CN117235519B - Energy data processing method, device and storage medium - Google Patents
Energy data processing method, device and storage medium Download PDFInfo
- Publication number
- CN117235519B CN117235519B CN202311191154.9A CN202311191154A CN117235519B CN 117235519 B CN117235519 B CN 117235519B CN 202311191154 A CN202311191154 A CN 202311191154A CN 117235519 B CN117235519 B CN 117235519B
- Authority
- CN
- China
- Prior art keywords
- data
- energy
- target
- data set
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 156
- 238000004146 energy storage Methods 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000011217 control strategy Methods 0.000 claims abstract description 12
- 238000013136 deep learning model Methods 0.000 claims description 27
- 238000010606 normalization Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims 2
- 230000000875 corresponding effect Effects 0.000 description 39
- 238000007726 management method Methods 0.000 description 32
- 238000013507 mapping Methods 0.000 description 8
- 238000010248 power generation Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 5
- 229910052799 carbon Inorganic materials 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an energy data processing method, an energy data processing device and a storage medium. The method comprises the following steps: basic data of a power station, an energy storage station and a data center station are acquired through the data center station, and an energy data processing model is built through the basic data; obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of a power station, an energy storage station and a data center station; processing the original data set to obtain a target data set; optimizing the energy data processing model through the target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting the obtained basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy. By adopting the embodiment of the invention, the energy data processing management efficiency is improved.
Description
Technical Field
The present invention relates to the field of new energy technologies, and in particular, to an energy data processing method, an apparatus, and a storage medium.
Background
Along with the gradual tightening of emission reduction situation and emission constraint of China, the scale of domestic carbon markets is increasingly enlarged, the demands of local and enterprises on energy management business are increasingly strong, and through the development of the energy management business, the energy consumption distribution, the carbon efficiency index analysis and the living enterprise carbon asset are analyzed, so that the energy conservation and carbon reduction of the enterprises can be facilitated, the energy consumption efficiency of the enterprises can be improved, the regional health energy construction can be driven, and the participation of the industry enterprises on the carbon market is standardized.
At present, most of the energy platforms on the market still stay on the data display level, cannot provide substantial value and management for enterprises, have no processing method of energy related services, have low data treatment efficiency, and have little auxiliary effect on energy management and control of the enterprises. Therefore, a problem of how to improve the efficiency of energy data processing management is to be solved.
Disclosure of Invention
The embodiment of the invention provides an energy data management method, which improves the energy data processing management efficiency.
In a first aspect, an embodiment of the present invention provides an energy data processing method applied to an energy management system, where the energy management system includes a power station, an energy storage station, and a data center station, and the method includes:
basic data of the power station, the energy storage station and the data center station are obtained through the data center station, and an energy data processing model is built through the basic data;
Obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station;
processing the original data set to obtain a target data set;
and optimizing the energy data processing model through the target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting the acquired basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy.
In a second aspect, an embodiment of the present invention provides an energy data processing apparatus applied to an energy management system, where the energy management system includes a power station, an energy storage station, and a data center station, the apparatus includes: an acquisition unit, a processing unit and an optimization unit, wherein,
The acquisition unit is used for acquiring basic data of the power station, the energy storage station and the data center station through the data center station, and establishing an energy data processing model through the basic data;
The processing unit is used for acquiring original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station; the method comprises the steps of processing the original data set to obtain a target data set;
The optimizing unit is used for optimizing the energy data processing model through the target data set to obtain a target energy data processing model, the target energy data processing model is used for predicting the obtained basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of the embodiment of the present application.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform part or all of the steps described in the first aspect of the embodiments of the present application.
The embodiment of the application has the following beneficial effects:
It can be seen that the energy data processing method described in the embodiment of the application is applied to an energy management system, the energy management system comprises a power station, an energy storage station and a data center station, basic data of the power station, the energy storage station and the data center station are acquired through the data center station, and an energy data processing model is established through the basic data; obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of a power station, an energy storage station and a data center station; processing the original data set to obtain a target data set; optimizing an energy data processing model through a target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting acquired basic data to obtain corresponding prediction data, the prediction data is used for adjusting an energy control strategy, and a more reasonable energy purchasing plan and energy use strategy can be formulated through predicting future energy prices and demand peaks and valleys, so that energy cost is reduced; the energy data processing model is built through the basic data, repeated work of data processing can be reduced, and the efficiency of data processing is improved; in addition, the energy data processing model is optimized through the target data set, the data processing efficiency is improved, the optimized model is used for processing large-scale energy data more quickly, the calculation and processing time is shortened, the data processing efficiency and response speed are improved, and the energy data processing management efficiency is improved.
Drawings
In order to more clearly describe the embodiments of the present invention or the technical solutions in the background art, the following description will describe the drawings that are required to be used in the embodiments of the present invention or the background art.
FIG. 1 is a schematic flow chart of an energy data processing method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an energy management system according to an embodiment of the present application;
FIG. 3 is a block diagram showing functional units of an energy data processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Referring to fig. 1, fig. 1 is a schematic flow chart of an energy data processing method according to an embodiment of the present application, and referring to fig. 2, fig. 2 is a schematic flow chart of an energy management system according to an embodiment of the present application; the energy data processing method as shown in fig. 1 is applied to an energy management system as shown in fig. 2, the energy management system including a power station, an energy storage station, and a data center station, the method comprising:
s101, basic data of the power station, the energy storage station and the data center station are obtained through the data center station, and an energy data processing model is built through the basic data.
In the energy management system, the power station is used for generating electric energy, and different energy sources such as fossil fuel, nuclear energy, wind energy, solar energy and the like can be adopted by the power station, so that the energy is converted into the electric energy through the power generation equipment. The purpose of the energy storage station is to store electrical energy, which can be converted into other forms of energy by various techniques and devices, such as batteries, supercapacitors, pumped storage, etc., and released as electrical energy when needed. The data center station is used for collecting, processing and analyzing energy data, and can monitor and record the data of the running states, the energy yield, the energy consumption and the like of the power station and the energy storage station in real time through methods such as sensors, monitoring equipment, a communication network and the like.
In an embodiment of the present application, the basic data may include at least one of the following: the internet of things data, static data, user data, operation data, environment data, energy data, etc., are not limited herein. The internet of things data refers to data related to energy acquired and transmitted through the internet of things technology, and the internet of things data can comprise at least one of the following: the power data of the power plant, the operation data of the energy storage devices of the energy storage station, etc., are not limited herein. Static data refers to data that is relatively fixed and infrequently changing in an energy management system, which is typically information related to the basic configuration, structure, and attributes of the energy system, and may include at least one of the following: the power plant data of the power plant, the parameter configuration data of the energy storage devices in the energy storage station, etc., are not limited herein. The user data may include at least one of: user energy consumption data, user behavior data, and the like, are not limited herein. The operational data may include at least one of: the historical operating data of the energy management system, the real-time status data of the devices of the energy management system, and the like are not limited herein. The environmental data may include at least one of: the air temperature data of the energy management system, solar radiation data of the power plant, and the like are not limited herein. The energy data may include at least one of: the supply data of the energy source, the use data of the energy source, and the like are not limited herein.
The method for acquiring the basic data can be extracting from a database, the basic data is stored in the database of the data center station, and the required basic data can be acquired by querying the database of the data center station.
In a specific implementation, the basic data of the power station, the energy storage station and the data center station can be acquired through the data center station, for example, three kinds of data including user data, operation data and energy data can be acquired as the basic data.
Optionally, step S101, obtaining, by the data center station, basic data of the power station, the energy storage station, and the data center station may include the following steps:
A1, acquiring target demand parameters of a user;
a2, determining target data identification information corresponding to the target demand parameters;
a3, obtaining basic data of the power station, the energy storage station and the data center station according to the target data identification information through the data center station.
In the embodiment of the present application, the target demand parameters of the user may include at least one of the following: the power generation amount of the power station, the energy storage amount of the energy storage station, the energy consumption data of the data center station, the power consumption demand of the user, and the like are not limited herein. The data identification information may include at least one of: the data time range, data type, data identifier, data source identification, etc., are not limited herein.
In a specific implementation, the target data identification information is obtained through the target demand parameter of the user, a mapping relation between the preset demand parameter and the data identification information can be stored in advance, the target data identification information corresponding to the target demand parameter is determined based on the mapping relation, for example, the electricity consumption demand of the user can be used as the target demand parameter of the user, the data time range can be used as the target data identification information, and then the target data identification information corresponding to the target demand parameter, namely the data time range corresponding to the electricity consumption demand, can be obtained.
Then, the data center station acquires the basic data according to the data time range, specifically, the query condition can be determined according to the data type and the data time range which need to be acquired, for example, the query condition is the power generation data of the power stations in No. 1 to No. 10 of a certain month. Basic data is extracted from a database of a data center station according to query conditions using a database query language or tool. The basic data extracted from the database is processed to ensure the accuracy and consistency of the data, for example, operations such as removing duplicate data and processing abnormal values can be performed on the extracted basic data, and the obtained basic data are integrated and correlated to obtain the basic data of the target object. The basic data may be converted and calculated according to the needs of the user, so as to obtain the basic data required by the user, for example, the power generation data of the power station may be converted into power generation cost or power generation income, which is not limited herein.
Optionally, step S101, establishing an energy data processing model through the basic data may include the following steps:
B1, classifying the basic data to obtain class a data, wherein a is an integer greater than or equal to 1;
B2, distributing a deep learning model for each type of data in the a type of data to obtain a deep learning models;
B3, determining the weight of each type of data in the type a data to obtain a weight values;
And B4, connecting the a deep learning models according to the a weight values to obtain the energy data processing model.
In the embodiment of the present application, the classification method for classifying the basic data may include at least one of the following: the classification by energy type, classification by energy source, classification by energy price, etc., are not limited herein. A deep learning model may be assigned to each of the class a data, wherein the deep learning model may include at least one of: convolutional neural network model, cyclic neural network model, long-term memory network model, etc., are not limited herein. Each deep learning model may be configured with a weight value to obtain a weight values, and the a deep learning models are connected according to the a weight values, for example, the a deep learning models may be cascaded, or some or all of the deep learning models may be connected in parallel.
Optionally, one or more deep learning models may be trained while assigning a deep learning model to each of the class a data. Specifically, the data preprocessing may be performed on any type of data, and the data preprocessing may include at least one of data cleaning, data normalization processing, data denoising, and the like, for example, performing data cleaning operation on the data, checking whether repeated records exist in the data, deleting the repeated records if the repeated records exist in the data, so as to ensure the uniqueness of the data, checking whether format errors exist in the data, performing data type conversion or correcting the format of the errors, and obtaining the processed basic data. The purpose of this is to ensure that the format and characteristics of the data in the underlying data are appropriate for the input requirements of the deep learning model, ready for subsequent model training.
Further, a corresponding deep learning model is allocated for each type of data in the class a data to train, for example, basic data can be divided into a training set, a verification set and a test set, the training set is used for model training, model tuning is performed through the verification set, and finally model performance is evaluated on the test set, so that a trained deep learning models are obtained. Then, the weight of each type of data in the class a data is obtained, specifically, a mapping relation between a preset data type and a weight value can be stored in advance, the weight value corresponding to each type of data in the class a data is determined based on the mapping relation, and a weight values are obtained, wherein the sum of the a weight values is 1, and the a weight values are all between 0 and 1. According to the a weight values, a deep learning models can be connected, for example, the a deep learning models can be cascaded to obtain an energy data processing model.
In this way, the target data identification information corresponding to the target demand parameter can be determined by acquiring the target demand parameter of the user, the basic data is acquired according to the target data identification information, and the basic data is acquired according to the target data identification information, so that personalized data identification information and basic data can be provided according to the demands of different users, the personalized demands of the users are met, and customized data service is provided; then, classifying the basic data, distributing a deep learning model for each type of data in the classified data, determining the weight of each type of data, cascading all the deep learning models according to the weight value to obtain an energy data processing model, and using different model structures and parameter settings for different types of data, so that the flexibility and adaptability of the model can be improved, the model can better adapt to the characteristics and the requirements of different types of data, and the energy data processing management efficiency is improved.
S102, acquiring original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station.
In an embodiment of the present application, the original data may include at least one of the following: the power generation data of the power plant, the energy storage data of the energy storage station, the server data of the data center station, and the like are not limited herein. And determining a target object according to the target data identification information, wherein the target object can be at least one of a power station, an energy storage station and a data center station.
In particular embodiments, the target object is determined from target data identification information, which may be a data identifier, e.g., the target data identification information is a power plant identifier, and the target object is a power plant. The original data can be power generation data of a power station, the basic data is obtained through a data center station, the basic data comprises the original data, and then the original data in the target object can be obtained from the basic data to obtain an original data set.
S103, processing the original data set to obtain a target data set.
In the embodiment of the application, a series of processing can be performed on the original data set, so that a target data set can be obtained, and the series of processing can include at least one of the following: noise reduction processing, normalization processing, sampling processing, and the like, are not limited herein.
Optionally, step S103, processing the original data set to obtain a target data set may include the following steps:
C1, carrying out noise reduction and normalization processing on the original data set to obtain a first data set;
C2, sampling the first data set to obtain a second data set;
c3, sorting the data in the second data set based on time sequence, and segmenting the sorted second data set to obtain a plurality of data segments, wherein each data segment corresponds to a time segment, and the time length of each time segment is equal;
and C4, merging the data in the data segments to obtain the target data set.
In an embodiment of the present application, the noise reduction method may include at least one of: mean filtering, median filtering, gaussian filtering, etc., are not limited herein. The normalization processing method may include at least one of: dispersion normalization, decimal scaling normalization, etc., are not limited herein. The sampling method may comprise at least one of: random sampling, uniform sampling, hierarchical sampling, clustered sampling, etc., are not limited herein.
In specific implementation, the method of median filtering can be adopted to perform noise reduction processing on the original data set, specifically, a median filter can be used to replace data with a median value of adjacent data, abnormal values and noise are removed, the window size of the median filter is determined, the window size can be 5, the data in the window are ordered, the intermediate value is taken as an output value of the window, the window is slid forwards for a time step, the time step can be 2, and the steps are repeated until all the data are processed. Then, normalization processing can be performed on the original data set by adopting a dispersion normalization method, specifically, a normalization range is determined first, for example, data is mapped between [0,1], the minimum value and the maximum value of the data in the original data set are calculated, and for each data in the original data set, normalization processing is performed by using the following formula:
Normalized value = (data i-min)/(max-min)
Based on the formula, the normalized value can be used as data in the first data set, and the data i is any data in the original data set.
Furthermore, the first data set may be sampled, for example, uniformly sampled, to obtain a second data set, then the data in the second data set is sorted according to a time sequence, and the sorted second data set is segmented, a method of equally-spaced segmentation may be adopted to obtain a plurality of data segments, and the data in the plurality of data segments are combined to obtain a target data set.
Optionally, step C4, performing merging processing on the data in the plurality of data segments to obtain the target data set may include the following steps:
d1, fitting the data of each data segment in the plurality of data segments to obtain a plurality of fitting straight lines;
D2, determining the slope and the intermediate value of each fitting straight line in the fitting straight lines, and determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of a data segment;
D3, determining the target data set according to the plurality of reference data.
In the embodiment of the application, since the data of each data segment corresponds to one time point, that is, each data segment can be regarded as a plurality of coordinate points, the abscissa of each coordinate point represents time, and the ordinate represents the size of a data value, and further, a fitting straight line is drawn according to the data value and the corresponding time point, so as to obtain a plurality of fitting straight lines.
And then, determining the slope and the intermediate value of each fitting straight line in the plurality of fitting straight lines, determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of one data segment, determining a target data set according to the plurality of reference data, and improving the model training efficiency due to the reduction of the data quantity, wherein the sampling data can represent the data condition of one time segment, so that the model capacity is not reduced to a certain extent.
Optionally, step D2, determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data may include the following steps:
E1, acquiring a slope i and an intermediate value i of a fitting straight line i, wherein the fitting straight line i is one fitting straight line in the fitting straight lines;
E2, determining a target adjusting parameter corresponding to the slope i;
and E3, adjusting the intermediate value i according to the target adjusting parameter to obtain the reference data corresponding to the fitting straight line i.
In specific implementation, taking a fitting straight line i as an example, the fitting straight line i is one fitting straight line of a plurality of fitting straight lines, then the slope i and the intermediate value i of the fitting straight line i can be obtained, a mapping relation between a preset slope and an adjusting parameter can be stored in advance, the value range of the adjusting parameter can be set to be-0.12, a target adjusting parameter corresponding to the slope i can be determined based on the mapping relation, and then the intermediate value i is adjusted according to the target adjusting parameter, so that reference data corresponding to the fitting straight line i is obtained, and the specific steps are as follows:
reference data= (1+ target adjustment parameter) ×intermediate value i corresponding to fitting straight line i
The reference data corresponding to the fitting straight line i can represent the data change rule of the data segment, so that the model training efficiency is improved due to the reduction of the data quantity, and the sampled data can represent the data condition of a time segment, so that the model capacity is not reduced to a certain extent.
And S104, optimizing the energy data processing model through the target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting the acquired basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy.
In the embodiment of the application, the target data set is the processed original data set, and the data in the target data set has better quality and higher accuracy than the data in the original data set. The energy data processing model is optimized by using the target data set to obtain a target energy data processing model, the target energy data processing model is used for predicting the acquired basic data to obtain prediction data, the prediction data is used for adjusting an energy control strategy, for example, the prediction data is used for displaying that the energy price can rise within a period of time in the future, the energy control strategy is adjusted according to the prediction data, the energy acquisition amount in the energy control strategy can be pre-increased, some energy is purchased before the energy price rises, the situation that high-price energy needs to be purchased in the future is avoided, the cost is saved for users, and meanwhile, the energy supply stability is ensured.
Optionally, step S104, optimizing the energy data processing model by using the target data set to obtain a target energy data processing model may include the following steps:
41. determining a target data type corresponding to the target data set;
42. Determining optimizable parameters in the energy data processing model according to the target data type to obtain b optimizable parameters; b is a positive integer;
43. And inputting the target data set into the energy data processing model for learning, and optimizing the b optimizable parameters in the learning process until the energy data processing model converges to obtain the target energy data processing model.
In the embodiment of the present application, the data type is narrowly understood as a data format type, a data source type, etc., which are not limited herein, and the data type is broadly understood as a data category, that is, classifying data, where each data type corresponds to one data category. The optimizable parameters may include at least one of: the learning rate, regularization parameters, initialization weights, etc., are not limited herein.
In specific implementation, the energy management system may determine a target data type corresponding to the target data set, may pre-store a mapping relationship between a preset data type and an optimization parameter, determine an optimizable parameter in an energy data processing model corresponding to the target data type based on the mapping relationship, obtain b optimizable parameters, input the target data set into the energy data processing model for learning, and optimize the b optimizable parameters in the learning process until the energy data processing model converges, for example, a parameter tuning method is adopted to process the energy data processing model until the energy data processing model converges, a range of the optimizable parameter to be tuned can be determined first, the optimizable parameter can be a learning rate, and a value range of the parameter can be preset or default of the energy management system. An evaluation index, which may be an accuracy rate, is selected to measure the performance of the model. According to the range of optimizable parameters and the complexity of the problem, a proper search method is selected, and the search method can be grid search. For grid search, a search space and a step length are required to be set, wherein the search space is a value range of an optimizable parameter, and the step length is the variation amplitude of the parameter in the search process. The appropriate search space and step size are set according to the characteristics of the parameters and the complexity of the problem, and the space and step size can be preset or default of the energy management system. And starting parameter searching according to the selected searching method and the set searching space. For grid search, traversing all possible parameter combinations, calculating an evaluation index value of each parameter combination, and recording the performance of each parameter combination according to the result of the evaluation index. And selecting the parameter combination with the best performance as the optimal parameter according to the calculation result of the evaluation index, and adjusting the optimizable parameter to the optimal parameter value after obtaining the optimal parameter to obtain the target energy data processing model.
It can be seen that the energy data processing method described in the embodiment of the application is applied to an energy management system, the energy management system comprises a power station, an energy storage station and a data center station, basic data of the power station, the energy storage station and the data center station are acquired through the data center station, and an energy data processing model is established through the basic data; obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of a power station, an energy storage station and a data center station; processing the original data set to obtain a target data set; optimizing an energy data processing model through a target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting acquired basic data to obtain corresponding prediction data, the prediction data is used for adjusting an energy control strategy, and a more reasonable energy purchasing plan and energy use strategy can be formulated through predicting future energy prices and demand peaks and valleys, so that energy cost is reduced; the energy data processing model is built through the basic data, repeated work of data processing can be reduced, and the efficiency of data processing is improved; in addition, the energy data processing model is optimized through the target data set, the data processing efficiency is improved, the optimized model is used for processing large-scale energy data more quickly, the calculation and processing time is shortened, the data processing efficiency and response speed are improved, and the energy data processing management efficiency is improved.
Referring to fig. 3, fig. 3 is a block diagram illustrating functional units of an energy data processing apparatus 300 according to an embodiment of the present application. The energy data processing apparatus 300 is applied to an energy management system including a power station, an energy storage station, and a data center station, and the energy data processing apparatus 300 includes: an acquisition unit 301, a processing unit 302, an optimization unit 303, wherein,
The acquiring unit 301 is configured to acquire basic data of the power station, the energy storage station, and the data center station through the data center station, and establish an energy data processing model through the basic data;
The processing unit 302 is configured to obtain, from the base data, original data in a target object, to obtain an original data set, where the target object is at least one of the power station, the energy storage station, and the data center station; the method comprises the steps of processing the original data set to obtain a target data set;
The optimizing unit 303 is configured to optimize the energy data processing model through the target data set to obtain a target energy data processing model, where the target energy data processing model is configured to predict the obtained basic data to obtain corresponding prediction data, and the prediction data is configured to adjust an energy control policy.
Optionally, in the aspect of acquiring, by the data center station, the basic data of the power station, the energy storage station, and the data center station, the acquiring unit 301 is specifically configured to:
Acquiring target demand parameters of a user;
determining target data identification information corresponding to the target demand parameters;
and acquiring basic data of the power station, the energy storage station and the data center station according to the target data identification information through the data center station.
Optionally, in the aspect of building an energy data processing model through the basic data, the obtaining unit 301 is specifically configured to:
Classifying the basic data to obtain class a data, wherein a is an integer greater than or equal to 1;
Distributing a deep learning model for each type of data in the a type of data to obtain a deep learning models;
determining the weight of each type of data in the type a data to obtain a weight values;
And connecting the a deep learning models according to the a weight values to obtain the energy data processing model.
Optionally, in the aspect of processing the original data set to obtain a target data set, the processing unit 302 is specifically configured to:
Noise reduction and normalization are carried out on the original data set to obtain a first data set;
sampling the first data set to obtain a second data set;
Sorting the data in the second data set based on time sequence, and segmenting the sorted second data set to obtain a plurality of data segments, wherein each data segment corresponds to a time segment, and the time length of each time segment is equal;
And merging the data in the plurality of data segments to obtain the target data set.
Optionally, in the aspect of merging the data in the plurality of data segments to obtain the target data set, the processing unit 302 is specifically configured to:
Fitting the data of each data segment in the plurality of data segments to obtain a plurality of fitting straight lines;
Determining the slope and the intermediate value of each fitting straight line in the plurality of fitting straight lines, and determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of a data segment;
The target data set is determined from the plurality of reference data.
Optionally, in determining the corresponding reference data according to the slope and the intermediate value of each fitting straight line, to obtain a plurality of reference data, the processing unit 302 is specifically configured to:
Acquiring a slope i and an intermediate value i of a fitting straight line i, wherein the fitting straight line i is one fitting straight line in the fitting straight lines;
determining a target adjusting parameter corresponding to the slope i;
And adjusting the intermediate value i according to the target adjusting parameter to obtain the reference data corresponding to the fitting straight line i.
Optionally, in optimizing the energy data processing model by the target data set to obtain a target energy data processing model, the optimizing unit 303 is specifically configured to:
Determining a target data type corresponding to the target data set;
Determining optimizable parameters in the energy data processing model according to the target data type to obtain b optimizable parameters; b is a positive integer;
And inputting the target data set into the energy data processing model for learning, and optimizing the b optimizable parameters in the learning process until the energy data processing model converges to obtain the target energy data processing model.
In a specific implementation, the acquiring unit 301, the processing unit 302, and the optimizing unit 303 described in the embodiments of the present invention may also execute other embodiments described in the energy data processing method provided in the embodiments of the present invention, which are not described herein again.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device includes a processor, a memory, a communication interface, and one or more programs, the processor, memory, and communication interface being interconnected by a bus.
The Memory includes, but is not limited to, a random access Memory (English: random Access Memory; RAM; short), a Read-Only Memory (English: ROM; short), an erasable programmable Read-Only Memory (English: erasable Programmable Read Only Memory; short: EPROM), or a portable Read-Only Memory (English: compact Disc Read-Only Memory; short: CD-ROM), which is used for related instructions and data. The transceiver is used for receiving and transmitting data.
The processor may be one or more central processing units (english: central Processing Unit, abbreviated as CPU), and in the case where the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU.
The electronic equipment is applied to an energy management system, wherein the energy management system comprises a power station, an energy storage station and a data center station; the one or more programs are stored in the memory and configured to be executed by the processor, and in an embodiment of the present application, the program includes instructions for:
basic data of the power station, the energy storage station and the data center station are obtained through the data center station, and an energy data processing model is built through the basic data;
Obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station; the method comprises the steps of processing the original data set to obtain a target data set;
and optimizing the energy data processing model through the target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting the acquired basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy.
Optionally, in the acquiring, by the data center station, the base data of the power station, the energy storage station, and the data center station, the program further includes instructions for:
Acquiring target demand parameters of a user;
determining target data identification information corresponding to the target demand parameters;
and acquiring basic data of the power station, the energy storage station and the data center station according to the target data identification information through the data center station.
Optionally, in the aspect of building an energy data processing model through the basic data, the program further includes instructions for performing the following steps:
Classifying the basic data to obtain class a data, wherein a is an integer greater than or equal to 1;
Distributing a deep learning model for each type of data in the a type of data to obtain a deep learning models;
determining the weight of each type of data in the type a data to obtain a weight values;
And connecting the a deep learning models according to the a weight values to obtain the energy data processing model.
Optionally, in the aspect of processing the original data set to obtain a target data set, the program further includes instructions for:
Noise reduction and normalization are carried out on the original data set to obtain a first data set;
sampling the first data set to obtain a second data set;
Sorting the data in the second data set based on time sequence, and segmenting the sorted second data set to obtain a plurality of data segments, wherein each data segment corresponds to a time segment, and the time length of each time segment is equal;
And merging the data in the plurality of data segments to obtain the target data set.
Optionally, in the aspect of merging the data in the plurality of data segments to obtain the target data set, the program further includes instructions for performing the following steps:
Fitting the data of each data segment in the plurality of data segments to obtain a plurality of fitting straight lines;
Determining the slope and the intermediate value of each fitting straight line in the plurality of fitting straight lines, and determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of a data segment;
The target data set is determined from the plurality of reference data.
Optionally, in determining the corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, the program further includes instructions for performing the following steps:
Acquiring a slope i and an intermediate value i of a fitting straight line i, wherein the fitting straight line i is one fitting straight line in the fitting straight lines;
determining a target adjusting parameter corresponding to the slope i;
And adjusting the intermediate value i according to the target adjusting parameter to obtain the reference data corresponding to the fitting straight line i.
Optionally, in optimizing the energy data processing model by the target data set to obtain a target energy data processing model, the program further includes instructions for:
Determining a target data type corresponding to the target data set;
Determining optimizable parameters in the energy data processing model according to the target data type to obtain b optimizable parameters; b is a positive integer;
And inputting the target data set into the energy data processing model for learning, and optimizing the b optimizable parameters in the learning process until the energy data processing model converges to obtain the target energy data processing model.
The embodiment of the application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program makes a computer execute part or all of the steps of any one of the above method embodiments, and the computer includes an electronic device.
Those of ordinary skill in the art will appreciate that implementing all or part of the above-described method embodiments may be accomplished by a computer program to instruct related hardware, the program may be stored in a computer readable storage medium, and the program may include the above-described method embodiments when executed. And the aforementioned storage medium includes: ROM or random access memory RAM, magnetic or optical disk, etc.
Claims (7)
1. An energy data processing method, characterized by being applied to an energy management system including a power station, an energy storage station, and a data center station, the method comprising:
Basic data of the power station, the energy storage station and the data center station are obtained through the data center station, and an energy data processing model is built through the basic data; the base data includes at least one of: thing networking data, static data, user data, operation data, environment data and energy data;
Obtaining original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station;
processing the original data set to obtain a target data set;
Optimizing the energy data processing model through the target data set to obtain a target energy data processing model, wherein the target energy data processing model is used for predicting the acquired basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy;
the processing the original data set to obtain a target data set includes:
Noise reduction and normalization are carried out on the original data set to obtain a first data set;
sampling the first data set to obtain a second data set;
Sorting the data in the second data set based on time sequence, and segmenting the sorted second data set to obtain a plurality of data segments, wherein each data segment corresponds to a time segment, and the time length of each time segment is equal;
Combining the data in the data segments to obtain the target data set;
The merging processing of the data in the plurality of data segments to obtain the target data set includes:
Fitting the data of each data segment in the plurality of data segments to obtain a plurality of fitting straight lines;
Determining the slope and the intermediate value of each fitting straight line in the plurality of fitting straight lines, and determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of a data segment;
Determining the target data set from the plurality of reference data;
the determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data includes:
Acquiring a slope i and an intermediate value i of a fitting straight line i, wherein the fitting straight line i is one fitting straight line in the fitting straight lines;
determining a target adjusting parameter corresponding to the slope i;
And adjusting the intermediate value i according to the target adjusting parameter to obtain the reference data corresponding to the fitting straight line i.
2. The method of claim 1, wherein said obtaining, by said data center station, base data for said power plant, said energy storage station, and said data center station comprises:
Acquiring target demand parameters of a user;
determining target data identification information corresponding to the target demand parameters;
and acquiring basic data of the power station, the energy storage station and the data center station according to the target data identification information through the data center station.
3. The method of claim 1, wherein said building an energy data processing model from said base data comprises:
Classifying the basic data to obtain class a data, wherein a is an integer greater than or equal to 1;
Distributing a deep learning model for each type of data in the a type of data to obtain a deep learning models;
determining the weight of each type of data in the type a data to obtain a weight values;
And connecting the a deep learning models according to the a weight values to obtain the energy data processing model.
4. A method according to any of claims 1-3, wherein optimizing the energy data processing model by the target data set results in a target energy data processing model comprising:
Determining a target data type corresponding to the target data set;
Determining optimizable parameters in the energy data processing model according to the target data type to obtain b optimizable parameters; b is a positive integer;
And inputting the target data set into the energy data processing model for learning, and optimizing the b optimizable parameters in the learning process until the energy data processing model converges to obtain the target energy data processing model.
5. An energy data processing apparatus for use in an energy management system, the energy management system including a power station, an energy storage station, and a data center station, the apparatus comprising: an acquisition unit, a processing unit and an optimization unit, wherein,
The acquisition unit is used for acquiring basic data of the power station, the energy storage station and the data center station through the data center station, and establishing an energy data processing model through the basic data; the base data includes at least one of: thing networking data, static data, user data, operation data, environment data and energy data;
The processing unit is used for acquiring original data in a target object from the basic data to obtain an original data set, wherein the target object is at least one of the power station, the energy storage station and the data center station; the method comprises the steps of processing the original data set to obtain a target data set;
the optimizing unit is used for optimizing the energy data processing model through the target data set to obtain a target energy data processing model, the target energy data processing model is used for predicting the acquired basic data to obtain corresponding prediction data, and the prediction data is used for adjusting an energy control strategy;
wherein, in the aspect of processing the original data set to obtain a target data set, the processing unit is specifically configured to:
Noise reduction and normalization are carried out on the original data set to obtain a first data set;
sampling the first data set to obtain a second data set;
Sorting the data in the second data set based on time sequence, and segmenting the sorted second data set to obtain a plurality of data segments, wherein each data segment corresponds to a time segment, and the time length of each time segment is equal;
Combining the data in the data segments to obtain the target data set;
The processing unit is specifically configured to, in the aspect of merging the data in the plurality of data segments to obtain the target data set:
Fitting the data of each data segment in the plurality of data segments to obtain a plurality of fitting straight lines;
Determining the slope and the intermediate value of each fitting straight line in the plurality of fitting straight lines, and determining corresponding reference data according to the slope and the intermediate value of each fitting straight line to obtain a plurality of reference data, wherein each reference data represents the data change rule of a data segment;
Determining the target data set from the plurality of reference data;
The processing unit is specifically configured to, in determining corresponding reference data according to the slope and the intermediate value of each fitting straight line, obtain a plurality of reference data:
Acquiring a slope i and an intermediate value i of a fitting straight line i, wherein the fitting straight line i is one fitting straight line in the fitting straight lines;
determining a target adjusting parameter corresponding to the slope i;
And adjusting the intermediate value i according to the target adjusting parameter to obtain the reference data corresponding to the fitting straight line i.
6. An electronic device comprising a processor, a memory, a communication interface, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the energy data processing method according to any one of claims 1 to 4 when the computer program is executed.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the energy data processing method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311191154.9A CN117235519B (en) | 2023-09-13 | 2023-09-13 | Energy data processing method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311191154.9A CN117235519B (en) | 2023-09-13 | 2023-09-13 | Energy data processing method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117235519A CN117235519A (en) | 2023-12-15 |
| CN117235519B true CN117235519B (en) | 2024-09-24 |
Family
ID=89096116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311191154.9A Active CN117235519B (en) | 2023-09-13 | 2023-09-13 | Energy data processing method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235519B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797889A (en) * | 2020-05-18 | 2020-10-20 | 山东科技大学 | Single variable alarm system performance evaluation method and system based on piecewise linear representation |
| CN116470486A (en) * | 2023-04-06 | 2023-07-21 | 国网浙江新兴科技有限公司 | Ultra-short-term photovoltaic power generation power prediction method, device and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4389706A (en) * | 1972-05-03 | 1983-06-21 | Westinghouse Electric Corp. | Digital computer monitored and/or operated system or process which is structured for operation with an improved automatic programming process and system |
| FR2992126A1 (en) * | 2012-06-15 | 2013-12-20 | France Telecom | METHOD AND DEVICE FOR FAST AND LITTLE INTRUSIVE ESTIMATING OF BANDWIDTH AVAILABLE BETWEEN TWO IP NODES |
| IL266447B2 (en) * | 2016-11-10 | 2023-11-01 | Asml Netherlands Bv | Design and correction using stack difference |
| CN108958801B (en) * | 2017-10-30 | 2021-06-25 | 上海寒武纪信息科技有限公司 | Neural network processor and method for executing vector maximum value instruction by using same |
| US11368400B2 (en) * | 2018-12-13 | 2022-06-21 | Amazon Technologies, Inc. | Continuously calibrated network system |
| CN110567445A (en) * | 2019-09-03 | 2019-12-13 | 天韵(广州)房地产开发有限公司 | building indoor actual measurement data acquisition and analysis system |
| CN111026744A (en) * | 2019-12-11 | 2020-04-17 | 新奥数能科技有限公司 | Data management method and device based on energy station system model framework |
| CN111522705A (en) * | 2020-03-23 | 2020-08-11 | 广东工业大学 | Intelligent operation and maintenance solution method for industrial big data |
| CN112800686A (en) * | 2021-03-29 | 2021-05-14 | 国网江西省电力有限公司电力科学研究院 | Transformer DGA online monitoring data abnormal mode judgment method |
| CN115965160B (en) * | 2023-01-18 | 2023-08-08 | 中国长江三峡集团有限公司 | Data center energy consumption prediction method and device, storage medium and electronic equipment |
-
2023
- 2023-09-13 CN CN202311191154.9A patent/CN117235519B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797889A (en) * | 2020-05-18 | 2020-10-20 | 山东科技大学 | Single variable alarm system performance evaluation method and system based on piecewise linear representation |
| CN116470486A (en) * | 2023-04-06 | 2023-07-21 | 国网浙江新兴科技有限公司 | Ultra-short-term photovoltaic power generation power prediction method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117235519A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114298863B (en) | Data acquisition method and system of intelligent meter reading terminal | |
| CN110610280A (en) | Short-term prediction method, model, device and system for power load | |
| CN111815060A (en) | Short-term load prediction method and device for power utilization area | |
| CN111062620B (en) | Intelligent electric power charging fairness analysis system and method based on hybrid charging data | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
| CN117113159A (en) | Deep learning-based power consumer side load classification method and system | |
| CN118017502A (en) | Digital twinning-based power distribution calculation power prediction method, system and medium | |
| CN117235519B (en) | Energy data processing method, device and storage medium | |
| CN115511230B (en) | Electric energy substitution potential analysis and prediction method | |
| CN116820767A (en) | Cloud resource management method and device, electronic equipment and storage medium | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| CN116249186A (en) | Data processing method and device of wireless network equipment, storage medium and electronic equipment | |
| CN113487080B (en) | Wind speed dynamic scene generation method, system and terminal based on wind speed classification | |
| CN112560325B (en) | Prediction method, system, equipment and storage medium for electricity conversion service | |
| CN114004408A (en) | User power load prediction method based on data analysis | |
| CN112614005A (en) | Enterprise rework state processing method and device | |
| CN118228887B (en) | Energy coordination optimization control method and system for virtual power plant | |
| CN113361960B (en) | Method, medium, device and equipment for quantifying large-scale demand response capacity | |
| CN118300101B (en) | Method, apparatus and storage medium for predicting electric load | |
| CN118331831A (en) | Application system efficiency evaluation method and device, electronic equipment and storage medium | |
| Dai et al. | Forecasting Method of Power Consumption Information for Power Users Based on Cloud Computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |