Multi-region electric power spot market node electricity price collaborative analysis method

Abstract

The invention discloses a multi-region electric power spot market node electricity price collaborative analysis method, and relates to the technical field of electric power markets, and the method comprises the steps: obtaining the historical data of each electric power market region, the historical data comprises node electricity price and supply and demand data, and carrying out the preprocessing of the historical data; constructing a direct-current power flow model, calculating to obtain transmission network state information between the nodes according to the direct-current power flow model, and describing power flow distribution of the power system; constructing an electricity price prediction model based on a machine learning algorithm according to the supply and demand data and the transmission network state information, and obtaining a node electricity price prediction value; and optimizing power dispatching among different regions according to the electricity price prediction model and the node electricity price, and dynamically adjusting the electricity price prediction model. According to the multi-region electric power spot market node electricity price collaborative analysis method provided by the invention, the problem of low cross-region electric power dispatching and resource allocation efficiency is solved, collaborative optimization of the node electricity price in the multi-region electric power spot market is realized, and the market operation efficiency and economy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power market, and more specifically, to a node electricity price collaborative analysis method in a multi-regional power spot market. Background Art

[0002] With the gradual opening of the power market and the diversification of power transactions, the fluctuation of power prices between multiple power market regions has become a key factor affecting the efficiency and economy of the power system. Node electricity price is a calculation method used to determine the power price at different locations in the power spot market. The power price is not only related to the supply and demand relationship of power, but also closely related to factors such as transmission restrictions and transmission losses of the power grid. The change of node electricity price reflects the balance of power supply and demand in different regions. Multi-regional power spot market refers to a market model for power transactions in multiple power market regions. There may be differences in power prices between different regions because the power supply and demand situation, transmission capacity, etc. in each region are different. Through the power market mechanism, the power prices in these regions will eventually affect the trading and dispatching of power. Collaborative analysis refers to finding the correlation and cooperation mechanism between power prices in different regions by analyzing the fluctuations and mutual influence of power prices in different power market regions. This method helps to evaluate the reasons for changes in power prices in different regions and predict the power price transmission effect between different regions, especially in the case of transmission constraints or resource scheduling, how to coordinate power transactions in different regions to optimize the efficiency of the overall power market.

[0003] Deficiencies of existing technologies: The electricity price in each power market area is not only affected by the local power supply and demand situation, but also closely related to the electricity price and power transmission constraints in neighboring areas. Existing power market scheduling methods are usually limited to a single area or ignore the transmission effect of electricity price changes between different regions, resulting in low efficiency in cross-regional power scheduling and resource allocation. Therefore, the present invention provides a collaborative analysis method for node electricity prices in a multi-regional power spot market, which realizes the collaborative optimization of node electricity prices in a multi-regional power spot market and improves market operation efficiency and economy.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a collaborative analysis method for node electricity prices in a multi-regional electricity spot market. By collaboratively analyzing electricity prices in different power market areas, cross-regional electricity transactions and resource scheduling are optimized to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets includes the following steps: Acquire historical data of each power market area, the historical data including node electricity prices, supply and demand data, and pre-process the historical data; Construct a DC power flow model, calculate the transmission network status information between nodes based on the DC power flow model, and describe the power flow distribution of the power system; According to the supply and demand data and transmission network status information, a power price prediction model is built based on the machine learning algorithm to obtain the node power price prediction value; Optimize power dispatch between different regions based on the electricity price prediction model and node electricity prices, and dynamically adjust the electricity price prediction model.

[0007] In a preferred embodiment, the step of obtaining the node electricity price is as follows: Obtain real-time and historical node local market prices through the data interface of the power trading platform; Real-time monitoring and recording of the operating status and transmission capacity of transmission lines, from which the real-time transmission limits between nodes are obtained; Collect historical operation data of the power system, including node electricity prices, grid operation status, and load changes. Through data analysis and statistical methods, establish a relationship model between network constraints and node electricity prices, and determine the factors affecting node electricity prices through network constraints. According to the topological structure file of the power system, the location and area of ​​each node are obtained, and the number of nodes in the power market area is obtained; The node electricity price is calculated by combining the local market price of the node, the real-time transmission restrictions between nodes, the factors affecting the node electricity price due to network constraints, and the number of nodes in the power market area.

[0008] In a preferred embodiment, the supply and demand data includes a node supply and demand balance factor, which is specifically obtained as follows: Obtain historical load data and historical power generation data of each node; Obtain the power consumption of power transmission between nodes, and add the historical load data and the power consumption of power transmission between nodes to obtain the total power demand; Subtract the historical power generation data from the total power demand to obtain the node supply and demand balance factor.

[0009] In a preferred embodiment, the process of preprocessing the historical data is as follows: Delete missing or invalid records, check whether there are extreme values ​​or logical errors in node electricity prices, and repair obviously unreasonable values; Use interpolation to fill in missing supply and demand data and node electricity prices. For missing data with regularity, use the median to fill in. Use statistical methods to detect and remove outliers, and smooth time series data such as electricity prices and loads to reduce data volatility; The data were transformed into a standard normal distribution and normalized.

[0010] In a preferred embodiment, the transmission network status information between the nodes is obtained as follows: Input the line parameters into the line admittance matrix, calculate the line admittance based on the line impedance, and extract the real part of the admittance to obtain the conductance; The voltage of the node is expressed in complex form, including amplitude and phase angle. The phase angle is obtained by obtaining the angle generated by the voltage relative to the reference node; A DC power flow model is constructed based on conductance and phase angle to obtain the transmission network status information between nodes.

[0011] In a preferred embodiment, the steps of optimizing the power dispatch between different regions according to the power price prediction model and the node power price and dynamically adjusting the power price prediction model are as follows: Compare the node electricity price prediction value calculated according to the electricity price prediction model with the actual node electricity price; If the absolute error between the predicted node electricity price and the actual node electricity price is greater than the preset error threshold, it is necessary to dynamically adjust the electricity price prediction model by changing the weight coefficient in the electricity price prediction model; if the absolute error between the predicted node electricity price and the actual node electricity price is less than the preset error threshold, there is no need to adjust the electricity price prediction model temporarily and continuous monitoring should be carried out.

[0012] Technical effects and advantages of the collaborative analysis method of node electricity prices in multi-regional electricity spot markets of the present invention: 1. The present invention can comprehensively consider the electricity market factors of multiple regions, optimize the formation mechanism of node electricity prices, and improve the accuracy of prices in reflecting the supply and demand relationship of electricity, thereby helping the market to better discover the true market value of electricity. Multi-regional electricity markets usually face the problem of unbalanced electricity exchange between different regions. Through collaborative analysis of node electricity prices, it is possible to optimize inter-regional electricity transactions, improve the rationality of cross-regional power dispatch, reduce power transmission losses, and improve overall market efficiency. Due to the large volatility of the supply and demand relationship of electricity, market electricity prices will be affected by short-term fluctuations, especially under the influence of factors such as extreme climate. This analysis method can coordinate the fluctuations in electricity prices among multiple regions, effectively reduce excessive fluctuations in a single region, reduce overreaction of the market, and ensure the smooth operation of the market.

[0013] 2. The present invention can coordinate the changes in the power supply and demand sides through the collaborative analysis method in the multi-regional power market, optimize the dispatch and utilization of clean energy, and help the market achieve the goal of low-carbon development. Through accurate collaborative analysis of electricity prices, the transparency of the power spot market can be improved, ensuring that all participants participate in transactions according to reasonable market rules, reducing the possibility of price manipulation, and ensuring the fairness of the market. The collaborative analysis of node electricity prices not only focuses on the supply side, but also helps the demand side to respond more effectively. Market participants can adjust their electricity consumption behavior based on accurate price signals, further promoting the improvement of market mechanisms and demand management. Through collaborative analysis of multi-regional power markets, it is possible to better respond to sudden changes in power demand or supply interruptions, improve the operational stability of the power grid, and ensure the safe and reliable operation of the power system. By collaboratively analyzing node electricity prices in power markets in multiple regions, it is possible to not only improve the efficiency, stability and fairness of the power market, but also optimize resource allocation, reduce energy waste, promote the development of green energy, and further improve the overall operation level of the power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a structural schematic diagram of the collaborative analysis method of node electricity prices in multi-regional electricity spot markets of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1, Figure 1 The present invention provides a method for collaborative analysis of node electricity prices in a multi-regional electricity spot market.

[0017] S10, obtaining historical data of each power market area, the historical data including node electricity prices and supply and demand data, and preprocessing the historical data; The node electricity price is the market price at each node (i.e. each generator or load point) in the electricity market at a specific moment.

[0018] The node electricity price reflects the supply and demand status of the power system, network constraints and transmission losses. The steps to obtain the node electricity price are as follows: The power market usually has a dedicated power trading platform, and real-time and historical node local market prices can be obtained through data interfaces with these platforms; The dispatching automation system and energy management system (EMS) of the power system will monitor and record the operating status and transmission capacity of the transmission lines in real time, from which the real-time transmission restrictions between nodes can be obtained; Collect historical operation data of the power system, including node electricity prices, grid operation status, load changes, etc., and establish a relationship model between network constraints and node electricity prices through data analysis and statistical methods to determine the influencing factors; The topology file of the power system will clearly state the location and region of each node, which can be obtained from the power grid operation management department and dispatching center of the power company; Combining the local market price of the node, the real-time transmission restrictions between nodes, the factors affecting the node electricity price due to network constraints, and the number of nodes in the power market area, the formula for calculating the node electricity price is as follows: ; In the formula, is the electricity price at node i, is the local market price at node i, is the transmission limit from node i to node j, is the impact factor of network constraints on node electricity prices, and n is the number of nodes in the power market area.

[0019] The supply and demand data include the supply and demand balance factor, which can be obtained in the following way: Obtain historical load data for each node from the grid company or market operator, usually in hours; Obtain historical power generation data for each node from power plants or grid operators, usually in hours; Obtain the power consumption of power transmission between nodes, add the historical load data to the power consumption of power transmission between nodes to get the total power demand, and subtract the historical power generation data from the total power demand to get the node supply and demand balance factor; The calculation formula for the node supply and demand balance factor is as follows: ; In the formula, is the node supply and demand balance factor, is the historical power generation data, is the historical load data, It is the amount of electricity consumed by power transmission between nodes; Preprocessing historical data is a key step to ensure the accuracy and reliability of subsequent analysis results. The purpose of preprocessing is to clean data, fill missing values, remove outliers, standardize data, etc.

[0020] Remove invalid data: Delete missing or invalid records, especially those with missing timestamps, node information, or unreasonable electricity price data.

[0021] Repair incorrect data: For example, check whether there are extreme values ​​or logical errors in node electricity prices, and repair obviously unreasonable values ​​(such as negative electricity prices or abnormally high electricity prices).

[0022] Fill missing values: Use interpolation methods (such as linear interpolation, time series interpolation) or model prediction (such as regression model) to fill in missing supply and demand data, node electricity prices, etc.

[0023] Mean or median filling: For some missing data with regularity, the mean or median can also be used to fill.

[0024] Linear interpolation: For missing time series data, linear interpolation can be used to fill in the missing data.

[0025] Remove outliers: Use statistical methods such as box plots or standard deviation to detect and remove outliers.

[0026] Smoothing data: Smoothing time series data such as electricity prices and loads (for example, using sliding average or exponential smoothing methods) to reduce data volatility.

[0027] Standardization: Transform the data into a standard normal distribution (mean 0 and standard deviation 1).

[0028] Normalization: Map the data to the interval [0, 1].

[0029] S20, constructing a DC power flow model, and calculating the transmission network status information between nodes according to the DC power flow model to describe the power flow distribution of the power system; The DC power flow model is a simplified power system power flow model, which is usually used for steady-state analysis of large-scale power systems. Compared with the AC power flow model, the DC power flow model ignores the influence of voltage amplitude changes and reactive power in the power system, and mainly focuses on the transmission and distribution of active power.

[0030] Input the line parameters into the line admittance matrix, calculate the line admittance based on the line impedance, and extract the real part of the admittance to obtain the conductance; The voltage of a node is usually expressed in complex form, including magnitude and phase angle; the angle generated by the voltage relative to a reference node (usually a reference ground or a specific node) is obtained to obtain the phase angle; A DC power flow model is constructed based on the conductance and phase angle to obtain the transmission network status information between nodes. The transmission network status information includes the power flow between nodes. The specific calculation formula is as follows: ; is the power flow from node i to node j at time t, is the conductance of the transmission line from node i to node j, is the phase angle of node i at time t, is the phase angle of node j at time t.

[0031] S30, constructing an electricity price prediction model based on a machine learning algorithm according to the supply and demand data and the transmission network status information to obtain a node electricity price prediction value; According to the supply and demand data and transmission network status information, an electricity price prediction model is constructed based on the machine learning algorithm, and the specific calculation formula for the node electricity price prediction value is as follows: ; In the formula, is the node electricity price forecast value, is the base cost of node i, is the node supply and demand balance factor, is the power flow between nodes, is the node supply and demand balance weight coefficient, is the power flow weight coefficient between nodes.

[0032] Building an electricity price prediction model based on machine learning algorithms and using supply and demand data and transmission network status information to obtain node electricity price predictions has the following main benefits: 1. Improve the accuracy of electricity price forecasts Machine learning algorithms can handle complex nonlinear relationships, extract the patterns of electricity price changes from multi-dimensional information such as supply and demand data, weather conditions, electricity consumption trends and grid load, and provide more accurate predictions.

[0033] By training with a large amount of historical data, the model can identify the key factors affecting electricity prices and reduce errors in human forecasting.

[0034] 2. Real-time dynamic adjustment Machine learning models can be updated in real time, and as new data is input, the model can automatically adjust the prediction results. This means that electricity price forecasts do not rely solely on static rules or prior experience, but can respond in real time to the ever-changing market environment and electricity demand.

[0035] Dynamically learn about factors such as fluctuations in electricity demand and weather changes to adjust electricity price forecasts in real time, helping decision makers respond quickly to market changes.

[0036] 3. Optimize electricity market transactions Through accurate electricity price forecasts, all parties in the electricity market (such as power generation companies, power trading platforms, consumers, etc.) can make better decisions. For example, power producers can choose the appropriate amount of power generation based on electricity price forecasts, and consumers can choose to use electricity during periods of low electricity prices.

[0037] For electricity trading platforms, it can better dispatch electricity and allocate electricity resources to avoid waste of resources or mismatch between supply and demand.

[0038] 4. Improve grid operation efficiency Electricity price forecasts can help grid operators allocate power resources more efficiently, predict changes in electricity prices in different regions or nodes, and adjust the output power of power plants.

[0039] Based on the prediction of node electricity prices, the load of the power grid can be reasonably allocated, thereby reducing the risk of overload, lowering the probability of downtime and failure, and ensuring the stability and security of the power grid.

[0040] 5. Promote the integration of renewable energy The electricity price forecast model can help managers evaluate the timing of access to renewable energy (such as wind and solar energy). Due to the volatility of renewable energy, accurate electricity price forecasts can help balance the use of clean energy and traditional energy generation, thereby increasing the access rate and utilization efficiency of renewable energy.

[0041] If it is predicted that electricity prices will rise, the grid can encourage users to use clean energy generation equipment or energy storage during periods of low electricity prices.

[0042] 6. Support policy and decision-making Governments and regulators can formulate more scientific electricity policies, such as price regulation, subsidies, and carbon emission limits, based on accurate electricity price forecast information.

[0043] The forecasting model can also provide an important basis for long-term investment and development planning in the power industry, helping all parties to conduct cost assessment and benefit analysis.

[0044] 7. Improve user experience Accurate electricity price forecasts can help consumers understand when it is more cost-effective to use electricity. This is especially true for users of smart homes or power management systems, which can enable intelligent scheduling and automatically increase power consumption or charge devices when electricity prices are low, thereby reducing electricity bills.

[0045] Power companies can optimize electricity price strategies based on forecast results, provide users with differentiated pricing, time-of-day pricing and other services, and improve user satisfaction.

[0046] S40, optimizing the power dispatch between different regions according to the power price prediction model and the node power price, and dynamically adjusting the power price prediction model.

[0047] The node electricity price forecast value calculated according to the electricity price forecast model is compared with the actual node electricity price. If the absolute error between the node electricity price forecast value and the actual node electricity price is greater than the preset error threshold, it is necessary to dynamically adjust the electricity price forecast model by changing the weight coefficient in the electricity price forecast model. If the absolute error between the node electricity price forecast value and the actual node electricity price is less than the preset error threshold, there is no need to adjust the electricity price forecast model temporarily, and continuous monitoring is carried out.

[0048] Dynamically adjusting the electricity price forecast model has many benefits for optimizing power dispatch, especially in multi-regional power systems, which can significantly improve dispatch efficiency, reduce costs, and promote sustainable development. The following are the main benefits of dynamically adjusting the electricity price forecast model: 1. Improve the accuracy of power dispatching The dynamic adjustment of electricity price forecasting models can update forecast results in a timely manner according to real-time electricity prices and demand changes. This enables power dispatching decisions to be optimized based on the latest market prices and load demand, thereby reducing power waste and avoiding overproduction or underproduction.

[0049] Volatility of electricity demand: Electricity demand is affected by factors such as weather, time period, and season. Dynamic adjustments can accurately reflect these changes and improve the accuracy of forecasts of short-term fluctuations.

[0050] Regional differences: Electricity markets in different regions may have different demands and electricity price levels. The dynamic adjustment model can accurately dispatch according to regional demand differences to avoid waste in power transmission and distribution.

[0051] 2. Optimize the operational efficiency of the electricity market The electricity price forecasting model helps the power dispatching system balance the supply and demand relationship between different time periods and different regions, making the operation of the power grid more efficient. By dynamically adjusting the model, you can: Improve cross-regional dispatching capabilities: According to the changes in electricity prices in each region, optimize the cross-regional power dispatching path, reduce power transmission losses, avoid excess high-cost electricity in low-price areas, and achieve cost optimization for the entire network.

[0052] Reduce system load fluctuations: Dynamically adjusted electricity price forecasts can flexibly respond to changes in demand, smooth system loads, and avoid system instability caused by electricity price fluctuations.

[0053] 3. Reduce electricity production and transmission costs The electricity price forecasting model can help the power dispatching center to determine the electricity price trend in advance, plan power generation and transmission rationally, and reduce production and transportation costs. For example: Adjust the power generation plan according to the electricity price: When the electricity price in a certain period or area is high, you can choose to increase the power generation in that area, otherwise reduce the power generation.

[0054] Reducing load during peak hours: Through electricity price forecasting, power dispatch can optimize power distribution during peak hours and reduce the increased costs caused by over-reliance on a certain power source.

[0055] 4. Increase the utilization of renewable energy As the share of renewable energy (such as wind and solar) increases, the supply of electricity becomes increasingly unstable. Dynamically adjusting the electricity price forecast model can help balance the uncertainty of renewable energy and the needs of the electricity market, thereby: Reduce waste: By predicting short-term electricity price trends, the dispatch system can determine when to use renewable energy and avoid wasting electricity during unneeded periods.

[0056] Encourage the use of clean energy: With the support of electricity price prediction models, the power grid can dispatch clean energy more intelligently, reduce dependence on fossil fuels, and promote the consumption of green energy.

[0057] 5. Promote flexibility and competitiveness in the electricity market Dynamically adjusting the electricity price forecast model can improve the flexibility of the electricity market, allowing power companies, users and other market participants to adjust strategies in real time based on market electricity price information and promote competition: Responding to electricity price changes: Dynamic electricity price models allow consumers and electricity suppliers to flexibly adjust electricity consumption and production plans based on electricity price forecasts, improving the decision-making efficiency of market participants.

[0058] Promoting competition and innovation: Fluctuations in electricity prices can stimulate innovation among market participants in demand response, energy storage technology and renewable energy, and promote the healthy development of the entire power industry.

[0059] 6. Enhance grid stability Dynamic adjustment of the electricity price forecasting model can improve the stability of the power grid. By optimizing power dispatch and reducing the imbalance of power transmission and distribution, it helps to relieve the pressure on the power grid and prevent power outages caused by power grid overload.

[0060] Predict emergencies in advance: Dynamic electricity price forecasts can provide timely warnings of sudden load changes, power generation interruptions, etc. in the power grid, and make corresponding adjustments to avoid collapse or failure of the power system.

[0061] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0062] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0063] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0064] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0066] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A collaborative analysis method for node electricity prices in multi-regional electricity spot markets, characterized in that: The following steps are involved: Acquire historical data of each power market area, the historical data including node electricity prices, supply and demand data, and pre-process the historical data; Construct a DC power flow model, calculate the transmission network status information between nodes based on the DC power flow model, and describe the power flow distribution of the power system; According to the supply and demand data and transmission network status information, a power price prediction model is built based on the machine learning algorithm to obtain the node power price prediction value; Optimize power dispatch between different regions based on the electricity price prediction model and node electricity prices, and dynamically adjust the electricity price prediction model.

2. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 1, characterized in that: The steps of obtaining the node electricity price are as follows: Obtain real-time and historical node local market prices through the data interface of the power trading platform; Real-time monitoring and recording of the operating status and transmission capacity of transmission lines, from which the real-time transmission limits between nodes are obtained; Collect historical operation data of the power system, including node electricity prices, grid operation status, and load changes. Through data analysis and statistical methods, establish a relationship model between network constraints and node electricity prices, and determine the factors affecting node electricity prices through network constraints. According to the topological structure file of the power system, the location and area of ​​each node are obtained, and the number of nodes in the power market area is obtained; The node electricity price is calculated by combining the local market price of the node, the real-time transmission restrictions between nodes, the factors affecting the node electricity price due to network constraints, and the number of nodes in the power market area.

3. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 2, characterized in that: The calculation formula of the node electricity price is as follows: ; In the formula, is the electricity price at node i, is the local market price at node i, is the transmission limit from node i to node j, is the impact factor of network constraints on node electricity prices, and n is the number of nodes in the power market area.

4. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 3 is characterized in that: The supply and demand data includes the node supply and demand balance factor, which is obtained in the following way: Obtain historical load data and historical power generation data of each node; Obtain the power consumption of power transmission between nodes, and add the historical load data and the power consumption of power transmission between nodes to obtain the total power demand; Subtract the historical power generation data from the total power demand to obtain the node supply and demand balance factor.

5. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 4, characterized in that: The calculation formula of the node supply and demand balance factor is as follows: ; In the formula, is the node supply and demand balance factor, is the historical power generation data, is the historical load data, It is the amount of electricity consumed by power transmission between nodes.

6. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 5, characterized in that: The process of preprocessing the historical data is as follows: Delete missing or invalid records, check whether there are extreme values ​​or logical errors in node electricity prices, and repair obviously unreasonable values; Use interpolation to fill in missing supply and demand data and node electricity prices. For missing data with regularity, use the median to fill in. Use statistical methods to detect and remove outliers, and smooth time series data such as electricity prices and loads to reduce data volatility; The data were transformed into a standard normal distribution and normalized.

7. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 6, characterized in that: The transmission network status information between the nodes is obtained in the following manner: Input the line parameters into the line admittance matrix, calculate the line admittance based on the line impedance, and extract the real part of the admittance to obtain the conductance; The voltage of the node is expressed in complex form, including amplitude and phase angle. The phase angle is obtained by obtaining the angle generated by the voltage relative to the reference node; A DC power flow model is constructed based on conductance and phase angle to obtain the transmission network status information between nodes.

8. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 7, characterized in that: The transmission network status information between the nodes includes the power flow between the nodes, and the specific calculation formula is as follows: ; is the power flow from node i to node j at time t, is the conductance of the transmission line from node i to node j, is the phase angle of node i at time t, is the phase angle of node j at time t, and n is the number of nodes in the electricity market area.

9. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 8, characterized in that: The specific calculation formula for the node electricity price prediction value is as follows: ; In the formula, is the node electricity price forecast value, is the base cost of node i, is the node supply and demand balance factor, is the power flow between nodes, is the node supply and demand balance weight coefficient, is the power flow weight coefficient between nodes.

10. The method for collaborative analysis of node electricity prices in multi-regional electricity spot markets according to claim 9, characterized in that: The steps of optimizing the power dispatch between different regions according to the power price prediction model and the node power price and dynamically adjusting the power price prediction model are as follows: Compare the node electricity price prediction value calculated according to the electricity price prediction model with the actual node electricity price; If the absolute error between the node electricity price prediction value and the actual node electricity price is greater than the preset error threshold, it is necessary to dynamically adjust the electricity price prediction model by changing the weight coefficient in the electricity price prediction model; If the absolute error between the node electricity price prediction value and the actual node electricity price is less than the preset error threshold, there is no need to adjust the electricity price prediction model temporarily and continuous monitoring is performed.

Images