New energy spot transaction price optimization experiment verification method considering carbon emission

Abstract

The invention provides a new energy spot transaction price optimization experiment verification method considering carbon emission, and relates to the technical field of carbon transaction optimization, and the method comprises the steps: obtaining new energy spot real-time transaction data and real-time carbon emission data in a carbon transaction market, and outputting initial data; performing data verification on the initial data, and performing preprocessing to obtain to-be-analyzed data; acquiring historical data matched with the initial data, performing association analysis on the historical data and the to-be-analyzed data in combination with a preset carbon transaction analysis model, and outputting a model analysis result; and performing optimization analysis on the model analysis result in combination with a preset optimization index, outputting an optimization analysis result, selecting a transaction optimization strategy matched with the optimization analysis result from a strategy database, and adjusting and optimizing the new energy spot real-time transaction data based on the transaction optimization strategy. According to the invention, by optimizing the transaction strategy, the efficiency and profitability of new energy spot transaction are gradually improved, and the development of the green energy market and the control of carbon emission are promoted.

Description

Technical Field

[0001] The present invention relates to the field of carbon trading optimization technology, and in particular to an experimental verification method for optimizing the spot trading price of new energy taking carbon emissions into account. Background Art

[0002] With the rapid growth of the global economy, greenhouse gas emissions have increased dramatically, posing an unprecedented threat to the climate and environment. To maintain sustainable economic and social development, economies around the world are gradually implementing plans to establish international carbon emissions trading rights to achieve green and low-carbon development across all industries worldwide.

[0003] However, current research on carbon market transaction price analysis and forecasting has problems such as insufficient carbon price information mining, low transaction efficiency, and low data forecasting accuracy.

[0004] Therefore, the present invention provides an experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account. Summary of the Invention

[0005] The present invention provides an experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account, which is used to gradually improve the efficiency and profitability of new energy spot transactions by optimizing trading strategies, thereby promoting the development of the green energy market and controlling carbon emissions.

[0006] The present invention provides an experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account, comprising:

[0007] Step 1: Obtain real-time spot trading data of new energy in the carbon trading market, and combine it with the acquired real-time carbon emission data to output initial data;

[0008] Step 2: Verify the initial data and perform preprocessing to obtain the data to be analyzed;

[0009] Step 3: Filtering the historical data that matches the initial data in the historical database, performing correlation analysis on the historical data and the data to be analyzed in combination with a preset carbon trading analysis model, and outputting the model analysis results;

[0010] Step 4: Optimize and analyze the model analysis results in combination with preset optimization indicators, output the optimization analysis results, select a trading optimization strategy that matches the optimization analysis results from the strategy database, and adjust and optimize the new energy spot real-time trading data based on the trading optimization strategy.

[0011] Preferably, before obtaining the real-time spot transaction data of new energy in the carbon trading market, the method includes:

[0012] Obtain the experimental purpose, experimental scope and parameter settings of the new energy spot transaction price optimization experiment, output the experimental plan, and determine the user's data analysis needs based on the experimental plan, and output the user's data analysis needs information.

[0013] Preferably, the step of obtaining real-time spot trading data of new energy in the carbon trading market includes:

[0014] Analyzing the demand information based on the user data, selecting a preset energy trading platform and a target service provider for providing transaction data;

[0015] Through the preset energy trading platform and the target service provider, the new energy spot types in the carbon trading market and the real-time price data, trading volume data and market supply and demand data under the corresponding types are obtained in real time, and the new energy spot real-time trading data is summarized and output.

[0016] Preferably, the combining of the acquired real-time carbon emission data to output the initial data includes:

[0017] Based on the preset energy trading platform and the target service provider, carbon emission inventory data and carbon emission quota data are obtained in real time, and real-time carbon emission data is output. The first data is summarized and output in combination with the new energy spot real-time trading data, and time alignment is performed in combination with the timestamp corresponding to the first data to output the initial data.

[0018] Preferably, the data verification of the initial data includes:

[0019] Performing data verification on the initial data using a preset data verification method, and outputting the initial data that meets the first threshold condition as second data;

[0020] The data verification process includes logic verification, consistency verification, valid range verification, format verification and external data source verification.

[0021] Preferably, the preprocessing to obtain the data to be analyzed includes:

[0022] Feature extraction is performed on the second data, and a first feature set is constructed. At the same time, an adaptive preprocessing method is selected from a method database based on the first feature set to preprocess the second data, and the second data that meets the second threshold condition is output as data to be analyzed.

[0023] Preferably, step 3 includes:

[0024] Classifying and dividing the first feature set to obtain a numerical feature set, a text feature set, and a time series feature set;

[0025] In combination with a preset feature-factor comparison table, a first factor set corresponding to the numerical feature set, a second factor set corresponding to the text feature set, and a third factor set corresponding to the time series feature set are obtained;

[0026] Based on experimental analysis requirements, weights are assigned to the factors in the first factor set, the second factor set, and the third factor set using a preset factor assignment algorithm, and at least two factor assignment schemes are output;

[0027] Based on the factor assignment scheme, historical carbon emission data with a similarity greater than a preset degree and historical new energy spot transaction data in the same time period corresponding to the historical carbon emission data are selected from the historical database, and the historical data are summarized and output;

[0028] Selecting a matching data analysis model from a model database based on the experimental analysis requirements, training and optimizing the data analysis model based on the historical data, and outputting the data analysis model that meets preset performance conditions as a preset carbon trading analysis model;

[0029] Combining the numerical feature set, the text feature set, and the time series feature set, and using the preset carbon trading analysis model to perform correlation analysis on the historical data and the data to be analyzed, analyzing the degree of correlation between the features, and outputting the correlation analysis results;

[0030] The association analysis results are parsed using a preset topology analysis algorithm to determine the first node corresponding to the carbon emission data, the second node corresponding to the new energy spot trading data, and the edges corresponding to the association relationship between the first nodes and the second nodes. Information is annotated for each of the first nodes, the second nodes, and the edges to construct a carbon emission-new energy spot trading topology structure diagram.

[0031] Preferably, step 4 includes:

[0032] Obtain carbon emission control policies and new energy promotion policies in regions involved in the carbon trading market in real time, and output real-time policy data;

[0033] At the same time, historical policy data corresponding to the real-time policy data is obtained from a historical database, and compared and analyzed with the real-time policy data to determine policy change items and change data under the corresponding items, and output the policy change data;

[0034] Based on the policy change data, combined with the model analysis results and user demand information obtained in the carbon trading market, select and determine the indicators to be optimized in the indicator database, and output the preset optimization indicators;

[0035] Obtain carbon emission change data and new energy spot trading change data in the carbon trading market during a first preset period, and output real-time change data. At the same time, use a preset prediction model to predict carbon emission data and new energy data in the carbon trading market during a second preset period, and output carbon emission-new energy prediction data;

[0036] Based on the preset optimization indicators, the model analysis results, real-time change data, and carbon emission-new energy forecast data are optimized and analyzed, and the optimization analysis results are output;

[0037] The algorithm used to analyze the impact relationship between carbon emission change data and new energy spot price change data is as follows:

[0038]

[0039] Among them, E(C,N j ,T) represents the impact value between the j-th new energy spot trading volume and carbon emission trading volume in the T period; p1(T) represents the average price of unit carbon emission trading in the T period; Em(t) represents the carbon emission at the t-th moment in the T period; t i1 Indicates the starting time node of the T period; t i2 Indicates the end time node of period T; p2 j (T) represents the unit transaction price of the jth new energy spot in the T period; Y j (t) represents the output of the jth new energy spot at time t during the T period; N j1 N represents the total demand for the jth new energy spot in the carbon trading market during the T period; sum1 N represents the total demand for all types of new energy spot in the carbon trading market during the T period; j2 N represents the total supply of the jth new energy spot in the T period; sum2 It represents the total supply of all types of new energy spot commodities in the carbon trading market during the T period;

[0040] Perform keyword recognition and extraction on the optimization analysis results to construct an optimization keyword set, and use preset index rules to filter out optimization strategies and optimization measures under the corresponding strategies that match the optimization keyword set in the strategy database;

[0041] Based on the optimization strategies and optimization measures, the carbon emission quota data and new energy spot price trading data in the carbon trading market are adjusted and optimized.

[0042] The present invention provides an experimental verification method for optimizing the spot transaction price of new energy that takes carbon emissions into account. The present invention analyzes real-time new energy spot transaction data and carbon emission data, combines historical data and preset models, and finds the best transaction optimization strategy, thereby adjusting and optimizing real-time transaction data to improve transaction efficiency and profitability. Based on the analysis of real-time data and historical data, the present invention can make more scientific and accurate decisions; through optimization analysis and selection of the best strategy, it can improve transaction efficiency and profitability; through model analysis and optimization, it can better manage market risks and reduce the impact of uncertainty; through optimization of trading strategies, it helps to promote the sustainable development of the new energy industry, promote green energy utilization and reduce carbon emissions. The present invention can better utilize data and models to optimize new energy spot transaction prices, promote the development of the green new energy market and control carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 It is a flow chart of an experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] like Figure 1 As shown, the experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account provided by the embodiment of the present invention includes:

[0047] Step 1: Obtain real-time spot trading data of new energy in the carbon trading market, and combine it with the acquired real-time carbon emission data to output initial data;

[0048] Step 2: Verify the initial data and perform preprocessing to obtain the data to be analyzed;

[0049] Step 3: Filter the historical data that matches the initial data in the historical database, perform correlation analysis on the historical data and the data to be analyzed in combination with the preset carbon trading analysis model, and output the model analysis results;

[0050] Step 4: Optimize the model analysis results based on the preset optimization indicators, output the optimization analysis results, select the trading optimization strategy that matches the optimization analysis results from the strategy database, and adjust and optimize the new energy spot real-time trading data based on the trading optimization strategy.

[0051] In this embodiment, the real-time spot transaction data of new energy: real-time market transaction data on new energy (such as wind energy, solar energy, etc.), including information such as the price, supply and demand of each type of new energy spot;

[0052] In this embodiment, real-time carbon emission data: real-time data on carbon emissions, used to measure carbon emissions, such as data on carbon emission quotas of various industries or enterprises;

[0053] In this embodiment, the initial data is a collection of new energy spot real-time transaction data and real-time carbon emission data;

[0054] In this embodiment, data verification: initial data is verified to ensure the accuracy and completeness of the data;

[0055] In this embodiment, preprocessing: processing the validated data, which may include operations such as data cleaning and missing value filling, to prepare the data for analysis;

[0056] In this embodiment, the data to be analyzed: after verification and preprocessing, prepares the data set for further analysis;

[0057] In this embodiment, historical database: a database that stores historical data, used for model training and comparison and analysis with real-time data;

[0058] In this embodiment, historical data: historical data that matches the initial data is filtered out from the historical database;

[0059] In this embodiment, a carbon trading analysis model is preset: a pre-set model is used to analyze the relationship between new energy spot trading data and carbon emission data;

[0060] In this embodiment, correlation analysis: historical data and data to be analyzed are compared and analyzed with a preset carbon trading analysis model to understand the correlation between them;

[0061] In this embodiment, model analysis results: conclusions and results obtained from the correlation analysis, which may include market trends, key factors, forecast results, etc.;

[0062] In this embodiment, the preset optimization indicator is an indicator used to evaluate the model analysis results, which is usually used to determine the best trading optimization strategy, such as profit maximization, carbon emission minimization, risk control, etc.

[0063] In this embodiment, optimization analysis: optimizing the model analysis results to find the best transaction optimization strategy;

[0064] In this embodiment, optimization analysis results: conclusions and results obtained after optimization processing;

[0065] In this embodiment, the strategy database: a database storing various transaction optimization strategies;

[0066] In this embodiment, the transaction optimization strategy refers to a specific strategy selected based on the optimization analysis results for adjusting and optimizing the real-time spot transaction data of new energy, including pricing strategy, supply and demand adjustment, risk management, etc.

[0067] The implementation principle and beneficial effects of this embodiment: The present invention analyzes real-time new energy spot trading data and carbon emission data, combines historical data and preset models, and finds the best trading optimization strategy, thereby adjusting and optimizing real-time trading data to improve trading efficiency and profitability. The present invention can make more scientific and accurate decisions based on the analysis of real-time data and historical data; improve trading efficiency and profitability through optimization analysis and selection of the best strategy; better manage market risks and reduce the impact of uncertainty through model analysis and optimization; and help promote the sustainable development of the new energy industry, promote green energy utilization and reduce carbon emissions by optimizing trading strategies. The present invention can make better use of data and models, optimize new energy spot trading prices, and promote the development of the green new energy market and the control of carbon emissions.

[0068] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention includes, before obtaining real-time spot transaction data of new energy products in a carbon trading market:

[0069] Obtain the experimental purpose, experimental scope and parameter settings of the new energy spot trading price optimization experiment, output the experimental plan, and determine the user's data analysis needs based on the experimental plan, and output the user's data analysis needs information.

[0070] In this embodiment, the experimental purpose: the goal or purpose of conducting the new energy spot transaction price optimization experiment is usually to improve transaction efficiency, reduce costs, reduce carbon emissions, etc.;

[0071] In this embodiment, experimental scope refers to the scope or field covered by the experiment, which may include a specific new energy market, carbon trading market, time range, etc.

[0072] In this embodiment, parameter setting refers to variables or parameters set in the experiment, which are used to control experimental conditions and perform data analysis. For example, the price fluctuation of new energy is set to be within ±5%, or the price of new energy is set to increase by 0.5% for every 1% increase in carbon emission price.

[0073] In this embodiment, experimental plan: a plan or scheme for how to design and execute a new energy spot trading price optimization experiment, including data collection methods, analysis methods, etc.

[0074] In this embodiment, data analysis requirements: the specific information or requirements required by the user when analyzing experimental data, which may include data type, analysis purpose, result display format, etc.;

[0075] In this embodiment, user data analysis requirement information: specific information of user data analysis requirements determined according to the experimental plan, used to guide data analysis and result interpretation.

[0076] The implementation principles and beneficial effects of this embodiment are as follows: Based on experimental design and user data analysis requirements, the present invention utilizes real-time data and model analysis to optimize new energy spot trading prices, thereby achieving the goals of improving trading efficiency and reducing carbon emissions. This invention can help users make more accurate decisions by meeting their data analysis needs; it can provide a data analysis result presentation format that meets user expectations based on user demand information; and it can develop more effective trading optimization strategies based on experimental results and user needs, thereby improving market competitiveness and profitability.

[0077] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention obtains real-time spot transaction data of new energy products in the carbon trading market, including:

[0078] Based on user data analysis demand information, select the preset energy trading platform and target service provider for providing transaction data;

[0079] Through the preset energy trading platform and target service providers, the new energy spot types in the carbon trading market and the real-time price data, trading volume data and market supply and demand data of the corresponding types are obtained in real time, and the real-time trading data of new energy spot is summarized and output.

[0080] In this embodiment, a preset energy trading platform is a trading platform that is predetermined to provide new energy spot trading data, typically an online platform or system for real-time trading and data acquisition;

[0081] In this embodiment, the target service provider refers to the selected service provider, which is responsible for providing new energy spot trading data to users and providing customized services based on user data analysis and demand information;

[0082] In this embodiment, new energy spot types include different types of new energy products that can be traded on the energy trading market, such as solar energy, wind energy, biomass energy, etc.

[0083] In this embodiment, price data: real-time price data of a specific new energy spot product, reflecting the price fluctuations of the energy product in the market, for example, the real-time price per unit of solar energy product;

[0084] In this embodiment, transaction volume data: real-time transaction volume data of a specific new energy spot product type, indicating the number of transactions within a certain period of time, used to analyze the degree of market activity;

[0085] In this embodiment, market supply and demand data: market supply and demand data of a specific new energy spot type, used to evaluate the supply and demand relationship and price trend of the market.

[0086] The implementation principles and beneficial effects of this embodiment are as follows: By presetting energy trading platforms and target service providers, the present invention obtains real-time new energy spot trading data in the carbon trading market, meets user data analysis requirements, and provides customized trading data services. Based on user demand information, the present invention provides new energy spot trading data that meets user requirements; by presetting energy trading platforms and target service providers, it achieves real-time acquisition and aggregation of new energy spot real-time trading data; and provides users with a wealth of price, trading volume, and market supply and demand data to support data analysis and decision-making.

[0087] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention combines the acquired real-time carbon emission data and outputs initial data, including:

[0088] Based on the preset energy trading platform and target service provider, carbon emission inventory data and carbon emission quota data are obtained in real time, and real-time carbon emission data is output. In addition, the first data is summarized and output in combination with the real-time transaction data of new energy spot, and time alignment is performed in combination with the timestamp corresponding to the first data to output the initial data.

[0089] In this embodiment, carbon emission inventory data refers to carbon emission data recorded in real time or listed in an inventory, which is usually used to track and manage carbon emissions, for example, a company's carbon emission data recorded every hour;

[0090] In this embodiment, carbon emission quota data refers to the carbon emission quota or limit data allocated to a specific entity, which is used to control carbon emissions. For example, a company's carbon emission quota for this quarter is 1,000 tons.

[0091] In this embodiment, the first data: an initial data set that integrates real-time spot trading data of new energy and carbon emission data, including data such as a company's new energy transaction price, carbon emissions, and quotas;

[0092] In this embodiment, timestamp: a time mark of a data record, used to ensure the temporal order and consistency of the data;

[0093] In this embodiment, time alignment: timestamps from different data sources are matched and aligned to facilitate effective data analysis and comparison.

[0094] The implementation principles and beneficial effects of this embodiment are as follows: The present invention integrates real-time new energy spot trading data and carbon emissions data to form an initial data set. By integrating new energy trading data and carbon emissions data, the present invention enables comprehensive analysis to understand the relationship and impact between the two. Time alignment ensures that data from different data sources are consistent at the same point in time, facilitating accurate data analysis and comparison. Based on this integrated initial data set, more effective trading strategies can be developed to optimize new energy spot trading prices and manage carbon emissions, thereby improving market competitiveness and environmental benefits.

[0095] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention verifies initial data, including:

[0096] Performing data verification on the initial data using a preset data verification method, and outputting the initial data that meets the first threshold condition as second data;

[0097] The data validation process includes logic validation, consistency validation, valid range validation, format validation, and external data source validation.

[0098] In this embodiment, the preset data verification method: pre-set verification steps and rules for verifying the initial data;

[0099] In this embodiment, the first threshold condition: a threshold condition for determining whether the verification criterion is met;

[0100] In this embodiment, the second data: a data set that satisfies the first threshold condition after verification;

[0101] In this embodiment, logic verification: ensures that the relationship and logic between data are correct, for example, ensures that the logical relationship between data fields is as expected;

[0102] In this embodiment, consistency verification: ensures that data is consistent across different data sources or time points to avoid data contradictions or inconsistencies;

[0103] In this embodiment, valid range verification: ensures that the data value is within a reasonable range to avoid abnormal or unreasonable data;

[0104] In this embodiment, format verification: ensures that the format of the data complies with the specified standards, such as date format, number format, etc.;

[0105] In this embodiment, external data source verification: ensures the consistency of data with an external data source or a reference data source to verify the accuracy and reliability of the data.

[0106] The implementation principles and beneficial effects of this embodiment are as follows: The present invention verifies initial data using a preset data verification method to ensure data quality and accuracy. Through data verification, the present invention ensures data logic, consistency, and accuracy, thereby improving data quality. It can detect and eliminate errors and anomalies in the data early, reducing potential problems in subsequent analysis and decision-making. Verified data is more reliable and can help develop more accurate trading strategies and decisions. It can also avoid additional time and cost investment due to data quality issues, thereby improving work efficiency.

[0107] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention performs preprocessing to obtain data to be analyzed, including:

[0108] Feature extraction is performed on the second data, and a first feature set is constructed. At the same time, an adaptive preprocessing method is selected from a method database based on the first feature set to preprocess the second data, and the second data that meets the second threshold condition is output as data to be analyzed.

[0109] In this embodiment, the first feature set: a feature set extracted from the second data;

[0110] In this embodiment, the method database: a database containing various preprocessing methods, used to select an adapted preprocessing method according to the feature set;

[0111] In this embodiment, preprocessing methods refer to various methods and techniques used to clean, transform, and process data, such as missing value filling, data standardization, feature encoding, etc.

[0112] In this embodiment, the second threshold condition is a set data processing condition. When the data meets the condition, it is output as data to be analyzed.

[0113] The implementation principle and beneficial effects of this embodiment: The present invention can perform feature extraction on the second data and select an adaptive preprocessing method based on the first feature set to perform data preprocessing to obtain the data to be analyzed. The present invention can improve the analyzability and accuracy of the data. Through feature extraction and preprocessing methods, it can better mine the potential information in the data, reduce data noise and redundancy, and thus provide a more reliable foundation for subsequent analysis and optimization. In this way, the present invention can more effectively discover the correlation and regularity between data, and provide support for the formulation of more accurate new energy spot trading price optimization strategies.

[0114] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention, in step 3, includes:

[0115] Classify the first feature set to obtain a numerical feature set, a text feature set, and a time series feature set;

[0116] Combined with the preset feature-factor comparison table, a first factor set corresponding to the numerical feature set, a second factor set corresponding to the text feature set, and a third factor set corresponding to the time series feature set are obtained;

[0117] Based on the experimental analysis requirements, and using a preset factor assignment algorithm, weights are assigned to the factors in the first factor set, the second factor set, and the third factor set, and at least two factor assignment schemes are output;

[0118] Based on the factor assignment scheme, historical carbon emission data with a similarity greater than a preset degree and historical new energy spot transaction data in the same time period corresponding to the historical carbon emission data are selected from the historical database, and the historical data are summarized and output;

[0119] Based on the experimental analysis requirements, a matching data analysis model is selected from the model database. At the same time, the data analysis model is trained and optimized based on historical data, and the data analysis model that meets the preset performance conditions is output as the preset carbon trading analysis model;

[0120] Combine numerical feature sets, text feature sets, and time series feature sets, and use the preset carbon trading analysis model to perform correlation analysis on historical data and the data to be analyzed, analyze the degree of correlation between each feature, and output the correlation analysis results;

[0121] The association analysis results are parsed using a preset topological analysis algorithm to determine the first node corresponding to the carbon emission data, the second node corresponding to the new energy spot trading data, and the edges corresponding to the association relationship between each first node and second node. Information is annotated for each first node, second node, and edge to construct a carbon emission-new energy spot trading topological structure diagram.

[0122] In this embodiment, the numerical feature set: numerical data features, such as transaction volume, price, etc.;

[0123] In this embodiment, the text feature set includes: text data features, such as transaction description, location, etc.;

[0124] In this embodiment, the time series feature set includes: time-related data features, such as transaction time, date, etc.;

[0125] In this embodiment, the preset feature-factor comparison table includes a comparison table of corresponding relationships between various data features and factors;

[0126] In this embodiment, the first factor set: a factor set corresponding to the numerical feature set;

[0127] In this embodiment, the second factor set: a factor set corresponding to the text feature set;

[0128] In this embodiment, the third factor set: a factor set corresponding to the time series feature set;

[0129] In this embodiment, experimental analysis requirements: that is, specific requirements and goals that need to be considered in the transaction price optimization experiment;

[0130] In this embodiment, the preset factor assignment algorithm: a pre-set algorithm for assigning weights to different factors to reflect the importance of different factors in the analysis;

[0131] In this embodiment, weight assignment is the process of assigning weights to each factor according to a preset factor assignment algorithm, so as to quantify the degree of influence of each factor on the analysis result;

[0132] In this embodiment, factor assignment scheme: a specific scheme for assigning weights to each factor, which may include different weight combinations to explore different analysis results;

[0133] In this embodiment, the preset degree refers to a preset standard or threshold for filtering historical data;

[0134] In this embodiment, historical carbon emission data: carbon emission data recorded in the past, used to analyze carbon emission trends and influencing factors;

[0135] In this embodiment, the historical new energy spot transaction data: the new energy spot transaction data recorded in the past, including information such as transaction volume and price;

[0136] In this embodiment, data analysis model: a mathematical model or algorithm used to analyze historical data and predict future trends;

[0137] In this embodiment, the preset performance conditions are: pre-set performance indicators or conditions that the data analysis model should meet, such as accuracy, generalization ability, etc.;

[0138] In this embodiment, the preset topology analysis algorithm is a pre-set algorithm for analyzing association relationships, which is usually used to construct a network structure or graph;

[0139] In this embodiment, the first node: a node corresponding to the carbon emission data in the topological structure diagram, representing a feature or attribute of the carbon emission data;

[0140] In this embodiment, the second node: a node corresponding to the new energy spot trading data in the topology diagram, representing a feature or attribute of the new energy spot trading data;

[0141] In this embodiment, edge: a line connecting two nodes, indicating the association relationship or influence between the nodes;

[0142] In this embodiment, information annotation: marking or describing nodes and edges to better understand their meaning or relevance;

[0143] In this embodiment, the carbon emission-new energy spot transaction topology diagram is a graphical representation showing the correlation between carbon emission data and new energy spot transaction data.

[0144] The implementation principle and beneficial effects of this embodiment: The present invention divides the feature set into numerical, text and time series feature sets, combines the factor assignment algorithm and historical data analysis, and constructs a carbon emission-new energy spot transaction topology structure diagram. First, based on the experimental requirements and the factor assignment algorithm, each factor is weighted, and then the data analysis model is trained through historical data, and finally correlation analysis and topology analysis are performed to construct a topology structure diagram. The present invention reveals the correlation between carbon emissions and new energy spot transactions by quantifying the influence of factors, combining historical data and data analysis models. The present invention can improve the accuracy and efficiency of trading decisions, provide more data support for market participants, and promote the healthy development of the new energy market and carbon emission control.

[0145] The experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account provided in an embodiment of the present invention, in step 4, includes:

[0146] Obtain carbon emission control policies and new energy promotion policies in regions involved in the carbon trading market in real time, and output real-time policy data;

[0147] At the same time, historical policy data corresponding to the real-time policy data is obtained from the historical database, and compared with the real-time policy data to determine the policy change items and the change data under the corresponding items, and output the policy change data;

[0148] Based on policy change data, combined with model analysis results and user demand information obtained in the carbon trading market, the indicators to be optimized are selected and determined in the indicator database, and the preset optimization indicators are output;

[0149] Obtain carbon emission change data and new energy spot trading change data in the carbon trading market during a first preset period, and output real-time change data. At the same time, use a preset prediction model to predict carbon emission data and new energy data in the carbon trading market during a second preset period, and output carbon emission-new energy prediction data;

[0150] Based on preset optimization indicators, optimize and analyze model analysis results, real-time change data, and carbon emission-new energy forecast data, and output optimization analysis results;

[0151] The algorithm used to analyze the impact relationship between carbon emission change data and new energy spot price change data is as follows:

[0152]

[0153] Among them, E(C,N j ,T) represents the impact value between the j-th new energy spot trading volume and carbon emission trading volume in the T period; p1(T) represents the average price of unit carbon emission trading in the T period; Em(t) represents the carbon emission at the t-th moment in the T period; t i1 Indicates the starting time node of the T period; t i2 Indicates the end time node of period T; p2 j (T) represents the unit transaction price of the jth new energy spot in the T period; Y j (t) represents the output of the jth new energy spot at time t during the T period; N j1 N represents the total demand for the jth new energy spot in the carbon trading market during the T period; sum1 N represents the total demand for all types of new energy spot in the carbon trading market during the T period; j2 N represents the total supply of the jth new energy spot in the T period; sum2 It represents the total supply of all types of new energy spot commodities in the carbon trading market during the T period;

[0154] Perform keyword recognition and extraction on the optimization analysis results to construct an optimization keyword set, and use the preset index rules to filter the strategy database to obtain the optimization strategy that matches the optimization keyword set and the optimization measures under the corresponding strategy;

[0155] Based on optimization strategies and measures, the carbon emission quota data and new energy spot price trading data in the carbon trading market are adjusted and optimized.

[0156] In this embodiment, carbon emission control policy: formulating and implementing government policies or regulations to control carbon emissions, aiming to reduce carbon emissions;

[0157] In this embodiment, new energy promotion policy refers to government policies that promote and support the development and application of new energy, including subsidies, tax reductions, technical support, etc.

[0158] In this embodiment, real-time policy data: data on carbon emission control and new energy promotion policies obtained in real time, reflecting the current policy status;

[0159] In this embodiment, historical policy data: data on carbon emission control and new energy promotion policies recorded in the past, used for comparing and analyzing policy changes;

[0160] In this embodiment, the changed items refer to the specific items or contents that have changed in the policy change, such as the subsidy amount, emission standards, etc.;

[0161] In this embodiment, policy change data: data recording policy changes, including information such as change items and change ranges;

[0162] In this embodiment, user demand information: the needs and opinions of participants in the carbon trading market are used to guide the formulation of optimization strategies;

[0163] In this embodiment, the indicator database: a database that stores and manages indicator information to be optimized;

[0164] In this embodiment, the first preset period is a designated initial period used to obtain carbon emission change data and new energy spot transaction change data in the carbon trading market;

[0165] In this embodiment, the carbon emission change data: records the changes in carbon emissions during the first preset period, for example, including specific carbon emission data at each time node;

[0166] In this embodiment, the new energy spot transaction change data: records the changes in the price or volume of new energy spot transactions within the first preset period to reflect changes in new energy market transactions;

[0167] In this embodiment, the real-time change data is a summary of the carbon emission change data and the new energy spot transaction change data within the first preset period;

[0168] In this embodiment, the preset prediction model: a model for predicting carbon emission data and new energy data within the second preset period, which can be predicted based on historical data and trends;

[0169] In this embodiment, the second preset period: a designated forecast period, used to forecast carbon emissions and new energy data, to provide a forecast basis for optimization analysis;

[0170] In this embodiment, carbon emission-new energy forecast data: carbon emission and new energy data predicted within the second preset time period, used as input data for optimization analysis;

[0171] In this embodiment, keyword identification and extraction: identifying and extracting keywords or terms related to the optimization analysis for use in constructing an optimization keyword set for matching in a policy database;

[0172] In this embodiment, the optimization keyword set: a set of keywords obtained by keyword recognition and extraction, used to screen matching optimization strategies and measures in the strategy database;

[0173] In this embodiment, preset indexing rules: pre-set rules or algorithms for matching corresponding optimization strategies and specific optimization measures according to the optimization keyword set in the strategy database;

[0174] In this embodiment, optimization strategy refers to a specific strategy or method proposed based on the optimization analysis results, which is used to adjust the carbon emission quota data and new energy spot price trading data in the carbon trading market. For example, the optimization strategy may be "increase the supply of new energy to meet the growing market demand." The purpose of this strategy is to adjust the supply of new energy according to the increase in market demand to ensure market supply and demand balance, while promoting the development of renewable energy.

[0175] In this embodiment, optimization measures: the operations or measures actually performed, adjust and optimize the carbon emission quota data and new energy spot price transaction data according to the optimization strategy. For the above-mentioned optimization strategy of "increasing the supply of new energy to meet the growing market demand", possible optimization measures are "increasing the production capacity of new energy power plants (such as wind farms, photovoltaic power plants, biomass power plants, etc.) to increase the supply of new energy". By increasing the production capacity of new energy power plants, the supply of new energy can be increased to meet market demand, and the spot price of new energy may be reduced.

[0176] The implementation principle and beneficial effects of this embodiment: The present invention adjusts and optimizes carbon emissions and new energy spot transactions by acquiring policy data in real time, analyzing policy changes and user needs, and combining prediction models and optimization algorithms. First, real-time policy data is acquired and compared with historical data to determine policy change items and output policy change data. Then, based on the optimization indicators and prediction data, optimization analysis is performed and optimization results are output. An optimization keyword set is constructed through keyword recognition and extraction, and matching optimization strategies and measures are screened to adjust and optimize carbon emissions and new energy prices. The present invention combines real-time policy data, user needs and prediction models to provide a systematic method to analyze and optimize the relationship between carbon emissions and new energy spot prices, providing better decision-making support for market participants, and through optimization algorithms and keyword recognition, proposes targeted optimization strategies and measures to adjust carbon emissions and new energy transaction prices, improve market efficiency and the interests of participants, and can more flexibly respond to policy changes, meet market needs, and promote the coordination of new energy development and carbon emission control.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An experimental verification method for optimizing the spot transaction price of new energy products taking carbon emissions into account, characterized in that: include: Step 1: Obtain real-time spot trading data of new energy in the carbon trading market, and combine it with the acquired real-time carbon emission data to output initial data; Step 2: Verify the initial data and perform preprocessing to obtain the data to be analyzed; Step 3: Filtering the historical data that matches the initial data in the historical database, performing correlation analysis on the historical data and the data to be analyzed in combination with a preset carbon trading analysis model, and outputting the model analysis results; Step 4: Optimize and analyze the model analysis results in combination with preset optimization indicators, output the optimization analysis results, select a trading optimization strategy that matches the optimization analysis results from the strategy database, and adjust and optimize the new energy spot real-time trading data based on the trading optimization strategy.

2. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 1 is characterized in that: Before obtaining the real-time spot transaction data of new energy in the carbon trading market, the following steps are included: Obtain the experimental purpose, experimental scope and parameter settings of the new energy spot transaction price optimization experiment, output the experimental plan, and determine the user's data analysis needs based on the experimental plan, and output the user's data analysis needs information.

3. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 2 is characterized in that: The acquisition of real-time spot trading data of new energy in the carbon trading market includes: Analyzing the demand information based on the user data, selecting a preset energy trading platform and a target service provider for providing transaction data; Through the preset energy trading platform and the target service provider, the new energy spot types in the carbon trading market and the real-time price data, trading volume data and market supply and demand data under the corresponding types are obtained in real time, and the new energy spot real-time trading data is summarized and output.

4. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 3 is characterized in that: The real-time carbon emission data obtained is combined to output initial data, including: Based on the preset energy trading platform and the target service provider, carbon emission inventory data and carbon emission quota data are obtained in real time, and real-time carbon emission data is output. The first data is summarized and output in combination with the new energy spot real-time trading data, and time alignment is performed in combination with the timestamp corresponding to the first data to output the initial data.

5. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 1 is characterized in that: The performing data verification on the initial data includes: Performing data verification on the initial data using a preset data verification method, and outputting the initial data that meets the first threshold condition as second data; The data verification process includes logic verification, consistency verification, valid range verification, format verification and external data source verification.

6. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 5 is characterized in that: The preprocessing to obtain the data to be analyzed includes: Feature extraction is performed on the second data, and a first feature set is constructed. At the same time, an adaptive preprocessing method is selected from a method database based on the first feature set to preprocess the second data, and the second data that meets the second threshold condition is output as data to be analyzed.

7. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 6 is characterized in that: Step 3 includes: Classifying and dividing the first feature set to obtain a numerical feature set, a text feature set, and a time series feature set; In combination with a preset feature-factor comparison table, a first factor set corresponding to the numerical feature set, a second factor set corresponding to the text feature set, and a third factor set corresponding to the time series feature set are obtained; Based on experimental analysis requirements, weights are assigned to the factors in the first factor set, the second factor set, and the third factor set using a preset factor assignment algorithm, and at least two factor assignment schemes are output; Based on the factor assignment scheme, historical carbon emission data with a similarity greater than a preset degree and historical new energy spot transaction data in the same time period corresponding to the historical carbon emission data are selected from the historical database, and the historical data are summarized and output; Selecting a matching data analysis model from a model database based on the experimental analysis requirements, training and optimizing the data analysis model based on the historical data, and outputting the data analysis model that meets preset performance conditions as a preset carbon trading analysis model; Combining the numerical feature set, the text feature set, and the time series feature set, and using the preset carbon trading analysis model to perform correlation analysis on the historical data and the data to be analyzed, analyzing the degree of correlation between the features, and outputting the correlation analysis results; The association analysis results are parsed using a preset topology analysis algorithm to determine the first node corresponding to the carbon emission data, the second node corresponding to the new energy spot trading data, and the edges corresponding to the association relationship between the first nodes and the second nodes. Information is annotated for each of the first nodes, the second nodes, and the edges to construct a carbon emission-new energy spot trading topology structure diagram.

8. The experimental verification method for optimizing the spot transaction price of new energy taking carbon emissions into account according to claim 1 is characterized in that: Step 4 includes: Obtain carbon emission control policies and new energy promotion policies in regions involved in the carbon trading market in real time, and output real-time policy data; At the same time, historical policy data corresponding to the real-time policy data is obtained from a historical database, and compared and analyzed with the real-time policy data to determine policy change items and change data under the corresponding items, and output the policy change data; Based on the policy change data, combined with the model analysis results and user demand information obtained in the carbon trading market, select and determine the indicators to be optimized in the indicator database, and output the preset optimization indicators; Obtain carbon emission change data and new energy spot trading change data in the carbon trading market during a first preset period, and output real-time change data. At the same time, use a preset prediction model to predict carbon emission data and new energy data in the carbon trading market during a second preset period, and output carbon emission-new energy prediction data; Based on the preset optimization indicators, the model analysis results, real-time change data, and carbon emission-new energy forecast data are optimized and analyzed, and the optimization analysis results are output; The algorithm used to analyze the impact relationship between carbon emission change data and new energy spot price change data is as follows: Among them, E(C,N j ,T) represents the impact value between the j-th new energy spot trading volume and carbon emission trading volume in the T period; p1(T) represents the average price of unit carbon emission trading in the T period; Em(t) represents the carbon emission at the t-th moment in the T period; t i1 Indicates the starting time node of the T period; t i2 Indicates the end time node of period T; p2 j (T) represents the unit transaction price of the jth new energy spot in the T period; Y j (t) represents the output of the jth new energy spot at time t during the T period; N j1 N represents the total demand for the jth new energy spot in the carbon trading market during the T period; sum1 N represents the total demand for all types of new energy spot in the carbon trading market during the T period; j2 N represents the total supply of the jth new energy spot in the T period; sum2 It represents the total supply of all types of new energy spot commodities in the carbon trading market during the T period; Perform keyword recognition and extraction on the optimization analysis results to construct an optimization keyword set, and use preset index rules to filter out optimization strategies and optimization measures under the corresponding strategies that match the optimization keyword set in the strategy database; Based on the optimization strategies and optimization measures, the carbon emission quota data and new energy spot price trading data in the carbon trading market are adjusted and optimized.

Images