Gradient algorithm-based balanced bidding method and device for electricity-carbon coupling market power generators

Abstract

The invention relates to an electricity-carbon coupling market power generator balanced bidding method and device based on a gradient algorithm. The method comprises the following steps: acquiring bid winning electric quantity and clearing electricity price of a power generator in each time period in a trading day; for each time period, determining the carbon transaction volume of the power generator; for each time period, determining a numerical value interval to which the carbon transaction volume belongs, and determining a carbon transaction cost corresponding to the carbon transaction volume according to the carbon transaction volume and an association relationship between the carbon transaction cost corresponding to the numerical value interval and the carbon transaction volume; the association relationship comprises a reward coefficient and a penalty coefficient of the carbon transaction; determining the total income of the power generator on the trading day; and when the total revenue of the power generator on the trading day is smaller than a preset total revenue, updating the quotation information until the determined total revenue of the power generator on the trading day is greater than or equal to the preset total revenue, and obtaining the quotation information obtained by the last update as target quotation information. According to the invention, the electricity market and the carbon market can be comprehensively considered, and quotation information conforming to expectation is generated.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for balanced bidding by power generators in an electricity-carbon coupling market based on a gradient algorithm. Background Art

[0002] The electricity market and the carbon market are independently operated markets with different rules, management systems and policy directions, but the electricity market and the carbon market can be coupled through the bidding information of power generators. In other words, the bidding information of power generators makes the electricity market and the carbon market influence each other.

[0003] The coupling relationship between the electricity market and the carbon market is mainly reflected in the following two aspects: First, the bidding information of power generators directly affects their winning bid electricity volume. The winning bid electricity volume determines the carbon emissions and quota volume, thus affecting the trading behavior of power generators in the carbon market. When there is a surplus of quotas, quotas can be sold to obtain additional income. When there is a shortage, quotas must be purchased. Second, the costs or benefits generated by carbon emissions will affect the bidding information of power generators in the electricity market, indirectly affecting the trading behavior of power generators in the electricity market.

[0004] Then, how to generate quotation information that meets expectations while taking into account both the electricity market and the carbon market becomes a question that needs to be considered. Summary of the invention

[0005] Based on this, it is necessary to provide a balanced bidding method and device for power generators in the electricity-carbon coupling market based on a gradient algorithm, which can generate expected quotation information while comprehensively considering the electricity duration and carbon duration, in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for balanced bidding of power generators in an electricity-carbon coupling market based on a gradient algorithm, the method comprising:

[0007] Send the bid information submitted by the power generator before the transaction day to the operator's equipment, and obtain the winning bid power and clearing power price of the power generator in each period during the transaction day fed back by the equipment based on the bid information;

[0008] For each time period, the carbon trading volume of the power producer is determined based on the winning electricity volume, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation;

[0009] For each time period, determine the numerical interval to which the carbon trading volume belongs, and determine the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume; wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the correlation includes the reward coefficient of carbon trading; wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the correlation includes the penalty coefficient of carbon trading;

[0010] Determine the total revenue of the power generator on the trading day based on the power clearing price of the power generator in each period, the amount of electricity won in each period and the carbon trading cost in each period;

[0011] In the case where the total revenue of the power generator on the trading day is less than the preset total revenue, the quotation information is updated, and the step of returning to the step of sending the quotation information submitted by the power generator before the trading day to the operator's equipment is continued until the total revenue of the determined power generator on the trading day is greater than or equal to the preset total revenue, and the quotation information obtained from the last update is obtained as the target quotation information.

[0012] In one embodiment, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, determining the carbon trading cost corresponding to the carbon trading amount according to the correlation between the carbon trading amount, the carbon trading cost corresponding to the numerical interval and the carbon trading amount includes:

[0013] Determining a first value according to the reward coefficient and the first increase coefficient in the association relationship;

[0014] Determine a first product value between the negative interval length and the first increase coefficient, and determine a second value according to the first product value and the carbon trading volume;

[0015] A second product value between the first value, the second value and the carbon trading price is determined, and the second product value is used as the carbon trading cost corresponding to the carbon trading volume.

[0016] In one embodiment, when the minimum value in the numerical interval is greater than the preset negative interval length and the maximum value is less than the preset positive interval length, the determining of the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume includes:

[0017] A third product value among the carbon trading price, the carbon trading volume and the penalty coefficient in the association relationship is determined, and the third product value is used as the carbon trading cost corresponding to the carbon trading volume.

[0018] In one embodiment, when the minimum value in the numerical interval is greater than or equal to the preset positive interval length, determining the carbon trading cost corresponding to the carbon trading amount according to the correlation between the carbon trading amount, the carbon trading cost corresponding to the numerical interval and the carbon trading amount includes:

[0019] Determine a third value according to the penalty coefficient and the second increase coefficient in the association relationship;

[0020] Determine a third product value of the carbon trading price, the third value and the length of the positive interval;

[0021] Determining a fourth value according to the penalty coefficient, the second increase coefficient and the carbon trading price;

[0022] Determine a fourth product value between the second increase coefficient and the positive interval length, and determine a difference between the carbon trading volume and the fourth product value as a fifth value;

[0023] determining a fifth product value between the fourth value and the fifth value;

[0024] A value obtained by adding the third product value and the fifth product value is determined as the carbon trading cost.

[0025] In one of the embodiments, the larger the first increase coefficient is, the smaller the corresponding preset negative interval length is; and the larger the second increase coefficient is, the larger the corresponding positive interval length is.

[0026] In one embodiment, the total revenue of the power generator on the trading day is determined based on the clearing electricity price of the power generator in each time period, the winning electricity volume in each time period, and the carbon trading cost in each time period, including:

[0027] For each time period, determine the sixth product value between the clearing electricity price and the winning bid electricity; determine the first difference between the sixth product value and the power generation cost; determine the second difference between the first difference and the carbon trading cost and use it as the income of the power generator in the time period;

[0028] Determine the sum of the generator's revenue in each period and use the sum as the generator's total revenue for the trading day.

[0029] In a second aspect, the present application provides a balanced bidding device for power generators in an electricity-carbon coupling market based on a gradient algorithm, the device comprising:

[0030] The communication device is used to send the quotation information submitted by the power generator before the transaction day to the operator's equipment, and obtain the winning bid power and clearing power price of the power generator in each period during the transaction day fed back by the equipment based on the quotation information;

[0031] A processing module is used to determine the carbon trading volume of the power supplier for each time period according to the bid-winning electricity volume, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation;

[0032] The processing module is further used to determine the numerical interval to which the carbon trading volume belongs for each time period, and determine the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume; wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the correlation includes the reward coefficient of carbon trading; wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the correlation includes the penalty coefficient of carbon trading;

[0033] The processing module is also used to determine the total revenue of the power generator on the trading day according to the clearing electricity price of the power generator in each period, the winning electricity volume in each period and the carbon trading cost in each period;

[0034] An iteration module, configured to update the quotation information when the total revenue of the power generator on the trading day is less than the preset total revenue, and return to the step of sending the quotation information submitted by the power generator before the trading day to the operator's device and continue to execute until the total revenue of the power generator on the trading day is greater than or equal to the preset total revenue;

[0035] The acquisition module is used to acquire the quotation information obtained by the last update as the target quotation information.

[0036] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0038] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0039] The method and device for balanced bidding of power generators in the electricity-carbon coupling market based on the gradient algorithm provided in this embodiment constructs a differentiated step-by-step carbon trading model by constructing numerical intervals, reward coefficients and penalty coefficients, thereby enhancing the market competitiveness of low-carbon trading volume (low-carbon units), effectively controlling carbon emissions and improving the enthusiasm of power generators for emission reduction. In addition, the method provided in this embodiment takes into account the dual attributes of electricity and carbon, fully reflects the coupling of the electricity and carbon markets, and continuously optimizes the quotation information of power generators by setting a preset total revenue, which helps power generators to make more accurate bidding strategies in the electricity-carbon coupling market. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of a method for balanced bidding of power generators in an electricity-carbon coupling market based on a gradient algorithm in one embodiment;

[0042] Figure 2 A schematic diagram of a process for solving a power generator equilibrium bidding model in one embodiment;

[0043] Figure 3 A schematic diagram of a power generator equilibrium bidding model in one embodiment;

[0044] Figure 4 It is a partial flow chart of a method for balanced bidding of power generators in an electricity-carbon coupling market based on a gradient algorithm in one embodiment;

[0045] Figure 5 It is a partial flow chart of a method for balanced bidding of power generators in the electricity-carbon coupling market based on a gradient algorithm in another embodiment;

[0046] Figure 6 is a schematic diagram of a stepped carbon trading model in one embodiment;

[0047] Figure 7 It is a structural block diagram of a balanced bidding device for power generators in an electricity-carbon coupling market based on a gradient algorithm in one embodiment;

[0048] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In one embodiment, Figure 1 As shown, a method for balanced bidding of power generators in the electricity-carbon coupling market based on a gradient algorithm is provided. This embodiment takes the method applied to a server as an example. It can be understood that the method can also be applied to a terminal, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0051] Step 101, sending the quotation information submitted by the power generator before the trading day to the operator's equipment, and obtaining the winning bid power and clearing power price of the power generator in each period during the trading day fed back by the equipment based on the quotation information.

[0052] The operator's device may be a server of the operator.

[0053] The quotation information can be understood as a quotation strategy. The quotation information can be obtained from the quotation curve of the power generator. For example, the power generator submits quotation information for 24 periods one day before the transaction date. The operator's equipment performs market clearing based on the quotation information for the 24 periods, and after clearing, the power generator's winning bid volume and winning bid price will be fed back.

[0054] For example, in the power producer quotation model, the maximum power generation capacity of the power producer is divided into n capacity segments, namely , where Represents the power generation capacity. For power generator i, the quotation for capacity segment j is , where Representative quotation, Represents capacity segment j.

[0055] The n capacity segments and the capacity price corresponding to each capacity segment can be expressed as: In the formula, Representative quotation.

[0056] Furthermore, on this basis, the price of each capacity segment can float within a certain range. At the same time, in order to ensure the accuracy of the final quotation information, the discrete quotation coefficient x is continuous to traverse enough quotation information. The floating price of the capacity segment can be expressed as In the formula, x is the bid coefficient of the power supplier, and the value range of x is Any value between is the floating amount. The final quotation curve of power generator i can be expressed as: According to the quotation curve, you can get the quotation corresponding to each capacity segment.

[0057] Exemplarily, in the market clearing model, the queuing method is used for market clearing, and the main steps are: in the day-ahead market, each power generator submits its own quotation curve one day before the trading day. After the operator's equipment receives quotation information from multiple power generators, it sorts the capacity segments in order from low to high according to the quotation information in each time period until the load demand is met, and determines at least one winning power generator and the winning power of each power generator. Finally, the quotation of the capacity segment corresponding to the winning power generator is the unified clearing price of the system, and each power generator settles according to this clearing price. After determining the winning power and clearing price, the operator's equipment feeds back the winning power and clearing price of the power generator in each time period during the trading day.

[0058] The winning bid volume refers to the volume of electricity that the power generator successfully obtains in the power market bidding. The clearing price refers to the price per kilowatt-hour that can achieve a balance between supply and demand in the power market.

[0059] Step 102, for each time period, determine the carbon trading volume of the power producer according to the bid-winning electricity, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation.

[0060] Among them, carbon emission quota refers to the carbon dioxide emission limit generated by power generation units, which covers direct carbon dioxide emissions generated by fossil fuel consumption and indirect carbon dioxide emissions generated by net purchased electricity. Unit carbon emission quota can be obtained through government allocation or market transactions.

[0061] Among them, the unit carbon emission coefficient can be determined from the carbon emission coefficients of various energy sources regularly released by the Intergovernmental Panel on Climate Change of the United Nations.

[0062] Among them, the unit carbon emission quota and unit carbon emission coefficient can be stored locally in advance and then retrieved when needed.

[0063] For example, when calculating the carbon trading volume, the carbon emission quota of power generator i can be calculated first, then the total carbon emissions of power generator i can be calculated, and finally the difference between the total carbon emissions of power generator i and the carbon emission quota can be determined, and the difference can be used as the carbon trading volume of power generator i.

[0064] When calculating the carbon emission quota of power generator i, the carbon emission quota can be determined based on the unit carbon emission quota and the winning bid electricity. Specifically, the formula Calculate the carbon emission quota, where represents the winning bid quantity of power generator i, represents the unit carbon emission quota corresponding to the unit power generation of power producer i, Represents the carbon emission quota of power generator i.

[0065] When calculating the total carbon emissions of power generator i, the total carbon emissions can be determined based on the unit carbon emission coefficient and the amount of electricity won. Specifically, the formula The total carbon emissions are calculated as follows: represents the winning bid quantity of power generator i, represents the unit carbon emission coefficient corresponding to the unit power generation of power generator i, Represents the total carbon emissions of power generator i.

[0066] When calculating the carbon trading volume of power generator i, the difference between the total carbon emissions of power generator i and the carbon emission quota is determined, and the difference is used as the carbon trading volume of power generator i. Specifically, it can be calculated according to the formula The total carbon emissions are calculated as follows: represents the total carbon emissions of power generator i, represents the carbon emission quota of power producer i, Represents the carbon trading volume of power generator i.

[0067] Step 103, for each time period, determine the numerical interval to which the carbon trading volume belongs, and determine the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume.

[0068] Wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the association relationship includes the reward coefficient of carbon trading. Wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the association relationship includes the penalty coefficient of carbon trading.

[0069] The preset negative interval length refers to a negative value, which can also be understood as the negative interval length of carbon trading. The preset negative interval length can be represented by l.

[0070] Among them, the association between carbon trading costs and carbon trading volumes is used to define how to calculate carbon trading costs based on carbon trading volumes. The association corresponding to different numerical intervals may be different, so as to provide different processing mechanisms for different carbon trading volumes, and the processing mechanism includes a reward mechanism and a penalty mechanism. For example, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the association corresponding to the numerical interval includes a reward coefficient for carbon trading, and the association is used to provide a reward mechanism for the carbon trading volume. For example, when the maximum value in the numerical interval is greater than the preset negative interval length, the association includes a penalty coefficient for carbon trading, and the association is used to provide a penalty mechanism for the carbon trading volume.

[0071] It should be noted that in carbon trading, the reward coefficient and the penalty coefficient are two important mechanisms to incentivize power generators to reduce carbon emissions and punish power generators that fail to achieve emission reduction targets. The reward coefficient described in this embodiment is a reward coefficient for the carbon trading price, which is used to increase the reward when the carbon trading volume is low. Similarly, the penalty coefficient is a penalty coefficient for the carbon trading price, which is used to punish when the carbon trading volume is high. The reward coefficient and the penalty coefficient can be obtained from relevant rules and regulations (such as the "Interim Regulations on Carbon Trading Management"). The reward coefficient and the penalty coefficient can be stored locally and retrieved when needed.

[0072] The associations corresponding to different numerical intervals may be predefined and stored locally or in the cloud, and the corresponding associations may be called according to the numerical intervals when needed. After determining the numerical interval to which the carbon trading volume belongs, the associations corresponding to the numerical intervals are matched from the local or cloud storage space.

[0073] Step 104, determining the total revenue of the power generator on the trading day according to the clearing electricity price of the power generator in each time period, the winning electricity volume in each time period and the carbon trading cost in each time period.

[0074] After the power generator submits the quotation information, the winning bid volume and electricity price information can be obtained, and then the generator's carbon emission quota can be calculated, transactions can be sought in the carbon market, and the clearing income can be calculated.

[0075] Assuming that each generator has one generator set, the power generation cost of generator i can be expressed as a quadratic function: , where represents the power generation cost of generator i, represents the winning bid quantity of power generator i, represents the linear coefficient of generator i, represents the quadratic term coefficient of generator i, represents the no-load cost of generator i. The marginal cost of the equipment submitted by generator i to the operator is , , where represents the linear coefficient of generator i, represents the quadratic term coefficient of generator i, Represents the winning bid amount of generator i.

[0076] Exemplarily, the total revenue of the generator on the trading day is determined by combining the power generation cost, marginal cost, clearing electricity price in each period, winning bid electricity in each period and carbon trading cost in each period of the generator i. For example, for each period, the initial revenue of the generator is determined according to the clearing electricity price and winning bid electricity, and then the cost of power generation, marginal cost, carbon trading cost and other costs are subtracted from the initial revenue to finally obtain the actual revenue obtained by the generator in the period. After obtaining the actual revenue of the generator in each period, the actual revenue of each period is added together to obtain the total revenue of the generator on the trading day.

[0077] Step 105, when the total revenue of the power generator on the trading day is less than the preset total revenue, update the quotation information, and return to step 101 and continue to execute until the total revenue of the determined power generator on the trading day is greater than or equal to the preset total revenue, and the quotation information obtained by the last update is obtained as the target quotation information.

[0078] That is to say, if the total revenue of the power generator on the trading day is less than the preset total revenue, it is necessary to adjust the power generator's quotation information (or quotation strategy), and re-obtain the winning electricity volume and clearing electricity price based on the adjusted quotation information, and recalculate the total revenue of the power generator on the trading day. If the recalculated total revenue is still less than the preset total revenue, it is necessary to adjust the power generator's quotation information again until the total revenue is greater than or equal to the preset total revenue.

[0079] The preset total revenue can be set according to actual needs and is not limited in this embodiment.

[0080] Exemplarily, the optimization target of step 105 may also be set to maximize the total benefit, and the quotation information when the total benefit is maximized may be obtained through model iteration.

[0081] For example, a multi-agent environment is constructed, and a single power generator is set as a single agent to participate in the multi-agent system game. The quotation information (or quotation strategy) of a single agent in 24 time periods is used as the action value. After the market is successfully cleared, the single agent can obtain the corresponding clearing income, and the total income of the single agent in a trading day is regarded as the reward value. The agent adjusts the action tendency to strengthen or weaken according to the level of the reward value. Through the continuous interaction process, the agent continuously optimizes its own quotation information (quotation strategy) and strives to maximize long-term benefits.

[0082] The multi-agent system consists of action space, state space and reward space. The bid coefficient x of the bid curve of 24 time periods submitted by agent (generator) i on the previous day is regarded as the action value, then the action space is The winning bid electricity and total revenue of agent (generator) i on the trading day are taken as the state space O, which can be expressed as The reward space of agent (generator) i can be expressed as .

[0083] A multi-agent deep deterministic policy gradient algorithm is introduced to solve the equilibrium bidding model of power generators in the electricity-carbon coupling market. Figure 2 The process diagram shown in Figure 3 The generator equilibrium bidding model shown in the figure and the description below, the specific steps of the multi-agent deep deterministic policy gradient algorithm are as follows:

[0084] Step 1: Randomly initialize the state of each power generator, including: initializing the action network and evaluation network of each power generator, initializing the experience pool, and setting the maximum number of iterations to , initialize the exploration noise .

[0085] The role of the action network is to generate an action based on the current state of the environment (or the local observation of the agent). This action is the behavior that the agent should take in the current state. The action network is usually a neural network whose input is the state of the environment or the local observation of the agent, and whose output is the action or the probability distribution of the action. During the training process, the action network selects actions based on the current strategy and state, and collects experience data by interacting with the environment. This data will be used to update the parameters of the action network to optimize the strategy.

[0086] Among them, the role of the evaluation network is to estimate the expected return of the action (or Q value) based on the current environment state, action, and possible next state. The evaluation network is usually also a neural network, whose input includes the current state, action, and possible next state (or some combination of this information), and the output is the Q value of the action. During the training process, the evaluation network will update its parameters based on the collected empirical data to more accurately estimate the expected return of the action. These estimates will be used to guide the update of the action network to optimize the strategy. For algorithms such as the Multi-Agent Deep Deterministic Policy Gradient Algorithm (MADDPG), the evaluation network plays a vital role in the centralized training stage. They have access to information from all agents, so that the expected return of each action can be more accurately evaluated. This information will be used to update the parameters of the action network and the evaluation network to optimize the strategy of the entire multi-agent system.

[0087] Among them, the samples in the experience pool include the current state, action, reward value and next state.

[0088] Step 2: If the number of iterations is less than the capacity of the experience pool, the action is randomly selected; otherwise, the action is selected according to the action network, and the winning bid volume and electricity price of each power generator are obtained in the market clearing.

[0089] Step 3: Calculate the total revenue (reward value) of each power generator and get the next state. Record the state, action, reward value and next state as an experience and store them in the experience pool.

[0090] Step 4: If the number of samples in the experience pool is less than the capacity of the experience pool, repeat steps 2 and 3.

[0091] Step 5: Traverse agent 1 to agent N. Extract n groups of data from the experience pool according to the priority experience extraction mechanism. Update the action network based on the extracted data. Update the evaluation network based on the extracted data.

[0092] Step 6: Explore the noise .

[0093] Step 7: If the maximum number of iterations is reached, end the entire loop; otherwise, repeat steps 2 to 6.

[0094] The introduction of a multi-agent deep deterministic policy gradient algorithm can reduce the difficulty of solving the problem, improve the efficiency of solving the problem, and help power generators make more accurate bidding strategies in the electricity-carbon coupling market.

[0095] In summary, the balanced bidding method for power generators in the electricity-carbon coupling market based on the gradient algorithm provided in this embodiment constructs a differentiated step-by-step carbon trading model by constructing numerical intervals, reward coefficients, and penalty coefficients, thereby enhancing the market competitiveness of low-carbon trading volume (low-carbon units), effectively controlling carbon emissions, and improving the enthusiasm of power generators for emission reduction. In addition, the method provided in this embodiment takes into account the dual attributes of electricity and carbon, fully reflects the coupling of the electricity and carbon markets, and continuously optimizes the quotation information of power generators by setting a preset total revenue, which helps power generators to make more accurate bidding strategies in the electricity-carbon coupling market.

[0096] For an exemplary embodiment, see Figure 4 , when the maximum value in the numerical interval is less than or equal to the preset negative interval length, step 103 determines the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume, including:

[0097] Step 401, determining a first value according to the reward coefficient and the first increase coefficient in the association relationship.

[0098] The relationship between the carbon trading volume and the numerical range can be expressed as , the preset negative interval length is ,in Indicates the preset negative interval length, represents the carbon trading volume, >1.

[0099] The first increase coefficient is used to increase the reward coefficient. The smaller the maximum value in the numerical interval, the larger the first increase coefficient can be, so as to enhance the degree of reward of the reward coefficient for the carbon trading price. Correspondingly, the larger the maximum value in the numerical interval, the smaller the first increase coefficient can be, so as to weaken the degree of reward of the reward coefficient for the carbon trading price. Exemplarily, the larger the first increase coefficient is, the smaller the corresponding preset negative interval length is.

[0100] Exemplarily, the product value between the reward coefficient and the first increase coefficient can be determined to be a first value, and the product value is, for example, , where represents the first increase coefficient, represents the reward coefficient. Further, after the product value is determined, the product value can be processed by an algorithm to obtain a value after the algorithm processing as a first value. For example, the first value can be .

[0101] Exemplarily, the first increase coefficient may be used as an index of the reward coefficient, with the exponential value of the reward coefficient being the first value.

[0102] Step 402: determine a first product value between the negative interval length and the first increase coefficient, and determine a second value according to the first product value and the carbon trading volume.

[0103] If the length of the negative interval is expressed as l and the first increase coefficient is a, then the first product value is expressed as al.

[0104] Exemplarily, the second value is determined according to the first product value and the carbon trading volume, and the second value can be obtained by adding the first product value to the carbon trading volume. Assume that the carbon trading volume is expressed as , the first product value is represented by al, and the second value is represented by .

[0105] Exemplarily, the second value is determined according to the first product value and the carbon trading amount, and the first product value, the carbon trading amount and other preset values ​​are added to obtain the second value.

[0106] Step 403: determine a second product value between the first value, the second value and the carbon trading price, and use the second product value as the carbon trading cost corresponding to the carbon trading volume.

[0107] The first value can be expressed as , the second value can be expressed as , the carbon trading price can be expressed as , the second product value .

[0108] For example, the carbon trading cost is expressed as Where represents the carbon trading cost of e-commerce company i, represents the carbon trading price, represents the incentive coefficient of carbon trading, The preset negative interval length.

[0109] The method provided in this embodiment constructs a differentiated stepped carbon trading model by constructing numerical intervals and reward coefficients, thereby enhancing the market competitiveness of low-carbon trading volume (low-carbon units), effectively controlling carbon emissions and increasing the enthusiasm of power generators for emission reduction.

[0110] In an exemplary embodiment, when the minimum value in the numerical interval is greater than the preset negative interval length and the maximum value is less than the preset positive interval length, step 103 determines the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume, including:

[0111] Step 1: determine the third product value between the carbon trading price, the carbon trading volume and the penalty coefficient in the association relationship, and use the third product value as the carbon trading cost corresponding to the carbon trading volume.

[0112] The relationship between the carbon trading volume and the numerical range can be expressed as The minimum value in this numerical range is , the maximum value is , Indicates the preset positive interval length.

[0113] The carbon trading price is expressed as , the carbon trading volume is expressed as , the penalty coefficient is expressed as , the third product value is expressed as .Right now ,but , where Represents the carbon trading cost of e-commerce company i.

[0114] The method provided in this embodiment constructs a differentiated stepped carbon trading model by constructing numerical intervals and penalty coefficients, thereby reducing the market competitiveness of high-carbon trading volumes (low-carbon units), effectively controlling carbon emissions and increasing the enthusiasm of power generators for emission reduction.

[0115] For an exemplary embodiment, see Figure 5 , when the minimum value in the numerical interval is greater than or equal to the preset positive interval length, step 103 determines the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume, including:

[0116] Step 501: Determine a third value according to the penalty coefficient and the second increase coefficient in the association relationship.

[0117] The relationship between the carbon trading volume and the numerical range can be expressed as The minimum value in this numerical range is ,in represents the second increase coefficient, Indicates the preset positive interval length.

[0118] The penalty coefficient can be expressed as , the second increase coefficient can be expressed as The third value can be expressed as Where The value of can be set according to actual needs. Exemplarily, the larger the second increase coefficient is, the larger the corresponding positive interval length is.

[0119] Step 502: determine a third product value of the carbon trading price, the third value, and the length of the positive interval.

[0120] The length of the positive interval can be expressed as , the carbon trading price can be expressed as , the third value can be expressed as The third product value can be expressed as [ ] .

[0121] Step 503: Determine a fourth value according to the penalty coefficient, the second increase coefficient and the carbon trading price.

[0122] The penalty coefficient can be expressed as , the second increase coefficient can be expressed as , the carbon trading price can be expressed as The fourth value can be expressed as .

[0123] Step 504: determine a fourth product value between the second increase coefficient and the length of the positive interval, and determine a difference between the carbon trading volume and the fourth product value as the fifth value.

[0124] The second increase factor can be expressed as , the length of the positive interval can be expressed as , the fourth product value can be expressed as .

[0125] The carbon trading volume can be expressed as , the fourth product value , the fifth value can be expressed as .

[0126] Step 505: determine a fifth product value between the fourth value and the fifth value.

[0127] The fourth value is expressed as , the fifth value is expressed as , the fifth product value is expressed as .

[0128] Step 506: Determine the value obtained by adding the third product value and the fifth product value and use it as the carbon trading cost.

[0129] The third product value is expressed as [ ] , the fifth product value is expressed as , the carbon trading cost is expressed as [ ] ,in represents the carbon trading cost of generator i, and .

[0130] The method provided in this embodiment constructs a differentiated stepped carbon trading model by constructing numerical intervals and penalty coefficients, thereby reducing the market competitiveness of high-carbon trading volumes (low-carbon units), effectively controlling carbon emissions and increasing the enthusiasm of power generators for emission reduction.

[0131] Combined with the description of step 103 in the embodiment, the schematic diagram of the step-by-step carbon trading model adopted in step 103 is as follows: Figure 6 shown.

[0132] In an exemplary embodiment, step 104 includes:

[0133] Step 1: For each time period, determine the sixth product value between the clearing electricity price and the winning electricity amount; determine the first difference between the sixth product value and the power generation cost; determine the second difference between the first difference and the carbon trading cost and use it as the income of the power generator in the time period.

[0134] The formula can be used Determine the revenue of the power generator in period t. represents the return in period t, represents the clearing electricity price in period t, represents the winning bid electricity of e-commerce company i in period t, represents the power generation cost of generator i in period t, represents the carbon trading cost of generator i in period t.

[0135] Step 2: Determine the sum of the generator's revenue in each period and use the sum as the generator's total revenue on the trading day.

[0136] The objective function can be Determine the total profit for 24 periods and maximize the total profit for 24 periods, where Where represents the total revenue, represents the clearing electricity price in period t, represents the winning bid electricity of e-commerce company i in period t, represents the power generation cost of generator i in period t, represents the carbon trading cost of power generator i in period t, represents the lower limit of the power generation company's output, Indicates the upper limit of the power generation company's output.

[0137] The method provided in this embodiment takes into account the dual attributes of electricity and carbon, fully reflects the coupling of the electricity and carbon markets, and continuously optimizes the quotation information of power generators by setting a preset total profit, which helps power generators to make more accurate bidding strategies in the electricity-carbon coupling market.

[0138] It should be understood that, although the steps in the flowcharts of the embodiments described above are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0139] Based on the same inventive concept, the embodiment of the present application also provides a device for implementing the above-mentioned method for implementing the balanced bidding for power generators in the electricity-carbon coupling market based on the gradient algorithm. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method. Therefore, the specific limitations in the embodiments of one or more embodiments of the device for implementing the balanced bidding for power generators in the electricity-carbon coupling market based on the gradient algorithm provided below can be referred to the limitations of the balanced bidding method for power generators in the electricity-carbon coupling market based on the gradient algorithm, and will not be repeated here.

[0140] In an exemplary embodiment, Figure 7 As shown, a balanced bidding device 70 for power generators in an electricity-carbon coupling market based on a gradient algorithm is provided, comprising:

[0141] The communication device 71 is used to send the quotation information submitted by the power generator before the transaction day to the operator's equipment, and obtain the winning bid power and clearing power price of the power generator in each period during the transaction day fed back by the equipment based on the quotation information.

[0142] The processing module 72 is used to determine the carbon trading volume of the power producer for each time period according to the bid-winning electricity, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation.

[0143] The processing module 72 is also used to determine the numerical interval to which the carbon trading volume belongs for each time period, and determine the carbon trading cost corresponding to the carbon trading volume based on the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume; wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the correlation includes the reward coefficient of carbon trading; wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the correlation includes the penalty coefficient of carbon trading.

[0144] The processing module 72 is further used to determine the total revenue of the power generator on the trading day according to the clearing electricity price of the power generator in each time period, the winning electricity volume in each time period and the carbon trading cost in each time period.

[0145] Iteration module 73 is used to update the quotation information when the total revenue of the power generator on the trading day is less than the preset total revenue, and return to the step of sending the quotation information submitted by the power generator before the trading day to the operator's equipment and continue to execute until the total revenue of the power generator on the trading day is determined to be greater than or equal to the preset total revenue.

[0146] The acquisition module 74 is used to acquire the quotation information obtained by the last update as the target quotation information.

[0147] In one embodiment, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the processing module 72 is used to: determine the first value based on the reward coefficient and the first increase coefficient in the association relationship; determine the first product value between the negative interval length and the first increase coefficient, and determine the second value based on the first product value and the carbon trading volume; determine the second product value between the first value, the second value and the carbon trading price, and use the second product value as the carbon trading cost corresponding to the carbon trading volume.

[0148] In one embodiment, when the minimum value in the numerical interval is greater than the preset negative interval length and the maximum value is less than the preset positive interval length, the processing module 72 is used to: determine the third product value between the carbon trading price, the carbon trading volume and the penalty coefficient in the association relationship, and use the third product value as the carbon trading cost corresponding to the carbon trading volume.

[0149] In one embodiment, when the minimum value in the numerical interval is greater than or equal to the preset positive interval length, the processing module 72 is used to: determine the third value based on the penalty coefficient and the second increase coefficient in the association relationship; determine the third product value of the carbon trading price, the third value and the positive interval length; determine the fourth value based on the penalty coefficient, the second increase coefficient and the carbon trading price; determine the fourth product value between the second increase coefficient and the positive interval length, and determine the difference between the carbon trading volume and the fourth product value as the fifth value; determine the fifth product value between the fourth value and the fifth value; determine the value obtained by adding the third product value and the fifth product value as the carbon trading cost.

[0150] In one embodiment, the larger the first increase coefficient is, the smaller the corresponding preset negative interval length is; and the larger the second increase coefficient is, the larger the corresponding positive interval length is.

[0151] In one embodiment, the processing module 72 is used to: determine, for each time period, the sixth product value between the clearing electricity price and the winning electricity amount; determine the first difference between the sixth product value and the power generation cost; determine the second difference between the first difference and the carbon trading cost and use it as the power generator's income in the time period; determine the sum of the power generator's income in each time period, and use the sum as the total income of the power generator on the trading day.

[0152] Each module in the above-mentioned gradient algorithm-based electricity-carbon coupling market power generator balanced bidding device 70 can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0153] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store quotation information, winning electricity volume, clearing electricity price, carbon trading volume, carbon trading cost, total revenue and other information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements the balanced bidding method for power generators in the electric-carbon coupling market based on the gradient algorithm provided in any of the above embodiments.

[0154] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for balanced bidding for power generators in the electricity-carbon coupling market based on a gradient algorithm as provided in any of the above embodiments is implemented.

[0156] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the balanced bidding method for power generators in the electricity-carbon coupling market based on a gradient algorithm as provided in any of the above embodiments.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0159] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for balanced bidding of power generators in the electricity-carbon coupling market based on a gradient algorithm, characterized in that: The method comprises: Send the bid information submitted by the power generator before the transaction day to the operator's equipment, and obtain the winning bid power and clearing power price of the power generator in each period during the transaction day fed back by the equipment based on the bid information; For each time period, the carbon trading volume of the power producer is determined based on the winning electricity volume, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation; For each time period, determine the numerical interval to which the carbon trading volume belongs, and determine the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume; wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the correlation includes the reward coefficient of carbon trading; wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the correlation includes the penalty coefficient of carbon trading; Determine the total revenue of the power generator on the trading day based on the power clearing price of the power generator in each period, the amount of electricity won in each period and the carbon trading cost in each period; In the case where the total revenue of the power generator on the trading day is less than the preset total revenue, the quotation information is updated, and the step of returning to the step of sending the quotation information submitted by the power generator before the trading day to the operator's equipment is continued until the total revenue of the determined power generator on the trading day is greater than or equal to the preset total revenue, and the quotation information obtained from the last update is obtained as the target quotation information.

2. The method according to claim 1, characterized in that: When the maximum value in the numerical interval is less than or equal to the preset negative interval length, the determining of the carbon trading cost corresponding to the carbon trading amount according to the correlation between the carbon trading amount, the carbon trading cost corresponding to the numerical interval and the carbon trading amount includes: Determining a first value according to the reward coefficient and the first increase coefficient in the association relationship; Determine a first product value between the negative interval length and the first increase coefficient, and determine a second value according to the first product value and the carbon trading volume; A second product value between the first value, the second value and the carbon trading price is determined, and the second product value is used as the carbon trading cost corresponding to the carbon trading volume.

3. The method according to claim 2, characterized in that When the minimum value in the numerical interval is greater than the preset negative interval length and the maximum value is less than the preset positive interval length, the determining of the carbon trading cost corresponding to the carbon trading amount according to the correlation between the carbon trading amount, the carbon trading cost corresponding to the numerical interval and the carbon trading amount includes: A third product value among the carbon trading price, the carbon trading volume and the penalty coefficient in the association relationship is determined, and the third product value is used as the carbon trading cost corresponding to the carbon trading volume.

4. The method according to claim 3, characterized in that When the minimum value in the numerical interval is greater than or equal to the preset positive interval length, the determining of the carbon trading cost corresponding to the carbon trading amount according to the correlation between the carbon trading amount, the carbon trading cost corresponding to the numerical interval and the carbon trading amount includes: Determine a third value according to the penalty coefficient and the second increase coefficient in the association relationship; Determine a third product value of the carbon trading price, the third value and the length of the positive interval; Determining a fourth value according to the penalty coefficient, the second increase coefficient and the carbon trading price; Determine a fourth product value between the second increase coefficient and the positive interval length, and determine a difference between the carbon trading volume and the fourth product value as a fifth value; determining a fifth product value between the fourth value and the fifth value; A value obtained by adding the third product value and the fifth product value is determined as the carbon trading cost.

5. The method according to claim 4, characterized in that The larger the first increase coefficient is, the smaller the corresponding preset negative interval length is; the larger the second increase coefficient is, the larger the corresponding positive interval length is.

6. The method according to any one of claims 1 to 5, characterized in that: The total revenue of the power generator on the trading day is determined based on the clearing electricity price of the power generator in each period, the winning electricity volume in each period and the carbon trading cost in each period, including: For each time period, determine the sixth product value between the clearing electricity price and the winning bid electricity; determine the first difference between the sixth product value and the power generation cost; determine the second difference between the first difference and the carbon trading cost and use it as the income of the power generator in the time period; Determine the sum of the generator's revenue in each period and use the sum as the generator's total revenue for the trading day.

7. A balanced bidding device for power generators in the electricity-carbon coupling market based on a gradient algorithm, characterized in that: The device comprises: The communication device is used to send the quotation information submitted by the power generator before the transaction day to the operator's equipment, and obtain the winning bid power and clearing power price of the power generator in each period during the transaction day fed back by the equipment based on the quotation information; A processing module is used to determine the carbon trading volume of the power supplier for each time period according to the bid-winning electricity volume, the unit carbon emission quota corresponding to the unit power generation, and the unit carbon emission coefficient corresponding to the unit power generation; The processing module is further used to determine the numerical interval to which the carbon trading volume belongs for each time period, and determine the carbon trading cost corresponding to the carbon trading volume according to the correlation between the carbon trading volume, the carbon trading cost corresponding to the numerical interval and the carbon trading volume; wherein, when the maximum value in the numerical interval is less than or equal to the preset negative interval length, the correlation includes the reward coefficient of carbon trading; wherein, when the minimum value in the numerical interval is greater than the preset negative interval length, the correlation includes the penalty coefficient of carbon trading; The processing module is also used to determine the total revenue of the power generator on the trading day according to the clearing electricity price of the power generator in each period, the winning electricity volume in each period and the carbon trading cost in each period; An iteration module, configured to update the quotation information when the total revenue of the power generator on the trading day is less than the preset total revenue, and return to the step of sending the quotation information submitted by the power generator before the trading day to the operator's device and continue to execute until the total revenue of the power generator on the trading day is greater than or equal to the preset total revenue; The acquisition module is used to acquire the quotation information obtained by the last update as the target quotation information.

8. 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 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images