CN117833361A - Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis - Google Patents
Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis Download PDFInfo
- Publication number
- CN117833361A CN117833361A CN202410007641.3A CN202410007641A CN117833361A CN 117833361 A CN117833361 A CN 117833361A CN 202410007641 A CN202410007641 A CN 202410007641A CN 117833361 A CN117833361 A CN 117833361A
- Authority
- CN
- China
- Prior art keywords
- power
- power supply
- load
- climate
- supply load
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012300 Sequence Analysis Methods 0.000 title claims abstract description 16
- 230000005611 electricity Effects 0.000 claims abstract description 145
- 238000010248 power generation Methods 0.000 claims abstract description 99
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 239000000203 mixture Substances 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 40
- 238000013135 deep learning Methods 0.000 claims description 18
- 238000012731 temporal analysis Methods 0.000 claims description 17
- 238000000700 time series analysis Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013136 deep learning model Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 4
- 238000001556 precipitation Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims 1
- 238000010219 correlation analysis Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000005612 types of electricity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of deep peak shaving of coal-fired power plants, in particular to a method and a device for predicting deep peak shaving of a coal-fired power plant based on time sequence analysis, which can comprehensively consider various influencing factors and improve the prediction accuracy of the power supply quantity of the coal-fired power plant; the method comprises the following steps: collecting historical electricity load information and historical power supply load information of an electricity utilization area; carrying out power component analysis on the historical power supply load information to obtain power supply load component characteristics of a power consumption area; the power consumption area power supply load composition characteristics comprise power supply load types and power supply amounts of the power supply load types, wherein the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads; acquiring historical climate information within the same time as the power supply load component characteristics of a power utilization area; and extracting climate factors influencing the power generation efficiency of various power generation modes from the historical climate information to obtain the climate characteristics of the power utilization area.
Description
Technical Field
The invention relates to the technical field of coal-fired power plant deep peak shaving, in particular to a coal-fired power plant deep peak shaving prediction method and device based on time sequence analysis.
Background
With the large-area access of new energy to the power grid, the deep peak shaving capability becomes one of important indexes for measuring the peak shaving capability of the thermal power generating unit, and is also an important guarantee for the stable operation of the power system; the traditional thermal power generation amount generally occupies a larger proportion, and new energy sources such as wind energy, solar energy and the like are added, so that the power generation amount of the power system becomes more unstable; this instability requires deep peak shaving capability of thermal power generating units to cope with fluctuations in new energy power generation.
By means of power prediction of the power supply area of the coal-fired power plant, the power demand condition of the power supply area of the coal-fired power plant can be known, so that a more reasonable scheduling plan is formulated, and stable operation of a power system is ensured; the existing prediction of the power supply quantity of the coal-fired power plant mainly adopts a traditional statistical method, such as linear regression and the like; although the methods are simple and feasible, the prediction accuracy is low, and the complexity and the dynamic property of the power system cannot be accurately reflected; meanwhile, the existing prediction method mainly focuses on the prediction of the power load, and ignores the influence of the power supply load component.
Therefore, it is needed to provide a coal-fired power plant depth peak shaving prediction method based on time series analysis to solve the above technical problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides the coal-fired power plant depth peak shaving prediction method based on time sequence analysis, which can comprehensively consider various influencing factors and improve the prediction accuracy of the power supply quantity of the coal-fired power plant.
In a first aspect, the present invention provides a coal-fired power plant depth peak shaving prediction method based on time series analysis, the method comprising:
collecting historical electricity load information and historical power supply load information of an electricity utilization area;
carrying out power component analysis on the historical power supply load information to obtain power supply load component characteristics of a power consumption area; the power consumption area power supply load component characteristics comprise power supply load types and power supply amounts of the power supply load types, wherein the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
acquiring historical climate information within the same time as the power supply load component characteristics of a power utilization area;
extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area; the climate characteristics of the electricity utilization area are respectively in one-to-one correspondence with the power supply load component characteristics of the electricity utilization area and the historical electricity utilization load information of the electricity utilization area in the time dimension;
Uploading the climate characteristics of the electricity utilization area and the corresponding historical electricity utilization load information of the electricity utilization area to a deep learning platform for learning and training to obtain an electricity utilization load prediction model of the electricity utilization area; uploading the climate characteristics of the electricity consumption region and the power supply load component characteristics of the electricity consumption region to a deep learning platform for learning and training to obtain a power supply load component prediction model of the electricity consumption region;
acquiring climate characteristics of a power utilization area of a prediction time node, and respectively inputting the climate characteristics of the power utilization area of the prediction time node into a power utilization load prediction model of the power utilization area and a power supply load component prediction model of the power utilization area to obtain power utilization load characteristics of the power utilization area at the prediction time node and power supply load component characteristics of the power utilization area at the prediction time node;
and calculating to obtain the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load of the power consumption area at the predicted time node and the power supply load composition characteristics of the power consumption area at the predicted time node.
On the other hand, the application also provides a coal-fired power plant depth peak shaving prediction device based on time sequence analysis, which comprises:
the data collection module is used for collecting historical electricity load information and historical power supply load information of an electricity utilization area;
The power component analysis module is used for carrying out power component analysis on the collected historical power supply load information to obtain power supply load component characteristics of a power consumption area, wherein the power supply load component characteristics of the power consumption area comprise power supply load types and power supply amounts of the power supply load types, and the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
the historical climate information acquisition module is used for acquiring historical climate information in the same time as the power supply load component characteristics of the power utilization area;
the climate factor extraction module is used for extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area, wherein the climate characteristics of the power utilization area are respectively in one-to-one correspondence with power supply load component characteristics of the power utilization area and the historical power utilization load information in the time dimension;
the deep learning platform module is used for receiving the climate characteristics of the power utilization area and the corresponding historical power utilization load information of the power utilization area and carrying out learning training to obtain a power utilization load prediction model of the power utilization area; receiving climate characteristics of the electricity consumption area and power supply load component characteristics of the electricity consumption area, and performing learning training to obtain a power supply load component prediction model of the electricity consumption area;
The prediction module acquires climate characteristics of a power utilization area of a prediction time node, sequentially inputs the climate characteristics of the power utilization area of the prediction time node into a power utilization area power utilization load prediction model and a power supply load component prediction model, and outputs power utilization load and power supply load component characteristics of the power utilization area at the prediction time node;
and the power supply quantity calculation module is used for calculating and obtaining the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load and the power supply load component characteristics of the power consumption area at the predicted time node.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program implementing the steps of any of the methods described above when executed by the processor.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that: the invention not only collects the historical electricity load information and the historical power supply load information of the electricity consumption area, but also acquires the historical climate information within the same time as the characteristic of the power supply load component of the electricity consumption area; this enables the predictive model to more fully account for various influencing factors, including power load, power load composition, and climate factors; according to the invention, a deep learning platform is used for learning and training, useful features can be extracted from a large amount of data, and a complex nonlinear model is established, so that the prediction precision is improved; by establishing an electricity load prediction model and a power supply load component prediction model of an electricity consumption area, the electricity load and the power supply load component can be predicted more accurately, so that the prediction accuracy of the power supply quantity of the coal-fired power plant is improved;
the invention can adapt to the access of new energy, and can better cope with the fluctuation of the power generation amount of the new energy by analyzing and predicting the power supply load components, thereby improving the stability of a power system; the invention considers the running condition of an actual power system, and can calculate and obtain the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load and the power supply load component characteristics of the power consumption area at the predicted time node; the method is beneficial to deep peak shaving of the coal-fired power plant and improves the stability of the power system; by improving the prediction precision of the power supply quantity of the coal-fired power plant, the invention can help to make a more reasonable scheduling plan, reduce unnecessary start and stop of a unit and reduce coal consumption, thereby saving energy and reducing environmental pollution; meanwhile, the running pressure of the power grid can be reduced by accurately predicting, the stability of the power system is improved, and long-term benefits are brought;
In conclusion, various influencing factors can be comprehensively considered, and the prediction accuracy of the power supply quantity of the coal-fired power plant is improved, so that the method and the system can better cope with the access of new energy sources and improve the stability of a power system; meanwhile, the invention has operability and practicability and can provide effective support for the operation of an actual power system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a coal-fired power plant depth peaking prediction method based on time series analysis according to an embodiment of the present invention;
FIG. 2 is a hardware architecture diagram of an electronic device according to an embodiment of the present invention;
fig. 3 is a block diagram of a coal-fired power plant depth peak shaving prediction device based on time series analysis according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Referring to fig. 1, an embodiment of the invention provides a coal-fired power plant depth peak shaving prediction method based on time series analysis, which includes:
step S1, collecting historical electricity load information and historical electricity supply load information of an electricity consumption area;
s2, carrying out power component analysis on the historical power supply load information to obtain power supply load component characteristics of a power consumption area; the power consumption area power supply load component characteristics comprise power supply load types and power supply amounts of the power supply load types, wherein the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
s3, acquiring historical climate information within the same time as the characteristic of the power supply load component of the power utilization area;
S4, extracting climate factors influencing the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area; the climate characteristics of the electricity utilization area are respectively in one-to-one correspondence with the power supply load component characteristics of the electricity utilization area and the historical electricity utilization load information of the electricity utilization area in the time dimension;
s5, uploading the climate characteristics of the electricity utilization area and the corresponding historical electricity utilization load information of the electricity utilization area to a deep learning platform for learning and training to obtain an electricity utilization load prediction model of the electricity utilization area; uploading the climate characteristics of the electricity consumption region and the power supply load component characteristics of the electricity consumption region to a deep learning platform for learning and training to obtain a power supply load component prediction model of the electricity consumption region;
s6, acquiring climate characteristics of a power utilization area of a predicted time node, and respectively inputting the climate characteristics of the power utilization area of the predicted time node into a power utilization load prediction model of the power utilization area and a power utilization load component prediction model of the power utilization area to obtain power utilization load characteristics of the power utilization area at the predicted time node and power utilization load component characteristics of the power utilization area at the predicted time node;
and S7, calculating to obtain the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load of the power consumption area at the predicted time node and the power supply load component characteristics of the power consumption area at the predicted time node.
In the embodiment, the method not only collects the historical power load information and the historical power load information of the power consumption area, but also obtains the historical climate information within the same time as the power load composition characteristics of the power consumption area; this enables the predictive model to more fully account for various influencing factors, including power load, power load composition, and climate factors; according to the method, a deep learning platform is used for learning and training, useful features can be extracted from a large amount of data, and a complex nonlinear model is built, so that the prediction precision is improved; by establishing an electricity load prediction model and a power supply load component prediction model of an electricity consumption area, the electricity load and the power supply load component can be predicted more accurately, so that the prediction accuracy of the power supply quantity of the coal-fired power plant is improved; the method can adapt to the access of new energy, and can better cope with the fluctuation of the power generation amount of the new energy by analyzing and predicting the power supply load components, thereby improving the stability of a power system; according to the method, the running condition of an actual power system is considered, and the power generation load of the coal-fired power plant at the predicted time node can be calculated according to the power consumption load and the power supply load component characteristics of the power consumption region at the predicted time node; the method is beneficial to deep peak shaving of the coal-fired power plant and improves the stability of the power system; by improving the prediction accuracy of the power supply quantity of the coal-fired power plant, the method can help to make a more reasonable scheduling plan, reduce unnecessary start and stop of a unit and reduce coal consumption, thereby saving energy and reducing environmental pollution; meanwhile, the running pressure of the power grid can be reduced by accurately predicting, the stability of the power system is improved, and long-term benefits are brought; in conclusion, various influencing factors can be comprehensively considered, and the prediction accuracy of the power supply quantity of the coal-fired power plant is improved, so that the method can better cope with the access of new energy sources, and the stability of a power system is improved; meanwhile, the method has operability and practicability, and can provide effective support for the operation of an actual power system.
The manner in which the individual steps shown in fig. 1 are performed is described below.
For step S1:
in the technical scheme of coal-fired power plant depth peak shaving prediction, the step S1 is a key data preparation stage, and aims to acquire historical electricity load information and historical electricity load information of an electricity utilization area; the specific embodiment of step S1 includes the following:
s11, data acquisition: collecting historical electricity load information and historical power supply load information of an electricity consumption area through a data acquisition system; the data can be obtained through the ways of an electricity consumption management system, a power grid dispatching system and the like of an electric company;
s12, data preprocessing: cleaning, sorting and formatting the collected data to ensure the accuracy and consistency of the data; the method comprises the steps of processing the problems of missing values, abnormal values, repeated data and the like, and providing a high-quality data base for subsequent analysis;
s13, data storage: storing the preprocessed data in a database or data warehouse for subsequent analysis and processing; selecting a proper data storage scheme to ensure the safety, reliability and expandability of data;
s14, data backup and security: to prevent data loss or corruption, data backup is necessary; meanwhile, the security of the data is ensured, and unauthorized access and tampering are prevented; through data backup and security measures, the security of the data can be ensured, the data is prevented from being lost or damaged, meanwhile, unauthorized access and tampering are prevented, and the security and reliability of the data are ensured;
S15, interface design: in order to interact with other systems or modules, appropriate interfaces need to be designed; the interfaces can be used for functions of data import and export, real-time data transmission and the like, and the integration and expandability of the whole system are improved; through interface design, data interaction with other systems or modules can be realized, the integration and expandability of the whole system are improved, the docking with other technical schemes or systems is facilitated, and wider data sharing and application are realized.
In the step, the step S1 plays a key role in data preparation in the technical scheme of coal-fired power plant depth peak shaving prediction, provides a complete, accurate, safe and extensible data base for subsequent prediction analysis, can improve the accuracy and reliability of prediction, and provides effective technical support for the depth peak shaving of the coal-fired power plant.
For step S2:
step S2, aiming at obtaining the power supply load component characteristics of the power utilization area by carrying out power component analysis on the historical power supply load information; this step is critical to the deep peak shaving prediction method, because knowing the type of power load and the amount of power supplied by each type can help accurately predict the amount of power supplied by a coal-fired power plant, especially in view of the volatility of new energy, embodiments include the following:
Using a time series analysis method, historical power load information may be analyzed using tools including, but not limited to, autoregressive models (AR), moving average Models (MA), autoregressive moving average models (ARMA), autoregressive integral moving average models (ARIMA), and the like; these models can help find trends, seasonal variations, and possible periodic effects over different time periods;
after historical power supply load information is analyzed, the obtained information is subdivided into different power supply load types, electric quantity statistics is carried out on each power supply load, and the power supply quantity of each power supply load is calculated; these data will be used in subsequent analysis to reveal the impact of various factors on the power load; in this scenario, attention is paid to the amount of power supply occupied by different power generation modes, such as wind power generation load, photovoltaic power generation load, hydroelectric power generation load, and the like;
integrating the identified power supply load types and the counted power supply quantity to form power supply load component characteristics of a power utilization area; analyzing the change rules and trends of the characteristics to get deep knowledge of the power supply structure and characteristics of the power utilization area; the power supply load component characteristics are visually displayed in a chart, a graph and other modes, so that better understanding and analysis of data are facilitated; visual display helps to intuitively reveal the distribution and change of the power supply load.
Through the implementation mode, the step S2 can provide comprehensive understanding of the power supply load component characteristics of the power utilization area, necessary data support is provided for subsequent deep peak shaving prediction, the characteristics are helpful for constructing and training a prediction model, the accuracy and reliability of prediction are improved, and in the field of deep peak shaving of coal-fired power plants, the implementation of the step is helpful for better coping with fluctuation of new energy power generation, and the stability and reliability of a power system are improved.
For step S3:
step S3 is one of key steps in a coal-fired power plant depth peak shaving prediction method based on time sequence analysis, and is mainly used for acquiring historical climate information within the same time as the power supply load component characteristics of a power consumption area, and the implementation of the step is important for improving the accuracy and reliability of a prediction model, and the specific implementation mode is as follows:
ensuring that the selected time range covers the time period to be predicted and is matched with the time range of the power supply load component characteristics of the power utilization area, thereby being beneficial to establishing accurate time sequence association and ensuring that the historical climate information can effectively reflect future meteorological conditions;
ensuring that the selected meteorological data source is reliable, accurate and has wide application; the data provided by the mechanisms such as a weather bureau, a weather observation station and the like are more reliable; selecting a meteorological site closer to the electricity utilization area to ensure that meteorological data better reflects meteorological conditions of the electricity utilization area;
Collecting required meteorological data including, but not limited to, temperature, humidity, precipitation, wind speed, wind direction, etc. according to the selected data sources, which will become input features for model training, helping the model to better understand the influence of meteorological factors on the power system;
before using the meteorological data, carrying out necessary preprocessing work, including processing missing values, interpolating and filling, removing abnormal values, smoothing data and the like; preprocessing helps to ensure the quality of the input data, avoiding erroneous predictions of the model due to low quality data.
Through the implementation manner, step S3 can acquire the historical climate information within the same time as the power supply load component characteristics of the power utilization area, and provide necessary data support for the subsequent deep peak shaving prediction; these climate information will be used to train the predictive model, improving the accuracy and reliability of the predictions; in the field of deep peak regulation of coal-fired power plants, the implementation of the step is beneficial to better coping with fluctuation of new energy power generation capacity and improving stability and reliability of a power system.
For step S4:
step S4 plays a vital role in a coal-fired power plant depth peak shaving prediction method based on time sequence analysis, and relates to the extraction of climate factors influencing the power generation efficiency of various power generation modes from historical climate information so as to form climate characteristics of a power utilization area; the implementation of this step helps to improve the accuracy and reliability of the prediction model, and the specific implementation modes are as follows:
S41, determining climate factors influencing the power generation efficiency: correlating with meteorological data over a corresponding period of time by analyzing historical power generation data, particularly the yields of wind power generation, photovoltaic power generation and hydroelectric power generation; using a statistical method or a machine learning technology to determine which meteorological factors have significant influence on the efficiency of different power generation modes; determining main climate factors influencing the power generation efficiency of various power generation modes according to the knowledge and experience of the power industry; such factors include temperature, humidity, precipitation, wind speed, wind direction, etc., which are closely related to the efficiency of power generation modes such as wind power generation, photovoltaic power generation, hydroelectric power generation, etc.;
s42, extracting climate data: extracting relevant climate data in the same time range as the power supply load component characteristics of the power utilization area from the historical climate data obtained in the step S3; the accuracy and consistency of the data are ensured, and mismatch of time ranges is avoided;
s43, feature extraction: extracting key features from the processed climate data according to the determined climate factors; these features will be used to describe the climate conditions of the electricity usage area and affect the efficiency of the electricity generation means; for example, statistical features such as average value, maximum value, minimum value and the like can be extracted from data such as temperature, humidity, precipitation and the like;
S44, feature integration: integrating the extracted climate characteristics with power supply load component characteristics of the power utilization area and historical power utilization load information; ensuring the consistency of time dimension among the features so as to carry out subsequent learning training and prediction;
s45, feature selection and optimization: according to actual requirements and data characteristics, selecting proper characteristics for learning and training; the feature is required to be subjected to pretreatment operations such as normalization, standardization and the like so as to improve the generalization capability and accuracy of the model; meanwhile, the features are optimized according to actual conditions, the features with redundancy or weak correlation are removed, and the features with large contribution to the prediction model are reserved.
Through the implementation manner, step S4 can extract climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to form climate characteristics of a power utilization area; these features will be used to train the deep learning model, improving the accuracy and reliability of the predictions; in the field of deep peak regulation of coal-fired power plants, the implementation of the step is helpful for more accurately predicting the generated energy and the required quantity of the power system, so that the dispatching plan is optimized and the stable operation of the power system is ensured.
For step S5:
In step S5, the input of the electricity consumption region electricity consumption load prediction model is the climate characteristic of the electricity consumption region, and the output of the electricity consumption region electricity consumption load prediction model is the electricity consumption load of the electricity consumption region; the input of the power consumption region power supply load component prediction model is the climate characteristic of the power consumption region, and the output of the power consumption region power supply load component prediction model is the power consumption region power supply load component characteristic;
the power utilization area power utilization load prediction model is used for predicting the total power utilization load of a specific power utilization area in a future period of time; the input of the model is the climate characteristics of the electricity consumption area, including factors such as temperature, humidity, wind speed and the like, because the factors can directly influence the use conditions of people on equipment such as air conditioning, heating and the like; the output of the model is the electricity load of the corresponding electricity utilization area at a future time point; this helps the power system planner to better understand future load demands, effectively configuring the power generation resources and the grid;
the power consumption region power supply load component prediction model aims at predicting the power supply quantity contributed by different types of power generation modes of a specific power consumption region in a future period of time; the input of the model still comprises the climate characteristics of the electricity consumption area, because the climate also has an effect on the operation of different types of electricity generation modes, for example, the efficiency of solar energy and wind energy electricity generation under different climate conditions can be different; the output of the model is the electric power quantity provided by different power generation modes at the future time point of the power utilization area; this helps the power system planner to learn more about future load compositions in order to better tune and manage the power system.
More specifically, the power consumption region power consumption load prediction model and the power consumption region power supply load component prediction model are built by training through a deep learning platform, and the power consumption region power consumption load prediction model is built by taking the power consumption region power consumption load prediction model as an example, and the power consumption region power consumption load prediction model is built by the following method:
s51, integrating the climate characteristics of the power utilization area extracted in the step S4 with the historical power utilization load information of the corresponding power utilization area to form a large data set; each row in the dataset represents a time node containing climate characteristics (e.g., temperature, humidity, wind speed, etc.) and corresponding electrical load for that time node;
s52, dividing the data set into a training set and a testing set, wherein the training set is used for training a model, and the testing set is used for evaluating the performance of the model; typically, the ratio of training set to test set is 70%:30%;
s53, carrying out necessary preprocessing on the data, including missing value filling, outlier processing, feature scaling and the like; for example, for continuous features such as temperature, humidity, etc., normalization processing may be performed; for classification features, one-Hot Encoding (One-Hot Encoding) may be performed;
s54, selecting a proper deep learning model for training; common models include long and short term memory networks (LSTM), recurrent Neural Networks (RNN), etc.; the models can capture long-term dependency in time series data, and are suitable for prediction of electricity load;
S55, inputting the training set into a deep learning model for training; setting proper super parameters such as learning rate, batch size, training wheel number and the like to optimize the performance of the model; during training, optimization algorithms (e.g., adam) may be used to minimize prediction errors; evaluating the trained model by using a test set, and calculating indexes such as prediction error, accuracy and the like to evaluate the performance of the model; common evaluation metrics include Mean Square Error (MSE) and Root Mean Square Error (RMSE); optimizing the model according to the evaluation result, such as adjusting super parameters, changing model architecture and the like, so as to improve the prediction precision and generalization capability of the model;
s56, model deployment: deploying the trained electricity load prediction model of the electricity utilization area into an actual power system to perform real-time prediction; and (3) inputting the climate characteristics of the electricity consumption area of the predicted time node obtained in the step (S6) into a model for calculation to obtain an electricity consumption load predicted value of the electricity consumption area at the predicted time node.
In the step, the deep learning platform is used for learning and training the climate characteristics of the electricity consumption area, a more accurate electricity consumption load prediction model and a more accurate electricity consumption load component prediction model of the electricity consumption area can be constructed, and the models can better capture the nonlinear relation between the characteristics of the electricity consumption load and the electricity consumption load component and the climate factors, so that the prediction accuracy is improved, the influence of climate change on the electricity consumption load and the electricity consumption load component can be better reflected in the prediction model, and a power system planner is helped to more accurately predict the future electricity demand and the electricity generation capacity, so that the power generation resources and the power grid are better configured;
The model constructed by the deep learning platform can be used for carrying out real-time prediction, and future power consumption load and power supply load components can be predicted according to current and historical climate information, so that the power system can better cope with emergency, the stability and reliability of the power system are improved, and the model training and prediction can be carried out by the deep learning platform, so that the automatic and intelligent power load prediction can be realized, the manual intervention can be reduced, the working efficiency can be improved, and the digital transformation of the power industry can be promoted;
in summary, step S5 performs model training and prediction through the deep learning platform, so as to improve prediction accuracy, consider historical climate information, perform real-time prediction, have advantages of expandability, realizing automation and intellectualization, and the like, which is helpful to better cope with fluctuation of new energy power generation, optimize resource allocation, and improve stability and reliability of the power system.
For step S6:
in the coal-fired power plant depth peak shaving prediction method based on time sequence analysis, the method is used for acquiring climate characteristics of a power utilization area of a prediction time node, inputting the characteristics into a power utilization load prediction model of the power utilization area and a power supply load component prediction model of the power utilization area so as to predict the power utilization load and the power supply load component characteristics of the power utilization area at the prediction time node, and comprises the following specific steps:
S61, acquiring climate characteristics of a power utilization area of a prediction time node: selecting a proper time node as a prediction target according to actual requirements and data characteristics, and acquiring the climate characteristics of the electricity utilization area of the time node from a related data source, wherein the climate characteristics are as described in the step S4;
s62, inputting climate characteristics of the electricity utilization area into an electricity utilization load prediction model of the electricity utilization area: inputting the acquired climate characteristics of the electricity utilization area of the prediction time node into an electricity utilization load prediction model of the electricity utilization area obtained by training in the step S5, wherein the model can predict future electricity utilization load according to current and historical climate information by learning the relation between the historical climate characteristics and the electricity utilization load, and obtaining an electricity utilization load prediction value of the electricity utilization area at the prediction time node through model calculation;
s63, inputting climate characteristics of the electricity utilization area into an electricity utilization area power supply load component prediction model: and (3) inputting the acquired climate characteristics of the power consumption region of the prediction time node into a power consumption region power supply load component prediction model obtained by training in the step (S5), wherein the model can learn the relation between the historical climate characteristics and the power supply load components, predict future power supply load components according to the current and historical climate information, and obtain the power supply load component characteristics of the power consumption region at the prediction time node through model calculation, wherein the power supply load component characteristics comprise the power quantity provided by each power generation mode.
Step S6 is to obtain the climate characteristics of the electricity consumption area of the prediction time node in real time, input the climate characteristics into an electricity consumption load prediction model of the electricity consumption area and a power supply load component prediction model, and realize real-time, accurate, extensible, automatic and intelligent power prediction.
For step S7:
step S7, calculating the power supply quantity of the coal-fired power plant at a predicted time node, wherein the power load of a power utilization area at the predicted time node and the power supply load component characteristics of the power utilization area at the predicted time node are combined; the specific calculation mode is as follows:
receiving the climate characteristics of the electricity consumption region of the predicted time node by an electricity consumption region electricity consumption load prediction model through a deep learning platform; the electricity consumption load prediction model of the electricity consumption region predicts the total electricity consumption load of the electricity consumption region at a prediction time node by learning the relation between the historical electricity consumption load information and the climate characteristics;
the power consumption region climate characteristic and the power consumption load component characteristic of the prediction time node are received by the power consumption region power consumption load component prediction model through the deep learning platform; the power consumption area power supply load component prediction model learns the relation between historical power consumption load component information and climate characteristics, and predicts each power supply load component of the power consumption area at a prediction time node, wherein the power supply load component comprises wind power generation load, photovoltaic power generation load and hydroelectric power generation load;
The output of the two models, namely the total power consumption load of the power consumption area at the predicted time node and the components of each power supply load, are utilized; the power load of the power supply area at the predicted time node is equal to the generated energy of the coal-fired power plant plus the generated energy (wind power, photovoltaic and hydraulic power) of other new energy sources; therefore, the power supply amount of the coal-fired power plant at the predicted time node can be calculated by the following formula:
wherein,representing the power supply quantity of the coal-fired power plant at the ith prediction time node; w (W) t i Representing an electricity load in an electricity utilization area of the ith prediction time node; />Representing wind power generation load at the i-th predicted time node; />Representing a photovoltaic power generation load at an ith predicted time node; />Representing the hydro-power generation load at the ith predicted time node;
according to the calculation, step S7 outputs the power generation load of the coal-fired power plant at the predicted time node, and the power generation load can be used for making a scheduling plan, so that the stable operation of the power system under the condition of new energy fluctuation is ensured, and the deep peak shaving capacity is improved.
In the step, the climate characteristics, the electricity load and different power supply load components (wind power, photovoltaic, hydraulic power and the like) of the electricity utilization area are considered, so that the calculation is more comprehensive, and the actual situation can be reflected more accurately; by obtaining the power generation load of the coal-fired power plant at the predicted time node, a more effective scheduling plan can be formulated, the stable operation of the power system under the condition of new energy fluctuation is ensured, and the deep peak shaving capacity is improved; and step S7, prediction and adjustment are performed by comprehensively considering various factors, so that the accuracy, the dynamic property, the integrity, the flexibility and the expandability of prediction are improved, more reasonable scheduling plans are formulated, and the stable operation of the power system and the access and the management of new energy are ensured.
As shown in fig. 2 and 3, the embodiment of the invention provides a coal-fired power plant depth peak shaving prediction device based on time sequence analysis. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 2, a hardware architecture diagram of an electronic device where a depth peak regulation prediction device of a coal-fired power plant is located according to an embodiment of the present invention is shown, where in addition to a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 2, the electronic device where the device is located may generally include other hardware, such as a forwarding chip responsible for processing a message, and so on. Taking a software implementation as an example, as shown in fig. 3, the device in a logic sense is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of an electronic device where the device is located and running the computer program.
As shown in fig. 3, the depth peak shaving prediction device for a coal-fired power plant based on time series analysis provided in this embodiment includes:
the data collection module is used for collecting historical electricity load information and historical power supply load information of an electricity utilization area;
The power component analysis module is used for carrying out power component analysis on the collected historical power supply load information to obtain power supply load component characteristics of a power consumption area, wherein the power supply load component characteristics of the power consumption area comprise power supply load types and power supply amounts of the power supply load types, and the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
the historical climate information acquisition module is used for acquiring historical climate information in the same time as the power supply load component characteristics of the power utilization area;
the climate factor extraction module is used for extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area, wherein the climate characteristics of the power utilization area are respectively in one-to-one correspondence with power supply load component characteristics of the power utilization area and the historical power utilization load information in the time dimension;
the deep learning platform module is used for receiving the climate characteristics of the power utilization area and the corresponding historical power utilization load information of the power utilization area and carrying out learning training to obtain a power utilization load prediction model of the power utilization area; receiving climate characteristics of the electricity consumption area and power supply load component characteristics of the electricity consumption area, and performing learning training to obtain a power supply load component prediction model of the electricity consumption area;
The prediction module acquires climate characteristics of a power utilization area of a prediction time node, sequentially inputs the climate characteristics of the power utilization area of the prediction time node into a power utilization area power utilization load prediction model and a power supply load component prediction model, and outputs power utilization load and power supply load component characteristics of the power utilization area at the prediction time node;
and the power supply quantity calculation module is used for calculating and obtaining the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load and the power supply load component characteristics of the power consumption area at the predicted time node.
In the embodiment, the device comprehensively considers the power supply load component characteristics of the power utilization area and the climatic factors influencing the efficiency of the power generation mode through the power component analysis module and the climatic factor extraction module, so that the complexity and the dynamics of the power system can be more comprehensively understood; the device utilizes the historical power load information, the historical power supply load information and the historical climate information to carry out detailed historical data analysis through the data collection module and the historical climate information acquisition module, thereby being beneficial to establishing a more accurate model and improving the prediction accuracy; the power consumption load prediction model and the power supply load component prediction model of the power consumption region are obtained through learning and training, the deep learning model can capture nonlinear relations, the method is suitable for complex power system changes, and compared with a traditional statistical method, the method improves prediction accuracy. The climate characteristics of the electricity consumption region of the predicted time node are input into the electricity consumption region electricity consumption load prediction model and the power supply load component prediction model, so that personalized prediction of the electricity consumption region at different time nodes is realized, the requirements of deep peak regulation are met better, and the peak regulation capacity of the thermal power unit is improved; the combination of the prediction module and the power supply amount calculation module enables the power supply amount of the coal-fired power plant to be calculated in real time at a prediction time node, is beneficial to making a more reasonable scheduling plan, and ensures the stable operation of a power system; by means of deep prediction of new energy power generation amount fluctuation, adaptability of the thermal power generating unit to new energy fluctuation is improved, and stability of the power system is enhanced. In general, the coal-fired power plant deep peak shaving prediction device based on time sequence analysis comprehensively considers various factors such as historical data, climate factors, power supply load components and the like through the combination of the time sequence analysis and the deep learning model, so that accuracy and practicability of coal-fired power plant deep peak shaving prediction are improved, and effective guarantee is provided for stable operation of an electric power system.
It can be understood that the structure illustrated in the embodiment of the invention does not constitute a specific limitation of the coal-fired power plant depth peak shaving prediction device based on time series analysis. In other embodiments of the invention, a coal-fired power plant depth peaking prediction device based on time series analysis may include more or fewer components than illustrated, or may combine certain components, or may split certain components, or may have a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the device is based on the same conception as the embodiment of the method of the present invention, and specific content can be referred to the description in the embodiment of the method of the present invention, which is not repeated here.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the coal-fired power plant depth peak shaving prediction method based on time sequence analysis in any embodiment of the invention when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium is stored with a computer program, when the computer program is executed by a processor, the processor is caused to execute the coal-fired power plant depth peak shaving prediction method based on time sequence analysis.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
It is noted that relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The coal-fired power plant depth peak shaving prediction method based on time sequence analysis is characterized by comprising the following steps of:
collecting historical electricity load information and historical power supply load information of an electricity utilization area;
carrying out power component analysis on the historical power supply load information to obtain power supply load component characteristics of a power consumption area; the power consumption area power supply load component characteristics comprise power supply load types and power supply amounts of the power supply load types, wherein the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
acquiring historical climate information within the same time as the power supply load component characteristics of a power utilization area;
Extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area; the climate characteristics of the electricity utilization area are respectively in one-to-one correspondence with the power supply load component characteristics of the electricity utilization area and the historical electricity utilization load information of the electricity utilization area in the time dimension;
uploading the climate characteristics of the electricity utilization area and the corresponding historical electricity utilization load information of the electricity utilization area to a deep learning platform for learning and training to obtain an electricity utilization load prediction model of the electricity utilization area; uploading the climate characteristics of the electricity consumption region and the power supply load component characteristics of the electricity consumption region to a deep learning platform for learning and training to obtain a power supply load component prediction model of the electricity consumption region;
acquiring climate characteristics of a power utilization area of a prediction time node, and respectively inputting the climate characteristics of the power utilization area of the prediction time node into a power utilization load prediction model of the power utilization area and a power supply load component prediction model of the power utilization area to obtain power utilization load characteristics of the power utilization area at the prediction time node and power supply load component characteristics of the power utilization area at the prediction time node;
and calculating to obtain the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load of the power consumption area at the predicted time node and the power supply load composition characteristics of the power consumption area at the predicted time node.
2. The coal-fired power plant depth peak shaving prediction method based on time series analysis as set forth in claim 1, wherein a calculation formula of the power supply amount of the coal-fired power plant at the predicted time node is:
wherein,representing the power supply quantity of the coal-fired power plant at the ith prediction time node; w (W) t i Representing an electricity load in an electricity utilization area of the ith prediction time node; />Representing wind power generation load at the i-th predicted time node; />Representing a photovoltaic power generation load at an ith predicted time node; />Representing the hydro-power generation load at the ith predicted time node.
3. The coal-fired power plant depth peaking prediction method based on time series analysis as claimed in claim 2, wherein the method for performing power component analysis on the historical power supply load information comprises the following steps:
analyzing the historical power supply load information by using a time sequence analysis method to obtain power supply load types;
carrying out electric quantity statistics on each power supply load, and calculating the power supply quantity of each power supply load;
and integrating the identified power supply load types and the counted power supply quantity to form power supply load component characteristics of the power utilization area.
4. The method for predicting deep peak shaver of coal-fired power plant based on time series analysis according to claim 3, wherein the method for extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information comprises the following steps:
Carrying out correlation analysis on the historical wind power generation load, the historical photovoltaic power generation load and the historical hydroelectric power generation load and meteorological data in corresponding time periods respectively, and determining climate factors influencing the power generation efficiency of various power generation modes;
extracting climate data within the same time range as the power supply load component characteristics of the power utilization area;
extracting key climate characteristics from climate data according to the determined climate factors;
and integrating the extracted climate characteristics with the power supply load component characteristics and the historical power consumption load information of the power consumption area to ensure the consistency of the time dimension among the characteristics.
5. The coal-fired power plant depth peak shaving prediction method based on time series analysis according to claim 4, wherein the construction method of the electricity consumption area electricity consumption load prediction model comprises the following steps:
integrating the climate characteristics of the power utilization area obtained by extraction and the historical power utilization load information of the corresponding power utilization area to form a data set;
dividing the data set into a training set and a testing set, wherein the training set is used for training a model, the testing set is used for evaluating the performance of the model, and the data set is preprocessed;
selecting a deep learning model capable of capturing the dependency relationship in the time series data for training; inputting the training set into a deep learning model for training, and evaluating the trained deep learning model by using the test set;
And deploying the trained electricity load prediction model of the electricity utilization area into an actual electric power system to perform real-time prediction.
6. The coal-fired power plant depth peaking prediction method based on time series analysis of claim 3, wherein the tools employed by the time series analysis method include an autoregressive model, a moving average model, an autoregressive moving average model, and an autoregressive integral moving average model.
7. The method for predicting deep peak shaver in coal-fired power plants based on time series analysis according to claim 4, wherein the climate factors affecting the power generation efficiency of various power generation modes include temperature, humidity, precipitation, wind speed and wind direction.
8. A coal-fired power plant depth peaking prediction device based on time series analysis, the device comprising:
the data collection module is used for collecting historical electricity load information and historical power supply load information of an electricity utilization area;
the power component analysis module is used for carrying out power component analysis on the collected historical power supply load information to obtain power supply load component characteristics of a power consumption area, wherein the power supply load component characteristics of the power consumption area comprise power supply load types and power supply amounts of the power supply load types, and the power supply load types comprise wind power generation loads, photovoltaic power generation loads and hydroelectric power generation loads;
The historical climate information acquisition module is used for acquiring historical climate information in the same time as the power supply load component characteristics of the power utilization area;
the climate factor extraction module is used for extracting climate factors affecting the power generation efficiency of various power generation modes from the historical climate information to obtain climate characteristics of a power utilization area, wherein the climate characteristics of the power utilization area are respectively in one-to-one correspondence with power supply load component characteristics of the power utilization area and the historical power utilization load information in the time dimension;
the deep learning platform module is used for receiving the climate characteristics of the power utilization area and the corresponding historical power utilization load information of the power utilization area and carrying out learning training to obtain a power utilization load prediction model of the power utilization area; receiving climate characteristics of the electricity consumption area and power supply load component characteristics of the electricity consumption area, and performing learning training to obtain a power supply load component prediction model of the electricity consumption area;
the prediction module acquires climate characteristics of a power utilization area of a prediction time node, sequentially inputs the climate characteristics of the power utilization area of the prediction time node into a power utilization area power utilization load prediction model and a power supply load component prediction model, and outputs power utilization load and power supply load component characteristics of the power utilization area at the prediction time node;
And the power supply quantity calculation module is used for calculating and obtaining the power generation load of the coal-fired power plant at the predicted time node according to the power consumption load and the power supply load component characteristics of the power consumption area at the predicted time node.
9. An electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and operable on the processor, the transceiver, the memory and the processor being connected by the bus, characterized in that the computer program when executed by the processor realizes the steps in the method according to any of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410007641.3A CN117833361A (en) | 2024-01-02 | 2024-01-02 | Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410007641.3A CN117833361A (en) | 2024-01-02 | 2024-01-02 | Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117833361A true CN117833361A (en) | 2024-04-05 |
Family
ID=90516969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410007641.3A Pending CN117833361A (en) | 2024-01-02 | 2024-01-02 | Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117833361A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365056A (en) * | 2020-11-12 | 2021-02-12 | 云南电网有限责任公司 | Electrical load joint prediction method and device, terminal and storage medium |
| CN116865236A (en) * | 2023-05-17 | 2023-10-10 | 山东国电投能源营销有限公司 | Medium-and-long-term power generation capacity prediction method and system based on new energy power generation |
| CN116914747A (en) * | 2023-09-06 | 2023-10-20 | 国网山西省电力公司营销服务中心 | Power consumer side load prediction method and system |
| CN117154690A (en) * | 2023-07-31 | 2023-12-01 | 国网山东省电力公司曲阜市供电公司 | Photovoltaic power generation power prediction method and system based on neural network |
-
2024
- 2024-01-02 CN CN202410007641.3A patent/CN117833361A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365056A (en) * | 2020-11-12 | 2021-02-12 | 云南电网有限责任公司 | Electrical load joint prediction method and device, terminal and storage medium |
| CN116865236A (en) * | 2023-05-17 | 2023-10-10 | 山东国电投能源营销有限公司 | Medium-and-long-term power generation capacity prediction method and system based on new energy power generation |
| CN117154690A (en) * | 2023-07-31 | 2023-12-01 | 国网山东省电力公司曲阜市供电公司 | Photovoltaic power generation power prediction method and system based on neural network |
| CN116914747A (en) * | 2023-09-06 | 2023-10-20 | 国网山西省电力公司营销服务中心 | Power consumer side load prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mavromatidis et al. | Design of distributed energy systems under uncertainty: A two-stage stochastic programming approach | |
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| Pinson et al. | Wind power forecasting using fuzzy neural networks enhanced with on-line prediction risk assessment | |
| Lin et al. | Reliability based power systems planning and operation with wind power integration: A review to models, algorithms and applications | |
| Kang et al. | Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters | |
| CN110717688A (en) | Water, wind and light short-term combined optimization scheduling method considering new energy output uncertainty | |
| Santos et al. | Impacts of operational variability and uncertainty on distributed generation investment planning: A comprehensive sensitivity analysis | |
| Alimou et al. | Assessing the security of electricity supply through multi-scale modeling: The TIMES-ANTARES linking approach | |
| CN108155674B (en) | Water, fire and electricity combined dispatching method and system considering uncertain distribution characteristics | |
| Bylling et al. | The impact of short-term variability and uncertainty on long-term power planning | |
| CN116914747B (en) | Power consumer side load prediction method and system | |
| CN116128167B (en) | Distributed photovoltaic power generation analysis method based on cloud computing real-time monitoring | |
| CN117013527A (en) | Distributed photovoltaic power generation power prediction method | |
| Chen et al. | Toward future information market: An information valuation paradigm | |
| CN116502771B (en) | Power distribution method and system based on electric power material prediction | |
| Hilbers et al. | Importance subsampling for power system planning under multi-year demand and weather uncertainty | |
| Meibom et al. | Wind power integration studies using a multi-stage stochastic electricity system model | |
| CN117833361A (en) | Coal-fired power plant depth peak shaving prediction method and device based on time sequence analysis | |
| Pérez-Vilarelle et al. | Modeling and simulation of wind energy production in the smart-grid scenario | |
| Holttinen et al. | Recommendations for wind integration studies | |
| Bagchi | Power system adequacy and cost/worth assessment incorporating virtual power plants | |
| Mantri et al. | Solar Power Generation Prediction for Better Energy Efficiency using Machine Learning | |
| Dogan et al. | Monte Carlo sampling vs. discrete forecast error scenarios in grid reliability assessment for short-term planning | |
| CN116979529B (en) | Power load evaluation method, system, equipment and storage medium | |
| Weerasinghe et al. | Modelling and forecasting the unit cost of electricity generated by fossil fuel power plants in Sri Lanka |
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 |