Settlement electricity price prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a settlement electricity price prediction method and device, electronic equipment and a storage medium, and the method and device are applied to the electronic equipment, and specifically comprise the steps: obtaining multiple groups of basic data; performing medium-and-long-term electricity price trend analysis and prediction processing based on the multiple groups of basic data to obtain a new energy medium-and-long-term electricity price; performing spot goods time-of-use electricity price prediction based on the multiple groups of basic data to obtain a new energy spot goods time-of-use electricity price; performing calculation based on the new energy spot goods time-of-use electricity price to obtain a new energy spot goods deviation settlement electricity price; and processing the new energy medium-and-long-term electricity price and the new energy spot goods deviation settlement electricity price according to the new energy kilowatt-hour electricity settlement price composition to obtain a new energy long-term settlement electricity price. According to the scheme, the new energy long-term settlement electricity price is obtained, so that investors can obtain a reliable investment basis for new energy investment development.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and more specifically, to a method, device, electronic device, and storage medium for predicting settlement electricity prices. Background Art

[0002] With the deepening of domestic power market reforms, most power markets now adopt a long-term settlement model. Furthermore, with the large-scale development of renewable energy, the inclusion of renewable energy in spot electricity trading is an inevitable trend. This participation of renewable energy in spot trading completely overturns the previous model of operating based solely on the amount of electricity generated. Spot electricity prices fluctuate continuously based on supply and demand at different times (hourly or 15-minute intervals) and at different points (each 220kV transformer area is considered a point), resulting in significantly increased uncertainty in the returns of new energy companies in the market. Some provinces with spot electricity markets, such as Shandong, even experience negative electricity prices.

[0003] Against the backdrop of the spot trading model disrupting the revenue model for new energy, effectively evaluating the long-term settlement price of new energy in the electricity market before investing, and evaluating the future trading potential between different types of new energy and different power stations based on the long-term settlement price, have become the most reliable investment basis for new energy investment and development. Summary of the Invention

[0004] In view of this, the present application provides a settlement electricity price prediction method, device, electronic device and storage medium for predicting the long-term settlement electricity price of new energy, so as to provide a reliable investment basis for new energy investment and development.

[0005] In order to achieve the above objectives, the following solutions are proposed:

[0006] A settlement electricity price prediction method is used to predict the long-term settlement electricity price of new energy, and is applied to electronic equipment. The settlement electricity price prediction method comprises the following steps:

[0007] Obtain multiple sets of basic data;

[0008] Performing medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources;

[0009] Performing spot time-of-use electricity price forecasting based on the multiple sets of basic data to obtain the spot time-of-use electricity price of new energy;

[0010] Calculating based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price;

[0011] The new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price are processed according to the new energy kilowatt-hour settlement price structure to obtain the new energy long-term settlement electricity price.

[0012] Optionally, the multiple sets of basic data include future multi-dimensional energy forecast data, electricity spot market data and future power generation capacity data of power plants.

[0013] Optionally, performing medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources includes the following steps:

[0014] Calculating the market supply-demand ratio index and the comprehensive marginal cost of the power system year by year based on the multiple sets of basic data;

[0015] Based on the market supply-demand ratio indicator, the comprehensive marginal cost of the power system and the predetermined deduction starting benchmark electricity price, an iterative calculation is performed year by year to obtain the medium- and long-term electricity price of new energy, which includes the predicted electricity price in future years.

[0016] Optionally, the performing of spot time-of-use electricity price forecasting based on the multiple sets of basic data to obtain the new energy spot time-of-use electricity price includes the following steps:

[0017] Calculating marginal power generation costs of various units based on primary fuel cost data in the multiple sets of basic data;

[0018] Determine the priority clearing sequence for each type of unit;

[0019] The marginal power generation cost and the priority clearing sequence are processed based on a pre-built spot dispatch economic model to obtain the new energy spot time-of-use electricity price.

[0020] Optionally, the calculation based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price includes the following steps:

[0021] The new energy spot deviation settlement electricity price is calculated based on the following equation:

[0022]

[0023] Among them, q t is the average hourly output of the new energy units, is the hourly electricity consumption of new energy in the medium and long term in each year in the future, Q is the actual power generation in the medium and long term in the future, It is the spot time-of-use electricity price of the new energy.

[0024] A settlement electricity price prediction device, used for predicting the long-term settlement electricity price of new energy, is applied to electronic equipment. The settlement electricity price prediction device includes:

[0025] A data acquisition module is configured to acquire multiple sets of basic data;

[0026] A first calculation module is configured to perform medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources;

[0027] A second calculation module is configured to perform a spot time-of-use electricity price forecast based on the multiple sets of basic data to obtain a new energy spot time-of-use electricity price;

[0028] a third calculation module configured to calculate based on the new energy spot time-of-use electricity price to obtain a new energy spot deviation settlement electricity price;

[0029] The prediction execution module is configured to process the new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price according to the new energy kilowatt-hour settlement price structure to obtain the new energy long-term settlement electricity price.

[0030] Optionally, the first calculation module includes:

[0031] A first calculation unit is configured to calculate the market supply-demand ratio index and the comprehensive marginal cost of the power system year by year based on the multiple sets of basic data;

[0032] The second calculation unit is configured to perform iterative calculations year by year based on the market supply-demand ratio indicator, the comprehensive marginal cost of the power system and a predetermined deduction starting benchmark electricity price to obtain the medium- and long-term electricity price of the new energy, which includes the predicted electricity price in future years.

[0033] Optionally, the second calculation module includes:

[0034] a third calculation unit, configured to calculate the marginal power generation cost of each type of unit based on the primary fuel cost data in the multiple sets of basic data;

[0035] A sequence determination unit is configured to determine a priority clearing sequence for each type of unit;

[0036] The fourth calculation unit is configured to process the marginal power generation cost and the priority clearing sequence based on a pre-built spot dispatch economic model to obtain the new energy spot time-of-use electricity price.

[0037] An electronic device comprising at least one processor and a memory connected to the processor, wherein:

[0038] The memory is used to store computer programs or instructions;

[0039] The processor is used to execute the computer program or instruction to enable the electronic device to implement the settlement electricity price prediction method as described above.

[0040] A computer-readable storage medium is applied to an electronic device, wherein the storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, thereby enabling the electronic device to implement the settlement electricity price prediction method as described above.

[0041] As can be seen from the above technical solution, the present application discloses a method, device, electronic device and storage medium for predicting settlement electricity prices. The method and device are applied to electronic devices, specifically to obtain multiple sets of basic data; perform medium- and long-term electricity price trend analysis and forecast processing based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy; perform spot time-of-use electricity price forecasts based on the multiple sets of basic data to obtain new energy spot time-of-use electricity prices; perform calculations based on the new energy spot time-of-use electricity prices to obtain new energy spot deviation settlement electricity prices; process the medium- and long-term electricity prices for new energy and the new energy spot deviation settlement electricity prices according to the new energy kilowatt-hour settlement price composition to obtain new energy long-term settlement electricity prices. The long-term settlement electricity prices for new energy are obtained according to this solution, so that investors can obtain a reliable investment basis for new energy investment and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 This is a flow chart of a method for predicting a settlement electricity price according to an embodiment of the present application;

[0044] Figure 2 This is a block diagram of a settlement electricity price prediction device according to an embodiment of the present application;

[0045] Figure 3 This is a block diagram of another device for predicting electricity prices according to an embodiment of the present application;

[0046] Figure 4 This is a block diagram of another device for predicting electricity prices according to an embodiment of the present application;

[0047] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described 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 making creative efforts are within the scope of protection of this application.

[0049] Figure 1 This is a flowchart of a settlement electricity price prediction method according to an embodiment of the present application.

[0050] like Figure 1 As shown, the settlement electricity price prediction method provided in this embodiment is applied to an electronic device for predicting the long-term settlement electricity price of renewable energy. The electronic device can be understood as a computer, server, or cloud platform with data computing and information processing capabilities. The settlement electricity price prediction method includes the following steps:

[0051] S1. Obtain basic data for calculating long-term settlement electricity prices for new energy.

[0052] The basic data here include future multi-dimensional energy forecast data, electricity spot market data and future power generation capacity data of power plants.

[0053] This multi-dimensional energy forecast data is sourced from multiple energy information agencies, such as Wood Mac and Bloomberg, and is used to forecast data for at least the next 20 years. The data list to be obtained is as follows:

[0054]

[0055] Electricity spot market data includes provincial power grid and electricity spot market data.

[0056] For provinces that have already launched electricity spot markets, it is necessary to obtain historical daily spot market power load, power generation of various power sources and daily spot electricity price data; for provinces that have not yet launched electricity spot markets and only have medium- and long-term transactions, it is necessary to provide the medium- and long-term transaction prices for each year and month in history.

[0057] The future power generation capacity data of a power station refers to the typical expected future power generation capacity curve of the power station provided by the new energy owner or project contractor.

[0058] The power generation capacity of a new energy project at different times will inevitably affect its trading profitability in the future spot market. Therefore, analyzing its power generation capacity at different times can better evaluate its trading characteristics. The contractor or designer can provide a typical power generation capacity curve for each time period based on the local wind and solar resource endowment, longitude and latitude geographical location, etc.

[0059] S2. Conduct medium- and long-term electricity price trend analysis and forecasting based on basic data.

[0060] Through the above-mentioned multiple sets of basic data, the medium- and long-term electricity price trend analysis and forecast processing are carried out to obtain the medium- and long-term electricity price P of new energy. y The medium- and long-term electricity prices are mainly determined by the market supply and demand relationship and the marginal cost changes of the power system. Therefore, the following steps are taken to deal with it:

[0061] First, based on the basic data obtained, the market supply-demand ratio indicators and the comprehensive marginal cost of the power system are calculated year by year.

[0062] The market supply-demand ratio indicators are:

[0063] In the above formula, supply y It is the sum of all installed capacity of power sources other than renewable energy in the provincial market in year y, which represents the supply capacity of adjustable power sources other than non-renewable energy in the market; demand y It is the daily electricity consumption data for the next year y. This indicator reflects the supply and demand relationship in the electricity market. The larger the denominator, the higher the demand. y The smaller it is, the tighter the supply and demand relationship is, which is more likely to lead to high prices. Conversely, the looser the supply and demand is.

[0064] The supply-demand ratio increment index Δsdi is used to represent the change in supply-demand relationship compared to the previous year. y for:

[0065] Δsdi y =sdi y -sdi y-1

[0066] Comprehensive marginal cost of power system:

[0067]

[0068] In the above formula, is the annual power generation of the gas-fired unit in year y, is the annual power generation of the coal-fired unit in year y, is the annual power generation of the new energy unit in year y. is the average fuel cost of the gas-fired unit in year y, is the average fuel cost of electricity generated by coal-fired units in year y, It is the marginal cost of power generation of the new energy unit in year y. However, based on the characteristics of new energy, this data is taken as 0.

[0069] The incremental index of the comprehensive power generation cost of the power system compared with the previous year is ΔCe y for:

[0070] ΔCe y =Ce y -Ce y-1

[0071] Then, determine the starting benchmark electricity price for the medium- and long-term price forecast: the medium- and long-term benchmark electricity price P0 is the actual medium- and long-term transaction price in the market in the forecast starting year, and is used as the starting baseline for the medium- and long-term electricity price trend forecast.

[0072] Finally, through iterative calculation year by year, the medium- and long-term electricity prices of new energy sources for each year in the future are obtained:

[0073] The calculation method for the medium- and long-term electricity price of new energy in year y is:

[0074]

[0075] In the above formula, it should be noted that when Δsdi y <0, then in the above formula The positive and negative signs are all "+" and "-" respectively, because Δsdi y <0 means that the supply and demand relationship is more tense, and the medium and long-term electricity price should rise. y <0 and ΔCe y <0, then The sign of the term is "-" because when supply and demand are tight, the downward impact of prices brought about by the downward trend in system marginal costs will be weakened.

[0076] n and m are exponential empirical parameters, which can be determined based on historical data regression. Their purpose is to control the impact of market changes on prices.

[0077] In order to make the results of medium- and long-term electricity price deduction closer to reality, the above calculation formula can also be added with upper and lower limits of medium- and long-term electricity prices. For example, the current national policy requires that medium- and long-term transaction prices must be within the range of 20% above and below the benchmark coal-fired electricity price.

[0078] S3. Predict spot time-of-use electricity prices based on multiple sets of basic data.

[0079] By forecasting the spot time-of-use electricity price based on multiple sets of basic data, the spot time-of-use electricity price of new energy is obtained. The spot time-of-use electricity price mainly depends on the power supply and demand relationship and the unit quotation in the time period. The power supply and demand relationship in the time period mainly depends on the new energy power generation capacity in the time period and the output space of other units that must be turned on. In the spot market, assuming that the market is relatively mature, based on the principles of market economics, it can be seen that the quotations of various units will be close to the marginal power generation cost of the unit (the price under full game is close to the cost). Therefore, it can be seen that the quotation of new energy will inevitably approach 0, so that it can be awarded first, while the quotations of coal-fired power and gas-fired units will be close to their marginal power generation cost. The specific process is as follows:

[0080] First, based on various primary fuel cost data obtained from a third party, the fuel cost required for thermal power and gas turbines to generate each kilowatt-hour of electricity is calculated, and this is used as the marginal power generation cost of this type of unit.

[0081] Then, it is determined whether each type of unit should be cleared first. For units such as nuclear power, hydropower, biomass, pumped storage and energy storage, which usually do not directly participate in the electricity spot market quotation, they are often cleared first. Then, new energy and thermal power are cleared and awarded according to the quotation. The main priority clearing sequence is determined as follows:

[0082]

[0083] Finally, a spot economic dispatch model is constructed to optimize the spot time-of-use electricity price forecast curve for each year in the future.

[0084] Model optimization objective function: optimal system-wide power generation cost on future typical spot days.

[0085] Known data: typical load curve for each future year (including electricity consumption in each period), typical new energy power generation capacity of the province in each future year (including new energy power generation in each period, wind and solar power generation), and installed capacity of various power sources in each future year.

[0086] Optimization variables: various power supply outputs.

[0087] Output result: Quotation of marginal pricing type power source in each period (i.e. marginal power generation cost of this type of power source). This data constitutes the future spot electricity price curve for each period.

[0088] The model optimization objective function in year y (minimizing the total system electricity purchase cost) is as follows:

[0089]

[0090] The load balance constraints for each period in year y are:

[0091]

[0092] if I t =0, otherwise I t =1

[0093] In the above model, type refers to the unit type number, which is divided into non-priority clearing units α_type and priority clearing units β_type, with a total of M types of units; t is the time period, and 24 time periods are provided.

[0094] The future annual power generation of non-priority clearing units is expressed as is the optimization variable, the maximum of which is the installed capacity of the unit in year y

[0095] The expected power generation of the priority clearing units in each year and time period in the future is expressed as This item is a known quantity. For example, for new energy, the new energy power generation in each period is decomposed according to the total new energy power generation in each year in the future and the typical power generation curve. For example, for units with general adjustability such as biomass, the hypothetical power generation is obtained by spreading the installed capacity and average load rate in each year in the future to each period.

[0096] Each type of non-priority clearing unit also has a corresponding marginal power generation cost in each future year (assuming it is a spot price quote). The spot price quote of the units with priority clearing can be designated as 0 according to the principles of the electricity market.

[0097] C type It is a 0 / 1 control variable that determines whether the unit is cleared first. If the unit is cleared first, it is 0; if not, it is 1.

[0098] I t It is the judgment variable of whether the priority clearing unit can cover the entire system load. If the power of the priority clearing unit is greater than or equal to the system load during this period, then I t =0, otherwise I t =1.

[0099] The time-based load is obtained by decomposing the system load in each future year based on the system power consumption forecast for each future year given by a third party and the typical load curve.

[0100] The output logic of the above annual optimization model is: the ultimate goal of the model is to output the system's total system electricity purchase cost on typical spot days in the future years, as well as the clearing electricity price in each period. t =0, the spot clearing electricity price is 0;

[0101] I t =1, the model needs to output the optimization results of various non-priority clearing units The market clearing electricity price is the clearing electricity quantity of non-optimal clearing units in the current period. Greater than 0 and less than If there is no such non-optimal clearing unit, all units that meet The bid of the unit type with the highest bid / marginal generation cost among the non-optimal clearing units is used as the spot clearing price.

[0102] Based on this model, we can derive the spot market clearing electricity price for each future time period each year, i.e., the spot time-of-use electricity price for renewable energy. If the output of the optimized clearing units can cover the system load, the electricity price for that period is zero. Otherwise, the market price is the bid / marginal generation cost of the marginal non-optimal clearing units that just barely meet the system load.

[0103] S4. Calculate the new energy spot deviation settlement electricity price based on the new energy spot time-of-use electricity price.

[0104] The spot electricity price is only the price of electricity in the spot market, and does not represent the price that new energy can be settled. Further price calculation must be combined with the typical power generation capacity characteristics of wind and solar power stations. The typical output characteristics of new energy are the average output of each hour of wind power or photovoltaic unit in a certain power station during a period of time, which can be recorded as q t＝ [q1,q2…q 24 Renewable energy output characteristics primarily depend on geographic location and long-term meteorological conditions. These characteristics are typically assumed to be consistent over time, thus ignoring future year-to-year and inter-annual variations. It's important to note that typical output characteristics for renewable energy rely on data from the specific renewable energy projects being evaluated. For example, wind power projects in different locations within the same province may have different typical output characteristics, resulting in varying amounts of short-term generating capacity during periods of high spot prices. This, in turn, determines their future spot trading capabilities.

[0105] Secondly, based on the previous step, we can get the spot time-of-use electricity price of new energy in the future years under the spot background Assuming that the total amount of electricity traded in the future is equal to the actual power generation Q, that is, according to the typical output characteristics, However, due to the characteristics of medium- and long-term transactions, the overall medium- and long-term electricity consumption in different time periods is equal, so the medium- and long-term hourly electricity consumption of new energy in each year in the future can be obtained as

[0106] The future new energy spot deviation settlement prices for each year are as follows:

[0107]

[0108] In the calculation process of the above formula, due to the different output characteristics of different types of power stations, settlement is based on spot prices in different time periods. Therefore, different output characteristics will result in different spot deviation settlement prices, especially for wind power and photovoltaic power, there will be significant differences.

[0109] S5. Execute settlement electricity price forecast based on the settlement price structure of new energy electricity.

[0110] The settlement price structure of new energy electricity is shown in the following table:

[0111]

[0112] The above table provides an overview of the complete revenue structure for renewable energy in a spot market environment. However, from a spot market and investment perspective, the main components that experience significant fluctuations and are predictable are medium- and long-term returns, spot deviation settlement revenue, and ancillary service sharing costs. Most provinces are increasingly allocating less base electricity to renewable energy, and this allocation will eventually be eliminated. In the spot market scenario, this component is assumed to be zero and therefore not considered. The green environmental premium, on the other hand, depends primarily on green certificate trading and green market prices, and is based on market assumptions and is not subject to forecasts. System operating expenses, imbalance fund sharing, and two detailed expenses are primarily dependent on future provincial policies and have little correlation with market development, making them unpredictable. Ancillary service sharing costs are not significant, and according to current policies, new energy units entering the market in some provinces are not subject to sharing, so they can be ignored.

[0113] Therefore, from the perspective of investment evaluation and forecasting, the main forecasts are the medium- and long-term electricity prices and spot deviation settlement fees. Secondly, the proportion of other fees is also relatively small. These two items alone constitute the most important part of the long-term settlement electricity price of new energy under the future spot market, that is: the settlement price per kilowatt-hour of new energy under the future spot environment (long-term settlement price of new energy) ≈ the medium- and long-term electricity price of new energy + the spot deviation settlement price of new energy.

[0114] Based on the above analysis, the following calculation can be performed to obtain the long-term settlement electricity price of new energy:

[0115]

[0116] Among them, P y =[p1,p2…p n ], is the medium- and long-term electricity price of new energy power stations in the next n years, This is the new energy spot deviation settlement price, which can be used as the basis for evaluating future new energy investment returns under the spot background.

[0117] As can be seen from the above technical solution, this embodiment provides a settlement electricity price prediction method, which is applied to electronic equipment, specifically obtaining multiple sets of basic data; performing medium- and long-term electricity price trend analysis and prediction processing based on the multiple sets of basic data to obtain the medium- and long-term electricity price of new energy; performing spot time-of-use electricity price prediction based on the multiple sets of basic data to obtain the new energy spot time-of-use electricity price; performing calculation based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price; processing the new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price according to the new energy kilowatt-hour settlement price composition to obtain the new energy long-term settlement electricity price. According to this solution, the long-term settlement electricity price of new energy is obtained, so that investors can obtain a reliable investment basis for new energy investment and development.

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] Figure 2 This is a block diagram of a settlement electricity price prediction device according to an embodiment of the present application.

[0120] like Figure 2 As shown, the settlement electricity price prediction device provided in this embodiment is applied to an electronic device for predicting the long-term settlement electricity price of renewable energy. The electronic device can be understood as a computer, server, or cloud platform with data computing and information processing capabilities. The settlement electricity price prediction device includes a data acquisition module 10, a first computing module 20, a second computing module 30, a third computing module 40, and a prediction execution module 50.

[0121] The data acquisition module is used to obtain basic data for calculating the long-term settlement electricity price of new energy.

[0122] The basic data here include future multi-dimensional energy forecast data, electricity spot market data and future power generation capacity data of power plants.

[0123] This multi-dimensional energy forecast data comes from multiple energy information agencies and is used to predict data for at least the next 20 years. Common institutions such as Wood Mac and Bloomberg provide electricity spot market data, including provincial power grid and electricity spot market data.

[0124] For provinces that have already launched electricity spot markets, it is necessary to obtain historical daily spot market power load, power generation of various power sources and daily spot electricity price data; for provinces that have not yet launched electricity spot markets and only have medium- and long-term transactions, it is necessary to provide the medium- and long-term transaction prices for each year and month in history.

[0125] The future power generation capacity data of a power station refers to the typical expected future power generation capacity curve of the power station provided by the new energy owner or project contractor.

[0126] The power generation capacity of a new energy project at different times will inevitably affect its trading profitability in the future spot market. Therefore, analyzing its power generation capacity at different times can better evaluate its trading characteristics. The contractor or designer can provide a typical power generation capacity curve for each time period based on the local wind and solar resource endowment, longitude and latitude geographical location, etc.

[0127] The first calculation module is used to perform medium- and long-term electricity price trend analysis and forecasting based on basic data.

[0128] Through the above-mentioned multiple sets of basic data, the medium- and long-term electricity price trend analysis and forecast processing are carried out to obtain the medium- and long-term electricity price P of new energy. y The medium and long-term electricity price mainly depends on the market supply and demand relationship and the change of the marginal cost of the power system. This module includes a first calculation unit 21 and a second calculation unit 22. Figure 3 shown.

[0129] The first calculation unit is used to calculate the market supply-demand ratio index and the comprehensive marginal cost of the power system year by year based on the acquired basic data.

[0130] The market supply-demand ratio indicators are:

[0131] In the above formula, supply y It is the sum of all installed capacity of power sources other than renewable energy in the provincial market in year y, which represents the supply capacity of adjustable power sources other than non-renewable energy in the market; demand y It is the daily electricity consumption data for the next year y. This indicator reflects the supply and demand relationship in the electricity market. The larger the denominator, the higher the demand. y The smaller it is, the tighter the supply and demand relationship is, which is more likely to lead to high prices. Conversely, the looser the supply and demand is.

[0132] The supply-demand ratio increment index Δsdi is used to represent the change in supply-demand relationship compared to the previous year.y for:

[0133] Δsdi y =sdi y -sdi y-1

[0134] Comprehensive marginal cost of power system:

[0135]

[0136] In the above formula, is the annual power generation of the gas-fired unit in year y, is the annual power generation of the coal-fired unit in year y, is the annual power generation of the new energy unit in year y. is the average fuel cost of the gas-fired unit in year y, is the average fuel cost of electricity generated by coal-fired units in year y, It is the marginal cost of power generation of the new energy unit in year y. However, based on the characteristics of new energy, this data is taken as 0.

[0137] The incremental index of the comprehensive power generation cost of the power system compared with the previous year is ΔCe y for:

[0138] ΔCe y =Ce y -Ce y-1

[0139] Then, determine the starting benchmark electricity price for the medium- and long-term price forecast: the medium- and long-term benchmark electricity price P0 is the actual medium- and long-term transaction price in the market in the forecast starting year, and is used as the starting baseline for the medium- and long-term electricity price trend forecast.

[0140] The second calculation unit is used to obtain the medium- and long-term electricity prices of new energy sources for each year in the future through iterative calculations year by year:

[0141] The calculation method for the medium- and long-term electricity price of new energy in year y is:

[0142]

[0143] In the above formula, it should be noted that when Δsdi y <0, then in the above formula The positive and negative signs are all "+" and "-" respectively, because Δsdi y <0 means that the supply and demand relationship is more tense, and the medium and long-term electricity price should rise. y <0 and ΔCe y <0, then The sign of the term is "-" because when supply and demand are tight, the downward impact of prices brought about by the downward trend in system marginal costs will be weakened.

[0144] n and m are exponential empirical parameters, which can be determined based on historical data regression. Their purpose is to control the impact of market changes on prices.

[0145] In order to make the results of medium- and long-term electricity price deduction closer to reality, the above calculation formula can also be added with upper and lower limits of medium- and long-term electricity prices. For example, the current national policy requires that medium- and long-term transaction prices must be within the range of 20% above and below the benchmark coal-fired electricity price.

[0146] The second calculation module is used to predict the spot time-of-use electricity price based on multiple sets of basic data.

[0147] By forecasting the spot time-of-use electricity price based on multiple sets of basic data, the spot time-of-use electricity price of new energy can be obtained. The spot time-of-use electricity price mainly depends on the power supply and demand relationship and the unit quotation in the time period. The power supply and demand relationship in the time period mainly depends on the new energy power generation capacity in the time period and the output space of other units that must be turned on. In the spot market, assuming that the market is relatively mature, based on the principles of market economics, it can be seen that the quotations of various units will be close to the marginal power generation cost of the unit (the price under full game is close to the cost). Therefore, it can be seen that the quotation of new energy will inevitably approach 0, so that it can be awarded first, while the quotations of coal-fired power and gas-fired units will be close to their marginal power generation cost. This module includes a third calculation unit 31, a sequence determination unit 32 and a fourth calculation unit 33. Figure 4 shown.

[0148] The third calculation unit is used to convert the fuel cost required for thermal power and gas turbines to generate one kilowatt-hour of electricity based on various primary fuel cost data obtained from a third party, and use this as the marginal power generation cost of the unit type.

[0149] The sequence determination unit is used to determine whether various units should be cleared first. For units such as nuclear power, hydropower, biomass, pumped storage, and energy storage, which usually do not directly participate in the electricity spot market quotation, they are often directly cleared first. Then, new energy and thermal power are cleared and awarded according to the quotation. The main priority clearing sequences are determined as follows:

[0150]

[0151]

[0152] The fourth calculation unit calculates the spot time-of-use electricity price of new energy based on the construction of the spot economic dispatch model, thereby optimizing the spot time-of-use electricity price forecast curve for each year in the future.

[0153] Model optimization objective function: optimal system-wide power generation cost on future typical spot days.

[0154] Known data: typical load curve for each future year (including electricity consumption in each period), typical new energy power generation capacity of the province in each future year (including new energy power generation in each period, wind and solar power generation), and installed capacity of various power sources in each future year.

[0155] Optimization variables: various power supply outputs.

[0156] Output result: Quotation of marginal pricing type power source in each period (i.e. marginal power generation cost of this type of power source). This data constitutes the future spot electricity price curve for each period.

[0157] The model optimization objective function in year y (minimizing the total system electricity purchase cost) is as follows:

[0158]

[0159] The load balance constraints for each period in year y are:

[0160]

[0161] if I t =0, otherwise I t =1

[0162] In the above model, type refers to the unit type number, which is divided into non-priority clearing units α_type and priority clearing units β_type, with a total of M types of units; t is the time period, and 24 time periods are provided.

[0163] The future annual power generation of non-priority clearing units is expressed as is the optimization variable, the maximum of which is the installed capacity of the unit in year y

[0164] The expected power generation of the priority clearing units in each year and time period in the future is expressed as This item is a known quantity. For example, for new energy, the new energy power generation in each period is decomposed according to the total new energy power generation in each year in the future and the typical power generation curve. For example, for units with general adjustability such as biomass, the hypothetical power generation is obtained by spreading the installed capacity and average load rate in each year in the future to each period.

[0165] Each type of non-priority clearing unit also has a corresponding marginal power generation cost in each future year (assuming it is a spot price quote). The spot price quote of the units with priority clearing can be designated as 0 according to the principles of the electricity market.

[0166] C type It is a 0 / 1 control variable that determines whether the unit is cleared first. If the unit is cleared first, it is 0; if not, it is 1.

[0167] I t It is the judgment variable of whether the priority clearing unit can cover the entire system load. If the power of the priority clearing unit is greater than or equal to the system load during this period, then I t =0, otherwise I t =1.

[0168] The time-based load is obtained by decomposing the system load in each future year based on the system power consumption forecast for each future year given by a third party and the typical load curve.

[0169] The output logic of the above annual optimization model is: the ultimate goal of the model is to output the system's total system electricity purchase cost on typical spot days in the future years, as well as the clearing electricity price in each period. t =0, the spot clearing electricity price is 0;

[0170] I t =1, the model needs to output the optimization results of various non-priority clearing units The market clearing electricity price is the clearing electricity quantity of non-optimal clearing units in the current period. Greater than 0 and less than If there is no such non-optimal clearing unit, all units that meet The bid of the unit type with the highest bid / marginal generation cost among the non-optimal clearing units is used as the spot clearing price.

[0171] Based on this model, we can derive the spot market clearing electricity price for each future time period each year, i.e., the spot time-of-use electricity price for renewable energy. If the output of the optimized clearing units can cover the system load, the electricity price for that period is zero. Otherwise, the market price is the bid / marginal generation cost of the marginal non-optimal clearing units that just barely meet the system load.

[0172] The third calculation module is used to calculate the new energy spot deviation settlement electricity price based on the new energy spot time-of-use electricity price.

[0173] The spot electricity price is only the price of electricity in the spot market, and does not represent the price that new energy can be settled. Further price calculation must be combined with the typical power generation capacity characteristics of wind and solar power stations. The typical output characteristics of new energy are the average output of each hour of wind power or photovoltaic unit in a certain power station during a period of time, which can be recorded as q t＝ [q1,q2…q 24Renewable energy output characteristics primarily depend on geographic location and long-term meteorological conditions. These characteristics are typically assumed to be consistent over time, thus ignoring future year-to-year and inter-annual variations. It's important to note that typical output characteristics for renewable energy rely on data from the specific renewable energy projects being evaluated. For example, wind power projects in different locations within the same province may have different typical output characteristics, resulting in varying amounts of short-term generating capacity during periods of high spot prices. This, in turn, determines their future spot trading capabilities.

[0174] Secondly, based on the previous step, we can get the spot time-of-use electricity price of new energy in the future years under the spot background Assuming that the total amount of electricity traded in the future is equal to the actual power generation Q, that is, according to the typical output characteristics, However, due to the characteristics of medium- and long-term transactions, the overall medium- and long-term electricity consumption in different time periods is equal, so the medium- and long-term hourly electricity consumption of new energy in each year in the future can be obtained as

[0175] The future new energy spot deviation settlement prices for each year are as follows:

[0176]

[0177] In the calculation process of the above formula, due to the different output characteristics of different types of power stations, settlement is based on spot prices in different time periods. Therefore, different output characteristics will result in different spot deviation settlement prices, especially for wind power and photovoltaic power, there will be significant differences.

[0178] The prediction execution module is used to execute the settlement electricity price prediction based on the settlement price structure of new energy electricity.

[0179] The following calculation can be performed using the following formula to obtain the long-term settlement electricity price of new energy:

[0180]

[0181] Among them, P y =[p1,p2…p n ], is the medium- and long-term electricity price of new energy power stations in the next n years, This is the new energy spot deviation settlement price, which can be used as the basis for evaluating future new energy investment returns under the spot background.

[0182] As can be seen from the above technical solution, this embodiment provides a settlement electricity price prediction device, which is applied to electronic equipment and specifically obtains multiple sets of basic data; performs medium- and long-term electricity price trend analysis and prediction processing based on the multiple sets of basic data to obtain the medium- and long-term electricity price of new energy; performs spot time-of-use electricity price prediction based on the multiple sets of basic data to obtain the new energy spot time-of-use electricity price; performs calculation based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price; and processes the new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price according to the new energy kilowatt-hour settlement price composition to obtain the new energy long-term settlement electricity price. The long-term settlement electricity price of new energy obtained according to this solution can enable investors to obtain a reliable investment basis for new energy investment and development.

[0183] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0184] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0185] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present application.

[0186] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This electronic device is merely an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0187] The electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 502 or a program loaded from an input device 506 into a random access memory RAM 503. Various programs and data required for the operation of the electronic device are also stored in the RAM. The processing device, ROM, and RAM are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0188] Typically, the following devices may be connected to the I / O interface: input devices such as a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 508 such as a magnetic tape, hard disk, etc.; and communication devices 509. Communication devices 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figures illustrate electronic devices with various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may be implemented or present instead.

[0189] The present application also provides a computer-readable storage medium embodiment.

[0190] The computer-readable storage medium is applied to an electronic device and carries one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device obtains multiple sets of basic data; performs medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term new energy electricity prices; performs spot time-of-use electricity price forecasting based on the multiple sets of basic data to obtain new energy spot time-of-use electricity prices; performs calculations based on the new energy spot time-of-use electricity prices to obtain new energy spot deviation settlement electricity prices; and processes the medium- and long-term new energy electricity prices and the new energy spot deviation settlement electricity prices according to the new energy kilowatt-hour settlement price structure to obtain new energy long-term settlement electricity prices. The long-term settlement electricity prices for new energy obtained according to this solution enable investors to obtain a reliable investment basis for new energy investment and development.

[0191] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0192] In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0193] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0194] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for predicting settlement electricity prices, used to predict long-term settlement electricity prices for renewable energy, applied to electronic equipment, characterized in that: The settlement electricity price prediction method comprises the following steps: Obtain multiple sets of basic data; Performing medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources; Performing spot time-of-use electricity price forecasting based on the multiple sets of basic data to obtain the spot time-of-use electricity price of new energy; Calculating based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price; The new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price are processed according to the new energy kilowatt-hour settlement price structure to obtain the new energy long-term settlement electricity price.

2. The method for predicting the settlement electricity price according to claim 1, wherein: The multiple sets of basic data include future multi-dimensional energy forecast data, electricity spot market data and future power generation capacity data of power plants.

3. The method for predicting the settlement electricity price according to claim 1, wherein: The method of performing medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources includes the following steps: Calculating the market supply-demand ratio index and the comprehensive marginal cost of the power system year by year based on the multiple sets of basic data; Based on the market supply-demand ratio indicator, the comprehensive marginal cost of the power system and the predetermined deduction starting benchmark electricity price, an iterative calculation is performed year by year to obtain the medium- and long-term electricity price of new energy, which includes the predicted electricity price in future years.

4. The method for predicting the settlement electricity price according to claim 1, wherein: The method of predicting the spot time-of-use electricity price based on the multiple sets of basic data to obtain the spot time-of-use electricity price of new energy includes the following steps: Calculating marginal power generation costs of various units based on primary fuel cost data in the multiple sets of basic data; Determine the priority clearing sequence for each type of unit; The marginal power generation cost and the priority clearing sequence are processed based on a pre-built spot dispatch economic model to obtain the new energy spot time-of-use electricity price.

5. The method for predicting the settlement electricity price according to claim 1, wherein: The calculation based on the new energy spot time-of-use electricity price to obtain the new energy spot deviation settlement electricity price includes the following steps: The new energy spot deviation settlement electricity price is calculated based on the following equation: : Among them, q t is the average hourly output of the new energy units, is the hourly electricity consumption of new energy in the medium and long term in each year in the future, Q is the actual power generation in the medium and long term in the future, It is the spot time-of-use electricity price of the new energy.

6. A settlement electricity price prediction device for predicting the long-term settlement electricity price of new energy, applied to electronic equipment, characterized in that: The settlement electricity price prediction device includes: A data acquisition module is configured to acquire multiple sets of basic data; A first calculation module is configured to perform medium- and long-term electricity price trend analysis and forecasting based on the multiple sets of basic data to obtain medium- and long-term electricity prices for new energy sources; A second calculation module is configured to perform a spot time-of-use electricity price forecast based on the multiple sets of basic data to obtain a new energy spot time-of-use electricity price; a third calculation module configured to calculate based on the new energy spot time-of-use electricity price to obtain a new energy spot deviation settlement electricity price; The prediction execution module is configured to process the new energy medium- and long-term electricity price and the new energy spot deviation settlement electricity price according to the new energy kilowatt-hour settlement price structure to obtain the new energy long-term settlement electricity price.

7. The settlement electricity price prediction device according to claim 6, wherein: The first calculation module includes: A first calculation unit is configured to calculate the market supply-demand ratio index and the comprehensive marginal cost of the power system year by year based on the multiple sets of basic data; The second calculation unit is configured to perform iterative calculations year by year based on the market supply-demand ratio indicator, the comprehensive marginal cost of the power system and a predetermined deduction starting benchmark electricity price to obtain the medium- and long-term electricity price of the new energy, which includes the predicted electricity price in future years.

8. The settlement electricity price prediction device according to claim 6, wherein: The second calculation module includes: a third calculation unit, configured to calculate the marginal power generation cost of each type of unit based on the primary fuel cost data in the multiple sets of basic data; A sequence determination unit is configured to determine a priority clearing sequence for each type of unit; The fourth calculation unit is configured to process the marginal power generation cost and the priority clearing sequence based on a pre-built spot dispatch economic model to obtain the new energy spot time-of-use electricity price.

9. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is configured to execute the computer program or instruction so as to enable the electronic device to implement the settlement electricity price prediction method according to any one of claims 1 to 5.

10. A computer-readable storage medium, applied to an electronic device, characterized in that: The storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device implements the settlement electricity price prediction method according to any one of claims 1 to 5.

Images