Abnormal bidding behavior identification method and system of electricity market subject behavior characteristics

Abstract

The invention belongs to the technical field of market transaction risk prevention and control, and particularly relates to an abnormal bidding behavior recognition method and system for electricity market subject behavior characteristics, and the method comprises the steps: constructing a market subject abnormal bidding behavior characteristic set through employing a series of algorithms based on the historical operation data of all market subjects in an electricity market; acquiring market operation data of a to-be-detected market subject, and comparing the market operation data with the market subject abnormal behavior feature set; according to a comparison result, determining whether the to-be-detected market subject has an abnormal bidding behavior, and if so, determining the type of the abnormal bidding behavior; furthermore, the system warns related market subjects according to the determined types of the abnormal bidding behaviors, so that the purpose of identifying and correcting the abnormal bidding behaviors of the power market subjects is achieved, and fairness and orderliness of power market transactions are maintained.

Description

Technical Field

[0001] The present invention belongs to the technical field of market transaction risk prevention and control, and particularly relates to a method and system for identifying abnormal bidding behaviors of the behavior characteristics of power market entities. Background Art

[0002] With the rapid development of the power trading market, the fairness, impartiality, and openness in the power trading process have attracted more and more attention from regulatory agencies, market entities, and other parties. However, in the process of power market transactions, there are occasional acts of a very small number of market entities using market power to manipulate transactions, obtain improper benefits, and artificially create market transaction risks, which seriously disrupt the fair, healthy, and orderly development of the power market. Therefore, the development of power market transaction risk prevention and control technology has become an inevitable demand.

[0003] For the above-mentioned artificially created transaction risks, a relatively prominent feature is that there will be some abnormal phenomena during the bidding process, which provides a valuable starting point for identifying the improper trading behaviors of power market entities. And how to reasonably screen and process the huge amount of original transaction data in the power market, and through what calculation methods to process these data, so as to obtain more comprehensive and accurate discriminant indicators to accurately identify these abnormal bidding behaviors has become one of the main difficulties in the effective supervision of the power market.

[0004] However, the current domestic and foreign research work on the supervision of abnormal bidding behaviors in the power market is still relatively few, and there are still problems such as the research level not being deep enough and the relevant theories, methods, etc. being in urgent need of improvement. At present, it is still impossible to accurately prevent, identify, and correct these artificially created transaction risks, and naturally it is also difficult to restrict the behaviors of market entities behind from obtaining improper benefits. This poses a challenge to maintaining the fair competition and market efficiency of the power market and ensuring the sustainable and healthy development of the power market.

[0005] In summary, the existing supervision and identification methods for abnormal bidding behaviors of power market entities still cannot fully solve the problem that some market entities carry out unfair competition through abnormal bidding to obtain excess profits and disrupt the fair competition order of the power market. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for identifying abnormal bidding behaviors of the behavior characteristics of power market entities, so as to solve the problem that the existing methods for supervising abnormal bidding behaviors in the power market are few in number and not accurate enough in the above background, thereby better maintaining the competitiveness and market efficiency of the power market and ensuring the sustainable and healthy development of the power market.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions:

[0008] As a preferred solution of the method for identifying abnormal bidding behaviors of the power market entity behavior characteristics described in the present invention, wherein: obtaining the market operation data of all market entities in the power market and calculating to construct a set of abnormal bidding behavior characteristics of the market entities;

[0009] Obtaining the market operation data of the market entity to be detected, and determining whether there is an abnormal bidding behavior of the market entity to be detected;

[0010] According to the comparison result, determining the type of the abnormal bidding behavior;

[0011] According to the determined type of the abnormal bidding behavior, warning the relevant power market entities to achieve the purpose of identifying and correcting the abnormal bidding behavior.

[0012] As a preferred solution of the method for identifying abnormal bidding behaviors of the power market entity behavior characteristics described in the present invention, wherein: the market operation data includes,

[0013] The declared electricity price P in the s-th segment s 、the declared electricity quantity Q in the s-th segment s 、the total winning electricity quantity Q w 、the total declared electricity quantity Q b 、the maximum generating electricity quantity Q of the unit max and the high-bidding electricity quantity Q hb ;

[0014] Wherein, the market operation data of the market entity is taken from the trading segment suspected of having abnormal bidding behaviors, and is denoted as s;

[0015] The definition method of the high-bidding electricity quantity Q hb is: selecting the sum of the electricity quantities corresponding to the bids that are greater than or equal to μ + kσ of all bids except the highest bid, where μ is the average value of all bids, σ is the standard deviation of all bids, and k is the confidence factor.

[0016] As a preferred solution of the method for identifying abnormal bidding behaviors of the power market entity behavior characteristics described in the present invention, wherein: the abnormal bidding behaviors of the market entities include market collusion, capacity withholding, extreme bidding, and jump-up behaviors;

[0017] The calculation method of the determination index of the abnormal bidding behavior characteristic set is:

[0018] The weighted average bid The calculation formula is:

[0019]

[0020] Wherein, I is the total number of bid segments; i is the first bid segment after the contract electricity quantity; P s is the declared electricity price in the s-th segment; Q sis the declared electricity quantity for the s-th segment;

[0021] The standard deviation σ of the winning bid rate ar The calculation method is as follows: calculate the winning bid rate AR, and then calculate the standard deviation of AR. The calculation formula is expressed as:

[0022]

[0023] where Q w is the total winning bid electricity quantity, and Q b is the total declared electricity quantity;

[0024]

[0025] where n is the total number of electricity market entities in the sample, and AR n is the winning bid rate of the n-th electricity market entity, is the average value of the winning bid rates of all electricity market entities;

[0026] The calculation of the withholding ratio R is expressed as:

[0027]

[0028] where Q max is the maximum generating capacity of the unit;

[0029] The calculation formula of the high bid ratio HR is expressed as:

[0030]

[0031] where Q hb is the high bid electricity quantity;

[0032] The market share S of the unit j The calculation formula is:

[0033]

[0034] where S j is the market share of the j-th unit; is the winning bid electricity quantity of the j-th unit; J is the total number of units in the market.

[0035] As a preferred solution of the abnormal bidding behavior recognition method for the behavior characteristics of electricity market entities described in the present invention, wherein: the obtaining of the market operation data of the market entity to be detected includes the declared electricity price P′ of the electricity market entity in the s-th segment s and the declared electricity quantity Q′ in the s-th segment s , the total winning bid electricity quantity Q′ w , the total declared electricity quantity Q′ b , the maximum generating capacity Q′ of the unit max and the high bid electricity quantity Q′hb , calculate the weighted average offer respectively Standard deviation of winning bid rate σ′ ar , retention ratio R′, high offer ratio HR', and unit market share S j ′.

[0036] As a preferred scheme of the method for identifying abnormal bidding behavior of the power market subject behavior characteristics described in the present invention, wherein: determining whether there is abnormal bidding behavior of the market subject to be detected includes comparing the weighted average offer in the data of the market subject to be detected with the standard deviation of winning bid rate σ′ ar A higher value is defined as a market collusion behavior; a higher retention ratio R′ and high offer ratio HR′ are defined as capacity withholding behaviors; a higher weighted average offer and unit market share S j ′ are defined as extreme offer behaviors; a higher total winning bid quantity Q′ w and the last section of the offer are higher, while the weighted average offer is lower, which is defined as a jump behavior.

[0037] As a preferred scheme of the method for identifying abnormal bidding behavior of the power market subject behavior characteristics described in the present invention, wherein: the higher last section of the offer is the corresponding value of the last section of the declared electricity price P′ in the s-th section s among them.

[0038] As a preferred scheme of the method for identifying abnormal bidding behavior of the power market subject behavior characteristics described in the present invention, wherein: the method for judging higher and lower values is that the value corresponding to μ + kσ of all values should be judged as higher; the value corresponding to μ - kσ of all values should be judged as lower; where μ is the average value of all offers, σ is the standard deviation of all offers, and k is a confidence factor.

[0039] As a preferred scheme of the system for identifying abnormal bidding behavior of the power market subject behavior characteristics described in the present invention, wherein: it includes a data processing module, a comparison and judgment module, a cause identification module, and a warning and prompt module.

[0040] A computer device includes a memory and a processor, the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of the method described in any one of the methods for identifying abnormal bidding behavior of the power market subject behavior characteristics.

[0041] A computer-readable storage medium stores a computer program, and is characterized in that when the computer program is executed by a processor, it implements the steps of the method described in any one of the methods for identifying abnormal bidding behavior of the power market subject behavior characteristics.

[0042] Advantages of the present invention: The method and system for identifying abnormal bidding behaviors of the behavior characteristics of power market entities provided by the present invention obtain the market operation data of all market entities in the power market, calculate their weighted average bids, standard deviation of winning bid rates, withholding ratios, high bid ratios, and unit dynamic market shares respectively, and construct a set of abnormal bidding behavior characteristics of market entities based on this; after calculating the market operation data of the market entity to be detected through the above calculations, put it into the characteristic set for comparison, and determine whether there is an abnormal bidding behavior of the market entity to be detected according to the comparison result; if so, further determine the type of its abnormal bidding behavior, issue a warning, and warn relevant power market entities, so as to achieve the purpose of identifying and correcting abnormal bidding behaviors of power market entities in the trading process; the proposed identification system is a practical product of the identification method, which strengthens the operability of the present invention. Description of the Drawings

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a schematic flow chart of a method for identifying abnormal bidding behaviors of the behavior characteristics of power market entities provided by an embodiment of the present invention.

[0045] Figure 2 It is a structural block diagram of a system for identifying abnormal bidding behaviors of the behavior characteristics of power market entities provided by an embodiment of the present invention. Detailed Embodiments

[0046] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment 1

[0048] Refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for identifying abnormal bidding behaviors of the behavior characteristics of power market entities, including:

[0049] As Figure 1 shown, a method for identifying abnormal bidding behaviors of the behavior characteristics of power market entities includes the following steps:

[0050] S1, Data processing: Obtain the market operation data of all market entities in the power market and calculate the weighted average bid price, standard deviation of winning bid rate, withholding ratio, high bid ratio, and dynamic market share of units, and construct a set of abnormal bidding behavior characteristics of market entities based on this.

[0051] S2, Comparison and judgment: Obtain the market operation data of the market entity to be detected, calculate the corresponding values according to the method in S1, and compare them with the set of abnormal behavior characteristics in S1 to determine whether there is abnormal bidding behavior in the market entity to be detected.

[0052] S3, Identify the reason: Further determine the type of its abnormal bidding behavior according to the comparison result in S2.

[0053] S4, Issue a warning: According to the type of abnormal bidding behavior determined in S3, warn the relevant power market entities to achieve the purpose of identifying and correcting abnormal bidding behavior.

[0054] In an optional embodiment, a method for identifying abnormal bidding behavior of power market entity behavior characteristics includes the following steps:

[0055] S100, Data processing: Obtain the market operation data of all market entities in the power market and calculate the weighted average bid price, standard deviation of winning bid rate, withholding ratio, high bid ratio, and dynamic market share of units, and construct the indicators of the set of abnormal bidding behavior characteristics of market entities based on this.

[0056] Specifically, the range of the market operation data of the market entity is taken from the trading segments suspected of having abnormal bidding behavior, which is denoted as s (session), and s can take multiple segments.

[0057] Specifically, the content of the market operation data of the market entity includes: the declared electricity price P s (price) in the s-th segment, the declared electricity quantity Q s (quantity) in the s-th segment, the total winning electricity quantity Q w (win), the total declared electricity quantity Q b (bid), the maximum generating capacity Q of the unit max and the high-bid electricity quantity Q hb (highbid). It should be noted that when calculating the above six values, data collection should be carried out for all market entities that have made bids within the s segment. Therefore, the values of the above six items of data should be a sum.

[0058] It should be noted that the high-bid electricity quantity Q hbThe definition method is as follows: Select the sum of the electricity quantities corresponding to the bids that are greater than or equal to μ + kσ of all bids except the highest bid, where μ is the average value of all bids, σ is the standard deviation of all bids, and k is the confidence factor. The value of k depends on the tolerance level of the electricity market. The larger k is, the higher the tolerance level of the market;

[0059] Specifically, the abnormal bidding behaviors concentrated in the characteristics of abnormal bidding behaviors of market entities include market collusion, capacity withholding, extreme bidding, and jump bidding;

[0060] In a specific embodiment, the following method is used to obtain the indicators of the abnormal bidding behavior characteristic set of market entities:

[0061] (1) Calculate the weighted average bid

[0062] where I is the total number of bid segments; i is the first bid segment after the contract electricity quantity; s is the bid segment to be detected, and multiple segments can be selected; P s is the declared electricity price of the s-th segment; Q s is the declared electricity quantity of the s-th segment;

[0063] (2) Calculate the standard deviation of the winning bid rate σ ar , first calculate the winning bid rate AR, and then calculate its standard deviation. The method is as follows:

[0064]

[0065] where Q w is the total winning electricity quantity, Q b is the total declared electricity quantity;

[0066]

[0067] where n is the total number of electricity market entities in the sample, AR n is the winning bid rate of the n-th electricity market entity, is the average value of the winning bid rates of all electricity market entities;

[0068] (3) Calculate the withholding ratio R:

[0069]

[0070] where Q max is the maximum power generation of the unit;

[0071] (4) Calculate the high bid ratio HR:

[0072]

[0073] where Q hbis the high - quoted electricity quantity;

[0074] (5) Calculate the market share S of the computer group j :

[0075]

[0076] where S j is the market share of the j - th unit; is the winning bid electricity quantity of the j - th unit; J is the total number of units in the market.

[0077] S200. Comparative judgment: Obtain the market operation data of the market entity to be detected, calculate the corresponding values according to the method of S100, and compare them with the abnormal behavior feature set in S100 to determine whether there is abnormal bidding behavior of the market entity to be detected;

[0078] Specifically, it is necessary to obtain the market operation data of the market entity to be detected, including: the declared electricity price P′ of the market entity to be detected in the s - th segment s , the declared electricity quantity Q′ in the s - th segment s , the total winning bid electricity quantity Q′ w , the total declared electricity quantity Q′ b , the maximum power generation Q′ of the unit max and the high - quoted electricity quantity Q′ hb ;

[0079] In a specific embodiment, the following method is used to compare the market operation data of the market entity to be detected with the abnormal behavior feature set in S100:

[0080] (1) Whether the data of the entity to be detected satisfies the condition of a relatively high weighted average bid and the standard deviation of the winning bid rate σ′ ar ;

[0081] (2) Whether the data of the entity to be detected satisfies the condition of relatively high retention ratio R′ and high - quoted ratio HR′;

[0082] (3) Whether the data of the entity to be detected satisfies the condition of relatively high weighted average bid and the market share S of the unit j ′;

[0083] (4) Whether the data of the entity to be detected satisfies the condition that the total winning bid electricity quantity Q′ w and the bid in the last segment are relatively high, while the weighted average bid is relatively low;

[0084] (5) If the input data satisfies one or more of the above conditions, the relevant data will be input into the next step; otherwise, the next step will not be carried out and no corresponding warning will be given;

[0085] It should be noted that the last paragraph of the quotation is the declared electricity price P' of the s-th paragraph s and is the corresponding value of the last paragraph in

[0086] It should be noted that the determination methods for higher and lower values are as follows: The value corresponding to μ + kσ greater than all values is determined to be higher; the value corresponding to μ - kσ less than all values is determined to be lower; where μ is the average value of all quotations, σ is the standard deviation of all quotations, and k is the confidence factor. The value of k depends on the tolerance of the electricity market. The larger k is, the higher the tolerance of the market indicates.

[0087] S300. Identification reason: Based on the comparison result of S200, determine the type of its abnormal bidding behavior;

[0088] In a specific embodiment, the following method is used to determine the type of abnormal bidding behavior of the subject to be detected:

[0089] (1) If the weighted average quotation and the standard deviation of the winning bid rate σ' ar are high, it is determined that the subject to be detected has a market collusion behavior;

[0090] (2) If the withholding ratio R' and the high quotation ratio HR' are high, it is determined that the subject to be detected has a capacity withholding behavior;

[0091] (3) If the weighted average quotation and the unit market share S j ' are high, it is determined that the subject to be detected has an extreme quotation behavior;

[0092] (4) If the total winning bid electricity quantity Q' w and the last paragraph of the quotation are high, while the weighted average quotation is low, it is determined that the subject to be detected has a jump-up behavior;

[0093] It should be noted that the last paragraph of the quotation is the declared electricity price P' of the s-th paragraph s and is the corresponding value of the last paragraph in

[0094] It should be noted that the determination methods for higher and lower values are as follows: The value corresponding to μ + kσ greater than all values is determined to be higher; the value corresponding to μ - kσ less than all values is determined to be lower; where μ is the average value of all quotations, σ is the standard deviation of all quotations, and k is the confidence factor. The value of k depends on the tolerance of the electricity market. The larger k is, the higher the tolerance of the market indicates.

[0095] S400. Issue a warning: Based on the types of abnormal bidding behaviors determined by S300, warn relevant electricity market entities to identify and correct abnormal bidding behaviors.

[0096] In an alternative embodiment, an abnormal bidding behavior recognition system for the behavioral characteristics of electricity market entities is also provided, which is used to implement the abnormal bidding behavior recognition method for the behavioral characteristics of electricity market entities, including:

[0097] A data processing module, which is used to obtain and clean the market operation data of market entities in the electricity market. Specifically, it is necessary to obtain the market operation data of all market entities and the market entities to be detected, and calculate their respective weighted average bids, standard deviation of winning bid rates, withholding ratios, high bid ratios, and unit dynamic market shares, and then construct a set of abnormal bidding behavior characteristics of market entities based on this;

[0098] A comparison and judgment module, which is used to further identify the reasons for the abnormal bidding behaviors of the market entities to be detected, and map the data characteristics presented by the comparison and judgment module to specific abnormal bidding behaviors to determine the types of abnormal bidding behaviors;

[0099] A cause identification module, which is used to further identify the reasons for the abnormal bidding behaviors of the market entities to be detected, map the data characteristics presented by the comparison and judgment module to specific abnormal bidding behaviors, and determine the types of abnormal bidding behaviors;

[0100] A warning prompt module, which is used to warn the market entities to be detected with abnormal bidding behaviors to identify and correct abnormal bidding behaviors.

[0101] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0102] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

[0103] Embodiment 2

[0104] AsFigure 2 As shown in the figure, this is the second embodiment of the present invention. This embodiment provides an abnormal bidding behavior recognition system for the behavior characteristics of power market entities, which is characterized by including:

[0105] A data processing module, which is used to obtain and clean the market operation data of market entities in the power market. Specifically, it is necessary to obtain the market operation data of all market entities and the market entities to be detected, and calculate their respective weighted average bids, standard deviation of winning bid rates, withholding ratios, high bid ratios, and unit dynamic market shares, and then construct a set of abnormal bidding behavior characteristics of market entities based on this;

[0106] A comparison and judgment module, which is used to further identify the reasons for the abnormal bidding behavior of the detected market entities, and map the data characteristics presented by the comparison and judgment module to specific abnormal bidding behaviors to determine the type of abnormal bidding behavior;

[0107] A cause identification module, which is used to further identify the reasons for the abnormal bidding behavior of the market entities to be detected, map the data characteristics presented by the comparison and judgment module to specific abnormal bidding behaviors, and determine the type of abnormal bidding behavior;

[0108] A warning and prompt module, which is used to warn the market entities to be detected with abnormal bidding behaviors, so as to achieve the purpose of identifying and correcting abnormal bidding behaviors.

[0109] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

[0111] Embodiment 3

[0112] The third embodiment of the present invention is different from the previous two embodiments in that:

[0113] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0114] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0115] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0116] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

Claims

1. A method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities, characterized by: include, Obtain and calculate the market operation data of all market players in the power market, and construct a feature set of abnormal bidding behavior of market players; Obtain the market operation data of the market subject to be tested and determine whether the market subject to be tested has abnormal bidding behavior; Determine the type of abnormal bidding behavior based on the comparison results; Based on the identified types of abnormal bidding behavior, relevant power market players will be warned to achieve the purpose of identifying and correcting abnormal bidding behavior.

2. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 1, characterized in that: The market operation data includes: The declared electricity price P for the sth segment s 、The declared electricity quantity Q of the sth segment s 、Total electricity quantity won Q w 、Declare total electricity consumption Q b 、The maximum power generation of the unit Q max With high quotation electricity Q hb ; Among them, the market operation data of the market entity is taken from the transaction segment where abnormal bidding behavior is suspected to occur, which will be recorded as s; High quotation electricity Q hb The definition method is to select the sum of the electricity corresponding to the quotations that are greater than or equal to μ+kσ of all quotations except the highest quotation, where μ is the average value of all quotations, σ is the standard deviation of all quotations, and k is the confidence factor.

3. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 2, characterized in that: The abnormal bidding behaviors of market players include market collusion, capacity retention, extreme bidding and price jumping behaviors; The calculation method of the abnormal bidding behavior feature set determination index is as follows: Weighted average quote The calculation formula is: Where I is the total number of quotation segments; i is the first quotation segment after the contract electricity; P s is the declared electricity price for the sth segment; Q s The electricity reported in paragraph s; Standard deviation of winning rateσ ar The calculation method is to calculate the winning rate AR, and then calculate the standard deviation of AR. The calculation formula is expressed as: Among them, Q w is the total amount of electricity won, Q b To report the total electricity consumption; Where n is the total number of electricity market players in the sample, AR n is the winning rate of the nth power market player, is the average of the bid winning rates of all power market players; The calculation of retention ratio R is expressed as: Among them, Q max is the maximum power generation of the unit; The calculation formula of high offer ratio HR is expressed as: Among them, Q hb It is the high quoted electricity quantity; Unit market share S j The calculation formula is: Among them, S j is the market share of the j-th unit; is the winning bid electricity of the j-th unit; J is the total number of units in the market.

4. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 3 is characterized by: The market operation data of the market subject to be detected includes the electricity price P′ declared by the power market subject in the sth period. s , the reported quantity Q′ of the sth segment s 、Total amount of electricity Q′ w , declare the total electricity consumption Q′ b , Maximum power generation of the unit Q′ max With high quotation quantity Q′ hb , respectively calculate the weighted average quotation Standard deviation of the winning rate σ′ ar , retention ratio R′, high bid ratio HR′ and unit market share S j ′.

5. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 4, characterized in that: The determination of whether the market subject to be detected has abnormal bidding behavior includes: and the standard deviation of the winning bid rate σ′ ar The higher one is defined as market collusion; the higher retention ratio R′ and high bid ratio HR′ are defined as capacity holding behavior; the weighted average bid and unit market share S j ′Higher ones are defined as extreme bidding behavior; The total amount of electricity Q′ w and the last paragraph has a higher bid, while the weighted average bid The lower one is defined as high jumping behavior.

6. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 5, characterized in that: The last segment’s bid price is higher than the declared electricity price P′ of the s segment. s The corresponding value of the last segment in .

7. The method for identifying abnormal bidding behavior based on the behavioral characteristics of power market entities according to claim 6, characterized in that: The method for judging higher and lower values ​​is that the value corresponding to the value of μ+kσ greater than or equal to all values ​​should be judged as higher; the value corresponding to the value of μ-kσ less than or equal to all values ​​should be judged as lower; where μ is the average of all quotations, σ is the standard deviation of all quotations, and k is the confidence factor.

8. A system for identifying abnormal bidding behavior based on the behavior characteristics of power market entities according to any one of claims 1 to 7, characterized in that: It includes a data processing module, a comparison and judgment module, a cause identification module, and an early warning module.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images