Power market multi-source scene data integration and feature library construction method and related device

Abstract

The invention discloses a power market multi-source scene data integration and feature library construction method and a related device, and the method comprises the steps: integrating a power market multi-source scene database based on power market operation data sets under a plurality of different scenes; and forming a power market multi-source scene feature library through feature engineering and data desensitization based on the generated power market multi-source scene database. The workload of constructing a corresponding database for each power market operation scene is reduced, and unified integration of power market databases from multiple sources is realized; the data security risk is reduced through data desensitization; the data redundancy is reduced by using the feature engineering, and the correlation among the features is improved.

Description

Background Art

[0002] As the internal operating mechanism of the power market becomes increasingly complex and the requirements for external policy mechanisms continue to increase, the difficulty of power market construction and mechanism decision-making has greatly increased. The traditional method of relying on manual experience for analysis is unsustainable. Power market simulation and deduction technology provides effective technical support for the study of complex operating mechanisms of power markets that adapt to new power systems.

[0003] In order to make the power market simulation system adapt to power market operation data under different market scenarios and rules, establishing a multi-source scenario feature library of the power market based on multi-source heterogeneous market data is an important prerequisite for supporting the development of power market simulation in multiple time scales and across market scenarios.

[0004] The power market data comes from multiple different systems, platforms and devices, such as the production system of power generation enterprises, the dispatching system of power grids, the metering system of electricity users, etc.; the data also comes from multiple different scenarios, such as different regions, provinces and cities. These data sources have great differences in data structure, format, protocol, etc., resulting in a large amount of data conversion and adaptation work required for data integration. Secondly, the data quality of different data sources varies, and there are problems such as missing data, errors, and duplications. In the process of data integration, these data need to be cleaned and verified to ensure the quality of the integrated data. However, due to the large amount and complexity of data, data cleaning and verification work is often very time-consuming and it is difficult to fully guarantee the accuracy of the data. Third, the power market data has the characteristics of strong real-time performance, and needs to reflect the market supply and demand relationship, price changes and other information in real time. However, in practical applications, due to factors such as communication delays between data sources and system processing capacity limitations, it is often difficult to achieve real-time synchronization of data, affecting the effect and real-time performance of data integration.

[0005] For the construction of feature library, it is a complex process to extract valuable features from multi-source scenario data in the power market. The selection and extraction of features need to be based on in-depth market analysis and professional knowledge, and the availability and interpretability of data need to be considered. However, in practical applications, due to factors such as large data volume, high dimensionality, and complex relationships between features, feature extraction is often very difficult. Secondly, the feature library is an important basis for power market analysis and prediction, and needs to be continuously updated and maintained. However, with the continuous development and changes of the power market, new data sources and features continue to emerge, which brings great challenges to the maintenance and management of the feature library. At the same time, the features in the feature library may also have problems such as redundancy and obsolescence, and need to be cleaned and optimized regularly. In the process of constructing the feature library, a series of technical problems need to be solved, such as data fusion, data mining, machine learning, etc. These technical problems require professional technicians to conduct research and development, and at the same time, continuous technical updates and upgrades are required to adapt to the development needs of the power market. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method and related devices for integrating multi-source scenario data and building a feature library for an electricity market in response to the deficiencies in the above-mentioned prior art. A multi-source scenario database for an electricity market is constructed based on historical operation data of a multi-source scenario electricity market, and then the electricity market scenario data is desensitized through normalization and standardization methods. The construction of a feature library for multi-source scenario data for an electricity market is realized through feature engineering, so as to solve the technical problems of incompatibility of multi-source data in the electricity market, low data information density, and idle and wasted data assets.

[0007] The present invention adopts the following technical solutions:

[0008] A method for integrating multi-source scenario data and constructing a feature library for a power market comprises the following steps:

[0009] Based on the power market operation data sets under multiple different scenarios, the multi-source scenario database of the power market is integrated;

[0010] The generated multi-source scenario database of the electricity market is processed through feature engineering and data desensitization technology to construct a multi-source scenario feature library of the electricity market.

[0011] Preferably, the integrated power market multi-source scenario database is specifically:

[0012] Constructing the power market scenario database of the target scenario respectively, integrating the power market scenario databases of multiple target scenarios by interpolation method to form a power market multi-source scenario database;

[0013] Among them, for the same type of data in the power market scenario database of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario.

[0014] Preferably, the historical operation data sets of the power market under multiple different scenarios are specifically:

[0015] Based on the historical operation data of the electricity market in a single scenario, the non-electricity market source data of the corresponding scenario is superimposed to construct the electricity market operation dataset of the corresponding scenario.

[0016] Preferably, the historical operation data of the power market includes electricity price data, load data, new energy data, other non-marketized unit data and inter-provincial power data;

[0017] Data from non-electricity market sources include meteorological data, primary energy price data, and socio-economic data.

[0018] Preferably, the electricity price data includes the day-ahead market electricity price and the real-time market electricity price;

[0019] Load data includes day-ahead load forecast values ​​and real-time load measurement values;

[0020] New energy data include day-ahead wind turbine output forecast, real-time wind turbine output, day-ahead photovoltaic unit output forecast, and real-time photovoltaic unit output;

[0021] Other non-market generating unit data include non-market generating unit output;

[0022] Inter-provincial power data include external / transmitted power;

[0023] Meteorological data include temperature, wind speed and light intensity;

[0024] Primary energy price data include coal prices and natural gas prices;

[0025] Socio-economic data include gross national product and consumer price index.

[0026] Preferably, the generated power market multi-source scenario database is processed by feature engineering and data desensitization technology to form a power market multi-source scenario feature database specifically as follows:

[0027] For the electricity price data in the multi-source scenario database of the power market, fixed value normalization is used for desensitization processing;

[0028] For the load data in the multi-source scenario database of the power market and the wind speed in the meteorological data, Z-score standardization is used for desensitization processing;

[0029] For the new energy data, other non-market unit data, inter-provincial power data, meteorological data, primary energy price data and social economic data in the multi-source scenario database of the power market, extreme value normalization is used for desensitization processing;

[0030] The multi-source desensitized database of the power market is constructed based on the data processed by fixed value normalization, Z score standardization and extreme value normalization.

[0031] Feature engineering technology is used to extract high-dimensional data from the electricity market multi-source desensitized database as key electricity market features, and to construct an electricity market data feature library.

[0032] Preferably, when performing normalization or standardization, all parameters in the process are stored to ensure that the processed data can still be reversibly transformed into the data before the process;

[0033] For data that is segmented and normalized, the parameters used for normalization of each segment are stored separately.

[0034] Preferably, for load, new energy output, and socio-economic data, the data for each year are taken as a unit and regarded as a separate data set, and desensitized by means of segmented normalization.

[0035] Preferably, the method of extreme value normalization is:

[0036]

[0037] The method of normalizing the fixed value is:

[0038]

[0039] The method of Z-score standardization is:

[0040]

[0041] in, is the i-th data point in the processed data set, X is the set of this type of data, x i is the i-th data point in the data set, max(X) is the maximum value in the data set, min(X) is the minimum value in the data set, X UB is the upper bound of the specified data set, X LB is the lower bound of the specified data set, is the mean of the data set, and σ is the variance of the data set.

[0042] Preferably, key electricity market characteristics include:

[0043] Market price characteristics, including power market price characteristics and day-ahead real-time market price consistency characteristics; power market price characteristics reflect the level of electricity prices, and day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks;

[0044] Market space characteristics, including day-ahead market space characteristics and real-time market space characteristics, reflecting the total load demand of market entities bidding on the supply and generation side of the day-ahead market and the real-time market;

[0045] Power meteorological characteristics include temperature characteristics and wind and light characteristics. The temperature characteristics are divided into 5 levels according to the threshold classification method, and the classification variables are encoded by one-hot encoding;

[0046] The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors;

[0047] The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas that will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units.

[0048] Preferably, the electricity market price characteristics are specifically:

[0049]

[0050] The consistency feature of the day-ahead real-time market price = |day-ahead market electricity price - real-time market electricity price|.

[0051] Preferably, the market space characteristics are specifically:

[0052] Day-ahead market space characteristics

[0053] = load forecast value of the day before - wind turbine output forecast of the day before

[0054] - Day-ahead PV unit output forecast - Non-market unit output - Real-time market space characteristics of external / transmitted power

[0055] = Real-time load measurement value - Real-time wind turbine output - Real-time photovoltaic unit output

[0056] -Non-market unit output-external / transmitted power

[0057] Among them, for the power market of the receiving province / region, the imported / transmitted power takes the positive value of the external power; for the power market of the sending province / region, the imported / transmitted power takes the negative value of the external power.

[0058] Preferably, the power meteorological characteristics are specifically:

[0059]

[0060] Among them, T vh is the temperature threshold, T h is the upper temperature threshold, T l is the lower temperature threshold, T vl is the low temperature threshold;

[0061]

[0062] Preferably, the primary energy characteristics are specifically:

[0063] Primary energy characteristics

[0064]

[0065] In a second aspect, an embodiment of the present invention provides a system for integrating multi-source scenario data and building a feature library for a power market, including:

[0066] The collection module integrates the multi-source scenario database of the power market based on the power market operation data sets under multiple different scenarios;

[0067] The construction module processes the generated power market multi-source scenario database through feature engineering and data desensitization technology to construct a multi-source scenario feature library for the power market.

[0068] Preferably, the integrated power market multi-source scenario database is specifically:

[0069] Constructing the power market scenario database of the target scenario respectively, integrating the power market scenario databases of multiple target scenarios by interpolation method to form a power market multi-source scenario database;

[0070] Among them, for the same type of data in the power market scenario database of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario.

[0071] Preferably, the historical operation data sets of the power market under multiple different scenarios are specifically:

[0072] Based on the historical operation data of the power market in a single scenario, the non-power market source data of the corresponding scenario are superimposed to construct the power market operation data set of the corresponding scenario; the historical operation data of the power market includes electricity price data, load data, new energy data, other non-marketized unit data and inter-provincial power data; the non-power market source data includes meteorological data, primary energy price data and socio-economic data.

[0073] Preferably, electricity price data include day-ahead market electricity prices and real-time market electricity prices; load data include day-ahead load forecast values ​​and real-time load measurement values; new energy data include day-ahead wind turbine output forecast, real-time wind turbine output, day-ahead photovoltaic unit output forecast and real-time photovoltaic unit output; other non-market unit data include non-market unit output; inter-provincial power data include external / transmitted power; meteorological data include temperature, wind speed and light intensity; primary energy price data include coal prices and natural gas prices; social and economic data include gross national product and consumer price index.

[0074] Preferably, the generated power market multi-source scenario database is processed by feature engineering and data desensitization technology to construct a power market multi-source scenario feature library specifically as follows:

[0075] For the electricity price data in the multi-source scenario database of the power market, fixed value normalization is used for desensitization processing;

[0076] For the load data in the multi-source scenario database of the power market and the wind speed in the meteorological data, Z-score standardization is used for desensitization processing;

[0077] For the new energy data, other non-market unit data, inter-provincial power data, meteorological data, primary energy price data and social economic data in the multi-source scenario database of the power market, extreme value normalization is used for desensitization processing;

[0078] The multi-source desensitized database of the power market is constructed based on the data processed by fixed value normalization, Z score standardization and extreme value normalization.

[0079] Feature engineering technology is used to extract high-dimensional data from the electricity market multi-source desensitized database as key electricity market features, and to construct an electricity market data feature library.

[0080] Preferably, when performing normalization or standardization, all parameters in the process are stored to ensure that the processed data can still be reversibly transformed into the data before the process; for data that is segmented and normalized, the parameters used in each segment of normalization are stored separately;

[0081] For load, new energy output, and socio-economic data, the annual data are taken as units, and each year is regarded as a separate data set, which is desensitized by means of segmented normalization.

[0082] Preferably, applying feature engineering to extract key electricity market features from data includes:

[0083] Market price characteristics, including power market price characteristics and day-ahead real-time market price consistency characteristics; power market price characteristics reflect the level of electricity prices, and day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks;

[0084] Market space characteristics, including day-ahead market space characteristics and real-time market space characteristics, reflecting the total load demand of market entities bidding on the supply and generation side of the day-ahead market and the real-time market;

[0085] Power meteorological characteristics include temperature characteristics and wind and light characteristics. The temperature characteristics are divided into 5 levels according to the threshold classification method, and the classification variables are encoded by one-hot encoding;

[0086] The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors;

[0087] The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas that will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units.

[0088] In a third aspect, a computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for integrating multi-source scenario data and constructing a feature library in the electricity market when executing the computer program.

[0089] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for integrating multi-source scenario data in the electricity market and constructing a feature library.

[0090] Compared with the prior art, the present invention has at least the following beneficial effects:

[0091] A method for integrating multi-source scenario data and building a feature library for the power market can unify power market data from different sources and scenarios, improve the utilization rate of multi-source data, and reduce the idleness and waste of power market data assets; it can also improve data information density and provide a better data foundation for subsequent data application links such as power market analysis and artificial intelligence.

[0092] Furthermore, it can unify the time granularity of multi-scenario data, prevent errors in data structure and type when storing and using data, and improve the versatility of data.

[0093] Furthermore, the dataset combines electricity market data with non-electricity market data and incorporates the correlation between external data and electricity market data into the dataset, which expands the depth of the dataset and enhances the analytical value of electricity market data.

[0094] Furthermore, data desensitization can be used to eliminate potential security risks when sensitive data is used for data analysis; through feature engineering, electricity market data can be summarized into typical market characteristics to improve the information density of the data.

[0095] Furthermore, by storing data processing parameters, the reversibility of the data processing process is ensured, the ability to restore the original data based on the processed data is retained, and the reliability of the database is improved.

[0096] Furthermore, for data that grows year by year with social and economic development, the data are detrended through piecewise normalization to accurately extract the data periodicity and eliminate the interference of the natural growth of the data on the data characteristics.

[0097] Furthermore, by simultaneously adopting a variety of data normalization and standardization methods, different types of electricity market data can be normalized and standardized while retaining data characteristics to the maximum extent, thus avoiding changes in the original distribution of the data or making the data characteristics insignificant due to normalization or standardization.

[0098] Furthermore, through the feature engineering of electricity market data, the original data set with low information density is converted into a feature library with high information density, which effectively integrates data from different scenarios, is conducive to the subsequent discovery of the general regularity of electricity market data, reduces the amount of calculation for subsequent analysis, and further highlights the correlation between electricity market characteristics and key influencing factors.

[0099] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0100] In summary, the present invention integrates the power market data of different dimensions and formats in different scenarios into a unified database through the integration of multi-source scenario data of the power market, laying the foundation for the subsequent application of a unified model or algorithm for global and extensive analysis. At the same time, the present invention eliminates the significant differences in power market data caused by differences in dimensions and orders of magnitude through the construction of a power market feature library, forms the same power market data features for different scenarios, lays the foundation for the subsequent application of complex analysis methods, reduces data redundancy, effectively improves the information density of data, and supports the study of complex operation mechanisms of power markets that adapt to new power systems.

[0101] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Figure 1 A schematic diagram of a flow chart of an embodiment of the present invention;

[0103] Figure 2 A schematic diagram of a process for constructing a historical operation data set of the power market of the present invention;

[0104] Figure 3 It is a schematic diagram of the integration process of the multi-source scenario database of the power market of the present invention;

[0105] Figure 4 It is a schematic diagram of the normalization and standardization desensitization process of the power market data of the present invention;

[0106] Figure 5 It is a schematic diagram of the process of multi-source data feature engineering of the power market of the present invention;

[0107] Figure 6 A schematic diagram of a computer device provided by an embodiment of the present invention;

[0108] Figure 7 The present invention is a block diagram of an electronic device provided according to an embodiment. DETAILED DESCRIPTION

[0109] 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 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.

[0110] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0111] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0112] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0113] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0114] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0115] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0116] The present invention provides a method for integrating multi-source scenario data and constructing a feature library of an electricity market. Based on the historical operation data of the multi-source scenario electricity market, a multi-source scenario database of the electricity market is constructed, and then the electricity market scenario data is desensitized by normalization, standardization and other methods, and the construction of the multi-source scenario data feature library of the electricity market is realized through feature engineering; the workload of constructing a corresponding database for each electricity market operation scenario is reduced, and unified integration of electricity market databases from multiple sources is realized; data security risks are reduced through data desensitization; and feature engineering is used to reduce data redundancy and improve the correlation between features.

[0117] See also Figure 1 The present invention provides a method for integrating multi-source scenario data and constructing a feature library in a power market, comprising the following steps:

[0118] S1. Based on the power market operation data sets under multiple different scenarios, integrate the power market multi-source scenario database;

[0119] S101, construction of historical operation data set of power market;

[0120] See also Figure 2 , based on the historical operation data of the power market in a single scenario, the non-power market source data of the corresponding scenario is superimposed to construct the power market operation dataset of the scenario.

[0121] Through the provincial power market technical support system, typical provincial power market operation data are collected. The data includes the following categories:

[0122]

[0123]

[0124] On the basis of typical provincial power market data, the following data that are obviously related to power market operations are superimposed to form a complete power market historical operation data set. The classification and source of the data are shown in the following table:

[0125]

[0126] S102, Integration of multi-source scenario databases in the power market

[0127] See also Figure 3 For each provincial power market in different scenarios, based on the power market historical operation data set construction method in step S101, a power market scenario database is constructed respectively.

[0128] After obtaining the power market database of all target scenarios, multiple databases are integrated through interpolation to form a power market multi-source scenario database. Specifically, for the same type of data of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario and complete the integration of the multi-source database.

[0129] Specifically, the data of scene A with the finest data granularity is assumed to be at the 15-minute level, containing 4 data points per hour, and the data of scene B with a coarser data granularity than scene A is assumed to be at the hourly level, containing 1 data point per hour. The data of the two data sets are as follows:

[0130]

[0131]

[0132] Among them, A 1 ~A 5 The data for scene A, B 1 , B 2 This is the data for scene B.

[0133] The electricity market data that may potentially need to be processed include electricity prices, load forecasts and measurements, and new energy unit forecasts and actual output values.

[0134] S2. Based on the electricity market multi-source scenario database generated in step S1, a multi-source scenario feature library of the electricity market is constructed through feature engineering and data desensitization.

[0135] S201. Normalization and standardization of power market data

[0136] See also Figure 4 For data such as electricity prices, loads, and unit output, extreme value normalization and Z-score standardization are used to desensitize them. While hiding the true value through normalization, the differences in order of magnitude between data are eliminated, laying the foundation for the next step of feature engineering.

[0137] The method of extreme value normalization is:

[0138]

[0139] in, is the i-th data point in the processed data set, X is the set of this type of data, x i is the ith data point in the data set, max(X) is the maximum value in the data set, and min(X) is the minimum value in the data set.

[0140] The method of normalizing the fixed value is:

[0141]

[0142] in, is the i-th data point in the processed data set, X is the set of this type of data, x i is the kth data point in the data set, X UB is the upper bound of the specified data set, X LB Lower bound for the specified data set.

[0143] The method of Z-score standardization is:

[0144]

[0145] in, is the i-th data point in the processed data set, x i is the ith data point in the data set, is the mean of the data set, σ is the variance of the data set, and n is the number of data points.

[0146] Different normalization / standardization methods are used for different types of data to ensure the most effective desensitization effect:

[0147]

[0148]

[0149] For data that develop rapidly over time, such as load, new energy output, and social and economic data, the data for each year are treated as a separate data set and normalized in sections to eliminate the inhibitory effect of changes in the "big trend" of data over a long period of time on changes in the "small trend" of data over a short period of time.

[0150] When performing normalization or standardization, all parameters in the process are stored to ensure that the processed data can still be transformed back to the data before the processing. For data that is normalized in sections, the parameters used in each section of normalization are stored separately.

[0151] S202. Feature Engineering of Multi-source Data in Electricity Market

[0152] See also Figure 5Based on the normalized and standardized anonymized multi-source power market database, feature engineering is used to extract key power market features from the data, and a power market data feature library is constructed to provide a higher quality data foundation for applications such as power market data analysis, power market deep learning algorithms, and power market large models.

[0153] The key power market characteristics are high-dimensional data extracted from low-dimensional power market data through feature engineering. They are characterized by high information density. The purpose of performing feature engineering is to correlate market characteristics with market signals (mainly price signals, market stability, etc.) that market operators and market participants focus on. Compared with data that have not been processed as features, the correlation is significantly higher, which can provide an important basis for market analysis.

[0154] Therefore, using market characteristics for subsequent data analysis and artificial intelligence applications will be more conducive to improving algorithm accuracy and algorithm calculation efficiency. The basis for extracting key features is related to the characteristics of various specific features. The main basis is the important issues that market operators and market participants are concerned about. For example, market space characteristics determine the supply and demand of the market and are highly correlated with prices. Wind and solar characteristics can be used to analyze the overall new energy supply in the market. Primary energy characteristics are used to analyze the impact of primary energy prices on electricity prices. While improving information density, they can also play a role in data visualization without the need to examine multiple data at the same time.

[0155] Except for the socio-economic data (Gross National Product, Price Index, etc.), the feature engineering processing is not performed on the method of the present invention. The feature processing methods corresponding to other types of data are shown in the following table:

[0156]

[0157]

[0158] 1. Price characteristics of the electricity market

[0159] Market price characteristics include power market price characteristics and day-ahead real-time market price consistency characteristics. Power market price characteristics reflect the level of electricity prices, while day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks.

[0160]

[0161] The consistency feature of the day-ahead real-time market price = |day-ahead market electricity price - real-time market electricity price|

[0162] 2. Market space characteristics

[0163] The market space characteristics include the day-ahead market space characteristics and the real-time market space characteristics, which respectively reflect the total load demand of the market entities bidding on the day-ahead market and the real-time market for power generation. The larger the market space, the higher the demand on the load side in the market, and therefore it is positively correlated with the electricity price.

[0164] Day-ahead market space characteristics

[0165] = load forecast value of the day before - wind turbine output forecast of the day before

[0166] - Day-ahead PV unit output forecast - Non-market unit output - Real-time market space characteristics of external / transmitted power

[0167] = Real-time load measurement value - Real-time wind turbine output - Real-time photovoltaic unit output

[0168] -Non-market unit output-external / transmitted power

[0169] Among them, for the power market of the receiving province / region, the imported / transmitted power takes the positive value of the external power; for the power market of the sending province / region, the imported / transmitted power takes the negative value of the external power.

[0170] 3. Power meteorological characteristics

[0171] The power meteorological characteristics include temperature characteristics and wind and solar characteristics. The temperature characteristics reflect the meteorological factors that affect the power load and thus the electricity price, while the wind and solar characteristics reflect the meteorological factors that affect the power generation of wind power and photovoltaic units.

[0172] Since both high and low temperatures may cause an increase in power load and thus an increase in electricity prices, when performing feature engineering on the temperature, the temperature is divided into five levels: too high, relatively high, moderate, relatively low, and too low by threshold classification, and the categorical variable is encoded using a one-hot encoding method:

[0173]

[0174] Among them, T vh is the temperature threshold, T h is the upper temperature threshold, T l is the lower temperature threshold, T vl The temperature is too low threshold.

[0175] The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors:

[0176]

[0177] 4. Primary energy characteristics

[0178] The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas, which will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units:

[0179]

[0180] After completing feature processing according to the above feature engineering method, a multi-source data feature library of the electricity market is constructed.

[0181] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0182] In another embodiment of the present invention, a system for integrating multi-source scenario data and building a feature library for an electricity market is provided. The system can be used to implement the above-mentioned method for integrating multi-source scenario data and building a feature library for an electricity market. Specifically, the system for integrating multi-source scenario data and building a feature library for an electricity market includes modules, modules, modules, modules and modules.

[0183] Among them, the collection module integrates the multi-source scenario database of the power market based on the power market operation data sets under multiple different scenarios; The construction module processes the generated power market multi-source scenario database through feature engineering and data desensitization technology to construct a multi-source scenario feature library for the power market. In the collection module, the integrated power market multi-source scenario database is specifically: Constructing the power market scenario database of the target scenario respectively, integrating the power market scenario databases of multiple target scenarios by interpolation method to form a power market multi-source scenario database; Among them, for the same type of data in the power market scenario database of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario. The historical operation data sets of the power market under multiple different scenarios are as follows: Based on the historical operation data of the power market in a single scenario, the non-power market source data of the corresponding scenario are superimposed to construct the power market operation data set of the corresponding scenario; the historical operation data of the power market includes electricity price data, load data, new energy data, other non-marketized unit data and inter-provincial power data; the non-power market source data includes meteorological data, primary energy price data and socio-economic data. Electricity price data include the day-ahead market electricity price and the real-time market electricity price; load data include the day-ahead load forecast and the real-time load measurement; new energy data include the day-ahead wind turbine output forecast, the real-time wind turbine output, the day-ahead photovoltaic unit output forecast and the real-time photovoltaic unit output; other non-market unit data include the output of non-market units; inter-provincial power data include external / transmitted power; meteorological data include temperature, wind speed and light intensity; primary energy price data include coal price and natural gas price; social and economic data include gross national product and consumer price index. In the construction module, the generated power market multi-source scenario database is processed through feature engineering and data desensitization technology, and the power market multi-source scenario feature library is constructed as follows: For the electricity price data in the multi-source scenario database of the power market, fixed value normalization is used for desensitization processing; For the load data in the multi-source scenario database of the power market and the wind speed in the meteorological data, Z-score standardization is used for desensitization processing; For the new energy data, other non-market unit data, inter-provincial power data, meteorological data, primary energy price data and social economic data in the multi-source scenario database of the power market, extreme value normalization is used for desensitization processing; The multi-source desensitized database of the power market is constructed based on the data processed by fixed value normalization, Z score standardization and extreme value normalization. Feature engineering technology is used to extract high-dimensional data from the electricity market multi-source desensitized database as key electricity market features, and to construct an electricity market data feature library. When performing normalization or standardization, all parameters in the process are stored to ensure that the processed data can still be reversibly transformed into the data before processing; for data that is segmented and normalized, the parameters used in each segment of normalization are stored separately; For load, new energy output, and socio-economic data, the annual data are taken as units, and each year is regarded as a separate data set, which is desensitized by means of segmented normalization. Feature engineering was applied to extract key electricity market features from the data including: Market price characteristics, including power market price characteristics and day-ahead real-time market price consistency characteristics; power market price characteristics reflect the level of electricity prices, and day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks; Market space characteristics, including day-ahead market space characteristics and real-time market space characteristics, reflecting the total load demand of market entities bidding on the supply and generation side of the day-ahead market and the real-time market; Power meteorological characteristics include temperature characteristics and wind and light characteristics. The temperature characteristics are divided into 5 levels according to the threshold classification method, and the classification variables are encoded by one-hot encoding; The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors; The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas that will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units.

[0184] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the multi-source scenario data integration and feature library construction method of the power market, including:

[0185] Based on the power market operation data sets under multiple different scenarios, a multi-source scenario database of the power market is integrated; the generated multi-source scenario database of the power market is processed through feature engineering and data desensitization technology to construct a multi-source scenario feature library of the power market.

[0186] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device, and can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that more specific examples (non-exhaustive list) of the computer-readable storage medium here include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0187] Computer readable storage media also include data signals propagated in baseband or as part of a carrier wave, which carry readable program codes. Such propagated data signals can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0188] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0189] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for integrating multi-source scenario data and building a feature library in the power market in the above embodiment; the processor may load and execute the following steps:

[0190] Based on the power market operation data sets under multiple different scenarios, a multi-source scenario database of the power market is integrated; the generated multi-source scenario database of the power market is processed through feature engineering and data desensitization technology to construct a multi-source scenario feature library of the power market.

[0191] See also Figure 6 , the terminal device is a computer device, and the computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the method for calculating the composition of fluid in the reservoir transformation wellbore in the embodiment is realized. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the calculation system for the composition of fluid in the reservoir transformation wellbore in the embodiment are realized. To avoid repetition, it is not described one by one here.

[0192] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 6 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0193] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, central processing units, graphics processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, data processing logic based on quantum computing, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0194] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0195] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0196] Any reference to memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0197] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0198] See also Figure 7The terminal device 600 is an electronic device, and the electronic device is in the form of a general computing device. The components of the electronic device may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0199] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0200] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0201] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0202] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0203] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0204] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0205] Example

[0206] Taking the power market of Province A (the sending province) and the power market of Province B (the receiving province) as examples, the power market of Province A has accumulated three years of market data after three years of continuous operation; the power market of Province B has accumulated two years of market data after two years of continuous operation.

[0207] (1-1) Construction of the electricity market historical operation dataset

[0208] The following data of Province A are obtained from the power market technical support system of Province A: day-ahead market electricity price, real-time market electricity price, day-ahead load forecast value, real-time load measurement value, day-ahead wind turbine output forecast, real-time wind turbine output, day-ahead photovoltaic unit output forecast, real-time photovoltaic unit output, non-marketized unit output, and externally transmitted power.

[0209] The following data of Province B are obtained from the power market technical support system of Province B: day-ahead market electricity price, real-time market electricity price, day-ahead load forecast value, real-time load measurement value, day-ahead wind turbine output forecast, real-time wind turbine output, day-ahead photovoltaic unit output forecast, real-time photovoltaic unit output, non-marketized unit output, and external power.

[0210] The temperature, wind speed, and light intensity data of the power market in Province A during the three years of operation, and the temperature, wind speed, and light intensity data of the power market in Province B during the two years of operation were obtained from the meteorological data platform.

[0211] Obtain the coal price for the corresponding time period from the coal data platform, obtain the natural gas price for the corresponding time period from the natural gas data platform, and obtain the gross national product and price index for the corresponding time period from the economic information disclosure channel.

[0212] The market operation data, meteorological data, coal prices, natural gas prices, and economic data of Province A are combined to construct the historical operation data set of the power market in Province A. The market operation data, meteorological data, coal prices, natural gas prices, and economic data of Province B are combined to construct the historical operation data set of the power market in Province B.

[0213] (1-2) Construction of the electricity market historical operation dataset

[0214] The time granularity of each data in the historical operation data set of the power market in Province A is compared with that in the historical operation data set of the power market in Province B, and linear interpolation is performed on the data with different time granularity.

[0215] Assume that the wind turbine output data in the power market of Province A is one point every 15 minutes, and the wind turbine output data in the power market of Province B is one point every hour. The example is as follows:

[0216]

[0217]

[0218] The linear difference of wind turbine output data in the power market of Province B is as follows:

[0219] time 1:00 1:15 1:30 1:45 2:00 2:15 2:30 2:45 3:00 Province B 170 187.75 205.5 223.25 241 259 277 295 313

[0220] After linear interpolation processing of all data with different time granularity between the historical operation data sets of the electricity markets in Province A and Province B, the historical operation data sets of the electricity markets in Province A and Province B can be integrated into a unified electricity market multi-source scenario database based on the same storage format.

[0221] (2-1) Normalization and standardization of power market data

[0222] For various types of data in the multi-source scenario database of the electricity market, the normalization and standardization methods corresponding to the various types of data specified in (2-1) are used to process and desensitize the data.

[0223] For example, let's assume that the upper limit of the price of the day-ahead electricity market in Province A is 800 yuan / MWh and the lower limit is -200 yuan / MWh. Let's assume that the price of the day-ahead electricity market in Province A is 600 yuan / MWh at a certain moment. Then the price after fixed value normalization is:

[0224]

[0225] After completing the extreme value normalization, it is necessary to record: "The day-ahead market electricity price in Province A, upper limit 800, lower limit -200", so that the original data can be restored based on the processed data later.

[0226] Assume that in the two-year electricity market operation of Province B, the maximum value of the wind turbine output forecast in the first year is 1000, and the minimum value is 600. The maximum value of the wind turbine output forecast in the second year is 1200, and the minimum value is 700. Assuming that the wind turbine output forecast value of Province B at a certain moment in the first year is 800, the wind turbine output forecast value after extreme value normalization is:

[0227]

[0228] Assuming that the predicted output value of the wind turbine generator set at a certain time in the second year in Province B is 980, the predicted output value of the wind turbine generator set after extreme value normalization is:

[0229]

[0230] After completing the extreme value normalization, it is necessary to record: "The predicted output value of wind turbines in Province B in the first year, the maximum value is 1000, the minimum value is 600" and "The predicted output value of wind turbines in Province B in the second year, the maximum value is 1200, the minimum value is 700" so that the original data can be restored based on the processed data later.

[0231] Assume that in the two-year power market operation of Province B, the mean value of the day-ahead load forecast in the first year is 800, the variance is 100, and the mean value of the day-ahead load forecast in the second year is 900, the variance is 120. Assuming that the day-ahead load forecast value of Province B at a certain moment in the first year is 650, the day-ahead load forecast value after extreme value normalization is:

[0232]

[0233] Assuming that the day-ahead load forecast value of province B at a certain time in the second year is 980, the day-ahead load forecast value after extreme value normalization is:

[0234]

[0235] After completing the Z-score standardization, it is necessary to record: "The day-ahead load forecast value of Province B in the first year, with a mean of 800 and a variance of 100" and "The day-ahead load forecast value of Province B in the second year, with a mean of 900 and a variance of 120" so that the original data can be restored based on the processed data later.

[0236] (2-2) Feature Engineering of Multi-source Data in Electricity Market

[0237] After completing the normalization and standardized desensitization of the electricity market data set, the multi-source desensitized database of the electricity market is characterized based on the electricity market data feature engineering method proposed in this patent.

[0238] Assume that a data sample in the multi-source desensitized database of the power market is as shown in the following table:

[0239]

[0240]

[0241] According to the characterization method defined in the patent, the characteristic values ​​of each type of feature are calculated separately:

[0242] 1. Market price characteristics

[0243]

[0244] The consistency characteristic of the real-time market price on the day before = |0.81-0.79| = 0.02

[0245] 2. Market space characteristics

[0246] Day-ahead market space characteristics = 1.21-0.4-0.2-0.1-0.3 = 0.21

[0247] Real-time market space characteristics = 1.18-0.35-0.24-0.1-0.3 = 0.19

[0248] 3. Power meteorological characteristics

[0249] Assume that the higher temperature threshold T h =0.65, lower temperature threshold T l =0.35. Then the temperature characteristics are:

[0250] Temperature characteristics = moderate (0.35<0.4<0.65) → [0,0,1,0,0]

[0251] Assume that the wind power installed capacity corresponding to the data is 400GW and the photovoltaic installed capacity is 300GW. Then the wind and solar characteristics are:

[0252]

[0253] 4. Primary energy characteristics

[0254] Assume that the installed capacity of coal-fired units corresponding to the data is 600GW and the installed capacity of gas-fired units is 200GW. Then the primary energy characteristics are:

[0255]

[0256] Through the above embodiments, the data of the two provincial power market scenarios in Province A and Province B are unified and normalized, the data format is unified, and the original data of Provinces A and B are merged into an overall data set; based on the processed data set, the high-dimensional characteristics of the power market are extracted, and 15 types of data are converted into 5 categories, a total of 7 market characteristics, which enhances the readability of the data and converts the original data into power market characteristics that are suitable for advanced algorithms and models, providing a data basis for subsequent market analysis.

[0257] In summary, the present invention provides a method for integrating multi-source scenario data and constructing a feature library for a power market and related devices, which reduces the workload of constructing a corresponding database for each power market operation scenario, and realizes the unified integration of power market databases from multiple sources; reduces data security risks through data desensitization; and uses feature engineering to reduce data redundancy and improve the correlation between features.

[0258] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0259] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0260] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention 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 the present invention.

[0261] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0262] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0263] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0264] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0265] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0266] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0267] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0268] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for integrating multi-source scenario data and constructing a feature library in a power market, characterized in that: The following steps are involved: Based on the power market operation data sets under multiple different scenarios, the multi-source scenario database of the power market is integrated; The generated multi-source scenario database of the electricity market is processed through feature engineering and data desensitization technology to construct a multi-source scenario feature library of the electricity market.

2. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 1 is characterized in that: The integrated power market multi-source scenario database is specifically: Constructing the power market scenario database of the target scenario respectively, integrating the power market scenario databases of multiple target scenarios by interpolation method to form a power market multi-source scenario database; Among them, for the same type of data in the power market scenario database of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario.

3. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 2 is characterized in that: The historical operation data sets of the power market under multiple different scenarios are as follows: Based on the historical operation data of the electricity market in a single scenario, the non-electricity market source data of the corresponding scenario is superimposed to construct the electricity market operation dataset of the corresponding scenario.

4. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 3 is characterized in that: The historical operation data of the power market includes electricity price data, load data, new energy data, other non-marketized unit data and inter-provincial power data; Data from non-electricity market sources include meteorological data, primary energy price data, and socio-economic data.

5. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 4 is characterized in that: Electricity price data includes day-ahead market electricity prices and real-time market electricity prices; Load data includes day-ahead load forecast values ​​and real-time load measurement values; New energy data include day-ahead wind turbine output forecast, real-time wind turbine output, day-ahead photovoltaic unit output forecast, and real-time photovoltaic unit output; Other non-market generating unit data include non-market generating unit output; Inter-provincial power data include external / transmitted power; Meteorological data include temperature, wind speed and light intensity; Primary energy price data include coal prices and natural gas prices; Socio-economic data include gross national product and consumer price index.

6. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 1, characterized in that: The generated power market multi-source scenario database is processed through feature engineering and data desensitization technology to form the power market multi-source scenario feature database as follows: For the electricity price data in the multi-source scenario database of the power market, fixed value normalization is used for desensitization processing; For the load data in the multi-source scenario database of the power market and the wind speed in the meteorological data, Z-score standardization is used for desensitization processing; For the new energy data, other non-market unit data, inter-provincial power data, meteorological data, primary energy price data and social economic data in the multi-source scenario database of the power market, extreme value normalization is used for desensitization processing; A multi-source desensitized database of the power market is constructed based on the data processed by fixed value normalization, Z score standardization and extreme value normalization. Feature engineering technology is used to extract high-dimensional data from the electricity market multi-source desensitized database as key electricity market features, and to construct an electricity market data feature library.

7. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 6, characterized in that: When performing normalization or standardization, store the parameters during the process; For data that is segmented and normalized, the parameters used for normalization of each segment are stored separately.

8. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 6, characterized in that: For load, new energy output, and socio-economic data, the annual data are taken as units, and each year is regarded as a separate data set, which is desensitized by means of segmented normalization.

9. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 6, characterized in that: The method of extreme value normalization is: The method of normalizing the fixed value is: The method of Z-score standardization is: in, is the i-th data point in the processed data set, X is the set of this type of data, x i is the i-th data point in the data set, max(X) is the maximum value in the data set, min(X) is the minimum value in the data set, X UB is the upper bound of the specified data set, X LB is the lower bound of the specified data set, is the mean of the data set, and σ is the variance of the data set.

10. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 6, characterized in that: Key electricity market characteristics include: Market price characteristics, including power market price characteristics and day-ahead real-time market price consistency characteristics; power market price characteristics reflect the level of electricity prices, and day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks; Market space characteristics, including day-ahead market space characteristics and real-time market space characteristics, reflecting the total load demand of market entities bidding on the supply and generation side of the day-ahead market and the real-time market; Power meteorological characteristics include temperature characteristics and wind and light characteristics. The temperature characteristics are divided into 5 levels according to the threshold classification method, and the classification variables are encoded by one-hot encoding; The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors; The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas that will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units.

11. The method for integrating multi-source scenario data and constructing a feature library for a power market according to claim 10, characterized in that: The specific characteristics of electricity market prices are as follows: The consistency feature of the day-ahead real-time market price = day-ahead market electricity price - real-time market electricity price |.

12. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 10, characterized in that: The specific characteristics of the market space are: Day-ahead market space characteristics = load forecast value of the day before - wind turbine output forecast of the day before - Day-ahead PV unit output forecast - Non-market unit output - Real-time market space characteristics of external / transmitted power = Real-time load measurement value - Real-time wind turbine output - Real-time photovoltaic unit output -Non-market unit output-external / transmitted power Among them, for the power market of the receiving province / region, the imported / transmitted power takes the positive value of the external power; for the power market of the sending province / region, the imported / transmitted power takes the negative value of the external power.

13. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 10, characterized in that: The specific characteristics of power meteorology are: Among them, T vh is the temperature threshold, T h is the upper temperature threshold, T l is the lower temperature threshold, T vl is the low temperature threshold; 14. The method for integrating multi-source scenario data and constructing a feature library for the power market according to claim 10, characterized in that: The specific characteristics of primary energy are: Primary energy characteristics 15. A system for integrating multi-source scenario data and building a feature library for a power market, characterized in that: include: The collection module integrates the multi-source scenario database of the power market based on the power market operation data sets under multiple different scenarios; The construction module processes the generated power market multi-source scenario database through feature engineering and data desensitization technology to construct a multi-source scenario feature library for the power market.

16. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 15, characterized in that: The integrated power market multi-source scenario database is specifically: Constructing the power market scenario database of the target scenario respectively, integrating the power market scenario databases of multiple target scenarios by interpolation method to form a power market multi-source scenario database; Among them, for the same type of data in the power market scenario database of each target scenario with different time granularity, the scenario data with the finest time granularity is used as the benchmark, and the corresponding category data of other scenarios are linearly interpolated to unify the data granularity of each scenario.

17. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 16, characterized in that: The historical operation data sets of the power market under multiple different scenarios are as follows: Based on the historical operation data of the power market in a single scenario, the non-power market source data of the corresponding scenario are superimposed to construct the power market operation data set of the corresponding scenario; the historical operation data of the power market includes electricity price data, load data, new energy data, other non-marketized unit data and inter-provincial power data; the non-power market source data includes meteorological data, primary energy price data and socio-economic data.

18. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 17, characterized in that: Electricity price data include the day-ahead market electricity price and the real-time market electricity price; load data include the day-ahead load forecast and the real-time load measurement; new energy data include the day-ahead wind turbine output forecast, the real-time wind turbine output, the day-ahead photovoltaic unit output forecast and the real-time photovoltaic unit output; other non-market unit data include the output of non-market units; inter-provincial power data include external / transmitted power; meteorological data include temperature, wind speed and light intensity; primary energy price data include coal price and natural gas price; social and economic data include gross national product and consumer price index.

19. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 15, characterized in that: The generated power market multi-source scenario database is processed through feature engineering and data desensitization technology, and the power market multi-source scenario feature database is constructed as follows: For the electricity price data in the multi-source scenario database of the power market, fixed value normalization is used for desensitization processing; For the load data in the multi-source scenario database of the power market and the wind speed in the meteorological data, Z-score standardization is used for desensitization processing; For the new energy data, other non-market unit data, inter-provincial power data, meteorological data, primary energy price data and social economic data in the multi-source scenario database of the power market, extreme value normalization is used for desensitization processing; The multi-source desensitized database of the power market is constructed based on the data processed by fixed value normalization, Z score standardization and extreme value normalization. Feature engineering technology is used to extract high-dimensional data from the electricity market multi-source desensitized database as key electricity market features, and to construct an electricity market data feature library.

20. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 19, characterized in that: When performing normalization or standardization, all parameters in the process are stored to ensure that the processed data can still be reversibly transformed into the data before processing; for data that is segmented and normalized, the parameters used in each segment of normalization are stored separately; For load, new energy output, and socio-economic data, the annual data are taken as units, and each year is regarded as a separate data set, which is desensitized by means of segmented normalization.

21. The system for integrating multi-source scenario data and building a feature library for the power market according to claim 19, characterized in that: Feature engineering was applied to extract key electricity market features from the data including: Market price characteristics, including power market price characteristics and day-ahead real-time market price consistency characteristics; power market price characteristics reflect the level of electricity prices, and day-ahead real-time market price consistency characteristics reflect market stability and potential price fluctuation risks; Market space characteristics, including day-ahead market space characteristics and real-time market space characteristics, reflecting the total load demand of market entities bidding on the supply and generation side of the day-ahead market and the real-time market; Power meteorological characteristics include temperature characteristics and wind and light characteristics. The temperature characteristics are divided into 5 levels according to the threshold classification method, and the classification variables are encoded by one-hot encoding; The wind and solar characteristics are processed by feature engineering based on wind speed, light intensity, and the installed capacity ratio of the corresponding types of new energy units according to meteorological factors; The primary energy characteristics reflect the price trend of primary energy such as coal and natural gas that will affect the power generation cost of coal-fired and gas-fired units. Feature engineering processing is performed based on the prices of coal and natural gas and the proportion of installed capacity of corresponding types of thermal power units.

22. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 14.

23. A computing device, characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include steps for executing the method of any one of claims 1 to 14.

Images