A multi-market coupling forecasting system for electricity, carbon and green certificates

Abstract

This specification provides an electricity-carbon-green certificate multi-market coupling prediction system, which predicts the changing law of short-term variables through a first model, predicts the changing law of medium- and long-term variables through a second model, automatically drives the first model to run through a computing engine, and automatically drives the second model to run when the first model runs for a preset number of times, and automatically drives the first model to continue running after the second model runs once... In this way, the changing law of short-term variables and long-term variables in multi-market coupling scenarios is automatically predicted, thereby meeting the needs of observing the changing law of short-term data in some scenarios; the changing law of long-term variables is further predicted based on the real-time prediction data of short-term variables, and the changing law of short-term variables is further predicted based on the real-time prediction data of long-term variables, while considering the impact of changes in the values ​​of short-term variables and long-term variables, so that data prediction is more accurate, which can provide more accurate support for data research.

Description

Technical Field

[0001] The present application relates to the field of renewable energy power generation technology, and in particular to an electricity-carbon-green certificate multi-market coupling forecasting system. Background Art

[0002] To promote carbon neutrality and green energy transformation, the coordination and coupling of the electricity market, carbon emissions market and green certificate market have become crucial. Establishing an electricity-carbon-green certificate multi-market coupling forecasting system will help analyze the inherent mechanism of the impact of the carbon market and green certificate market on the electricity market.

[0003] The existing electricity-carbon-green certificate multi-market coupling forecasting system is usually a medium- and long-term data forecasting system, which means that it assumes that it takes a long time for data to change, such as a year.

[0004] However, in actual situations, some variables are short-term data, that is, the data changes in a short period of time, such as power demand and power price data, which change every day. The existing multi-market coupling forecasting system is difficult to accurately reflect the changing patterns of short-term data. Summary of the invention

[0005] This specification provides an electricity-carbon-green certificate multi-market coupling forecasting system to solve the problem that the existing multi-market coupling forecasting system is difficult to accurately reflect the law of short-term data changes.

[0006] To solve the above technical problems, the first aspect of this specification provides an electricity-carbon-green certificate multi-market coupling prediction system, including: a first model, used to predict the change law of multiple first-category variables in the electricity-carbon-green certificate multi-market coupling scenario; the data change cycle of the first-category variables is shorter than the preset time threshold; a second model, used to predict the change law of multiple second-category variables in the electricity-carbon-green certificate multi-market coupling scenario; the data change cycle of the second-category variables exceeds the preset time threshold; a computing engine, including a counter and a first driving module and a second driving module; the counter is used to record the number of times the first model is run; when the count value of the counter reaches the preset number of times, the second driving module drives the second model to run once; then, the first driving module drives the first model to continue running; when the second model runs, the data generated by the latest run of the first model is used, and when the first model runs, the data generated by the latest run of the second model is used.

[0007] In some embodiments, the first category of variables includes: actual electricity demand, spot electricity price, expected electricity supply; actual green certificate demand, green certificate supply-demand ratio, green certificate supply, expected renewable energy output, green certificate price, renewable energy profit margin; expected carbon quota supply, carbon quota supply-demand ratio, carbon quota price, expected carbon quota demand, conventional energy profit margin, and expected conventional energy output; the second category of variables includes installed capacity of renewable energy units, installed capacity of conventional energy units, and expected total carbon quota supply; the installed capacity of renewable energy units output by the second model is further input into the first model to determine the expected output of renewable energy in the first model; the installed capacity of conventional energy units output by the second model is further input into the first model to determine the expected output of conventional energy in the first model; the expected total carbon quota supply output by the second model is further input into the first model to determine the expected supply of carbon quota in the first model; the expected output of renewable energy in the first model is further input into the second model to determine the installed capacity of renewable energy units in the second model; the expected output of conventional energy in the first model is further input into the second model to determine the installed capacity of conventional energy units in the second model.

[0008] In some embodiments, the relationship between the expected output of conventional energy and the profit margin of conventional energy is:

[0009]

[0010]

[0011] Among them, ΔQ f1 (t) represents the expected output change of conventional energy affected by profit change, in KWH; ΔP f (t) represents the change in the profit margin of conventional energy; K represents the proportionality coefficient; Q f (t+1) represents the expected output of conventional energy on day t+1, in KWH; Q f (t) represents the expected output of conventional energy on day t, in KWH;

[0012] The relationship between the expected demand for carbon quotas and the expected output of conventional energy is:

[0013]

[0014] Among them, Q C,d( t) represents the expected demand for carbon quotas, in tCO2; E f represents the carbon emission factor;

[0015] The relationship between the expected supply of carbon quotas and the expected supply of total carbon quotas is:

[0016]

[0017] Among them, Q C,p (t) represents the expected supply of carbon quota, in tCO2; Q C,t represents the expected supply of total carbon quotas, in tCO2; r1 represents the auction ratio coefficient; It indicates the total output of conventional energy in a certain period of time; It represents the total expected output of conventional energy in one year;

[0018] The relationship between the expected demand and supply of carbon quotas and the carbon quota supply-demand ratio is:

[0019]

[0020] Among them, R C (t) represents the carbon quota supply-demand ratio;

[0021] The relationship between the carbon quota supply-demand ratio and the carbon quota price:

[0022]

[0023]

[0024] Among them, ΔP C (t) represents the change in carbon quota price; ΔR C (t) represents the change in the carbon quota supply-demand ratio; P C (t+1) represents the carbon quota price on day t+1; P C (t) represents the carbon quota price on day t;

[0025] The relationship between carbon quota price and expected output of conventional energy is:

[0026]

[0027]

[0028] Among them, ΔQ f2 (t) represents the expected change in conventional energy output due to changes in carbon quota prices, in KWH;

[0029] In some embodiments, the relationship between the expected output of renewable energy and the profit margin of renewable energy is:

[0030]

[0031]

[0032] Among them, ΔQ r(t) represents the expected output change of renewable energy, in KWH; ΔP r (t) represents the change in the profit margin of renewable energy; Q r (t+1) represents the expected output of renewable energy on day t+1, in KWH; Q r (t) represents the expected output of renewable energy on day t, in KWH;

[0033] The relationship between the actual supply of green certificates and the expected output of renewable energy is as follows:

[0034]

[0035] Among them, Q TGC,P (t) represents the actual supply of green certificates, in units;

[0036] The relationship between the green certificate supply-demand ratio and the actual supply and demand of green certificates is as follows:

[0037]

[0038] Among them, R TGC (t) represents the green certificate supply-demand ratio; Q TGC,d (t) represents the actual demand for green certificates, in units;

[0039] The relationship between the actual demand for green certificates and the actual demand for electricity is:

[0040]

[0041] Among them, Q e,d (t) represents the actual power demand, in KWH; G r Indicates renewable energy planning targets;

[0042] The relationship between renewable energy profit margin and green certificate price:

[0043]

[0044] Among them, P r (t) represents the profit margin of renewable energy; P e (t) represents the spot electricity price; P e0 (t) represents the base price of electricity; P TGC (t) represents the green certificate price; P TGC0 (t) represents the base price of green certificates.

[0045] In some embodiments, the expression for the actual power demand is:

[0046]

[0047] Among them, Qe,d (t) represents the actual power demand, in KWH; Q a (t) represents the load reference, in KWH;

[0048] The relationship between the expected power supply and the expected output of renewable energy and conventional energy is as follows:

[0049]

[0050] Among them, Q e (t) represents the expected power supply, in KWH; Q r (t) represents the expected output of renewable energy on day t, in KWH; Q f (t) represents the expected output of conventional energy on day t, in KWH.

[0051] The relationship between conventional energy profit margin and electricity price:

[0052]

[0053] Among them, P f (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P c (t) represents the carbon quota price on day t; P c0 (t) represents the carbon quota base price on day t;

[0054] The relationship between the spot profit margin of renewable energy and electricity price:

[0055]

[0056] Among them, P r (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P TGC (t) represents the green certificate price on the tth day; P TGC0 (t) represents the base price of the green certificate on the tth day.

[0057] The relationship between the power supply-demand ratio and the spot electricity price is:

[0058]

[0059]

[0060] Among them, ΔP e (t) represents the change in spot electricity price; ΔRe (t) represents the change in the power supply-demand ratio; ΔP e (t+1) represents the spot electricity price on day t+1; P e (t) represents the spot electricity price on day t.

[0061] In some embodiments, the system further includes: an interactive module for a user to input an additional threshold, wherein the additional threshold indicates that when the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, the second model outputs the expanded installed capacity.

[0062] In some embodiments, the interaction module is further used to present to the user the installed capacity outputted each time the second model is run.

[0063] In some embodiments, the second model performs the following operations: obtaining a predetermined number of installed capacity data output by the second model before the current time; using a network model to learn the changing trend between the predetermined number of installed capacity data, and predicting the installed capacity after the current time, and using the installed capacity prediction value as the required installed capacity.

[0064] In some embodiments, the second model performs the following operations: the interactive module is also used for the user to input the maximum value of the installed capacity expansion; when the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, if the difference is greater than the maximum value of the installed capacity expansion, the installed capacity after expansion output by the second model is the sum of the existing installed capacity and the maximum value of the installed capacity expansion.

[0065] In some embodiments, the first model and / or the second model includes N variables; the data on the changes of NM variables over time are input into the electricity-carbon-green certificate multi-market coupling forecasting system to obtain the law of changes of M variables over time; wherein M and N are integers greater than 0; the interactive module is also used to obtain the initial value of any variable among the M variables input by the user.

[0066] The second aspect of this specification provides an electronic device, comprising: a memory and a processor, the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to implement the electricity-carbon-green certificate multi-market coupling forecasting system as described in any one of the first aspects.

[0067] The electricity-carbon-green certificate multi-market coupling prediction system provided in this specification predicts the changing law of short-term variables through the first model, predicts the changing law of medium- and long-term variables through the second model, automatically drives the first model to run through the computing engine, and automatically drives the second model to run when the first model runs a preset number of times, and automatically drives the first model to continue running after the second model runs once... In this way, the changing law of short-term variables and long-term variables in the electricity-carbon-green certificate multi-market coupling scenario is automatically predicted, thereby meeting the needs of observing the changing law of short-term data in some scenarios.

[0068] In addition, in the above-mentioned electricity-carbon-green certificate multi-market coupled prediction system, the second model uses the data generated by the latest operation of the first model when it is running, and the first model uses the data generated by the latest operation of the second model when it is running. That is to say, the real-time prediction data of short-term variables is used to further predict the changing law of long-term variables, and the real-time prediction data of long-term variables is used to further predict the changing law of short-term variables. At the same time, the impact of changes in the values ​​of short-term variables and changes in the values ​​of long-term variables are taken into account, and the impact of any one of them is not ignored. Therefore, the data prediction of the multi-market coupled prediction system is more accurate, and can provide more accurate support for data research. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0070] Figure 1 A schematic diagram of the electricity-carbon-green certificate multi-market coupling forecasting system provided in this specification;

[0071] Figure 2 Another schematic diagram of the electricity-carbon-green certificate multi-market coupling forecasting system provided for this specification;

[0072] Figure 3 A schematic diagram of a multi-market coupled forecasting system for electricity, carbon and green certificates when short-term variables and long-term variables are not separated;

[0073] Figure 4 This is a schematic diagram of the structure of the electronic device provided in this manual. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0075] This specification provides a multi-market coupling forecasting system for electricity, carbon and green certificates, such as Figure 1 As shown, the system includes a first model, a second model and a calculation engine.

[0076] The first model is used to predict the changing rules of multiple first-category variables in the scenario of electricity-carbon-green certificate multi-market coupling. The data change cycle of the first-category variables is shorter than the preset time threshold, that is, the first-category variables are variables with a short data change cycle, that is, short-term variables. For example, the first-category variables can be electricity demand and electricity prices.

[0077] The second model is used to predict the changing patterns of multiple second-category variables in the scenario of electricity-carbon-green certificate multi-market coupling. The data change cycle of the second-category variables exceeds the preset time threshold, that is, the second-category variables are variables with a longer data change cycle, that is, medium- and long-term variables. For example, the second-category variables can be installed capacity, including installed capacity of renewable energy units and installed capacity of conventional energy units.

[0078] The above-mentioned preset time threshold can be determined according to the predetermined short-term and medium- to long-term time lengths. For example, the short-term can be one day, and the medium- to long-term can be one month or one year, so the preset time threshold can be, for example, 25 hours.

[0079] The computing engine includes a counter and a first driving module and a second driving module. The counter is used to record the number of times the first model is run. When the count value of the counter reaches a preset number of times, the second driving module drives the second model to run once. Then, the first driving module drives the first model to continue running.

[0080] When the second model is running, the data generated after the first model is most recently run is used, and when the first model is running, the data generated after the second model is most recently run is used.

[0081] The electricity-carbon-green certificate multi-market coupling prediction system provided in this specification predicts the changing law of short-term variables through the first model, predicts the changing law of medium- and long-term variables through the second model, automatically drives the first model to run through the computing engine, and automatically drives the second model to run when the first model runs a preset number of times, and automatically drives the first model to continue running after the second model runs once... In this way, the changing law of short-term variables and long-term variables in the electricity-carbon-green certificate multi-market coupling scenario is automatically predicted, thereby meeting the needs of observing the changing law of short-term data in some scenarios.

[0082] In addition, in the above-mentioned electricity-carbon-green certificate multi-market coupled prediction system, the second model uses the data generated by the latest operation of the first model when it is running, and the first model uses the data generated by the latest operation of the second model when it is running. That is to say, the real-time prediction data of short-term variables is used to further predict the changing law of long-term variables, and the real-time prediction data of long-term variables is used to further predict the changing law of short-term variables. At the same time, the impact of changes in the values ​​of short-term variables and changes in the values ​​of long-term variables are taken into account, and the impact of any one of them is not ignored. Therefore, the data prediction of the multi-market coupled prediction system is more accurate, and can provide more accurate support for data research.

[0083] In some embodiments, Figure 2 As shown, the first category of variables includes: actual electricity demand, spot electricity price, expected electricity supply; actual demand for green certificates, green certificate supply-demand ratio, green certificate supply, expected output of renewable energy, green certificate price, and profit margin of renewable energy; expected supply of carbon quota, carbon quota supply-demand ratio, carbon quota price, expected demand for carbon quota, profit margin of conventional energy, and expected output of conventional energy.

[0084] The second category of variables includes installed capacity of renewable energy units, installed capacity of conventional energy units, and expected supply of total carbon quotas.

[0085] The installed capacity of renewable energy units output by the second model is further input into the first model to determine the expected output of renewable energy in the first model; the installed capacity of conventional energy units output by the second model is further input into the first model to determine the expected output of conventional energy in the first model; the expected supply of total carbon quota output by the second model is further input into the first model to determine the expected supply of carbon quota in the first model.

[0086] The expected output of renewable energy in the first model is further input into the second model to determine the installed capacity of renewable energy units in the second model; the expected output of conventional energy in the first model is further input into the second model to determine the installed capacity of conventional energy units in the second model.

[0087] Specifically, the first model can be constructed based on the following five premises: 1. Considering the operation of electricity-carbon-green certificate multi-market coupled transactions, planning issues are not considered, and the investment in renewable energy capacity and conventional energy capacity is ignored; 2. In the model of the carbon market trading module, the supply and demand relationship of carbon quotas is considered to affect carbon prices; 3. In the model of the green certificate market trading module, the supply and demand relationship of green certificates is considered to affect the price of green certificates; 4. In the multi-market coupled prediction model, the influence of electricity supply and demand on spot market electricity prices is considered, and the supply and demand relationship is affected by green certificate transactions and carbon transactions on the spot market supply; 5. The electricity market considered is the spot market.

[0088] The first model can specifically include a carbon market trading module, a green certificate market trading module and an electricity market trading module.

[0089] In the carbon market trading module, such as Figure 2 As shown, the price of carbon quota is affected by the carbon quota supply-demand ratio, which can be calculated based on the expected demand for carbon quota and the expected supply of carbon quota. The expected demand for carbon quota is affected by the expected output of conventional energy, and the expected output of conventional energy is affected by the price of carbon quota, thus forming a closed loop. At the same time, the expected output of conventional energy is affected by the profit margin of conventional energy. Based on the above qualitative analysis, the following relationships between the variables can be obtained:

[0090] 1.1 The relationship between the expected output of conventional energy and the profit margin of conventional energy is:

[0091] (1)

[0092] (2)

[0093] Among them, ΔQ f1 (t) represents the expected output change of conventional energy affected by profit change, in KWH; ΔP f (t) represents the change in the profit margin of conventional energy; K represents the proportionality coefficient; Q f (t+1) represents the expected output of conventional energy on day t+1, in KWH; Q f (t) represents the expected output of conventional energy on day t, in KWH.

[0094] The expected output of conventional energy can be calculated based on the installed capacity of conventional energy units provided by the second model. Specifically, in some embodiments, the expected output of conventional energy = installed capacity of conventional energy units * average annual utilization hours * profit margin of conventional energy / 12, and the average annual utilization hours of conventional energy units are generally 5294 hours / year.

[0095] The profit margin of conventional energy, i.e. the profit rate, can be expressed by price. Specifically, the profit margin of conventional energy = [electricity price / electricity benchmark price] / [carbon quota price / carbon quota benchmark price]. The electricity benchmark price can be 0.38 yuan / kWh, and the carbon quota benchmark price can be 50 yuan / ton. The daily carbon quota price can be obtained from the carbon market trading platform.

[0096] 1.2 The relationship between the expected demand for carbon quotas and the expected output of conventional energy:

[0097] (3)

[0098] Among them, Q C,d( t) represents the expected demand for carbon quotas, in tCO2; E f Represents carbon emission factor. Carbon emission factor refers to the amount of carbon emissions generated per unit of electricity generated.

[0099] 1.3 Relationship between expected carbon quota supply and expected total carbon quota supply:

[0100] (4)

[0101] Among them, Q C,p (t) represents the expected supply of carbon quota, in tCO2; Q C,t represents the expected supply of total carbon quotas, in tCO2; r1 represents the power industry proportion coefficient; It indicates the total output of conventional energy in a certain period of time; It represents the total expected output of conventional energy in one year.

[0102] The expected supply of total carbon quotas may be provided by the second model.

[0103] 1.4 The relationship between the expected demand for carbon quotas, the expected supply of carbon quotas and the carbon quota supply-demand ratio is:

[0104] (5)

[0105] Among them, R C (t) represents the carbon quota supply-demand ratio.

[0106] 1.5 The relationship between the carbon quota supply-demand ratio and the carbon quota price:

[0107] (6)

[0108] (7)

[0109] Among them, ΔP C (t) represents the change in carbon quota price; ΔR C(t) represents the change in the carbon quota supply-demand ratio; P C (t+1) represents the carbon quota price on day t+1; P C (t) represents the carbon quota price on the tth day; f() represents the functional relationship between the change in carbon quota price and the change in the carbon quota supply-demand ratio, and a specific expression can be fitted based on the acquired variable data. The daily carbon quota price can be obtained from the carbon market trading platform.

[0110] 1.6 The relationship between carbon quota price and expected output of conventional energy:

[0111] (8)

[0112] (9)

[0113] Among them, ΔQ f2 (t) represents the expected change in conventional energy output due to changes in carbon quota prices, in KWH; g() represents ΔQ f2 (t) and ΔP C The functional relationship expression of (t) can be used to fit a specific expression based on the acquired variable data.

[0114] In the carbon trading market, GDP and carbon emission intensity jointly determine the carbon reduction target, and the carbon reduction target affects the supply of carbon quotas. The expected demand for carbon quotas is related to the expected output of conventional energy. The higher the expected output of conventional energy, the higher the expected demand for carbon quotas. The causal links in the carbon market trading module are:

[0115] Changes in carbon quota prices → expected output of conventional energy → expected demand for carbon quotas → carbon quota supply-demand ratio → carbon quota price → expected output of conventional energy, expected supply of carbon quotas → carbon quota supply-demand ratio, conventional energy profit margin → expected output of conventional energy.

[0116] Figure 3 This is a schematic diagram of a multi-market coupled forecasting system for electricity, carbon and green certificates when short-term variables and long-term variables are not separated. Figure 3 The electricity-carbon-green certificate multi-market coupling prediction system provided in this manual separates short-term variables from long-term variables, so that the carbon market trading module can be simplified as follows: (1) When the carbon market trading module is running, the default supply of total carbon quotas is fixed, which simplifies the auction ratio → auction quota → carbon price path; (2) Simplifies the carbon quota demand → carbon quota price → carbon quota demand feedback loop; (3) Simplifies the carbon quota price → carbon quota supply → carbon quota price feedback loop; (4) Simplifies the conventional energy power generation income → conventional energy installed capacity → conventional energy power generation → carbon quota supply → carbon price → conventional energy power generation cost path.

[0117] In the Green Certificate Market Trading Module, refer to Figure 2 , the spot profit margin of renewable energy is affected by the change of green certificate price, the green certificate price is affected by the green certificate supply-demand ratio, the green certificate supply-demand ratio can be calculated based on the actual demand for green certificates and the actual supply of green certificates, the actual demand for green certificates is affected by the actual demand for electricity, the actual supply of green certificates is affected by the expected output of renewable energy, and the expected output of renewable energy is affected by the profit margin of renewable energy, thus forming a closed loop. Based on the above qualitative analysis, the following relationships between the variables can be obtained:

[0118] 2.1 The relationship between expected output of renewable energy and profit margin of renewable energy:

[0119] (10)

[0120] (11)

[0121] Among them, ΔQ r (t) represents the expected output change of renewable energy, in KWH; ΔP r (t) represents the change in the profit margin of renewable energy; Q r (t+1) represents the expected output of renewable energy on day t+1, in KWH; Q r (t) represents the expected output of renewable energy on day t, in KWH; f() represents ΔQ r (t) and ΔP r The functional relationship expression of (t) can be used to fit a specific expression based on the acquired variable data.

[0122] The expected output of renewable energy can be calculated based on the installed capacity of renewable energy units provided by the second model. Specifically, in some embodiments, the expected output of renewable energy = installed capacity of renewable energy units * annual average utilization hours * renewable energy profit margin / 12, and the annual average utilization hours of renewable energy units are generally 2147 hours / year.

[0123] The profit margin of renewable energy, i.e. the profit rate, can be expressed by price. Specifically, the profit margin of renewable energy = [electricity price / electricity benchmark price] * [green certificate price / green certificate benchmark price]. The electricity benchmark price can be 0.38 yuan / kWh, and the green certificate benchmark price can be 0.22 yuan / kWh. The daily green certificate price can be obtained from the green certificate trading platform.

[0124] 2.2 The relationship between the actual supply of green certificates and the expected output of renewable energy:

[0125] (12)

[0126] Among them, Q TGC,P (t) represents the actual supply of green certificates, in units of pieces.

[0127] 2.3 The relationship between the supply-demand ratio of green certificates and the actual supply and demand of green certificates:

[0128] (13)

[0129] Among them, R TGC (t) represents the supply-demand ratio of green certificates; Q TGC,d (t) represents the actual demand for green certificates, in units of pieces.

[0130] 2.4 The relationship between the actual demand for green certificates and the actual demand for electricity:

[0131] (14)

[0132] Among them, Q e,d (t) represents the actual power demand, in KWH; G r Represents the renewable energy planning target. The renewable energy planning target is specifically the proportion of renewable energy in electricity consumption. Based on this proportion and the total electricity consumption, the installed capacity of renewable energy units can be calculated.

[0133] 2.5 The relationship between renewable energy profit margin and green certificate price:

[0134] (15)

[0135] Among them, P r (t) represents the profit margin of renewable energy; P e (t) represents the spot electricity price; P e0 (t) represents the base price of electricity; P TGC (t) represents the green certificate price; P TGC0 (t) represents the green certificate benchmark price. The daily green certificate price can be obtained from the green certificate trading platform.

[0136] When considering the profit margin of renewable energy, the traditional model does not consider the price of green certificates as a direct factor affecting the profit margin of renewable energy. In the simplified model of the green certificate trading module of the present invention, the impact of the price of green certificates on the profit margin of renewable energy is considered. The price of green certificates and the profit margin of renewable energy change in the same direction: when the price of green certificates rises, the profit of renewable energy will increase; when the price of green certificates falls, the profit of renewable energy will decrease.

[0137] Impact of actual demand for green certificates: Green certificates are an indicator for measuring the amount of electricity generated by renewable energy. The medium- and long-term electricity bundled with green certificates does not generate additional green certificate revenue. When considering the impact on the actual demand for green certificates, the traditional multi-market coupling forecasting model uses the change in the RPS quota ratio to affect the demand for green certificates. The simplified model of the present invention uses the actual demand for electricity in the spot power market to affect the actual demand for green certificates. The actual demand for electricity and the actual demand for green certificates change in the same direction: when the actual demand for electricity increases, the actual demand for green certificates will also increase; when the actual demand for electricity decreases, the actual demand for green certificates will also decrease.

[0138] The causal chain in the green certificate market trading module is: renewable energy profit margin → expected renewable energy output → actual supply of green certificates → green certificate supply-demand ratio → green certificate price → renewable energy profit margin, actual electricity demand → actual demand for green certificates → green certificate supply-demand ratio → green certificate price → renewable energy profit margin.

[0139] Figure 3 This is a schematic diagram of a multi-market coupled forecasting system for electricity, carbon and green certificates when short-term variables and long-term variables are not separated. Figure 3 The electricity-carbon-green certificate multi-market coupling forecasting system provided in this manual separates short-term variables from long-term variables, so that the green certificate trading module can be simplified as follows: (1) The path of RPS quota ratio → green certificate demand is modified to actual electricity demand → actual green certificate demand; (2) The path of green certificate price → renewable energy profit margin → expected renewable energy output is introduced; (3) The path of renewable energy power generation income → renewable energy installed capacity → renewable energy power generation → green certificate demand → green certificate price is simplified.

[0140] like Figure 2 As shown, the electricity-carbon-green certificate multi-market coupling prediction system provided in this specification has two coupling relationships: 1. Coupling of the carbon market and the spot electricity market: the profit margin of conventional energy is affected by the electricity price in the spot electricity market. Changes in electricity prices affect the profit margin of conventional energy. The profit margin of conventional energy affects the expected output of conventional energy. The expected output of conventional energy affects the expected electricity supply in the spot market, thereby realizing the coupling of the electricity-carbon market; 2. Coupling of the green certificate market and the spot electricity market: the profit margin of renewable energy is affected by the electricity price in the spot electricity market. Changes in electricity prices affect the profit margin of renewable energy. The profit margin of renewable energy affects the expected output of renewable energy. The expected output of renewable energy affects the expected electricity supply in the spot market, thereby realizing the coupling of the electricity-green certificate market.

[0141] Combining the green certificate trading module and the carbon market trading module, a simplified model of electricity-carbon-green certificate multi-market coupling trading is constructed, in which the main mathematical relationships are as follows:

[0142] The expression of actual power demand is:

[0143] (16)

[0144] Among them, Q e,d (t) represents the actual power demand, in KWH; Q a (t) represents the load reference, the unit is KWH.

[0145] The relationship between the expected power supply and the expected output of renewable energy and conventional energy is as follows:

[0146] (17)

[0147] Among them, Q e (t) represents the expected power supply, in KWH; Q r (t) represents the expected output of renewable energy on day t, in KWH; It represents the expected output of conventional energy on day t, in KWH.

[0148] The relationship between conventional energy profit margin and electricity price:

[0149] (18)

[0150] Among them, P f (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P c (t) represents the carbon quota price on day t; P c0 (t) represents the carbon quota base price on day t.

[0151] The relationship between the spot profit margin of renewable energy and electricity price:

[0152] (19)

[0153] Among them, P r (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P TGC (t) represents the green certificate price on the tth day; P TGC0 (t) represents the base price of the green certificate on the tth day.

[0154] The relationship between the power supply-demand ratio and the spot electricity price is:

[0155] (20)

[0156] (twenty one)

[0157] Among them, ΔP e (t) represents the change in spot electricity price; ΔR e (t) represents the change in the power supply-demand ratio; ΔP e (t+1) represents the spot electricity price on day t+1; P e (t) represents the spot electricity price on day t.

[0158] The electricity-carbon-green certificate multi-market coupling prediction system proposed in this invention analyzes the multi-market coupling transaction relationship, in which the green certificate trading module and the electricity market module have important interactions, and the key influences mainly include: (1) the actual electricity demand in the electricity market determines the actual demand for green certificates; (2) the spot electricity price affects the profit margin of renewable energy; (3) the expected output of renewable energy affects the expected supply of electricity. The key influences of the carbon market trading module and the electricity market module include: (1) the spot electricity price affects the profit margin of conventional energy (2) the expected output of conventional energy affects the expected supply of electricity.

[0159] In some embodiments, the system further includes: an interactive module for a user to input an additional threshold, wherein the additional threshold indicates that when the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, the second model outputs the expanded installed capacity.

[0160] The additional threshold can represent the actual expansion plan. Whether it is a conventional energy unit or a renewable energy unit, the cost of expansion is often relatively large, and it will not be easily expanded unless it is absolutely necessary. The design of the additional threshold makes it possible to automatically predict the actual process of installed capacity changes without the user manually entering the installed capacity, thereby making the values ​​of the long-term and short-term variables predicted by the system more accurate.

[0161] In some embodiments, the interaction module is further used to present the installed capacity output by the second model each time it is run to the user. By presenting the installed capacity output by the second model to the user, the user can observe the changing trend of the installed capacity, feel the limiting effect of the installed capacity on the multi-market coupling transaction, and thus decide whether to increase the installed capacity.

[0162] In some embodiments, the second model performs the following operations: obtaining a predetermined number of installed capacity data output by the second model before the current time; using a network model to learn the change trend between the predetermined number of installed capacity data, and predicting the installed capacity after the current time, and using the installed capacity prediction value as the required installed capacity. The above-mentioned installed capacity can be the installed capacity of conventional energy units or the installed capacity of renewable energy units. The second model can use two modules to process the installed capacity of conventional energy units and the installed capacity of renewable energy units respectively.

[0163] It should be noted that the second model is a variable coupling model, in which the expected output of conventional energy and renewable energy are affected by other variables. The installed capacity of conventional energy units in the first model is affected by the expected output of conventional energy. Therefore, the installed capacity of conventional energy units fed back by the second model must be different from the installed capacity of conventional energy units output to the second model by the first model. The difference and change trend between the installed capacity of conventional energy units fed back to the first model by the second model and the installed capacity of conventional energy units fed back to the second model by the first model can reflect the actual situation of multi-market coupling transactions for the actual demand for installed capacity expansion, making the predicted values ​​of each variable in the electricity-carbon-green certificate multi-market coupling prediction system more accurate.

[0164] In some embodiments, the second model performs the following operations: the interactive module is also used for the user to input the maximum value of the installed capacity expansion; when the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, if the difference is greater than the maximum value of the installed capacity expansion, the installed capacity after expansion output by the second model is the sum of the existing installed capacity and the maximum value of the installed capacity expansion. The above-mentioned installed capacity can be the installed capacity of conventional energy units or the installed capacity of renewable energy units. The installed capacity of conventional energy units and the installed capacity of renewable energy units can be set to different values.

[0165] By setting the maximum value of installed capacity expansion, the installed capacity expansion can be limited. This setting method takes into account the limitations of actual expansion conditions of conventional energy units and renewable energy units, making the predicted values ​​of each variable in the electricity-carbon-green certificate multi-market coupling forecasting system more accurate.

[0166] In some embodiments, the first model and / or the second model includes N variables; the data on the changes of NM variables over time are input into the electricity-carbon-green certificate multi-market coupling forecasting system to obtain the law of changes of M variables over time; wherein M and N are integers greater than 0; the interactive module is also used to obtain the initial value of any variable among the M variables input by the user.

[0167] Since the variables in the first model and the second model are complex and have direct or indirect influence relationships, the values ​​of unknown variables and their laws of change over time can be obtained when only the laws of change of some variables over time and the initial values ​​of some variables are known. Therefore, by inputting the data of changes of NM variables over time and the initial values ​​of any of the M variables into the electricity-carbon-green certificate multi-market coupling forecasting system, the change relationship between the variables at two positions (for example, when variable A increases, variable B decreases) can be observed for data research.

[0168] The embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, the electronic device may include a processor 401 and a memory 402, wherein the processor 401 and the memory 402 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0169] The processor 401 may be a central processing unit (CPU). The processor 401 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0170] The memory 402, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the wind-solar power generation company trading strategy optimization method under the background of certificate-electricity separation in the embodiment of the present invention. The processor 401 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 402, that is, to implement the wind-solar power generation company trading strategy optimization method under the background of certificate-electricity separation in the above method embodiment.

[0171] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 401, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The one or more modules are stored in the memory 402, and when executed by the processor 401, the following is performed: Figure 3 The illustrated embodiment shows a method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity.

[0173] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the method embodiment, and will not be repeated here.

[0174] This specification also provides a computer storage medium, which stores computer program instructions. When the computer program instructions are executed, the steps of the method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity are implemented.

[0175] This specification also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity.

[0176] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0177] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0178] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0179] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0180] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each implementation method of the present application.

[0181] The present application can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0182] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0183] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present application without departing from the spirit of the present application, and it is intended that the appended claims include these modifications and variations without departing from the spirit of the present application.

Claims

1. An electricity-carbon-green certificate multi-market coupling forecasting system, characterized in that: include: The first model is used to predict the change rules of multiple first-category variables in the scenario of electricity-carbon-green certificate multi-market coupling; the data change cycle of the first-category variables is shorter than the preset time threshold; The second model is used to predict the change rules of multiple second-category variables in the scenario of electricity-carbon-green certificate multi-market coupling; the data change cycle of the second-category variables exceeds the preset time threshold; A calculation engine, comprising a counter and a first driving module and a second driving module; the counter is used to record the number of times the first model is run; When the count value of the counter reaches a preset number of times, the second driving module drives the second model to run once; then, the first driving module drives the first model to continue running; When the second model is running, the data generated by the latest running of the first model is used, and when the first model is running, the data generated by the latest running of the second model is used; The first category of variables includes: actual electricity demand, spot electricity price, expected electricity supply; actual green certificate demand, green certificate supply-demand ratio, green certificate supply, expected renewable energy output, green certificate price, renewable energy profit margin; expected carbon quota supply, carbon quota supply-demand ratio, carbon quota price, expected carbon quota demand, conventional energy profit margin, and conventional energy expected output; The second category of variables includes installed capacity of renewable energy units, installed capacity of conventional energy units, and expected supply of total carbon quotas; The installed capacity of renewable energy units output by the second model is further input into the first model to determine the expected output of renewable energy in the first model; the installed capacity of conventional energy units output by the second model is further input into the first model to determine the expected output of conventional energy in the first model; the expected supply of total carbon quota output by the second model is further input into the first model to determine the expected supply of carbon quota in the first model; The expected output of renewable energy in the first model is further input into the second model to determine the installed capacity of renewable energy units in the second model; the expected output of conventional energy in the first model is further input into the second model to determine the installed capacity of conventional energy units in the second model; The system further comprises: an interactive module for a user to input an additional threshold, wherein the additional threshold indicates that when the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, the second model outputs the expanded installed capacity.

2. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The relationship between the expected output of conventional energy and the profit margin of conventional energy is: ； ； Among them, ΔQ f1 (t) represents the expected change in conventional energy output affected by profit changes, in kWh; ΔP f (t) represents the change in the profit margin of conventional energy; K represents the proportionality coefficient; Q f (t+1) represents the expected output of conventional energy on day t+1, in kWh; Q f (t) represents the expected output of conventional energy on day t, in kWh; The relationship between the expected demand for carbon quotas and the expected output of conventional energy is: ； Among them, Q C,d( t) represents the expected demand for carbon quotas, in tCO2; E f represents the carbon emission factor; The relationship between the expected supply of carbon quotas and the expected supply of total carbon quotas is: ； Among them, Q C,p (t) represents the expected supply of carbon quota, in tCO2; Q C,t represents the expected supply of total carbon quotas, in tCO2; r1 represents the power industry proportion coefficient; It indicates the total output of conventional energy in a certain period of time; It represents the total expected output of conventional energy in one year; The relationship between the expected demand and supply of carbon quotas and the carbon quota supply-demand ratio is: ； Among them, R C (t) represents the carbon quota supply-demand ratio; The relationship between the carbon quota supply-demand ratio and the carbon quota price: ； ； Among them, ΔP C (t) represents the change in carbon quota price; ΔR C (t) represents the change in the carbon quota supply-demand ratio; P C (t+1) represents the carbon quota price on day t+1; P C (t) represents the carbon quota price on day t; The relationship between carbon quota price and expected output of conventional energy is: ； ； Among them, ΔQ f2 (t) represents the expected change in conventional energy output due to changes in carbon quota prices, in kWh.

3. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The relationship between the expected output of renewable energy and the profit margin of renewable energy is as follows: ； ； Among them, ΔQ r (t) represents the expected output change of renewable energy, in kWh; ΔP r (t) represents the change in the profit margin of renewable energy; Q r (t+1) represents the expected output of renewable energy on day t+1, in kWh; Q r (t) represents the expected output of renewable energy on day t, in kWh; The relationship between the actual supply of green certificates and the expected output of renewable energy is as follows: ； Among them, Q TGC,P (t) represents the actual supply of green certificates, in units; The relationship between the green certificate supply-demand ratio and the actual supply and demand of green certificates is as follows: ； Among them, R TGC (t) represents the green certificate supply-demand ratio; Q TGC,d (t) represents the actual demand for green certificates, in units; The relationship between the actual demand for green certificates and the actual demand for electricity is: ； Among them, Q e,d (t) represents the actual power demand, in kWh; G r represents the renewable energy planning target; The relationship between renewable energy profit margin and green certificate price: ； Among them, P r (t) represents the profit margin of renewable energy; P e (t) represents the spot electricity price; P e0 (t) represents the base price of electricity; P TGC (t) represents the green certificate price; P TGC0 (t) represents the base price of green certificates.

4. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The expression of actual power demand is: ； Among them, Q e,d (t) represents the actual power demand, in kWh; Q a (t) represents the load reference in kWh; The relationship between the expected power supply and the expected output of renewable energy and conventional energy is as follows: ； Among them, Q e (t) represents the expected power supply, in kWh; Q r (t) represents the expected output of renewable energy on day t, in kWh; Q f (t) represents the expected output of conventional energy on day t, in kWh; The relationship between conventional energy profit margin and electricity price: ； Among them, P f (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P c (t) represents the carbon quota price on day t; P c0 (t) represents the carbon quota base price on day t; The relationship between the spot profit margin of renewable energy and electricity price: ； Among them, P r (t) represents the profit margin of conventional energy; P e (t) represents the electricity price on the tth day, i.e., the spot electricity price; P e0 (t) represents the base price of electricity on day t; P TGC (t) represents the green certificate price on the tth day; P TGC0 (t) represents the base price of green certificates on day t; The relationship between the power supply-demand ratio and the spot electricity price is: ； ； Among them, ΔP e (t) represents the change in spot electricity price; ΔR e (t) represents the change in the power supply-demand ratio; ΔP e (t+1) represents the spot electricity price on day t+1; P e (t) represents the spot electricity price on day t.

5. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The interaction module is also used to present the installed capacity outputted by the second model each time it is run to the user.

6. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The second model performs the following operations: Obtaining a predetermined number of installed capacity data output by the second model before the current time; A network model is used to learn the variation trend between the predetermined number of installed capacity data, and the installed capacity after the current time is predicted, and the predicted installed capacity value is used as the required installed capacity.

7. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The second model performs the following operations: The interaction module is also used for the user to input the maximum value of installed capacity expansion; When the difference between the required installed capacity and the existing installed capacity is greater than the additional threshold, if the difference is greater than the maximum installed capacity expansion value, the installed capacity after expansion output by the second model is the sum of the existing installed capacity and the maximum installed capacity expansion value.

8. The electricity-carbon-green certificate multi-market coupling forecasting system according to claim 1 is characterized in that: The first model and / or the second model includes N variables; Input the data of NM variables changing over time into the electricity-carbon-green certificate multi-market coupling forecasting system to obtain the law of M variables changing over time; where M and N are integers greater than 0; The interaction module is also used to obtain the initial value of any variable among the M variables input by the user.

9. An electronic device, characterized in that: include: A memory and a processor, the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the electricity-carbon-green certificate multi-market coupling forecasting system as described in any one of claims 1 to 8 by executing the computer instructions.

Images