Electricity price prediction method and device, computer device, readable storage medium and program product

Abstract

The application relates to a power price prediction method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring public input information of a power market; constructing a unit commitment model of each market member in the power market according to the public input information, with the target of minimizing the power purchase cost; solving the unit commitment model based on a preset constraint condition to obtain a market clearing price of the power market; correcting the market clearing price of the power market based on a power price difference value and the public input information at each time point in a historical time period, to obtain a power price prediction result of the power market, wherein the power price difference value refers to a difference value between a predicted power price and an actual power price. The method can improve the accuracy of power price prediction.

Description

Technical Field

[0001] This application relates to the field of power system operation technology, and in particular to a method, apparatus, computer equipment, readable storage medium, and program product for predicting electricity prices. Background Technology

[0002] Electricity price forecasting in the electricity market refers to the prediction and analysis of electricity transaction prices for a specific future period based on various factors such as historical data, market rules, policy guidance, supply and demand, fuel costs, and weather conditions, using mathematical models and algorithms. With the deepening of electricity market reforms, electricity price forecasting has become a crucial element in market participants' decision-making, its importance permeating every aspect of the electricity market and serving as a core support for its stable, efficient, and sustainable development.

[0003] Currently, electricity price forecasting methods generally involve using simulation to recreate the market clearing situation as much as possible to predict future electricity prices, or using data analysis and other means to analyze and study historical data to explore the intrinsic relationship between electricity prices and influencing factors (such as centrally dispatched load, bidding space, and bid prices) and the development and change patterns of electricity prices themselves, in order to predict future electricity prices.

[0004] However, the above-mentioned electricity price forecasting methods suffer from low accuracy. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, readable storage medium, and program product that can improve the accuracy of electricity price forecasting in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for predicting electricity prices, including:

[0007] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0008] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0009] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0010] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0011] In one embodiment, the above-mentioned method of constructing a unit combination model for each market participant in the electricity market based on public input information, with the objective of minimizing the cost of electricity purchased from the market, includes:

[0012] Based on public input information, determine the bidding results of each market participant in the electricity market;

[0013] With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0014] In one embodiment, determining the bidding results of each market participant in the electricity market based on public input information includes:

[0015] Electricity price forecasts are performed based on public input information to obtain initial electricity price forecast results;

[0016] Based on market participant information and initial electricity price forecasts from the public input information, the bidding results of each market participant in the electricity market are determined.

[0017] In one embodiment, determining the bidding results of each market participant in the electricity market based on market participant information in the public input information and the initial electricity price forecast results includes:

[0018] Based on relevant information about market participants, initial electricity price forecasts, and pre-set pricing strategies, a pricing model for each market participant in the electricity market is constructed. The pre-set pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on forecasted prices.

[0019] Solve the pricing model for each market participant to obtain their pricing results.

[0020] In one embodiment, the market clearing price of the electricity market is corrected based on the price differences at various times within a historical period and common input information to obtain the electricity market price prediction result, including:

[0021] Based on the electricity price difference at each time point and common input information, the predicted price error is determined;

[0022] The electricity market price forecast is determined based on the market clearing price and the error in the forecast price.

[0023] In one embodiment, determining the predicted price error based on the electricity price difference at each time point and common input information includes:

[0024] The common input information is fed into the electricity price prediction model for prediction, and the initial electricity price prediction result is obtained.

[0025] Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, an error distribution function is constructed.

[0026] Solve for the error distribution function to obtain the predicted price error.

[0027] Secondly, this application also provides an electricity price forecasting device, comprising:

[0028] The acquisition module is used to acquire public input information of the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center.

[0029] The module is designed to construct unit combination models for each market participant in the electricity market based on public input information, with the goal of minimizing the cost of electricity purchased from the market.

[0030] The solver module is used to solve the unit combination model based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0031] The correction module is used to correct the market clearing price of the electricity market based on the price difference at various times within a historical period and common input information, so as to obtain the electricity price prediction result of the electricity market. The price difference refers to the difference between the predicted electricity price and the actual electricity price.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0034] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0035] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0036] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0039] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0040] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0041] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0044] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0045] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0046] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0047] The aforementioned electricity price forecasting method, apparatus, computer equipment, readable storage medium, and program product feed publicly available data such as meteorological, energy price, day-ahead boundary information, and market participant information into a unit combination model aimed at minimizing electricity purchase costs. Based on hard constraints such as physics, power, and reserve, the market clearing price of the electricity market is calculated. Then, historical electricity price differences and common input information are used to correct the market clearing price, thereby obtaining the electricity market price forecast result. Compared with methods that directly forecast electricity prices, this application constructs a unit combination model for each market participant based on minimizing electricity purchase costs, determines the market clearing price of the electricity market, and corrects the market clearing price of the electricity market based on the electricity price differences at various times within a historical period and common input information. This effectively corrects systematic errors and improves the accuracy of the determined electricity market price forecast result. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a diagram illustrating the application environment of the electricity price forecasting method in one embodiment;

[0050] Figure 2 This is a flowchart illustrating an electricity price forecasting method in one embodiment;

[0051] Figure 3 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0052] Figure 4 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0053] Figure 5 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0054] Figure 6 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0055] Figure 7 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0056] Figure 8 This is a flowchart illustrating the electricity price forecasting method in another embodiment;

[0057] Figure 9This is a structural block diagram of an electricity price prediction device in one embodiment;

[0058] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] Electricity price forecasting in the electricity market refers to the prediction and analysis of electricity transaction prices for a specific future period based on various factors such as historical data, market rules, policy guidance, supply and demand, fuel costs, and weather conditions, using mathematical models and algorithms. With the deepening of electricity market reforms, electricity price forecasting has become a crucial element in market participants' decision-making, its importance permeating every aspect of the electricity market and serving as a core support for its stable, efficient, and sustainable development.

[0061] Currently, electricity price forecasting methods generally involve using simulation to recreate the market clearing situation as much as possible to predict future electricity prices, or using data analysis and other means to analyze and study historical data to explore the intrinsic relationship between electricity prices and influencing factors (such as centrally dispatched load, bidding space, and bid prices) and the development and change patterns of electricity prices themselves, in order to predict future electricity prices.

[0062] However, the aforementioned electricity price forecasting methods suffer from low accuracy. Therefore, this application provides an electricity price forecasting method to address this problem.

[0063] The electricity price forecasting method provided in this application can be applied to, for example... Figure 1 In the application environment shown, the application environment includes a data storage system 102 and a server 104. The data storage system 102 can store the data that the server 104 needs to process. The data storage system 102 can be integrated onto the server 104, or it can be located in the cloud or on other network servers. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0064] The data storage system 102 can communicate with the server 104. For example, the server 104 can send a data request to the data storage system 102 to obtain data from the data storage system 102, and then process the obtained data to obtain the electricity price forecast.

[0065] In other possible implementations, the electricity price prediction method provided in this application can also be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc.

[0066] In one exemplary embodiment, such as Figure 2 As shown, an electricity price forecasting method is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes:

[0067] S201. Obtain public input information for the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center.

[0068] Meteorological forecast information can include elements such as temperature, humidity, rainfall, radiation, and wind speed. Meteorological forecast information can be represented by W.

[0069] Among them, energy price information can be primary energy price information, including thermal coal price, natural gas price, etc., and energy price information can be represented by J.

[0070] The day-ahead boundary information released by the power trading center may include system load forecast information. Wind power generation forecast information Photovoltaic power generation forecast information Hydropower generation forecast information Non-market member power generation forecast information and connecting line project forecast information The boundary information can be represented by M1.

[0071] System load forecast information This refers to the load demand forecast curves of the entire network at 96 points, generated by the dispatching agency every 15 minutes starting from midnight the following day. The load forecast information of this system comprehensively considers the load of similar historical days, workday type, meteorological factors, user electricity demand, holidays or major social events, demand response and orderly electricity consumption, etc., and is used as one of the core boundary conditions for the clearing of the day-ahead spot market.

[0072] Wind power generation forecast information This refers to the quantitative prediction of wind farm output power at different time scales, from minutes to years, using historical meteorological observations, numerical weather prediction (NWP), and supervisory control and data acquisition (SCADA) data, through physical models, statistical methods, or artificial intelligence algorithms. Its core is to transform meteorological variables such as wind speed, wind direction, and air density into power generation curves, thereby providing a wind power output prediction curve arranged at 15-minute (or 1-hour) intervals and the corresponding error range, which is used for grid dispatching, spot market bidding, reserve capacity arrangement, and equipment maintenance planning.

[0073] Photovoltaic power generation forecast information This refers to the quantitative prediction of the power output curve of a photovoltaic power station for different trading periods such as day-ahead, intraday, and real-time. It takes into account numerical weather forecast data such as solar irradiance, cloud cover, temperature, humidity, and wind speed, as well as power station operating parameters such as photovoltaic module efficiency, inverter status, surface reflectivity, dust accumulation, and tracking angle. It utilizes physical models, machine learning, or deep learning algorithms to quantitatively predict the power output curve of a photovoltaic power station for several minutes to several days (usually 15 minutes or 1 hour). The prediction provides the corresponding confidence interval or maximum / minimum technical output, which is used for grid security-constrained economic dispatch, spot market clearing, reserve capacity arrangement, maintenance plans, and inter-regional power transmission plans.

[0074] Hydropower generation forecast information This refers to the quantitative prediction of hydropower station power output curves for several hours to several days in different trading periods, such as day-ahead, intraday, and real-time, taking into account multiple constraints such as basin hydrology and meteorology (rainfall, runoff, snowmelt), reservoir water level and regulation capacity, unit maintenance and dispatching procedures, flood control, navigation, and ecology. The prediction results provide corresponding confidence intervals or maximum / minimum technical output for grid security-constrained economic dispatching, spot market clearing, reserve capacity arrangement, and inter-regional power transmission plans.

[0075] Non-market member power generation forecast information This refers to the proxy power generation forecast curve uniformly compiled by power grid companies or dispatching agencies on behalf of generating units that have not yet registered as market entities (such as some guaranteed thermal power, imported power, distributed renewable energy, pumped storage, etc.). The power generation forecast information of non-market members, during day-ahead, intraday, and real-time trading periods, comprehensively considers non-market factors such as unit maintenance plans, water, wind, solar power, fuel supply, heating constraints, grid operation modes, and policy directives to quantitatively estimate power generation output for several hours to several days (usually 15 minutes or 1 hour), forming an output curve with confidence intervals. This curve serves as the core boundary condition for spot market clearing, power balance, reserve arrangements, and priority generation and priority consumption matching, ensuring that non-market power and market power are cleared and settled safely and fairly on the same platform.

[0076] Forecast information for the connecting line project It refers to the result of market operators quantifying and publishing the active power flow curves of inter-provincial (regional) AC / DC interconnection lines in advance during trading periods such as day-ahead, intraday, and real-time.

[0077] The market participant information includes market participant information, operational information, and grid topology information, denoted by M2. Market participant information refers to the static profiles and real-time status sets of all entities that have completed market access and registered with the trading center, such as power generation companies, power sales companies, power users, independent energy storage, and virtual power plants. Operational information refers to all dynamic boundary and result data directly related to market clearing released by the market operator on the operating day and in future periods, usually issued in the form of 96-point (15-minute) or 288-point (5-minute) curves. Grid topology information refers to the grid connection relationships and physical parameter models used for market clearing and security verification.

[0078] In this embodiment, when it is necessary to predict electricity prices, it is necessary to obtain meteorological forecast information, energy price information, day-ahead boundary information and market participant information released by the power trading center.

[0079] S202. With the goal of minimizing electricity purchase costs, construct a unit combination model for each market participant in the electricity market based on public input information.

[0080] In this embodiment, after obtaining the common input information, with the goal of minimizing the total cost of electricity purchase, the unit combination model of each market member in the electricity market is constructed based on the obtained common input information.

[0081] Optionally, after obtaining the common input information, the common input information can be processed to obtain the processed common input information. Then, based on the processed common input information, a unit combination model of each market member in the electricity market can be constructed with the goal of minimizing the electricity purchase cost.

[0082] S203. Solve the unit combination model based on preset constraints to obtain the market clearing price of the electricity market; the preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0083] The market-clearing price refers to the price level at which the supply and demand in a specific market are exactly equal. At this price, all goods willing to be sold at that price can be successfully sold without excess inventory; all consumer demand willing to buy at that price can be met without queuing or rationing; the market reaches supply and demand equilibrium, and the price at this point is called the equilibrium price, while the corresponding transaction volume is called the equilibrium quantity.

[0084] In this embodiment, after constructing the unit combination model of the electricity market as described above, the unit combination model can be solved based on preset constraints to obtain the market clearing price of the electricity market.

[0085] It should be noted that the physical constraints of generator operation also include: upper and lower limits of generator output, generator segmented output and total output constraints, generator segmented output constraints, minimum continuous start-stop constraints, and generator ramping constraints. These constraints will be described in detail below:

[0086] (1) The upper and lower limits of generator output can be expressed by the following formula (1):

[0087]

[0088] in, and They represent the generating units. The minimum and maximum output values, A binary variable representing the unit During the period Whether it is running (1 indicates that the computer is on, 0 indicates that the computer is off). This refers to the output value of generator unit i.

[0089] (2) The constraints on the generator's segmented output and total output can be expressed by the following formula (2):

[0090]

[0091] in, This refers to market participant i winning the bid in segment s during time period t, where s refers to the number of segmented bids and t refers to time period t.

[0092] (3) The generator segmented output constraint can be expressed by the following formula (3):

[0093]

[0094] in, This refers to the endpoint of the s-segment price output of market member i.

[0095] (4) The minimum continuous start-stop constraint of the generator can be expressed by the following formulas (4) and (5):

[0096]

[0097]

[0098] in, and They represent the generating units. The minimum continuous start-up time and the minimum continuous downtime.

[0099] (5) The constraints on the start-up and shutdown states of the unit can be expressed by the following formula (6):

[0100]

[0101] in, A binary variable representing the unit During the period Is there a power-on action? (1 indicates power-on is performed, 0 indicates no action is taken). A binary variable representing the unit During the period Is there a power-on action? (1 indicates power-off, 0 indicates no action).

[0102] (6) The ramping constraint of the generator set can be expressed by the following formulas (7) and (8):

[0103]

[0104]

[0105] in, and They represent the generating units. The uphill and downhill rates.

[0106] Optionally, the power balance and capacity constraints of the power generation system can be expressed by the following formula (9):

[0107]

[0108] in, Indicates time period The load demand.

[0109] Optionally, the safety reserve constraint of the power generation system can be expressed by the following formulas (10) and (11):

[0110]

[0111]

[0112] in, They represent the generating units. exist The ability to be on standby at all times. This is the system's reserve coefficient.

[0113] S204. Based on the price difference at various points in the historical time period and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0114] In this embodiment, after determining the market clearing price of the electricity market as described above, the price difference between the predicted electricity price and the actual electricity price at each time point in the historical time period can be further obtained. Based on the price difference and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price prediction result of the electricity market.

[0115] In this embodiment, publicly available data such as meteorological, energy price, day-ahead boundary information, and market participant information are fed into a unit combination model aimed at minimizing electricity purchase costs. Based on hard constraints such as physics, power, and reserve, the market clearing price of the electricity market is calculated. Then, historical electricity price differences and common input information are used to correct the market clearing price, thereby obtaining the electricity market price forecast result. Compared with methods that directly predict electricity prices, this application constructs a unit combination model for each market participant based on minimizing electricity purchase costs, determines the market clearing price of the electricity market, and corrects the market clearing price of the electricity market based on the electricity price differences at various times in the historical time period and common input information. This effectively corrects systematic errors and improves the accuracy of the determined electricity market price forecast result.

[0116] In this embodiment, in the above Figure 2 Based on the illustrated embodiments, the detailed process of constructing the unit combination model for each market participant will be explained. In an exemplary embodiment, such as Figure 3 As shown, the above S202 includes:

[0117] S301. Based on the public input information, determine the bidding results of each market participant in the electricity market.

[0118] In this embodiment, after obtaining the public input information, the bidding results of each market participant in the electricity market can be determined based on the public input information.

[0119] S302. With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0120] In this embodiment, after obtaining the bidding results of each market participant, a unit combination model can be constructed based on the bidding results of each market participant and the day-ahead boundary information, with the goal of minimizing the market electricity purchase cost. Optionally, the form of the unit combination model can be expressed by the following formula (12):

[0121]

[0122] in, This refers to the output quote for unit i in section S. This refers to market participant i's bid contribution in segment s during time period t. Indicates the unit Startup costs.

[0123] In this embodiment, publicly available information is directly transformed into the bidding results of each member, eliminating repeated probing and opaque games. These real bids, together with the day-ahead boundary information, are then used to construct a unit combination model with the goal of minimizing the electricity purchase cost. This model calculates in one go which market member should start and which should stop, thus eliminating information rent in the market and further reducing the total electricity purchase cost of the system.

[0124] In this embodiment, in the above Figure 3 Based on the illustrated embodiment, a detailed process for determining the bidding results of each market participant in the electricity market based on public input information will be explained. In an exemplary embodiment, such as Figure 4 As shown, the above S301 includes:

[0125] S401. Based on public input information, predict electricity prices to obtain initial electricity price prediction results.

[0126] In this embodiment, after collecting the common input information, the common input information can be input into the electricity price prediction model to predict the electricity price and obtain the initial electricity price prediction result.

[0127] Optionally, the electricity price forecasting model may include classic time series statistical models, traditional machine learning models, deep learning models, and Transformer models.

[0128] Classical time-series statistical models, such as the Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA), are suitable for capturing the linear autocorrelation and seasonality of electricity price series. These models are simple and highly interpretable, but their ability to capture nonlinearity and external shocks is relatively weak, and they are often used as baseline models. Exponential smoothing models, on the other hand, are suitable for series with obvious trends and seasonality and are computationally efficient.

[0129] Traditional machine learning models, such as gradient boosting trees, extreme gradient boosting (XGBoost), lightweight gradient boosting machine (LightGBM), categorical boosting (CatBoost), and random forests, are currently the mainstream models in structured data prediction competitions.

[0130] Among them, deep learning models, such as Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs), are specifically designed for sequential data. They can effectively capture the long-term and short-term dependencies and complex patterns of electricity prices, and are particularly good at handling nonlinear relationships. They are powerful tools for dealing with complex time-series problems such as electricity price forecasting.

[0131] Among them, the Transformer model, which is mainly based on the self-attention mechanism, can better capture long-distance dependencies in the sequence and performs well when dealing with ultra-long sequences. It is one of the most cutting-edge time series prediction models.

[0132] It should be noted that the initial electricity price forecasts may be the same or different based on different electricity price forecasting models. For example, by inputting common input information into different electricity price forecasting models, multiple initial electricity price forecasts can be obtained. These multiple initial electricity price forecasts can be represented as follows: ,in, This represents the initial electricity price forecast result obtained from the electricity price forecasting model i, where , representing the electricity price prediction results at different times obtained using the electricity price prediction model i.

[0133] S402. Based on the market member information and initial electricity price forecast results in the public input information, determine the bidding results of each market member in the electricity market.

[0134] In this embodiment, after obtaining the initial electricity price forecast results of each market participant, the bidding results of each market participant in the electricity market can be determined based on the relevant information of the market participants and the initial electricity price forecast results.

[0135] Optionally, the following describes a detailed process for determining the bid results of each market participant in the electricity market based on market participant information in the public input information and the initial electricity price forecast results. See [link to relevant documentation]. Figure 5 The aforementioned S402 includes:

[0136] S4021. Based on relevant information of market participants, initial electricity price forecast results, and preset pricing strategies, construct pricing models for each market participant in the electricity market; preset pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on predicted prices.

[0137] The cost-plus pricing strategy refers to a pricing strategy based on the physical marginal cost of the generator set. It usually involves adding a fixed profit margin or a markup to cover start-up costs to the marginal cost. In this case, market participants act as price takers in a perfectly competitive market, or as a basic pricing method required by regulations.

[0138] The marginal cost strategy refers to submitting a bid directly based on the generator unit's true marginal cost. This is theoretically the optimal strategy in a perfectly competitive market. It is suitable for units with extremely low marginal costs, such as hydropower and nuclear power plants, or for thermal power units forced to bid at cost in highly competitive markets. While this strategy ensures that the unit will be called up when the market price is higher than its cost, avoiding downtime risk, it also forgoes all potential excess profits.

[0139] Among them, the price-based strategy relies on the initial electricity price forecast and makes its bid decision based on the initial electricity price forecast. The basic idea is that if the initial electricity price forecast is much higher than the marginal cost, it may bid slightly lower to ensure winning the bid; if the initial electricity price forecast is close to the marginal cost, it will bid at the marginal cost; and if the initial electricity price forecast is lower than the marginal cost, it may choose not to bid.

[0140] Optionally, preset pricing strategies also include game theory-based pricing strategies, which are central to simulating market power and strategic pricing. In this approach, generators are no longer seen as price takers, but rather recognize that their pricing will influence the market-clearing price. Typical game theory methods include guessing the supply function, where each generator needs to predict its competitors' supply functions and then, like a leader, formulate its own optimal supply function.

[0141] Optionally, the preset bidding strategy also includes a history-based and learning-based bidding strategy. This method analyzes historical market clearing data and uses reinforcement learning to analyze the behavior patterns of simulated competitors, modeling the bidding process as a Markov decision process. The engine updates its strategy network by continuously trying bids and receiving rewards, and finally learns the optimal bidding strategy for a specific market condition.

[0142] In this embodiment, market participant information, initial electricity price forecasts, and preset pricing strategies from the public input information are used to generate pricing models for each market participant in the electricity market, defining the first... The preset pricing strategy is If the first The market member adopted the first Preset pricing strategy At the same time pricing strategies The electricity price forecast results used in this study are: Then the pricing model of market member i can be expressed by the following formula (13):

[0143]

[0144] in, and These represent the cost information and current medium- to long-term holdings of market participant i, respectively. and Representing market members The minimum and maximum output values.

[0145] It should be noted that this pricing model is a core component of power market simulation, decision support, or smart trading systems. Its core function is to simulate the pricing behavior of different types of power generation manufacturers (market participants) in the spot market (such as the day-ahead market). The pricing model incorporates a variety of economic and game theory-driven pricing strategy algorithms.

[0146] S4022. Solve the pricing model for each market participant to obtain their pricing results.

[0147] In this embodiment, after obtaining the pricing models of each market member, the pricing models of each market member can be solved to obtain the pricing results of each market member.

[0148] For example, the bidding results of market member i It can be expressed by the following formula (14):

[0149]

[0150] in, Indicates market members The The end point and declared price of the segment.

[0151] In this embodiment, based on the relevant information of each market member and the initial electricity price forecast results, a bidding model for each market member in the electricity market is constructed. Then, based on the bidding models of each market member, the bidding results of each market member are obtained, providing a data foundation for accurate electricity price prediction based on the bidding results of each market member.

[0152] In this embodiment, in the above Figure 2 Based on the illustrated embodiment, the detailed process of obtaining electricity price forecasts for each market participant will be explained. In an exemplary embodiment, such as Figure 6 As shown, the above S204 includes:

[0153] S501. Based on the electricity price difference at each time point and common input information, determine the predicted price error.

[0154] In this embodiment, after obtaining the common input information, the price difference at each time point within the historical time period can also be obtained. Then, based on the price difference at each time point within the historical time period and the common input information, the predicted price error is determined.

[0155] Optionally, a detailed method for determining the predicted price error based on the electricity price difference at each time point and common input information is provided below; see [link to relevant documentation]. Figure 7 The aforementioned S501 includes:

[0156] S5011. Input the common input information into the electricity price prediction model for prediction to obtain the initial electricity price prediction result.

[0157] In this embodiment, after obtaining the common input information, the common input information can be input into the electricity price prediction model for prediction to obtain the initial electricity price prediction result.

[0158] It should be noted that the process of predicting electricity prices in the electricity price forecasting model is consistent with the description in S401 above, and can be directly referred to in S401 above, so it will not be repeated here.

[0159] S5012. Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, construct the error distribution function.

[0160] In this embodiment, after obtaining the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, an error distribution function can be constructed based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results.

[0161] For example, in In time series forecasting, the initial electricity price forecast, voltage differences at various points in the historical time period, and day-ahead boundary information from the common input information are used. An autoregressive exogenous variable model (ARX) is employed, but its autoregressive term only points to data from the same historical time period. The endogenous variables of the ARX model are... error and hysteresis error , , The exogenous variable is the extreme value of the error from the previous day. Holiday dummy variables Bidding Space Prediction Construct the error distribution function, as shown in the following formula (15):

[0162]

[0163] in The coefficients to be estimated are denoted as . It follows a homoscedastic normal distribution, that is Footnote Let and represent time t of the previous n natural days, respectively, and the predicted bidding space. It is calculated from the day-ahead boundary information in the public input information.

[0164] S5013. Solve for the error distribution function to obtain the predicted price error.

[0165] In this embodiment, after obtaining the error distribution function, the error distribution function can be solved based on the random post-processing technique, that is, the error distribution function can be solved by time series analysis to obtain the predicted price error.

[0166] Thus, based on the electricity price difference at each time point and the common input information, the predicted price error is calculated.

[0167] S502. Determine the electricity market price forecast results based on the market clearing price and the forecast price error.

[0168] In this embodiment, after obtaining the predicted price error, the electricity price prediction result of the electricity market can be determined based on the sum of the market clearing price and the predicted price error.

[0169] In this embodiment, the predicted price error is determined by the price difference at each time point and common input information. Then, the market clearing price is corrected based on the predicted price error to obtain the electricity price prediction result of the electricity market. This provides the accuracy of the electricity price prediction result of the electricity market and ensures the orderly operation of the power grid system.

[0170] In one exemplary embodiment, see Figure 8 It also provides a method for predicting electricity prices, including:

[0171] T1. Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0172] T2. Based on the public input information, predict the electricity price to obtain the initial electricity price prediction result;

[0173] T3. Based on relevant information of market participants, initial electricity price forecasts, and pre-set pricing strategies, construct pricing models for each market participant in the electricity market; the pre-set pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on forecasted prices.

[0174] T4. Solve the pricing model for each market participant to obtain the pricing results for each market participant;

[0175] T5. With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0176] T6. Solve the unit combination model based on preset constraints to obtain the market clearing price of the electricity market; the preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0177] T7. Input the common input information into the electricity price prediction model to make a prediction and obtain the initial electricity price prediction result;

[0178] T8. Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, construct the error distribution function; the electricity price difference refers to the difference between the predicted electricity price and the actual electricity price.

[0179] T9. Solve for the error distribution function to obtain the predicted price error;

[0180] T10. Determine the electricity market price forecast result based on the market clearing price and the forecast price error.

[0181] It should be noted that the descriptions of T1-T10 above can be found in the relevant descriptions in the above embodiments, and their effects are similar, so they will not be repeated here.

[0182] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0183] Based on the same inventive concept, this application also provides an electricity price forecasting device for implementing the electricity price forecasting method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the electricity price forecasting device provided below can be found in the limitations of the electricity price forecasting method described above, and will not be repeated here.

[0184] In one exemplary embodiment, such as Figure 9 As shown, an electricity price prediction device is provided, including: an acquisition module 10, a construction module 11, a solution module 12, and a correction module 13, wherein:

[0185] The acquisition module 10 is used to acquire public input information of the electricity market; the public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market member information released by the electricity trading center.

[0186] Module 11 is used to construct unit combination models for each market participant in the electricity market based on common input information with the goal of minimizing electricity purchase costs.

[0187] The solver module 12 is used to solve the unit combination model based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0188] The correction module 13 is used to correct the market clearing price of the electricity market based on the price difference at each moment in the historical time period and the public input information, so as to obtain the electricity price prediction result of the electricity market. The price difference refers to the difference between the predicted electricity price and the actual electricity price.

[0189] In an exemplary embodiment, the above-described building module 11 includes:

[0190] The first determining unit is specifically used to determine the bidding results of each market participant in the electricity market based on public input information;

[0191] The building unit is specifically used to construct a unit combination model based on the bidding results of each market participant and the day-ahead boundary information, with the goal of minimizing the market electricity purchase cost.

[0192] In an exemplary embodiment, the first determining unit is further configured to perform electricity price forecasting based on public input information to obtain an initial electricity price forecast result; and to determine the bidding results of each market participant in the electricity market based on market participant information in the public input information and the initial electricity price forecast result.

[0193] In an exemplary embodiment, the first determining unit is further configured to construct a pricing model for each market participant in the electricity market based on relevant information about market participants, initial electricity price forecast results, and a preset pricing strategy; the preset pricing strategy includes any one of a cost-plus pricing strategy, a marginal cost pricing strategy, and a pricing strategy based on predicted prices; and solve the pricing model of each market participant to obtain the pricing results of each market participant.

[0194] In an exemplary embodiment, the above-mentioned correction module 13 further includes:

[0195] The second determining unit is specifically used to determine the predicted price error based on the electricity price difference at each time point and common input information;

[0196] The third determining unit is specifically used to determine the electricity market price forecast result based on the market clearing price and the forecast price error.

[0197] In an exemplary embodiment, the second determining unit is further configured to input the common input information into the electricity price prediction model for prediction to obtain an initial electricity price prediction result; construct an error distribution function based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction result; and solve the error distribution function to obtain the predicted price error.

[0198] Each module in the aforementioned electricity price forecasting device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0199] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores electricity market data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements an electricity price forecasting method.

[0200] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0201] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0202] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0203] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0204] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0205] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0206] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0207] Based on public input information, determine the bidding results of each market participant in the electricity market;

[0208] With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0209] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0210] Electricity price forecasts are performed based on public input information to obtain initial electricity price forecast results;

[0211] Based on market participant information and initial electricity price forecasts from the public input information, the bidding results of each market participant in the electricity market are determined.

[0212] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0213] Based on relevant information about market participants, initial electricity price forecasts, and pre-set pricing strategies, a pricing model for each market participant in the electricity market is constructed. The pre-set pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on forecasted prices.

[0214] Solve the pricing model for each market participant to obtain their pricing results.

[0215] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0216] Based on the electricity price difference at each time point and common input information, the predicted price error is determined;

[0217] The electricity market price forecast is determined based on the market clearing price and the error in the forecast price.

[0218] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0219] The common input information is fed into the electricity price prediction model for prediction, and the initial electricity price prediction result is obtained.

[0220] Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, an error distribution function is constructed.

[0221] Solve for the error distribution function to obtain the predicted price error.

[0222] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0223] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0224] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0225] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0226] Based on the price differences at various points in time during historical periods and public input information, the market clearing price of the electricity market is corrected to obtain the electricity price forecast result. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0227] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0228] Based on public input information, determine the bidding results of each market participant in the electricity market;

[0229] With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0230] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0231] Electricity price forecasts are performed based on public input information to obtain initial electricity price forecast results;

[0232] Based on market participant information and initial electricity price forecasts from the public input information, the bidding results of each market participant in the electricity market are determined.

[0233] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0234] Based on relevant information about market participants, initial electricity price forecasts, and pre-set pricing strategies, a pricing model for each market participant in the electricity market is constructed. The pre-set pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on forecasted prices.

[0235] Solve the pricing model for each market participant to obtain their pricing results.

[0236] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0237] Based on the electricity price difference at each time point and common input information, the predicted price error is determined;

[0238] The electricity market price forecast is determined based on the market clearing price and the error in the forecast price.

[0239] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0240] The common input information is fed into the electricity price prediction model for prediction, and the initial electricity price prediction result is obtained.

[0241] Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, an error distribution function is constructed.

[0242] Solve for the error distribution function to obtain the predicted price error.

[0243] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0244] Obtain public input information from the electricity market; public input information includes: weather forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center;

[0245] With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on public input information;

[0246] The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market. The preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system.

[0247] Based on the price differences at various points in time during historical periods and common input information, the market clearing prices of each electricity market are corrected to obtain the electricity price forecast results. The price difference refers to the difference between the forecasted electricity price and the actual electricity price.

[0248] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0249] Based on public input information, determine the bidding results of each market participant in the electricity market;

[0250] With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

[0251] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0252] Electricity price forecasts are performed based on public input information to obtain initial electricity price forecast results;

[0253] Based on market participant information and initial electricity price forecasts from the public input information, the bidding results of each market participant in the electricity market are determined.

[0254] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0255] Based on relevant information about market participants, initial electricity price forecasts, and pre-set pricing strategies, a pricing model for each market participant in the electricity market is constructed. The pre-set pricing strategies include any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on forecasted prices.

[0256] Solve the pricing model for each market participant to obtain their pricing results.

[0257] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0258] Based on the electricity price difference at each time point and common input information, the predicted price error is determined;

[0259] The electricity market price forecast is determined based on the market clearing price and the error in the forecast price.

[0260] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0261] The common input information is fed into the electricity price prediction model for prediction, and the initial electricity price prediction result is obtained.

[0262] Based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction results, an error distribution function is constructed.

[0263] Solve for the error distribution function to obtain the predicted price error.

[0264] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0265] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0266] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting electricity prices, characterized in that, The method includes: Obtain public input information from the electricity market; the public input information includes: meteorological forecast information, energy price information, and day-ahead boundary information and market participant information released by the electricity trading center; With the goal of minimizing electricity purchase costs, a unit combination model for each market participant in the electricity market is constructed based on the aforementioned public input information; The unit combination model is solved based on preset constraints to obtain the market clearing price of the electricity market; the preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system. Based on the price differences at various points in the historical time period and the public input information, the market clearing price of the electricity market is corrected to obtain the electricity price prediction result of the electricity market. The price difference refers to the difference between the predicted electricity price and the actual electricity price.

2. The method according to claim 1, characterized in that, The method of constructing unit combination models for each market participant in the electricity market, with the objective of minimizing the cost of electricity purchased from the market, based on the public input information, includes: Based on the public input information, determine the bidding results of each market participant in the electricity market; With the goal of minimizing market electricity purchase costs, a unit combination model is constructed based on the bidding results of each market participant and the day-ahead boundary information.

3. The method according to claim 2, characterized in that, The step of determining the bidding results of each market participant in the electricity market based on the public input information includes: Based on the public input information, electricity price prediction is performed to obtain an initial electricity price prediction result; Based on the market member information in the public input information and the initial electricity price forecast results, the bidding results of each market member in the electricity market are determined.

4. The method according to claim 3, characterized in that, The step of determining the bidding results of each market participant in the electricity market based on the market participant information in the public input information and the initial electricity price forecast results includes: Based on the relevant information of the market participants, the initial electricity price forecast results, and the preset pricing strategy, a pricing model for each market participant in the electricity market is constructed; the preset pricing strategy includes any one of the following: cost-plus pricing strategy, marginal cost pricing strategy, and pricing strategy based on predicted price. Solve the pricing model for each of the market participants to obtain their pricing results.

5. The method according to claim 1, characterized in that, The electricity market clearing price is corrected based on the electricity price differences at various points in the historical time period and the common input information to obtain the electricity market price prediction result, including: Based on the electricity price difference at each of the aforementioned times and the aforementioned common input information, the predicted price error is determined; The electricity price forecast result for the electricity market is determined based on the market clearing price and the forecast price error.

6. The method according to claim 5, characterized in that, The determination of the predicted price error based on the electricity price difference at each of the stated times and the common input information includes: The common input information is input into the electricity price prediction model for prediction to obtain the initial electricity price prediction result; An error distribution function is constructed based on the voltage difference at each time point, the day-ahead boundary information in the common input information, and the initial electricity price prediction result; Solve for the error distribution function to obtain the predicted price error.

7. An electricity price forecasting device, characterized in that, The device includes: The acquisition module is used to acquire public input information of the electricity market; the public input information includes: meteorological forecast information, energy price information, and day-ahead boundary information and market member information released by the electricity trading center; The module is used to construct a unit combination model for each market member in the electricity market based on the public input information, with the goal of minimizing the cost of electricity purchased from the market. The solution module is used to solve the unit combination model based on preset constraints to obtain the market clearing price of the electricity market; the preset constraints include the physical constraints of generator unit operation, the power balance and capacity constraints of the power generation system, and the safety reserve constraints of the power generation system. The correction module is used to correct the market clearing price of the electricity market based on the price difference at various times within a historical period and the public input information, so as to obtain the electricity price prediction result of the electricity market. The price difference refers to the difference between the predicted electricity price and the actual electricity price.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images