Power market transaction strategy optimization method and system

Abstract

The invention relates to the technical field of electricity market transaction, in particular to an electricity market transaction strategy optimization method and system. Comprising the steps of establishing a power prediction model and a power demand model; establishing a power prediction curve according to the power prediction model, and generating a quotation strategy according to the power demand model and the power prediction curve; and obtaining real-time transaction parameters according to the preset feedback time node, and judging whether to correct the quotation strategy according to the real-time transaction parameters. By establishing a power prediction model and a power demand model, the real-time productivity of a supply end and the real-time power demand of a demand end are predicted, a game model is established, the unit electric quantity quotation and the power generation power of a station are generated according to a real-time iterative optimal solution, the productivity of the station is dynamically adjusted, and the overall income value is improved. According to the method, a plurality of time intervals are established, and corresponding transaction volume functions are respectively established for power consumption peaks and power consumption troughs in a single day, so that gradient adjustment of electric quantity quotation in different time periods is realized, and the transaction efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power market transactions, and in particular to a method and system for optimizing power market transaction strategies. Background Art

[0002] Electricity market transactions refer to day-ahead transactions, intraday transactions, and real-time transactions conducted on a smaller time scale. The above three transaction forms are the three most common time scale transactions in the current electricity market.

[0003] New energy stations can use real-time power market transactions to adjust the capacity they provide according to the current predicted transaction volume, thereby reducing their forecast risks. Compared with medium- and long-term power transactions, the transaction price of power spot transactions fluctuates significantly with the fluctuation of time and the changes in market transaction volume. Such frequent price fluctuations not only bring certain risks to both parties to the transaction, but also can effectively enhance the enthusiasm of transactions and expand the profit space of trading entities. Summary of the invention

[0004] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a method and system for optimizing electricity market transaction strategies, aiming to improve the efficiency and profit value of electricity market transactions and increase the profit margins of new energy sites.

[0005] In some embodiments of the present application, by establishing a power prediction model and a power demand model, the real-time supply-side production capacity and the demand-side power demand are predicted, and a game model is established to generate the unit electricity quotation and power generation power of the station according to the real-time iterative optimal solution, and the production capacity of the station is dynamically adjusted, thereby improving the overall profit value.

[0006] In some embodiments of the present application, by establishing multiple time intervals, corresponding trading volume functions are established for the peak and trough electricity consumption within a single day, thereby achieving gradient adjustment of electricity price quotations in different time periods and improving trading efficiency in the electricity market.

[0007] In some embodiments of the present application, a method for optimizing a power market transaction strategy is provided, comprising:

[0008] Establish power forecasting model and power demand model;

[0009] Establish a power forecast curve based on the power forecast model, and generate a quotation strategy based on the power demand model and the power forecast curve;

[0010] The real-time trading parameters are obtained according to the preset feedback time nodes, and it is determined whether to modify the quotation strategy according to the real-time trading parameters.

[0011] In some embodiments of the present application, the establishment of the power demand model includes:

[0012] Using the day as the standard period, multiple time intervals are generated;

[0013] Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day;

[0014] Establish the quote-volume function in each time interval based on market transaction data;

[0015] Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval;

[0016] Set the update time node of the transaction volume function series F.

[0017] In some embodiments of the present application, when generating a quotation strategy according to the power demand model and the power forecast curve, it includes:

[0018] Set the duration of a single quotation cycle c;

[0019] Obtain the target transaction volume function F'(x) according to the current time interval;

[0020] Establish the power-generation function Y(x);

[0021] Generate quotation model;

[0022]

[0023] h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a);

[0024] Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period;

[0025] Iterate the quotation model and output multiple feasible solutions;

[0026] Set the current quotation strategy based on all feasible solutions.

[0027] In some embodiments of the present application, when the quotation model is iterated cyclically, it includes:

[0028] The value range of the generated power a is set according to the power prediction curve;

[0029] The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x);

[0030] Set the single iteration amount;

[0031] Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output;

[0032] Set the current quotation strategy based on the feasible solution with the largest expected return value.

[0033] In some embodiments of the present application, the setting of the single quotation cycle duration c includes:

[0034] Generate a fluctuation evaluation value g,

[0035] Among them, βi is the influencing factor of the i-th evaluation index, ji is the reference value of the i-th evaluation index, and m is the number of evaluation indicators;

[0036] Presetting a first fluctuation evaluation value interval (G1, G2), a second fluctuation evaluation value interval (G2, G3) and a third fluctuation evaluation value interval (G3, G4);

[0037] If the fluctuation evaluation value g is within the preset first fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset first duration c1, that is, c=c1;

[0038] If the fluctuation evaluation value g is within the preset second fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset second duration c2, that is, c=c2;

[0039] If the fluctuation evaluation value g is in the preset third fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset third duration c3, that is, c=c3; and c1>c2>c3.

[0040] In some embodiments of the present application, when determining whether to modify the quotation strategy according to the real-time transaction parameters, it includes:

[0041] Get all quotation strategies between the current feedback time node and the previous feedback time node;

[0042] Establish the expected return value sequence H, H = (h'1, h'2…h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy;

[0043] Get the actual total benefit value ΔH between the current feedback time node and the previous feedback time node;

[0044] Generate the profit difference p of the current feedback time node,

[0045] If p is greater than the preset profit difference threshold, a correction instruction is generated.

[0046] In some embodiments of the present application, a power market transaction strategy optimization system is provided, including:

[0047] Central control unit, used to establish power prediction model and power demand model;

[0048] The central control unit is also used to establish a power prediction curve according to the power prediction model, and generate a quotation strategy according to the power demand model and the power prediction curve;

[0049] A correction unit, used to obtain real-time trading parameters according to a preset feedback time node, and determine whether to correct the quotation strategy according to the real-time trading parameters;

[0050] The central control unit comprises:

[0051] The first processing module is used to generate multiple time intervals with the day as the standard period;

[0052] Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day;

[0053] Establish the quote-volume function in each time interval based on market transaction data;

[0054] Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval;

[0055] The first processing module is also used to set an update time node of the transaction volume function series F.

[0056] In some embodiments of the present application, the central control unit further includes

[0057] The second processing module is used to set the duration c of a single quotation cycle;

[0058] Obtain the target transaction volume function F'(x) according to the current time interval;

[0059] Establish the power-generation function Y(x);

[0060] Generate quotation model;

[0061]

[0062] h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a);

[0063] Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period;

[0064] Iterate the quotation model and output multiple feasible solutions;

[0065] Set the current quotation strategy based on all feasible solutions.

[0066] In some embodiments of the present application, when the quotation model is iterated cyclically, it includes:

[0067] The value range of the generated power a is set according to the power prediction curve;

[0068] The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x);

[0069] Set the single iteration amount;

[0070] Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output;

[0071] Set the current quotation strategy based on the feasible solution with the largest expected return value.

[0072] In some embodiments of the present application, the correction unit includes:

[0073] The first correction module is used to obtain all quotation strategies between the current feedback time node and the previous feedback time node;

[0074] The first correction module is also used to establish an expected return value sequence H, H = (h'1, h'2...h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy;

[0075] The second correction module is used to obtain the actual total benefit value ΔH between the current feedback time node and the previous feedback time node;

[0076] The second correction module is also used to generate the profit difference p of the current feedback time node.

[0077]

[0078] If p is greater than a preset profit difference threshold, the second correction module generates a correction instruction.

[0079] Compared with the prior art, the power market transaction strategy optimization method and system of the present application embodiment have the following beneficial effects:

[0080] By establishing a power prediction model and a power demand model, the real-time supply-side production capacity and demand-side power demand are predicted, and a game model is established to generate the unit electricity quotation and power generation power of the station based on the real-time iterative optimal solution, dynamically adjust the production capacity of the station, and thus improve the overall profit value.

[0081] By establishing multiple time intervals, corresponding trading volume functions are established for the peak and trough electricity consumption within a single day, thereby achieving gradient adjustment of electricity price quotations in different time periods and improving trading efficiency in the electricity market. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is a flow chart of a method for optimizing power market transaction strategy in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0083] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0084] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0085] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0086] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0087] like Figure 1 As shown, a method for optimizing a power market transaction strategy according to a preferred embodiment of the present application includes:

[0088] S101: Establish a power prediction model and a power demand model;

[0089] S102: Establishing a power prediction curve according to the power prediction model, and generating a quotation strategy according to the power demand model and the power prediction curve;

[0090] S103: Acquire real-time transaction parameters according to a preset feedback time node, and determine whether to modify the quotation strategy according to the real-time transaction parameters.

[0091] Specifically, when establishing an electricity demand model, it includes:

[0092] Using the day as the standard period, multiple time intervals are generated;

[0093] Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day;

[0094] Establish the quote-volume function in each time interval based on market transaction data;

[0095] Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval;

[0096] Set the update time node of the transaction volume function series F.

[0097] Specifically, since there are peak and trough periods of electricity consumption within a single day, by establishing multiple time intervals in a single day and establishing quotation-trading volume functions corresponding to each time interval, accurate prediction of market electricity demand can be achieved, providing data support for the subsequent formulation of trading strategies, improving the transaction tolerance and quotation flexibility, and facilitating traders to adjust quotation strategies.

[0098] Specifically, due to seasonal differences in electricity demand, the transaction volume function series F is regularly updated by setting update time nodes based on historical transaction data, making each quotation-transaction volume function more accurate.

[0099] In a preferred embodiment of the present application, when generating a quotation strategy according to the power demand model and the power forecast curve, it includes:

[0100] Set the duration of a single quotation cycle c;

[0101] Obtain the target transaction volume function F'(x) according to the current time interval;

[0102] Establish the power-generation function Y(x);

[0103] Generate quotation model;

[0104]

[0105] h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a);

[0106] Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period;

[0107] Iterate the quotation model and output multiple feasible solutions;

[0108] Set the current quotation strategy based on all feasible solutions.

[0109] Specifically, when the quotation model is iterated, it includes:

[0110] The value range of the generated power a is set according to the power prediction curve;

[0111] The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x);

[0112] Set the single iteration amount;

[0113] Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output;

[0114] Set the current quotation strategy based on the feasible solution with the largest expected return value.

[0115] Specifically, by establishing a quotation model, the quotation strategy in each small interval is dynamically adjusted based on global considerations to achieve overall optimization. At the same time, by setting the value range of each parameter and the number of single iterations, the overall operation volume is reduced and the quotation efficiency is improved.

[0116] Specifically, the single iteration amount is the single change amount of each parameter in the feasible solution.

[0117] Specifically, by dynamically adjusting the penalty cost and storage cost, multi-directional optimization processing can be performed to improve the adaptability of the quotation model.

[0118] Specifically, when setting the duration c of a single quotation cycle, it includes:

[0119] Generate a fluctuation evaluation value g,

[0120] Among them, βi is the influencing factor of the i-th evaluation index, ji is the reference value of the i-th evaluation index, and m is the number of evaluation indicators;

[0121] Presetting a first fluctuation evaluation value interval (G1, G2), a second fluctuation evaluation value interval (G2, G3) and a third fluctuation evaluation value interval (G3, G4);

[0122] If the fluctuation evaluation value g is within the preset first fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset first duration c1, that is, c=c1;

[0123] If the fluctuation evaluation value g is within the preset second fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset second duration c2, that is, c=c2;

[0124] If the fluctuation evaluation value g is in the preset third fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset third duration c3, that is, c=c3; and c1>c2>c3.

[0125] Specifically, the evaluation indicators include but are not limited to the credibility of the power prediction model, the fluctuation value of the power prediction curve, the environmental complexity and other parameters. By generating the fluctuation evaluation value, the quotation frequency is dynamically adjusted, thereby improving the transaction tolerance and quotation flexibility, and facilitating timely adjustment of the quotation strategy.

[0126] In a preferred embodiment of the present application, when determining whether to modify the quotation strategy according to the real-time transaction parameters, it includes:

[0127] Specifically, the evaluation indicators include but are not limited to the credibility of the power prediction model, the fluctuation value of the power prediction curve, the environmental complexity and other parameters.

[0128] Get all quotation strategies between the current feedback time node and the previous feedback time node;

[0129] Establish the expected return value sequence H, H = (h'1, h'2…h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy;

[0130] Get the actual total benefit value ΔH between the current feedback time node and the previous feedback time node;

[0131] Generate the profit difference p of the current feedback time node,

[0132] If p is greater than the preset profit difference threshold, a correction instruction is generated.

[0133] Specifically, when the expected return difference is greater than the preset threshold, it means that the actual return generated based on the current quotation model cannot meet expectations, and the corresponding quotation-trading volume function and power prediction model need to be corrected. At the same time, the various parameters in the quotation model are adjusted to improve the accuracy of the quotation strategy.

[0134] Based on another preferred embodiment of a method for optimizing a power market transaction strategy in any of the above preferred embodiments, this preferred embodiment provides a system for optimizing a power market transaction strategy, including:

[0135] Central control unit, used to establish power prediction model and power demand model;

[0136] The central control unit is also used to establish a power prediction curve according to the power prediction model and generate a quotation strategy according to the power demand model and the power prediction curve;

[0137] A correction unit, used to obtain real-time trading parameters according to a preset feedback time node, and determine whether to correct the quotation strategy according to the real-time trading parameters;

[0138] The central control unit includes;

[0139] The first processing module is used to generate multiple time intervals with the day as the standard period;

[0140] Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day;

[0141] Establish the quote-volume function in each time interval based on market transaction data;

[0142] Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval;

[0143] The first processing module is also used to set an update time node of the transaction volume function sequence F.

[0144] In a preferred embodiment of the present application, the central control unit also includes

[0145] The second processing module is used to set the duration c of a single quotation cycle;

[0146] Obtain the target transaction volume function F'(x) according to the current time interval;

[0147] Establish the power-generation function Y(x);

[0148] Generate quotation model;

[0149]

[0150] h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a);

[0151] Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period;

[0152] Iterate the quotation model and output multiple feasible solutions;

[0153] Set the current quotation strategy based on all feasible solutions.

[0154] Specifically, when the quotation model is iterated, it includes:

[0155] The value range of the generated power a is set according to the power prediction curve;

[0156] The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x);

[0157] Set the single iteration amount;

[0158] Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output;

[0159] Set the current quotation strategy based on the feasible solution with the largest expected return value.

[0160] In a preferred embodiment of the present application, the correction unit includes:

[0161] The first correction module is used to obtain all quotation strategies between the current feedback time node and the previous feedback time node;

[0162] The first correction module is also used to establish an expected return value sequence H, H = (h'1, h'2...h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy;

[0163] The second correction module is used to obtain the actual total benefit value ΔH between the current feedback time node and the previous feedback time node;

[0164] The second correction module is also used to generate the profit difference p of the current feedback time node.

[0165] If p is greater than the preset profit difference threshold, the second correction module generates a correction instruction.

[0166] According to the first concept of the present application, by establishing a power prediction model and a power demand model, the real-time supply-side production capacity and demand-side power demand are predicted, and a game model is established to generate the unit electricity quotation and power generation power of the station according to the real-time iterative optimal solution, and dynamically adjust the production capacity of the station, thereby improving the overall profit value.

[0167] According to the second concept of the present application, by establishing multiple time intervals, corresponding trading volume functions are established for the peak and trough electricity consumption within a single day, thereby achieving gradient adjustment of electricity price quotations in different time periods and improving trading efficiency in the electricity market.

[0168] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for optimizing power market transaction strategy, characterized in that: include: Establish power forecasting model and power demand model; Establish a power forecast curve based on the power forecast model, and generate a quotation strategy based on the power demand model and the power forecast curve; Obtain real-time trading parameters according to the preset feedback time node, and determine whether to modify the quotation strategy based on the real-time trading parameters; The establishment of the power demand model includes: Using the day as the standard period, multiple time intervals are generated; Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day; Establish the quote-volume function in each time interval based on market transaction data; Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval; Set the update time node of the transaction volume function series F.

2. The method for optimizing power market transaction strategy according to claim 1, characterized in that: When generating a bidding strategy based on the power demand model and power forecast curve, it includes: Set the duration of a single quotation cycle c; Obtain the target transaction volume function F'(x) according to the current time interval; Establish the power-generation function Y(x); Generate quotation model; h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a); Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period; Iterate the quotation model and output multiple feasible solutions; Set the current quotation strategy based on all feasible solutions.

3. The method for optimizing power market transaction strategy according to claim 2, characterized in that: When looping through the quote model, it includes: The value range of the generated power a is set according to the power prediction curve; The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x); Set the single iteration amount; Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output; Set the current quotation strategy based on the feasible solution with the largest expected return value.

4. The method for optimizing power market transaction strategy according to claim 3, characterized in that: The setting of the single quotation cycle duration c includes: Generate a fluctuation evaluation value g, Among them, βi is the influencing factor of the i-th evaluation index, ji is the reference value of the i-th evaluation index, and m is the number of evaluation indicators; Presetting a first fluctuation evaluation value interval (G1, G2), a second fluctuation evaluation value interval (G2, G3) and a third fluctuation evaluation value interval (G3, G4); If the fluctuation evaluation value g is within the preset first fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset first duration c1, that is, c=c1; If the fluctuation evaluation value g is within the preset second fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset second duration c2, that is, c=c2; If the fluctuation evaluation value g is in the preset third fluctuation evaluation value interval, the single quotation cycle duration c is set to the preset third duration c3, that is, c=c3; and c1>c2>c3.

5. The method for optimizing power market transaction strategy according to claim 4, characterized in that: When determining whether to modify the quotation strategy based on real-time trading parameters, it includes: Get all quotation strategies between the current feedback time node and the previous feedback time node; Establish the expected return value sequence H, H = (h'1, h'2…h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy; Get the actual total benefit value ΔH between the current feedback time node and the previous feedback time node; Generate the profit difference p of the current feedback time node, If p is greater than the preset profit difference threshold, a correction instruction is generated.

6. A power market transaction strategy optimization system, characterized in that: include: Central control unit, used to establish power prediction model and power demand model; The central control unit is also used to establish a power prediction curve according to the power prediction model, and generate a quotation strategy according to the power demand model and the power prediction curve; A correction unit, used to obtain real-time trading parameters according to a preset feedback time node, and determine whether to correct the quotation strategy according to the real-time trading parameters; The central control unit comprises: The first processing module is used to generate multiple time intervals with the day as the standard period; Establish a time interval sequence T, T = (t1, t2…tn), where n is the number of time intervals and ti is the i-th time interval in a single day; Establish the quote-volume function in each time interval based on market transaction data; Establish the trading volume function series F, F = [F1(x), F2(x)…F n (x)], where F i (x) is the quote-volume function of the i-th time interval; The first processing module is also used to set an update time node of the transaction volume function series F.

7. The power market transaction strategy optimization system according to claim 6, characterized in that: The central control unit also includes The second processing module is used to set the duration c of a single quotation cycle; Obtain the target transaction volume function F'(x) according to the current time interval; Establish the power-generation function Y(x); Generate quotation model; h=b*F'(b)-e1*Q1-e2*Q2+e3*Q2-K(a); Where a is the power generation; b is the unit power quotation; Q1 is the abandoned power in the current quotation period; Q2 is the stored power in the current quotation period; K(x) is the functional relationship between power generation and power generation cost; e1 is the penalty cost of the unit abandoned power; e2 is the storage cost of the unit stored power, and e3 is the profit of the unit stored power; h is the expected profit value in the current quotation period; Iterate the quotation model and output multiple feasible solutions; Set the current quotation strategy based on all feasible solutions.

8. The power market transaction strategy optimization system according to claim 7, characterized in that: When looping through the quote model, it includes: The value range of the generated power a is set according to the power prediction curve; The value range of the unit electricity quotation b is set according to the target transaction volume function F'(x); Set the single iteration amount; Output the feasible solution (ai, bi, hi) of each iteration, where ai is the output power of the i-th iteration, bi is the unit power quotation of the i-th iteration; hi is the expected profit value of the i-th iteration output; Set the current quotation strategy based on the feasible solution with the largest expected return value.

9. The power market transaction strategy optimization system according to claim 8, characterized in that: The correction unit comprises: The first correction module is used to obtain all quotation strategies between the current feedback time node and the previous feedback time node; The first correction module is also used to establish an expected return value sequence H, H = (h'1, h'2...h' m1 ), where m1 is the number of quotation strategies between the current feedback time node and the previous feedback time node; h' i is the expected return value of the i-th quotation strategy; The second correction module is used to obtain the actual total benefit value ΔH between the current feedback time node and the previous feedback time node; The second correction module is also used to generate the profit difference p of the current feedback time node. If p is greater than a preset profit difference threshold, the second correction module generates a correction instruction.

Images