A power spot market long-period electricity price prediction method, device and storage medium

Abstract

This invention discloses a method, equipment, and storage medium for long-term electricity price forecasting in the electricity spot market. The method includes: extracting and preprocessing features from multi-source basic data to construct a generator set result set; calculating the relative output depth operator of the generator sets based on the generator set result set, and then calculating the weighted average output depth of the entire system; calculating the nonlinear price mapping operator based on the weighted average output depth of the entire system and the system supply and demand factors calculated from the generator set result set, and obtaining a preliminary predicted electricity price based on the nonlinear price mapping operator; and obtaining a full-year electricity price forecast sequence based on the preliminary predicted electricity price. By defining and applying the relative output depth operator, it is possible to reverse-engineer the bidding game psychology and strategy shift characteristics of power generation entities at different operating depths without accessing commercial privacy data such as competitors' bid prices, by utilizing publicly available generator physical characteristics.

Description

Technical Field

[0001] This invention relates to the field of electricity price forecasting technology, specifically to a method, equipment, and storage medium for long-term electricity price forecasting in the electricity spot market. Background Technology

[0002] Currently, forecasts for electricity spot clearing prices mainly focus on market simulation and data-driven methods.

[0003] Currently, existing technologies mainly have the following problems: Market simulation methods attempt to reconstruct the physical operating state of the power grid to derive prices by constructing complex power supply and demand optimization models. However, this method is highly dependent on high-precision data such as the entire network topology, node voltage, and the private declaration price curves of each generating unit. When facing long-term forecasts spanning up to one year, not only does the amount of computation increase exponentially, but the inability to obtain the bidding behavior of competing entities in future years also leads to gaps in forecast accuracy.

[0004] Data-driven approaches utilize various artificial intelligence algorithms to uncover historical electricity price patterns. While they possess strong nonlinear fitting capabilities, their nature as black-box models prevents them from reflecting the intrinsic supporting effects of installed capacity structure adjustments, policy boundary evolution, and the physical constraints of the power system on electricity price formation.

[0005] Existing forecasting technologies struggle to effectively balance the coupling between physical operational constraints and market game behavior, leading to severe deviations in electricity price forecasts under extreme conditions such as extreme loads and difficulties in peak shaving. Summary of the Invention

[0006] This invention proposes a method, equipment, and storage medium for long-term electricity price forecasting in the electricity spot market to solve the problems mentioned in the background.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: A long-term electricity price forecasting method for the electricity spot market of the present invention includes the following steps: S1. Perform feature extraction and preprocessing on multi-source basic data to construct a generator set result set; S2. Based on the generator set result set, calculate the relative output depth operator of the generator set, and then calculate the weighted average output depth of the entire system. S3. Based on the weighted average output depth of the entire system and the system supply and demand factors calculated from the generator set result set, the price nonlinear mapping operator is then calculated, and the preliminary predicted electricity price is obtained based on the price nonlinear mapping operator. S4. Based on the preliminary electricity price forecast, obtain the annual electricity price forecast sequence.

[0008] Preferably, step S1 includes the following steps: Preprocessing of multi-source basic data, and feature extraction of predicted annual power load, typical output sequence of new energy sources and cross-regional DC transmission plan to construct the initial scenario for the whole year; Based on multi-source basic data, the physical output of the generator set is calculated. The calculation process is coupled with the minimum output constraint, maximum output limit of conventional power source and the spatiotemporal constraints of energy storage system charging and discharging. Construct a generator set result set that includes the predicted annual power load, typical output sequence of new energy sources, inter-regional DC transmission plan, physical output of generator units, minimum output constraints of conventional power sources, and maximum output limit.

[0009] Preferably, step S2 includes the following steps: For each generator unit at any given time, a relative output depth operator is defined:

[0010] in, for Time of the first The generator set output, For the first Minimum technical output of the generator set, For the first Maximum output limit of generator set for Time of the first The depth of output adjustment of each generator set; according to Time of the first The output adjustment depth of each generator unit is calculated, and the weighted average output depth of the entire system is calculated.

[0011] Preferably, step S3 includes the following steps: The system supply and demand factor is calculated based on the weighted average output depth of the entire system and the result set of the generator sets. Based on the weighted average output depth of the entire system and combined with the system's supply and demand factors, a nonlinear price mapping operator is calculated. A preliminary electricity price forecast is obtained based on the price nonlinear mapping operator.

[0012] Preferably, step S4 includes the following steps: An autoregressive model is used to fit the random noise in historical spot clearing data to generate a random correction term that conforms to a Gaussian distribution. Finally, the preliminary electricity price forecast is combined with the stochastic correction term to obtain the annual electricity price forecast sequence.

[0013] Preferably, S2 further includes: By adjusting the output of each generator set, the real-time status of the generator sets is divided into the following ranges: when Operating in the low-end range: When the output is less than the technical lower limit, the unit faces the risk of shutdown or extremely high cold start costs, and the price tends to be close to the market lower limit. ; when Located in the normal adjustment range: The unit is in the normal adjustment depth, and the unit price mainly reflects its variable cost, which fluctuates linearly with the increase of output. when Located in the premium game range: when output approaches its limit and the system's adjustable capacity reaches its limit, generator sets, as marginal price setters, use scarcity to raise their prices, pushing towards the market ceiling. Approaching.

[0014] Preferably, the formula for calculating the system supply and demand factor is as follows:

[0015] in, To predict annual electricity load, A typical power generation sequence for new energy; The calculation formula for the price nonlinear mapping operator is as follows:

[0016] in, The weighted average output depth of the entire system. This is the market sensitivity coefficient. This marks the critical point for a shift in market pricing logic. This is an adjustment coefficient that evolves dynamically with policy changes; The formula for calculating the preliminary electricity price forecast is as follows:

[0017] in, For the initial prediction of electricity price at time t, The policy requires the lower limit of the electricity spot market price declaration. The policy requires the upper limit of the electricity spot market price declaration.

[0018] Preferably, the calculation formula for the annual electricity price forecast sequence is as follows:

[0019] in, The final predicted price at time t, For the initial prediction of electricity price at time t, This is a random correction term.

[0020] In another aspect, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0021] In another aspect, the present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method described above.

[0022] As can be seen from the above technical solution, the present invention provides a method for predicting long-term electricity prices in the electricity spot market. Compared with the prior art, the present invention has the following advantages: 1. By defining and applying a relative output depth operator, this invention can utilize publicly available unit physical characteristics to reverse-engineer the bidding psychology and strategy shift characteristics of power generation entities at different operating depths without accessing commercial privacy data such as competitors' bid prices.

[0023] 2. By introducing a Sigmoid nonlinear mapping kernel based on system supply and demand factors, this invention can accurately capture the deep valley electricity price of the duck curve during periods of large-scale fluctuations in new energy sources, as well as the price surge characteristics when the system's reserve capacity is insufficient.

[0024] 3. By adjusting specific parameters, this invention can directly quantify and assess the long-term disturbances of macroeconomic policies such as carbon trading cost price, mandatory participation of new energy in the spot market, and changes in the policy on guaranteed purchase of electricity on the central and fluctuating characteristics of electricity prices. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a long-term electricity price forecasting method for the electricity spot market according to the present invention.

[0026] Figure 2 This is a diagram showing the working positions of various units on a certain day according to the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0028] like Figure 1 and Figure 2 As shown in this embodiment, a method, device, and storage medium for predicting long-term electricity prices in the electricity spot market are provided to address the problems described in the background section.

[0029] To achieve the above objectives, the present invention adopts the following technical solution: A long-term electricity price forecasting method for the electricity spot market of the present invention includes the following steps: S1. Perform feature extraction and preprocessing on multi-source basic data to construct a generator set result set; S2. Based on the generator set result set, calculate the relative output depth operator of the generator set, and then calculate the weighted average output depth of the entire system. S3. Based on the weighted average output depth of the entire system and the system supply and demand factors calculated from the generator set result set, the price nonlinear mapping operator is then calculated, and the preliminary predicted electricity price is obtained based on the price nonlinear mapping operator. S4. Based on the preliminary electricity price forecast, obtain the annual electricity price forecast sequence.

[0030] Furthermore, S1 includes the following steps: Preprocessing of multi-source basic data, and feature extraction of predicted annual power load, typical output sequence of new energy sources and cross-regional DC transmission plan to construct the initial scenario for the whole year; Based on multi-source basic data, the physical output of the generator set is calculated. The calculation process is coupled with the minimum output constraint, maximum output limit of conventional power source and the spatiotemporal constraints of energy storage system charging and discharging. Construct a generator set result set that includes the predicted annual power load, typical output sequence of new energy sources, inter-regional DC transmission plan, physical output of generator units, minimum output constraints of conventional power sources, and maximum output limit.

[0031] like Figure 2 As shown in the figure, based on the data in the figure, we can determine the predicted annual power load, the typical output sequence of new energy sources, and the inter-regional DC transmission plan, extract features, and calculate the physical output of the generator units. Furthermore, S2 includes the following steps: For each generator unit at any given time, a relative output depth operator is defined:

[0032] in, for Time of the first The generator set output, For the first Minimum technical output of the generator set, For the first Maximum output limit of generator set for Time of the first The depth of output adjustment of each generator set; according to Time of the first The output adjustment depth of each generator unit is calculated, and the weighted average output depth of the entire system is calculated.

[0033] Furthermore, S3 includes the following steps: The system supply and demand factor is calculated based on the weighted average output depth of the entire system and the result set of the generator sets. Based on the weighted average output depth of the entire system and combined with the system's supply and demand factors, a nonlinear price mapping operator is calculated. A preliminary electricity price forecast is obtained based on the price nonlinear mapping operator.

[0034] Furthermore, S4 includes the following steps: An autoregressive model is used to fit the random noise in historical spot clearing data to generate a random correction term that conforms to a Gaussian distribution. Finally, the preliminary electricity price forecast is combined with the stochastic correction term to obtain the annual electricity price forecast sequence.

[0035] Furthermore, S2 also includes: By adjusting the output depth of each generator set, the real-time status of the generator sets is divided into the following intervals: when Operating in the low-end range: When the output is less than the technical lower limit, the unit faces the risk of shutdown or extremely high cold start costs, and the price tends to be close to the market lower limit. ; when Located in the normal adjustment range: The unit is in the normal adjustment depth, and the unit price mainly reflects its variable cost, which fluctuates linearly with the increase of output. when Located in the premium game range: when output approaches its limit and the system's adjustable capacity reaches its limit, generator sets, as marginal price setters, use scarcity to raise their prices, pushing towards the market ceiling. Approaching.

[0036] Furthermore, the formula for calculating the system's supply and demand factors is as follows:

[0037] in, To predict annual electricity load, A typical power generation sequence for new energy; The calculation formula for the price nonlinear mapping operator is as follows:

[0038] in, The weighted average output depth of the entire system. This is the market sensitivity coefficient. This marks the critical point for a shift in market pricing logic. This is an adjustment coefficient that evolves dynamically with policy changes; The preliminary formula for calculating electricity prices is as follows:

[0039] in, For the initial prediction of electricity price at time t, The policy requires the lower limit of the electricity spot market price declaration. The policy requires the upper limit of the electricity spot market price declaration.

[0040] Furthermore, the formula for calculating the annual electricity price forecast series is as follows:

[0041] in, The final predicted price at time t, For the initial prediction of electricity price at time t, This is a random correction term.

[0042] In another aspect, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0043] In another aspect, the present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method described above.

[0044] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk), etc.

[0045] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0046] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0047] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting long-term electricity prices in the electricity spot market, characterized in that, Includes the following steps: S1. Perform feature extraction and preprocessing on multi-source basic data to construct a generator set result set; S2. Based on the generator set result set, calculate the relative output depth operator of the generator set, and then calculate the weighted average output depth of the entire system. S3. Based on the weighted average output depth of the entire system and the system supply and demand factors calculated from the generator set result set, the price nonlinear mapping operator is then calculated, and the preliminary predicted electricity price is obtained based on the price nonlinear mapping operator. S4. Based on the preliminary electricity price forecast, obtain the annual electricity price forecast sequence.

2. The method for predicting long-term electricity prices in the electricity spot market according to claim 1, characterized in that: S1 includes the following steps: Preprocessing of multi-source basic data, and feature extraction of predicted annual power load, typical output sequence of new energy sources and cross-regional DC transmission plan to construct the initial scenario for the whole year; Based on multi-source basic data, the physical output of the generator set is calculated. The calculation process is coupled with the minimum output constraint, maximum output limit of conventional power source and the spatiotemporal constraints of energy storage system charging and discharging. Construct a generator set result set that includes the predicted annual power load, typical output sequence of new energy sources, inter-regional DC transmission plan, physical output of generator units, minimum output constraints of conventional power sources, and maximum output limit.

3. The method for predicting long-term electricity prices in the electricity spot market according to claim 2, characterized in that: S2 includes the following steps: For each generator unit at any given time, a relative output depth operator is defined: in, for Time of the first The generator set output, For the first Minimum technical output of the generator set, For the first Maximum output limit of generator set for Time of the first The depth of output adjustment of each generator set; according to Time of the first The output adjustment depth of each generator unit is calculated, and the weighted average output depth of the entire system is calculated.

4. The method for predicting long-term electricity prices in the electricity spot market according to claim 3, characterized in that: S3 includes the following steps: The system supply and demand factor is calculated based on the weighted average output depth of the entire system and the result set of the generator sets. Based on the weighted average output depth of the entire system and combined with the system's supply and demand factors, a nonlinear price mapping operator is calculated. A preliminary electricity price forecast is obtained based on the price nonlinear mapping operator.

5. The method for predicting long-term electricity prices in the electricity spot market according to claim 4, characterized in that: S4 includes the following steps: An autoregressive model is used to fit the random noise in historical spot clearing data to generate a random correction term that conforms to a Gaussian distribution. Finally, the preliminary electricity price forecast is combined with the stochastic correction term to obtain the annual electricity price forecast sequence.

6. The method for predicting long-term electricity prices in the electricity spot market according to claim 5, characterized in that: S2 further includes: By adjusting the output depth of each generator set, the real-time status of the generator sets is divided into the following intervals: when Operating in the low-end range: When the output is less than the technical lower limit, the unit faces the risk of shutdown or extremely high cold start costs, and the price tends to be close to the market lower limit. ; when Located in the normal adjustment range: The unit is in the normal adjustment depth, and the unit price mainly reflects its variable cost, which fluctuates linearly with the increase of output. when Located in the premium game range: when output approaches its limit and the system's adjustable capacity reaches its limit, generator sets, as marginal price setters, use scarcity to raise their prices, pushing towards the market ceiling. Approaching.

7. The method for predicting long-term electricity prices in the electricity spot market according to claim 6, characterized in that: The formula for calculating the system's supply and demand factors is as follows: in, To predict annual electricity load, It is a typical power generation sequence for new energy; The calculation formula for the price nonlinear mapping operator is as follows: in, The weighted average output depth of the entire system. This is the market sensitivity coefficient. This marks the critical point for a shift in market pricing logic. This is an adjustment coefficient that evolves dynamically with policy changes; The formula for calculating the preliminary electricity price forecast is as follows: in, For the initial prediction of electricity price at time t, The policy requires the lower limit of the electricity spot market price declaration. The policy requires the upper limit of the electricity spot market price declaration.

8. The method for predicting long-term electricity prices in the electricity spot market according to claim 7, characterized in that: The formula for calculating the annual electricity price forecast series is as follows: in, The final predicted price at time t, For the initial prediction of electricity price at time t, This is a random correction term.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 8.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the computer program is executed by the processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 8.

Images