Electric power spot transaction risk assessment method

Abstract

The invention relates to the field of electric power transaction risk assessment, in particular to an electric power spot transaction risk assessment method, which comprises the following steps: S1, acquiring photoelectric influence information and wind power influence information of a region where a target electric power spot supplier is located; s2, according to the photoelectric influence information and the wind power influence information, calculating the total predicted generating capacity of the target power generation party in the target time period; s3, acquiring power consumption influence information and historical power consumption information of the power grid; s4, calculating the first total electricity consumption # imgabs0 # of the power grid in the target time period according to the electricity consumption influence information and the historical electricity consumption information; according to the method, the situation that in a common power grid electricity consumption calculation method, only the individual influence of seasons, GDP growth rates, industry types and population density on the total electricity consumption is calculated is considered, and the situation that the calculation result of the power grid electricity consumption is not accurate enough due to the mutual influence among the factors is not considered, so that four coupling influence coefficients are introduced; and the accuracy of the finally calculated total power generation amount of the power grid is higher.

Description

Technical Field

[0001] The present invention relates to the field of power trading risk assessment, and specifically to a method for assessing the risk of power spot trading. Background Art

[0002] Power spot refers to the electric energy product traded in real time in the power market. The buyer and seller conduct transactions at the market price according to the current (or short-term) power supply and demand situation, usually involving the delivery of power on the next day or the same day. The risk of power spot trading is directly related to the power generation volume of the power spot supplier. If the power spot supplier cannot provide the required power spot volume as stipulated in the contract, there is a direct default risk. Generally, the power generation prediction method for power spot suppliers relying on clean energy only calculates based on the single influence of factors such as wind power or sunlight intensity, without considering the mutual influence between these factors, resulting in low final calculation accuracy. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a method for assessing the risk of power spot trading, which solves the technical problems in the above background art.

[0004] To achieve the above object, the present invention provides the following technical solutions: A method for assessing the risk of power spot trading, comprising the following steps: S1. Obtain the photovoltaic influence information and wind power influence information in the region where the target power spot supplier is located; The photovoltaic influence information includes: the solar irradiance and the solar incidence angle at each moment in the target time period; The wind power influence information includes: the atmospheric pressure and the wind speed at each moment in the target time period; S2. Calculate the total predicted power generation of the target power generation party in the target time period according to the photovoltaic influence information and the wind power influence information ; S3. Obtain the power consumption influence information and historical power consumption information of the power grid; S4. Calculate the first total power consumption of the power grid in the target time period according to the power consumption influence information and the historical power consumption information ; S5. Calculate the trading risk value according to the total predicted power generation and the first total power consumption ; .

[0005] Further, in step S2, it specifically includes the following steps: S21. Obtain the temperature information at each moment in the region where the target power spot supplier is located in the target time period; S22. Calculate the actual air density according to the temperature information and the photovoltaic efficiency influence value ; S23. Calculate the first coupling term according to the photovoltaic influence information and the wind power influence information and the second coupling term ; S24. According to the actual air density , the photovoltaic efficiency influence value , the first coupling term and the second coupling term calculate the predicted photovoltaic power generation and the predicted wind power generation ; S25. According to the predicted photovoltaic power generation and the predicted wind power generation calculate the total predicted power generation , and its calculation formula is: ; In the formula, represents the total predicted power generation of the target power generation party in the target time period.

[0006] Furthermore, in step S22, the calculation formula of the actual air density is: ; In the formula, represents the air density at the t-th moment; represents the atmospheric pressure at the t-th moment; represents the specific gas constant; represents the temperature information at the t-th moment; in the present invention, is 287.05; The calculation formula of the photovoltaic efficiency influence value is: ; In the formula, represents the actual efficiency of the photovoltaic panel at the t-th moment; represents the standard efficiency of the photovoltaic panel under standard test conditions; represents the temperature coefficient of the photovoltaic efficiency; represents the solar irradiance at the t-th moment; represents the rated operating temperature of the photovoltaic panel.

[0007] Furthermore, in step S23, the calculation formula of the first coupling term is: ; In the formula, Indicates the suppression coefficient of PV output on wind power; Indicates the maximum possible irradiance; The second coupling term The calculation formula is: ; In the formula, Indicates the mechanical suppression coefficient; Indicates the wind speed at the t-th moment; Indicates the cut-out wind speed of the wind turbine; Indicates the attenuation coefficient of dust on power generation; Indicates the dust deposition amount increased by the measured unit wind speed; Indicates the critical wind speed for sand initiation; Indicates Function; Indicates the base of the natural logarithm; Indicates the wind speed heat dissipation coefficient; Indicates the basic heat dissipation constant.

[0008] Furthermore, in step S24, the PV power generation prediction value The calculation formula is: ; In the formula, Indicates the total effective area of the PV panels; Indicates the total number of moments in the target time period; Indicates the comprehensive system loss; Indicates the solar light incident angle at the t-th moment; Indicates the time interval; The wind power generation prediction value The calculation formula is: ; In the formula, Indicates the swept area of the wind turbine; Indicates the wind energy utilization coefficient; Indicates the mechanical and electrical efficiency of the wind turbine.

[0009] Furthermore, in step S3, the information on the impact of electricity consumption includes: season, GDP growth rate, industry type, and population density; the historical electricity consumption information represents the total daily electricity consumption of the power grid history.

[0010] Furthermore, in step S4, it specifically includes the following steps: S41. Set a sliding window with a length of 1 year in the historical electricity consumption information. Each time the sliding window slides, a training sample is obtained, and the total electricity consumption in the L days after each training sample is used as the sample label.

[0011] S42. Train the long short - term memory network using the training samples and sample labels to obtain the target model; S43. Input the total daily electricity consumption in the past year into the target model to output the second total electricity consumption for the target time period ; S44. Calibrate the second total electricity consumption according to the electricity consumption impact information to obtain the first total electricity consumption .

[0012] Further, in step S44, it specifically includes the following steps: S441. Calculate the first coupling influence coefficient , and its calculation formula is: ; In the formula, represents the seasonal coefficient; represents the GDP growth rate; represents the first interaction weight parameter; S442. Calculate the second coupling influence coefficient , and its calculation formula is: ; In the formula, represents the industrial structure coefficient; represents the second interaction weight parameter; S443. Calculate the third coupling influence coefficient , and its calculation formula is: ; In the formula, represents the third interaction weight parameter; S444. Calculate the fourth coupling influence coefficient , and its calculation formula is: ; In the formula, represents the population density coefficient; represents the fourth interaction weight parameter; S445. Calibrate the second total electricity consumption according to the first coupling influence coefficient , the second coupling influence coefficient , the third coupling influence coefficient and the fourth coupling influence coefficient to obtain the first total electricity consumption . .

[0013] Further, in step S445, the calculation formula of the first total electricity consumption is: ; In the formula, , , and respectively represent the first, second, third, and fourth empirical coefficients with respect to .

[0014] Furthermore, in step S5, the calculation formula for the trading risk value is: ; In the formula, represents the electricity spot trading volume.

[0015] Compared with the prior art, the present invention provides a method for evaluating the risk of electricity spot trading, which has the following beneficial effects: 1. In the present invention, a first coupling term and a second coupling term are introduced to quantify the comprehensive influence of meteorological conditions on photovoltaic power generation and wind power generation. Compared with common calculation methods, the prediction accuracy of power generation is higher, which is convenient for calculating the risk value of electricity spot trading in the later stage.

[0016] 2. The present invention takes into account that in common power grid electricity consumption calculation methods, only the individual influences of season, GDP growth rate, industrial type, and population density on total electricity consumption are calculated, without considering the mutual influence between these factors, resulting in inaccurate calculation results of power grid electricity consumption. Therefore, four coupling influence coefficients are introduced, and the accuracy of the total power generation of the power grid finally calculated is higher. Therefore, the accuracy of the finally calculated trading risk value is also higher, which is convenient for electricity spot suppliers to select coping strategies according to the risk value. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a schematic diagram of a method for evaluating the risk of electricity spot trading according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Thereby, the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0019] Those of ordinary skill in the art can understand that all or part of the steps in implementing the following embodiments of the method can be completed by instructing relevant hardware through a program. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0020] Power spot refers to the electrical energy product traded in real time in the power market. The buyer and seller conduct transactions at the market price according to the current (or short-term) power supply and demand situation, usually involving the delivery of electricity on the next day or the same day. Different from long-term contracts (such as annual and monthly contracts), power spot trading is closer to the actual electricity consumption moment, and the price changes frequently with the supply and demand fluctuations. Some power spot suppliers relying on renewable energy generate electricity through wind and solar power. This highly weather-dependent prediction method is severely affected by the weather, and there may be significant errors even in short-term predictions. For example, the predicted photovoltaic output for the next day is 80%, but it is only 50% on an actual cloudy day, resulting in power generation enterprises having to purchase spot electricity at a high price to make up the gap. In addition, transmission congestion or network failures may cause the local area electricity price to deviate from the system electricity price, affecting the execution of transactions. Therefore, please refer to Figure 1 As shown, the present invention proposes a method for evaluating the risk of power spot trading, including the following steps: S1. Obtain the photovoltaic influence information and wind power influence information in the area where the target power spot supplier is located; specifically, for power spot suppliers relying on clean energy generation, wind and light conditions are important conditions affecting the power generation amount. After the power spot supplier and the demander sign a contract, wind and light conditions are important factors for whether the power spot supplier can fulfill the contract. Therefore, in step S1, the photovoltaic influence information includes: the solar irradiance and the solar incident angle at each moment in the target time period; The wind power influence information includes: the atmospheric pressure and the wind speed at each moment in the target time period; specifically, the photovoltaic influence information and the wind power influence information can be directly obtained from the prediction information of the target time period published by the meteorological station in the area where the target power spot supplier is located.

[0021] S2. Calculate the total predicted power generation amount of the target power generation party in the target time period according to the photovoltaic influence information and the wind power influence information Specifically, the common methods for predicting photovoltaic power generation only consider the individual effects of information such as solar irradiance, solar incidence angle, and the operating parameters of photovoltaic panels on photovoltaic power generation. Similarly, wind power generation is predicted based on information such as air density, wind speed, and the operating parameters of wind turbines. However, the above prediction methods do not consider that photovoltaic power generation and wind power generation are also affected by other factors. For example, on a windless sunny day, due to the suppression of air flow by the high-pressure system, high irradiance is often accompanied by low wind speed. At this time, photovoltaic output is more, and wind power output is less. Strong winds are usually caused by low-pressure systems, and low-pressure systems are often accompanied by cloud cover. At this time, wind power output is more, and photovoltaic output is less. From the above content, it can be seen that in step S2, it specifically includes the following steps: S21. Obtain the temperature information at each moment in the target time period in the area where the target electricity spot supplier is located; S22. Calculate the actual air density and the photovoltaic efficiency influence value Specifically, in step S22, the formula for calculating the actual air density is: ; In the formula, represents the air density at the t-th moment; represents the atmospheric pressure at the t-th moment; represents the specific gas constant; represents the temperature information at the t-th moment; in the present invention, is 287.05; The formula for calculating the photovoltaic efficiency influence value is: ; In the formula, represents the actual efficiency of the photovoltaic panel at the t-th moment; represents the standard efficiency of the photovoltaic panel under standard test conditions; represents the temperature coefficient of photovoltaic efficiency; represents the solar irradiance at the t-th moment; represents the rated operating temperature of the photovoltaic panel; in the present invention, is -0.004.

[0022] S23. Calculate the first coupling term and the second coupling term Specifically, in step S23, the formula for calculating the first coupling term is: ; In the formula, Indicates the suppression coefficient of PV output on wind power; Indicates the maximum possible irradiance; in the present invention, Is 0.3; Is 1000; it should be noted that when , Otherwise, calculate according to the original formula; The second coupling term The calculation formula is: ; In the formula, Indicates the mechanical suppression coefficient; Indicates the wind speed at the t-th moment; Indicates the cut-out wind speed of the wind turbine; Indicates the attenuation coefficient of dust on power generation; Indicates the dust deposition amount increased by the measured unit wind speed; Indicates the critical wind speed for sand initiation; Indicates Function; Indicates the base of the natural logarithm; Indicates the wind speed heat dissipation coefficient; Indicates the basic heat dissipation constant; in the present invention, Is 0.2; Obtained according to the parameters provided by the wind turbine manufacturer; Is 0.13; Is 0.05; Is 1.3; Is 800.

[0023] S24. According to the actual air density , the PV efficiency influence value , the first coupling term And the second coupling term Calculate the PV power generation prediction value And the wind power generation prediction value ; Specifically, in step S24, the PV power generation prediction value The calculation formula is: ; In the formula, Indicates the total effective area of the PV panels; Indicates the total number of moments in the target time period; Indicates the comprehensive system loss; Indicates the solar incidence angle at the t-th moment; Indicates the time interval; in the present invention, Obtained according to the data provided by the manufacturer; Is 24; is 0.82; is 1; Wind power generation prediction volume The calculation formula is: ; In the formula, represents the swept area of the fan; represents the wind energy utilization coefficient; represents the mechanical and electrical efficiency of the fan; in the present invention, , and are all obtained according to the information provided by the manufacturer.

[0024] S25. According to the photovoltaic power generation prediction volume and the wind power generation prediction volume calculate the total predicted power generation , and its calculation formula is: ; In the formula, represents the total predicted power generation of the target power generation party in the target time period.

[0025] Since the traditional calculation methods of wind power generation and photovoltaic power generation only consider the influence of single variables such as solar irradiance and wind speed on power generation, ignoring the interaction between meteorological conditions, resulting in inaccurate calculation of the final total predicted power generation. Therefore, in step S2 of the present invention, the first coupling term and the second coupling term are introduced to quantify the comprehensive influence of meteorological conditions on photovoltaic power generation and wind power generation. Compared with the common calculation methods, the prediction accuracy of power generation is higher, so as to facilitate the calculation of the risk value of power spot trading in the later stage.

[0026] S3. Obtain the power consumption influence information and historical power consumption information of the power grid; specifically, in step S3, the power consumption influence information includes: season, GDP growth rate, industry type and population density; the historical power consumption information represents the total daily power consumption of the power grid history.

[0027] S4. Calculate the first total power consumption of the power grid in the target time period according to the power consumption influence information and the historical power consumption information ; specifically, if the transmission line capacity of the power grid is insufficient, "nodal price" may be formed in the congested area (such as the PJM market in the United States), which is significantly different from the system average price, resulting in the power spot supply party connecting to the grid at the low-price node in the congested area but selling electricity at the high-price node, resulting in profit compression. In addition, the power grid needs to balance power generation and load in real time. If the spot trading power quantity causes local voltage or frequency to exceed the limit, it may be forced to be adjusted by the dispatching agency, generating additional costs. Therefore, in step S4, it specifically includes the following steps: S41. Set a sliding window with a length of 1 year in the historical electricity consumption information. Each time the sliding window slides, a training sample is obtained, and the total electricity consumption in the L days after each training sample is the sample label. Specifically, L represents the time interval from the current to the target time period.

[0028] S42. Use the training samples and sample labels to train the long short-term memory network to obtain the target model. S43. Input the total electricity consumption of each day in the past year into the target model, and output the second total electricity consumption of the target time period. ; S44. Calibrate the second total electricity consumption according to the electricity consumption impact information to obtain the first total electricity consumption ; Specifically, using the long short-term memory network to predict the total electricity consumption of the target time period only takes into account the periodic change trend of the grid electricity consumption, and does not consider the changes in GDP growth rate, industrial type and population density. Therefore, in step S44, it specifically includes the following steps: S441. Calculate the first coupling impact coefficient , and its calculation formula is: ; In the formula, represents the seasonal coefficient; represents the GDP growth rate; represents the first interaction weight parameter; in the present invention, is the percentage of the temperature deviation from the historical average; if the GDP growth rate is 5%, then is 0.05; is 0.12; S442. Calculate the second coupling impact coefficient , and its calculation formula is: ; In the formula, represents the industrial structure coefficient; represents the second interaction weight parameter; in the present invention, , the reference value is 0.6; is 0.05; S443. Calculate the third coupling impact coefficient , and its calculation formula is: ; In the formula, represents the third interaction weight parameter; in the present invention, is 0.08; S444. Calculate the fourth coupling impact coefficient , and its calculation formula is: ; In the formula, represents the population density coefficient; represents the fourth interaction weight parameter; in the present invention, the reference density is 2000; is 0.06; S445. According to the first coupling influence coefficient , the second coupling influence coefficient , the third coupling influence coefficient and the fourth coupling influence coefficient correct the second total power consumption to obtain the first total power consumption ; specifically, since the common methods for correcting power consumption only consider the individual effects of season, GDP growth rate, industrial type, and population density on the total power consumption, without considering the mutual influence between these factors. For example, when it is hot in summer, the power consumption of the tertiary industry (such as commercial air conditioners) surges, but the power consumption of the secondary industry (such as factories) may decrease due to reduced production caused by high temperature; areas with high GDP are usually densely populated and have a high proportion of the tertiary industry, resulting in a higher power demand per capita (such as concentrated office buildings and data centers). Therefore, in step S445, the calculation formula of the first total power consumption is: ; In the formula, , , and respectively represent the first, second, third, and fourth empirical coefficients regarding ; in the present invention, , , and are 0.1, 0.11, 0.06, and 0.003 respectively; S5. Calculate the trading risk value and the first total power consumption ; specifically, in step S5, the calculation formula of the trading risk value is:

[0029] ; In the formula, represents the spot power trading volume.

[0029] In step S4 of the present invention, considering that in the common power grid power consumption calculation method, only the individual impacts of season, GDP growth rate, industrial type, and population density on the total power consumption are calculated, without considering the mutual impacts among these factors, resulting in inaccurate calculation results of the power grid power consumption, four coupling impact coefficients are introduced. As a result, the accuracy of the finally calculated total power generation of the power grid is higher, and thus the accuracy of the finally calculated transaction risk value is also higher, facilitating the power spot supplier to select coping strategies based on the risk value.

[0030] The above embodiments have introduced the present invention in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for evaluating the risk of spot power trading, characterized in that, It includes the following steps: S1. Obtain the photovoltaic impact information and wind power impact information in the region where the target electricity spot supplier is located; The photovoltaic impact information includes: the solar irradiance and the solar incident angle at each moment in the target time period; The wind power impact information includes: the atmospheric pressure and the wind speed at each moment in the target time period; S2. Calculate the total predicted power generation of the target power generation party during the target time period based on the optoelectronic influence information and the wind power influence information ; S3. Obtain the electricity consumption impact information and historical electricity consumption information of the power grid; S4. Calculate the first total power consumption of the power grid during the target time period based on the power consumption impact information and the historical power consumption information ; S5. Calculate the trading risk value according to the total predicted power generation and the first total power consumption . .

2. The power spot trading risk assessment method according to claim 1, wherein, In step S2, it specifically includes the following steps: S21. Obtain the temperature information at each moment in the region where the target electricity spot supplier is located in the target time period; S22. Calculate the actual air density and the photovoltaic efficiency influence value respectively according to the temperature information and the photovoltaic efficiency influence value ; S23. Calculate the first coupling term according to the optoelectronic influence information and the wind power influence information and the second coupling term ; S24. Calculate the predicted photovoltaic power generation and the predicted wind power generation based on the actual air density , the influence value of photovoltaic efficiency , the first coupling term and the second coupling term ; and the predicted wind power generation ; S25. Calculate the total predicted power generation according to the predicted photovoltaic power generation and the predicted wind power generation . The calculation formula is as follows: ​ ， In the formula, represents the total predicted power generation of the target power generation party during the target time period.

3. The power spot trading risk assessment method according to claim 2, wherein In step S22, the formula for calculating the actual air density is as follows: ， In the formula, represents the air density at the t-th moment; represents the atmospheric pressure at the t-th moment; represents the specific gas constant; represents the temperature information at the t-th moment; Photovoltaic efficiency impact value The calculation formula is as follows: ， In the formula, represents the actual efficiency of the photovoltaic panel at the t-th moment; represents the standard efficiency of the photovoltaic panel under standard test conditions; represents the temperature coefficient of the photovoltaic efficiency; represents the solar irradiance at the t-th moment; represents the rated operating temperature of the photovoltaic panel.

4. The power spot trading risk assessment method according to claim 2, wherein, In step S23, the first coupling term is calculated by the formula: ， In the formula, represents the suppression coefficient of PV output on wind power; represents the maximum possible irradiance; Second coupling term The calculation formula is as follows: ， In the formula, represents the mechanical inhibition coefficient; represents the wind speed at the t-th moment; represents the cut-out wind speed of the wind turbine; represents the attenuation coefficient of sand and dust on power generation; represents the sand and dust deposition amount increased by the measured unit wind speed; represents the critical wind speed for sand movement; represents function; represents the base of the natural logarithm; represents the wind speed heat dissipation coefficient; represents the basic heat dissipation constant.

5. The power spot trading risk assessment method according to claim 2, wherein In step S24, the predicted photovoltaic power generation is calculated as follows: ， In the formula, represents the total effective area of the photovoltaic panel; represents the total number of moments in the target time period; represents the comprehensive system loss; represents the solar light incident angle at the t-th moment; represents the time interval; Wind power generation prediction amount The calculation formula is as follows: ， In the formula, represents the swept area of the wind turbine; represents the wind energy utilization coefficient; represents the mechanical and electrical efficiency of the wind turbine.

6. The power spot trading risk assessment method according to claim 1, wherein In step S3, the electricity consumption impact information includes: season, GDP growth rate, industry type and population density; the historical electricity consumption information represents the total daily electricity consumption of the power grid in history.

7. The risk assessment method for power spot trading according to claim 1, wherein In step S4, it specifically includes the following steps: S41. Set a sliding window with a length of 1 year in the historical electricity consumption information. Each time the sliding window slides, a training sample is obtained, and the total electricity consumption in the next L days after each training sample is the sample label; S42. Use the training samples and sample labels to train the long short-term memory network to obtain the target model; S43. Input the total daily electricity consumption in the past year into the target model to output the second total electricity consumption in the target time period. ; S44. Correct the second total power consumption according to the power consumption impact information to obtain the first total power consumption .

8. The power spot trading risk assessment method according to claim 7, wherein In step S44, it specifically includes the following steps: S441. Calculate the first coupling influence coefficient based on the electricity consumption influence information , and its calculation formula is as follows: ， In the formula, represents the seasonal coefficient; represents the GDP growth rate; represents the first interaction weight parameter; S442. Calculate the second coupling influence coefficient , and its calculation formula is as follows: ， In the formula, represents the industrial structure coefficient; represents the second interaction weight parameter; S443. Calculate the third coupling influence coefficient , and its calculation formula is as follows: ， In the formula, represents the third interaction weight parameter; S444. Calculate the fourth coupling influence coefficient , and its calculation formula is as follows: ， In the formula, represents the population density coefficient; represents the fourth interaction weight parameter; S445. Correct the second total power consumption according to the first coupling influence coefficient , the second coupling influence coefficient , the third coupling influence coefficient and the fourth coupling influence coefficient to obtain the first total power consumption .

9. The power spot trading risk assessment method according to claim 8, wherein In step S445, the total electricity consumption for the first time is calculated by the formula: ， In the formula, , , and respectively represent the first, second, third, and fourth empirical coefficients with respect to .

10. The power spot trading risk assessment method according to claim 1, wherein In step S5, the transaction risk value is calculated as follows: ， In the formula, represents the electricity spot trading volume.

Images