the multiple transaction risk types based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets; and obtain the target weights corresponding to the risk indicators included in the multiple risk indicator sets based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0145] Optionally, the first determination module includes: a first acquisition submodule, used to obtain the scoring results of each transaction risk type in multiple transaction risk types relative to other transaction risk types, and the scoring results of each risk indicator in multiple risk indicator sets relative to other risk indicators; a first construction submodule, used to construct a criterion layer comparison matrix based on the scoring results of each transaction risk type relative to other transaction risk types, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on the scoring results of each risk indicator relative to other risk indicators, a decision layer comparison matrix is constructed, wherein the rows and columns of the decision layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other risk indicators, The risk indicators included are: the elements in the decision-making layer comparison matrix are the scoring results of the corresponding risk indicators relative to another risk indicator; the second construction submodule is used to construct a criterion layer judgment matrix based on the criterion layer comparison matrix and a preset first comparison factor, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; based on the decision-making layer comparison matrix and the preset second comparison factor, a decision-making layer judgment matrix is constructed, wherein the elements included in the decision-making layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; the first determination submodule is used to determine the first weights corresponding to multiple transaction risk types respectively based on the criterion layer judgment matrix; based on the decision-making layer judgment matrix, determine the first weights corresponding to the risk indicators included in multiple risk indicator sets respectively.
[0146] Optionally, the first determination submodule is further used to obtain a first weight corresponding to any transaction risk type among multiple transaction risk types in the following manner:
[0147]
[0148] Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij (j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of multiple transaction risk types; based on the criterion layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the multiple transaction risk types; based on the decision layer judgment matrix, the first weight corresponding to any transaction risk type is obtained to obtain the first weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0149] Optionally, the above-mentioned device also includes: a first verification module, which is used to perform consistency verification on the first weights corresponding to the multiple transaction risk types, and to perform consistency verification on the first weights corresponding to the risk indicators included in multiple risk indicator sets; a first updating module, which is used to update the criterion layer judgment matrix and / or the decision layer judgment matrix when the consistency verification of the first weights corresponding to the multiple transaction risk types fails and / or the consistency verification of the first weights corresponding to the risk indicators included in multiple risk indicator sets fails; a third determination module, which is used to determine the new first weights corresponding to the multiple transaction risk types based on the updated criterion layer judgment matrix; and / or to determine the new first weights corresponding to the risk indicators included in multiple risk indicator sets based on the decision layer judgment matrix.
[0150] Optionally, the second acquisition module is further used to obtain a target weight corresponding to any transaction risk type among multiple transaction risk types by:
[0151]
[0152] Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η s represents the second weight corresponding to any transaction risk type, d1 and d2 represent the linear combination coefficients to be solved, d1' represents the result obtained by normalizing d1, and d'2 represents the result obtained by normalizing d2; based on the first weights and second weights corresponding to a plurality of transaction risk types, respectively, a method of obtaining the target weight corresponding to any transaction risk type is adopted to obtain the target weights corresponding to the plurality of transaction risk types; based on the first weights and second weights corresponding to the risk indicators included in a plurality of risk indicator sets, respectively, a method of obtaining the target weight corresponding to any transaction risk type is adopted to obtain the target weights corresponding to the risk indicators included in a plurality of risk indicator sets.
[0153] Optionally, the above-mentioned risk identification module includes: a first scoring module, which is used to obtain risk scores corresponding to multiple transaction risk types based on target power transaction data and target weights of risk indicators corresponding to multiple transaction risk types; a second scoring module, which is used to obtain a total risk score for cross-regional power transactions based on the risk scores corresponding to multiple transaction risk types and target weights of risk indicators corresponding to multiple transaction risk types; and a third scoring module, which is used to use the risk scores corresponding to multiple transaction risk types and / or the total risk score as risk identification results for cross-regional power transactions.
[0154] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0155] It should be noted that the above-mentioned indicator acquisition module 300, weight determination module 302, data determination module 304, and risk identification module 306 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment. It should be noted that the above-mentioned modules can be run in a computer terminal as part of the device.
[0156] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.
[0157] The above-mentioned cross-regional electricity trading risk identification device may also include a processor and a memory. The above-mentioned indicator acquisition module 300, weight determination module 302, data determination module 304, risk identification module 306, etc. are all stored in the memory as program modules, and the processor executes the above-mentioned program modules stored in the memory to realize the corresponding functions.
[0158] The processor includes a kernel, which retrieves the corresponding program module from the memory. The kernel may be one or more. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory includes at least one memory chip.
[0159] According to an embodiment of the present invention, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute any of the above-mentioned cross-regional power transaction risk identification methods.
[0160] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group, and the non-volatile storage medium includes a stored program.
[0161] Optionally, when the program is running, the device where the non-volatile storage medium is located is controlled to perform the following functions: obtain multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond one-to-one to the multiple risk indicator sets; determine target weights corresponding to the multiple transaction risk types, and target weights corresponding to the risk indicators included in the multiple risk indicator sets; determine target power transaction data for cross-regional power transactions, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; determine the risk identification results of cross-regional power transactions based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0162] According to an embodiment of the present invention, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein when the program is run, any of the above-mentioned cross-regional power transaction risk identification methods is executed.
[0163] According to an embodiment of the present invention, there is also provided an embodiment of a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes any one of the above-mentioned steps of the cross-regional electricity trading risk identification method.
[0164] Optionally, the above-mentioned computer program product, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond one-to-one to the multiple risk indicator sets; determining target weights corresponding to the multiple transaction risk types, and target weights corresponding to the risk indicators included in the multiple risk indicator sets; determining target power transaction data for cross-regional power transactions, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; determining the risk identification results of cross-regional power transactions based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
[0165] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the program: obtaining a plurality of transaction risk types corresponding to cross-regional power transactions, and a plurality of risk indicator sets corresponding to the plurality of transaction risk types, wherein the plurality of transaction risk types correspond one-to-one to the plurality of risk indicator sets; determining target weights corresponding to the plurality of transaction risk types, and target weights corresponding to the risk indicators included in the plurality of risk indicator sets; determining target power transaction data for cross-regional power transactions, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the plurality of risk indicator sets; determining a risk identification result for cross-regional power transactions based on the target power transaction data, the target weights corresponding to the plurality of transaction risk types, and the target weights corresponding to the risk indicators included in the plurality of risk indicator sets.
[0166] The above sequence of the embodiments of the present invention is for description only and does not represent the superiority or inferiority of the embodiments.
[0167] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0168] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above modules can be a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.
[0169] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.
[0170] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.
[0171] If the above-mentioned integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present invention is essentially 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. The computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0172] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for identifying risks in cross-regional power transactions. It is characterized in that include: Acquire multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond to the multiple risk indicator sets one-to-one; Determining target weights corresponding to the plurality of transaction risk types, and target weights corresponding to the risk indicators included in the plurality of risk indicator sets; Determining target power transaction data of the inter-regional power transaction, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the plurality of risk indicator sets; Based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, the risk identification result of the cross-regional power transaction is determined.
2. The method according to claim 1, It is characterized in that The determining of the target weights respectively corresponding to the multiple transaction risk types and the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets includes: Taking the risk identification result of the cross-regional power transaction as the target layer, the multiple transaction risk types as the criterion layer, and the risk indicators included in the multiple risk indicator sets as the decision layer, a hierarchical analysis method is used to determine the first weights corresponding to the multiple transaction risk types, and the first weights corresponding to the risk indicators included in the multiple risk indicator sets; Acquire multiple groups of power transaction data of the cross-regional power transaction, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; Based on the multiple groups of power transaction data, using an entropy weight method, determining second weights corresponding to the multiple transaction risk types, and second weights corresponding to the risk indicators included in the multiple risk indicator sets; Based on the first weights and the second weights respectively corresponding to the multiple transaction risk types, the target weights respectively corresponding to the multiple transaction risk types are obtained; based on the first weights and the second weights respectively corresponding to the risk indicators included in the multiple risk indicator sets, the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets are obtained.
3. The method according to claim 2, It is characterized in that The method uses the risk identification result of the cross-regional power transaction as the target layer, the multiple transaction risk types as the criterion layer, and the risk indicators included in the multiple risk indicator sets as the decision layer, and adopts the hierarchical analysis method to determine the first weights corresponding to the multiple transaction risk types and the first weights corresponding to the risk indicators included in the multiple risk indicator sets, including: Obtaining scoring results of each transaction risk type in the plurality of transaction risk types relative to other transaction risk types, and scoring results of each risk indicator in the plurality of risk indicator sets relative to other risk indicators; Based on the scoring results of each transaction risk type relative to other transaction risk types, a criterion layer comparison matrix is constructed, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on the scoring results of each risk indicator relative to other risk indicators, a decision layer comparison matrix is constructed, wherein the rows and columns of the decision layer comparison matrix are risk indicators included in multiple risk indicator sets, and the elements in the decision layer comparison matrix are the scoring results of the corresponding risk indicator relative to another risk indicator; Based on the criterion layer comparison matrix and the preset first comparison factor, a criterion layer judgment matrix is constructed, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; based on the decision layer comparison matrix and the preset second comparison factor, a decision layer judgment matrix is constructed, wherein the elements included in the decision layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; Based on the criterion layer judgment matrix, first weights corresponding to the multiple transaction risk types are determined; based on the decision layer judgment matrix, first weights corresponding to the risk indicators included in the multiple risk indicator sets are determined.
4. The method according to claim 3, It is characterized in that Determining first weights corresponding to the plurality of transaction risk types respectively based on the criterion layer judgment matrix; Determining first weights corresponding to the risk indicators included in the plurality of risk indicator sets based on the decision-making layer judgment matrix includes: The first weight corresponding to any transaction risk type among the multiple transaction risk types is obtained in the following manner: Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij (j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of the multiple transaction risk types; Based on the criterion layer judgment matrix, obtaining the first weights corresponding to any one of the transaction risk types, respectively obtaining the first weights corresponding to the multiple transaction risk types; Based on the decision-making layer judgment matrix, the first weights corresponding to the risk indicators included in the plurality of risk indicator sets are obtained by obtaining the first weight corresponding to any one of the transaction risk types.
5. The method according to claim 3, It is characterized in that Determining first weights corresponding to the plurality of transaction risk types respectively based on the criterion layer judgment matrix; After determining first weights respectively corresponding to the risk indicators included in the plurality of risk indicator sets based on the decision-making layer judgment matrix, the method further includes: Performing consistency checks on the first weights respectively corresponding to the multiple transaction risk types, and performing consistency checks on the first weights respectively corresponding to the risk indicators included in the multiple risk indicator sets; When the first weights corresponding to the plurality of transaction risk types respectively fail to pass the consistency check and / or the first weights corresponding to the risk indicators included in the plurality of risk indicator sets respectively fail to pass the consistency check, the criterion layer judgment matrix and / or the decision layer judgment matrix are updated; Based on the updated criterion layer judgment matrix, determine the new first weights corresponding to the multiple transaction risk types respectively; and / or based on the decision layer judgment matrix, determine the new first weights corresponding to the risk indicators included in the multiple risk indicator sets respectively.
6. The method according to claim 2, It is characterized in that The target weights corresponding to the multiple transaction risk types are obtained based on the first weights and the second weights corresponding to the multiple transaction risk types respectively; Based on the first weights and the second weights respectively corresponding to the risk indicators included in the plurality of risk indicator sets, Obtaining target weights corresponding to the risk indicators included in the plurality of risk indicator sets, including: The target weight corresponding to any transaction risk type among the multiple transaction risk types is obtained in the following manner: Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η s represents the second weight corresponding to any transaction risk type, d 1 ,d 2 represents the linear combination coefficient to be solved, d 1 ' indicates that the d 1 The normalized result is d' 2 Indicates that the 2 The result obtained by normalization; Based on the first weights and the second weights respectively corresponding to the multiple transaction risk types, the target weights respectively corresponding to the multiple transaction risk types are obtained by adopting a method of obtaining the target weight corresponding to any one of the transaction risk types; Based on the first weights and the second weights respectively corresponding to the risk indicators included in the multiple risk indicator sets, the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets are obtained by obtaining the target weight corresponding to any transaction risk type.
7. The method according to any one of claims 1 to 6, It is characterized in that The determining of the risk identification result of the cross-regional power transaction based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets, includes: Based on the target power transaction data and the target weights of the risk indicators corresponding to the multiple transaction risk types, obtaining risk scores corresponding to the multiple transaction risk types respectively; Based on the risk scores corresponding to the multiple transaction risk types, respectively, and the target weights of the risk indicators corresponding to the multiple transaction risk types, obtaining a total risk score of the cross-regional power transaction; The risk scores respectively corresponding to the multiple transaction risk types and / or the total risk score are used as the risk identification result of the cross-regional electricity transaction.
8. A device for identifying risks in cross-regional power transactions. It is characterized in that include: An indicator acquisition module, used to acquire multiple transaction risk types corresponding to cross-regional power transactions, and multiple risk indicator sets corresponding to the multiple transaction risk types, wherein the multiple transaction risk types correspond to the multiple risk indicator sets one-to-one; A weight determination module, used to determine target weights corresponding to the plurality of transaction risk types, and target weights corresponding to the risk indicators included in the plurality of risk indicator sets; A data determination module, configured to determine target power transaction data of the inter-regional power transaction, wherein the target power transaction data at least includes indicator values corresponding to the risk indicators included in the plurality of risk indicator sets; A risk identification module is used to determine the risk identification result of the cross-regional power transaction based on the target power transaction data, the target weights corresponding to the multiple transaction risk types, and the target weights corresponding to the risk indicators included in the multiple risk indicator sets.
9. The device according to claim 8, It is characterized in that The weight determination module comprises: A first determination module is used to use the risk identification result of the cross-regional power transaction as a target layer, the multiple transaction risk types as a criterion layer, and the risk indicators included in the multiple risk indicator sets as a decision layer, and use a hierarchical analysis method to determine the first weights corresponding to the multiple transaction risk types and the first weights corresponding to the risk indicators included in the multiple risk indicator sets; A first acquisition module is used to acquire multiple groups of power transaction data of the cross-regional power transaction, wherein each group of power transaction data in the multiple groups of power transaction data includes indicator values corresponding to the risk indicators included in the multiple risk indicator sets; A second determination module is used to determine, based on the multiple groups of power transaction data, the second weights corresponding to the multiple transaction risk types and the second weights corresponding to the risk indicators included in the multiple risk indicator sets by using an entropy weight method; The second acquisition module is used to obtain the target weights corresponding to the multiple transaction risk types based on the first weights and the second weights corresponding to the multiple transaction risk types respectively; and to obtain the target weights corresponding to the risk indicators included in the multiple risk indicator sets based on the first weights and the second weights corresponding to the risk indicators included in the multiple risk indicator sets respectively.
10. The device according to claim 9, It is characterized in that The first determining module includes: A first acquisition submodule is used to acquire the scoring results of each transaction risk type in the multiple transaction risk types relative to other transaction risk types, and the scoring results of each risk indicator in the multiple risk indicator sets relative to other risk indicators; A first construction submodule is used to construct a criterion layer comparison matrix based on the scoring results of each transaction risk type relative to other transaction risk types, wherein the rows and columns of the criterion layer comparison matrix are multiple transaction risk types, and the elements in the criterion layer comparison matrix are the scoring results of the corresponding transaction risk type relative to other transaction risk types; based on the scoring results of each risk indicator relative to other risk indicators, a decision layer comparison matrix is constructed, wherein the rows and columns of the decision layer comparison matrix are risk indicators included in multiple risk indicator sets, and the elements in the decision layer comparison matrix are the scoring results of the corresponding risk indicator relative to another risk indicator; A second construction submodule is used to construct a criterion layer judgment matrix based on the criterion layer comparison matrix and the preset first comparison factor, wherein the elements included in the criterion layer judgment matrix are used to indicate the importance of the corresponding transaction risk type relative to other risk types; and to construct a decision layer judgment matrix based on the decision layer comparison matrix and the preset second comparison factor, wherein the elements included in the decision layer judgment matrix are used to indicate the importance of the corresponding risk indicator relative to other indicators; The first determination submodule is used to determine the first weights corresponding to the multiple transaction risk types based on the criterion layer judgment matrix; based on the decision layer judgment matrix, determine the first weights corresponding to the risk indicators included in the multiple risk indicator sets.
11. The device according to claim 10, It is characterized in that The first determining submodule is further used for: The first weight corresponding to any transaction risk type among the multiple transaction risk types is obtained in the following manner: Among them, η i represents the first weight corresponding to any transaction risk type; i is the row identifier corresponding to any transaction risk type in the criterion layer judgment matrix; e ij (j=1, 2, ..., n) represents the element in the i-th row and j-th column in the criterion layer judgment matrix; n is the total number of the multiple transaction risk types; Based on the criterion layer judgment matrix, obtaining the first weights corresponding to any one of the transaction risk types, respectively obtaining the first weights corresponding to the multiple transaction risk types; Based on the decision-making layer judgment matrix, the first weights corresponding to the risk indicators included in the plurality of risk indicator sets are obtained by obtaining the first weight corresponding to any one of the transaction risk types.
12. The device according to claim 10, It is characterized in that The device also includes: A first verification module, configured to perform consistency verification on the first weights respectively corresponding to the plurality of transaction risk types, and to perform consistency verification on the first weights respectively corresponding to the risk indicators included in the plurality of risk indicator sets; A first updating module, configured to update the criterion layer judgment matrix and / or the decision layer judgment matrix when the first weights corresponding to the plurality of transaction risk types respectively fail to pass the consistency check and / or the first weights corresponding to the risk indicators included in the plurality of risk indicator sets respectively fail to pass the consistency check; The third determination module is used to determine the new first weights corresponding to the multiple transaction risk types based on the updated criterion layer judgment matrix; and / or to determine the new first weights corresponding to the risk indicators included in the multiple risk indicator sets based on the decision layer judgment matrix.
13. The device according to claim 9, It is characterized in that The second acquisition module is also used for: The target weight corresponding to any transaction risk type among the multiple transaction risk types is obtained in the following manner: Where W represents the target weight corresponding to any transaction risk type, η c represents the first weight corresponding to any transaction risk type, η s represents the second weight corresponding to any transaction risk type, d 1 ,d 2 represents the linear combination coefficient to be solved, d 1 ' indicates that the d 1 The normalized result is d' 2 Indicates that the 2 The result obtained by normalization; Based on the first weights and the second weights respectively corresponding to the multiple transaction risk types, the target weights respectively corresponding to the multiple transaction risk types are obtained by adopting a method of obtaining the target weight corresponding to any one of the transaction risk types; Based on the first weights and the second weights respectively corresponding to the risk indicators included in the multiple risk indicator sets, the target weights respectively corresponding to the risk indicators included in the multiple risk indicator sets are obtained by obtaining the target weight corresponding to any transaction risk type.
14. The device according to any one of claims 8 to 13, It is characterized in that The risk identification module includes: A first scoring module is used to obtain risk scores corresponding to the multiple transaction risk types respectively based on the target power transaction data and the target weights of the risk indicators corresponding to the multiple transaction risk types; A second scoring module is used to obtain a total risk score of the cross-regional power transaction based on the risk scores corresponding to the multiple transaction risk types and the target weights of the risk indicators corresponding to the multiple transaction risk types; The third scoring module is used to use the risk scores corresponding to the multiple transaction risk types and / or the total risk score as the risk identification result of the cross-regional power transaction.
15. A non-volatile storage medium, It is characterized in that The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the cross-regional electricity trading risk identification method described in any one of claims 1 to 7.
16. An electronic device, It is characterized in that It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the cross-regional electricity trading risk identification method as described in any one of claims 1 to 7.
