CN115313355A - Automatic prediction method and system for big data of smart power grid in short-term load prediction - Google Patents
Automatic prediction method and system for big data of smart power grid in short-term load prediction Download PDFInfo
- Publication number
- CN115313355A CN115313355A CN202210725298.7A CN202210725298A CN115313355A CN 115313355 A CN115313355 A CN 115313355A CN 202210725298 A CN202210725298 A CN 202210725298A CN 115313355 A CN115313355 A CN 115313355A
- Authority
- CN
- China
- Prior art keywords
- short
- load
- data
- prediction
- day
- 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
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an automatic prediction method and system of smart grid big data in short-term load prediction, which are used for obtaining historical operating data of a smart grid power load in a target area and corresponding load type, weather condition, date type and social event and constructing an original data set; preprocessing an original data set to obtain time sequence data; constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data; inputting the load type, weather condition, date type, social event and power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day; the method and the device have the advantages that the influence of various related factors on the load characteristic change is refined, the sensitivity and the adaptability of the prediction model to the power load sudden change event are improved, the robustness of the prediction method is ensured, and the accuracy of the load prediction in a short period is greatly improved.
Description
Technical Field
The invention belongs to the field of power load prediction, and particularly relates to an automatic prediction method and system for big data of a smart power grid in short-term load prediction.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The smart power grid is a novel power grid of the modern society, and 6 modern advanced technologies are adopted: the control technology, the communication technology, the sensing measurement technology, the computer technology, the information technology and the physical power grid technology are highly integrated in a backbone grid frame of the extra-high voltage power grid and are matched with power grids of various voltage levels to develop in a coordinated mode to form a novel power grid.
The intelligent analysis of the massive heterogeneous data generated by the smart grid is very important for the construction, maintenance and management of the smart grid, wherein the short-term load prediction is the most important, such as the short-term load prediction of one hour to one week, and can provide data support for a power generation plan to determine the power generation plan which most meets the economic requirements, safety requirements, environmental natural requirements and equipment limitation requirements, so as to ensure the economic and safe operation of a power system.
In recent years, with the relative maturity of key technologies such as cloud computing and big data, the global big data technology is greatly improved, but it is to be understood that there is still a relatively large development space in short-term load prediction, and how to further refine, deepen and perfect the application of the big data technology in short-term power load prediction still faces a series of challenges.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an automatic prediction method and system for big data of a smart power grid in short-term load prediction, which introduces the load type, the weather condition, the date type and the social event factors into the load prediction, refines the influence of a plurality of related factors on the load characteristic change, improves the sensitivity and adaptability of a prediction model to the power load sudden change event, ensures the robustness of the prediction method and greatly improves the accuracy of the load prediction in a short term.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the invention provides an automatic prediction method of big data of a smart power grid in short-term load prediction;
an automatic prediction method of smart grid big data in short-term load prediction comprises the following steps:
acquiring short-term historical operating data of the smart grid power load in a target area, and corresponding load type, weather condition, date type and social event, and constructing an original data set;
preprocessing an original data set to obtain time sequence data;
constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
Further, the load types include commercial power, industrial power, residential power, and agricultural power;
the weather conditions comprise temperature, humidity and wind speed;
the date type comprises seasons, whether the date is a working day, whether the date is a rest day and a legal holiday;
the social events comprise natural disasters, accident disasters, social security events and social health events.
Further, the preprocessing comprises removing abnormal data and invalid data, filling missing values, standardizing and normalizing, and converting formats.
Further, the format conversion is to combine the power load value, the load type, the weather condition, the date type and the social event of each day into a day vector, and construct time series data according to the time sequence of the day vector.
Further, the short-term load prediction model takes the power load value, the load type, the weather condition, the date type and the social event as input, and takes the power load value as output.
Further, the time sequence data are divided into training sets and testing sets, the number of the training sets accounts for 2/3 of the number of the time sequence data, and the number of the testing sets accounts for 1/3 of the number of the time sequence data.
Further, the specific process of training the short-term load prediction model is as follows:
training a short-term load prediction model by taking the power load value of the current day as an output and taking the power load value of the previous day and the load type, the weather condition, the date type and the social event of the current day as inputs in a training set;
and testing the short-term load prediction model after training by using the test set, and calculating the error of the short-term load prediction model until the short-term load prediction model which is qualified in testing is obtained.
The invention provides an automatic prediction system of smart grid big data in short-term load prediction.
An automatic prediction system of smart grid big data in short-term load prediction comprises a data acquisition module, a preprocessing module, a model building module and a prediction module;
a data acquisition module configured to: acquiring short-term historical operating data of a smart grid power load in a target area and corresponding load types, weather conditions, date types and social events, and constructing an original data set;
a pre-processing module configured to: preprocessing an original data set to obtain time sequence data;
a model building module configured to: constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
a prediction module configured to: and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
The third aspect of the present invention provides a computer readable storage medium, on which a program is stored, which when executed by a processor, implements the steps in the automatic prediction method of smart grid big data in short-term load prediction according to the first aspect of the present invention.
A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the method for automatically predicting short-term load of smart grid big data according to the first aspect of the present invention.
The above one or more technical solutions have the following beneficial effects:
the invention provides an automatic prediction method and system for smart grid big data in short-term load prediction, which introduces load type, weather condition, date type and social event factors into the load prediction, further enhances the refined processing analysis of each factor in the power load prediction through big data technology, such as enhancing the analysis of the influence of meteorological factors on power load, enhancing the analysis of load characteristics of special dates and enhancing the identification and analysis of various load types of a power system, thus the influence of various related factors on the load characteristic change can be refined, the charge change rule of each area and each local area can be more easily mastered, the development trend of the charge change rule can be found, the sensitivity and adaptability of a prediction model to power load sudden change events can be improved, the robustness of the prediction method can be ensured, and the accuracy of the load prediction in a short period can be greatly improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of a method of the first embodiment;
FIG. 2 is a diagram illustrating a short term load prediction model according to a first embodiment;
fig. 3 is a system configuration diagram of the second embodiment.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present disclosure; as used herein, the singular is intended to include the plural unless the context clearly dictates otherwise, and furthermore, it should be understood that the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
In the power load prediction, a nonlinear relation exists between weather and a power load value, so that in the short-term load prediction, the weather factor can be considered, and the neural network technology has strong multi-nonlinear capturing and mapping capacity, can accurately acquire and analyze the relation between the weather and the power load value, and can more intuitively reflect the relation between the weather, the temperature and the like and the power load, so that the load type, the weather condition, the date type and the social event factor are introduced into the load prediction, the influence of a plurality of related factors on the load characteristic change is refined, and the accuracy of the load prediction in a short term is greatly improved.
Example one
The embodiment discloses an automatic prediction method of smart grid big data in short-term load prediction;
as shown in fig. 1, an automatic prediction method of smart grid big data in short-term load prediction includes:
s1: acquiring short-term historical operating data of a smart grid power load in a target area and corresponding load types, weather conditions, date types and social events, and constructing an original data set;
the load types comprise commercial power consumption, industrial power consumption, residential power consumption and agricultural power consumption;
the weather conditions comprise temperature, humidity and wind speed;
the date type comprises season, whether the date is a working day, whether the date is a rest day and a legal holiday;
the social events comprise natural disasters, accident disasters, social security events and social health events.
The date type is composed of three-bit strings composed of numbers, wherein the first bit represents the season, and the spring, summer, autumn and winter are respectively represented by 0, 1,2 and 3; the second represents the working day or the rest day, 1 is the working day, and 0 is the rest day; the third represents legal holidays, the illegal holiday-setting holidays are 0, and the Yuan Dan, the spring festival, the Qingming festival, the labor festival, the Dragon festival, the mid-autumn festival and the national day festival are respectively paired, 1-7; for example, "125" represents summer + weekday + morning festival.
In the social events, 0 is a natural disaster, 1 is an accident disaster, 2 is a social security event, and 3 is a social hygiene event.
Natural disasters including flood and drought disasters, meteorological disasters, earthquake disasters, geological disasters, marine disasters, biological disasters, forest and grassland fires and the like.
Accident disasters comprise various safety accidents, transportation accidents, public facility and equipment accidents, nuclear radiation accidents, environmental pollution, ecological destruction events and the like of enterprises such as industrial, mining, commerce and trade and the like.
Public health incidents including epidemic diseases, mass unexplained diseases, food safety and occupational hazards, animal epidemics and other incidents that seriously affect public health and life safety, such as pneumonia epidemics, are public health incidents.
Social security incidents include economic security incidents, foreign-related emergencies, group emergencies, and the like.
Acquiring information such as load data from a power grid energy management system EMS, for example, power loads of different load types every day in 20 years; and acquiring power grid influence factor data information such as weather data and the like, such as temperature, humidity and wind speed of each day from a meteorological office.
The power grid energy management system EMS can provide an interface for acquiring load data and acquire historical operating data of the power load through the data interface; the open data of weather can be acquired from a website of a weather bureau by adopting a web page data capturing mode such as web crawlers.
S2: preprocessing an original data set to obtain time sequence data;
the acquired original data has some special cases, and in order to reduce the influence on subsequent prediction and improve the accuracy of prediction, the acquired original data needs to be preprocessed.
The data captured by the web crawler may capture some abnormal data and invalid data due to the setting problem of the capture strategy, such as html codes in the wind speed "1.6m/s < br/>", invalid temperatures in the temperature "90 °", and captured messy codes, and the specific processing method is as follows: the abnormal data and the invalid data are directly removed and then filled with default values, and the default values can be set as the average value of a certain stage, such as the default value of the temperature, and set as the average air temperature of a specific season.
The problem that units and calculation modes are not uniform possibly exists in data collected from multiple places, and the data are subjected to standardization processing and normalization processing to obtain data with uniform standards.
And (3) converting the format of the preprocessed standard data to obtain time series data, wherein the specific method comprises the following steps: and (3) forming a day vector by the power load value, the load type, the weather condition, the date type and the social event of each day, and constructing time sequence data according to the time sequence of the day vector.
S3: constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
FIG. 2 is a schematic diagram of a short-term load prediction model, in which an input layer has n neurons, a hidden layer has p neurons, an output layer has m neurons, and the weight between the ith neuron of the input layer and the jth neuron of the hidden layer can be represented by ω ij (i =1,2.., n, j =1,2.., n, j, p) to denote that the weight between the jth neuron of the hidden layer and the kth neuron of the output layer may use ω jk (j =1,2.., p, k =1,2.., m).
In the use of the short-term load prediction model, the following parameters are mainly included: the number of input layer neurons, the number of hidden layers, the number of neurons of each hidden layer, the number of output layer neurons, the weight between the input layer neurons and the hidden layer neurons, the weight between the hidden layer neurons and the output layer neurons, and parameters such as learning rate, error rate, iteration times and the like during model training.
In the load prediction of this embodiment, the load values, specifically, the power load value, the load type, the weather condition, the date type, and the social event are predicted by the weather, the date, the social event, so the number of neurons in the input layer is 5, which are the power load value, the load type, the weather condition, the date type, and the social event, respectively, the number of layers of the hidden layer is not limited, and the number of neurons in the output layer is 1, which is the predicted load value.
Therefore, the short-term load prediction model is constructed by taking the power load value, the load type, the weather condition, the date type and the social event as input and taking the power load value as output.
And training the model by using a training set, and testing the trained model by using a testing set, so as to ensure that the prediction error rate of the model is within a reasonable range.
And dividing the previously obtained time sequence data into training sets and test sets, wherein the number of the training sets accounts for 2/3 of the number of the time sequence data, and the number of the test sets accounts for 1/3 of the number of the time sequence data.
And training a short-term load prediction model by taking the power load value of the previous day and the load type, the weather condition, the date type and the social event of the current day as input and the power load value of the current day as output in the training set, and training the current neural network model by using the data in the training set.
And testing the short-term load prediction model after training by using the test set, calculating the error of the short-term load prediction model, checking the prediction accuracy of the current neural network model, and if the prediction accuracy of the current neural network model meets the expected requirement, directly using the current neural network model for prediction, thereby ensuring the prediction accuracy. If the error is larger than the error threshold value, continuing training the current neural network model, adjusting the weight value in the current neural network model, specifically, firstly obtaining unused data in a training set, continuing training the neural network model, taking the trained neural network model as the current neural network model, and continuing verifying the test set until the error meets the requirement.
S4: and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
Since the daily load value is in a continuous relationship and usually varies depending on the season, weather, holidays, and emergencies, the load value in the case of a specific load type, weather condition, date type, and social event is predicted based on the power load value in the previous day.
Acquiring load data, namely a load type and a load value, of a day before a forecast day from a power grid energy management system EMS, and acquiring weather conditions, namely temperature, humidity and wind speed, of a next day (the forecast day) from a meteorological office in advance; calculating the date type (season, whether the date is a working day, whether the date is a rest day and legal holidays) through an algorithm; and continuously using the social event data of the previous day, inputting the data into a trained short-term load prediction model, and outputting a load value which is a final power load prediction value of the prediction day.
Example two
The embodiment discloses an automatic prediction system of smart grid big data in short-term load prediction;
as shown in fig. 3, an automatic prediction system for smart grid big data in short-term load prediction includes a data acquisition module, a preprocessing module, a model construction module, and a prediction module;
a data acquisition module configured to: acquiring short-term historical operating data of the smart grid power load in a target area, and corresponding load type, weather condition, date type and social event, and constructing an original data set;
a pre-processing module configured to: preprocessing an original data set to obtain time sequence data;
a model building module configured to: constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
a prediction module configured to: and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
EXAMPLE III
An object of the present embodiment is to provide a computer-readable storage medium.
The computer readable storage medium stores thereon a computer program, which when executed by a processor implements the steps in the automatic prediction method of smart grid big data in short-term load prediction according to embodiment 1 of the present disclosure.
Example four
An object of the present embodiment is to provide an electronic device.
The electronic device comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the automatic prediction method of the smart grid big data in the short-term load prediction according to embodiment 1 of the disclosure.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. An automatic prediction method of smart grid big data in short-term load prediction is characterized by comprising the following steps:
acquiring historical operating data of a smart grid power load in a target area and corresponding load types, weather conditions, date types and social events, and constructing an original data set;
preprocessing an original data set to obtain time sequence data;
constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
2. The method for automatically predicting the short-term load forecast of the big data of the smart grid as recited in claim 1, wherein said load types comprise commercial power utilization, industrial power utilization, residential power utilization and agricultural power utilization;
the weather conditions comprise temperature, humidity and wind speed;
the date type comprises season, whether the date is a working day, whether the date is a rest day and a legal holiday;
the social events comprise natural disasters, accident disasters, social security events and social health events.
3. The method as claimed in claim 1, wherein the preprocessing includes removing abnormal data and invalid data, filling missing values, normalizing and normalizing, and format conversion.
4. The method for automatically predicting the short-term load of the smart grid big data according to claim 3, wherein the format conversion comprises the steps of forming a day vector by the power load value, the weather condition, the date type and the social event of each day, and forming time sequence data according to the time sequence of the day vector.
5. The method as claimed in claim 1, wherein the short-term load prediction model takes as input a power load value, a load type, a weather condition, a date type, a social event, and an output a power load value.
6. The method for automatically predicting the short-term load of the smart grid big data, as claimed in claim 1, wherein the time series data are divided into training sets and testing sets, the number of the training sets is 2/3 of the number of the time series data, and the number of the testing sets is 1/3 of the number of the time series data.
7. The method for automatically predicting the short-term load of the smart grid big data in the prediction of the short-term load according to claim 6, wherein the specific process of training the short-term load prediction model is as follows:
training a short-term load prediction model by taking the power load value of the current day as an output and taking the power load value of the previous day and the load type, the weather condition, the date type and the social event of the current day as inputs in a training set;
and testing the short-term load prediction model after training by using the test set, and calculating the error of the short-term load prediction model until the short-term load prediction model which is qualified in testing is obtained.
8. An automatic prediction system of smart grid big data in short-term load prediction is characterized in that: the system comprises a data acquisition module, a preprocessing module, a model construction module and a prediction module;
a data acquisition module configured to: acquiring short-term historical operating data of a smart grid power load in a target area and corresponding load types, weather conditions, date types and social events, and constructing an original data set;
a pre-processing module configured to: preprocessing an original data set to obtain time sequence data;
a model building module configured to: constructing a short-term load prediction model based on a memory neural network, and training the short-term load prediction model by using time series data;
a prediction module configured to: and inputting the load type, the weather condition, the date type, the social event and the power load value of the previous day of the forecast day into a trained short-term load forecast model to obtain a power load forecast value of the forecast day.
9. Computer-readable storage medium, on which a program is stored, which, when being executed by a processor, carries out the steps of a method for automatic prediction of smart grid big data in short-term load prediction according to any one of claims 1 to 7.
10. Electronic equipment comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method for automatic prediction of smart grid big data in short-term load prediction according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210725298.7A CN115313355A (en) | 2022-06-24 | 2022-06-24 | Automatic prediction method and system for big data of smart power grid in short-term load prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210725298.7A CN115313355A (en) | 2022-06-24 | 2022-06-24 | Automatic prediction method and system for big data of smart power grid in short-term load prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115313355A true CN115313355A (en) | 2022-11-08 |
Family
ID=83854841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210725298.7A Pending CN115313355A (en) | 2022-06-24 | 2022-06-24 | Automatic prediction method and system for big data of smart power grid in short-term load prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115313355A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829152A (en) * | 2022-12-21 | 2023-03-21 | 杭州易龙电安科技有限公司 | Power load prediction method, device and medium based on machine learning algorithm |
| 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 |
-
2022
- 2022-06-24 CN CN202210725298.7A patent/CN115313355A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829152A (en) * | 2022-12-21 | 2023-03-21 | 杭州易龙电安科技有限公司 | Power load prediction method, device and medium based on machine learning algorithm |
| CN115829152B (en) * | 2022-12-21 | 2023-07-07 | 杭州易龙电安科技有限公司 | Power load prediction method, device and medium based on machine learning algorithm |
| 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 |
| CN116914747B (en) * | 2023-09-06 | 2024-01-12 | 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 |
|---|---|---|
| AU2020101900A4 (en) | A method, device and equipment for detecting abnormal electric meter | |
| CN110807550B (en) | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment | |
| Du et al. | Power load forecasting using BiLSTM-attention | |
| CN115313355A (en) | Automatic prediction method and system for big data of smart power grid in short-term load prediction | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| Kang et al. | Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters | |
| CN106570581A (en) | Attribute association based load prediction system and method in energy Internet environment | |
| CN106228278A (en) | Photovoltaic power prognoses system | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN113743673B (en) | Power load prediction method during typhoon | |
| CN111091240A (en) | Public institution electric power energy efficiency monitoring system and service method | |
| Liu et al. | Photovoltaic generation power prediction research based on high quality context ontology and gated recurrent neural network | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN115469627B (en) | Intelligent factory operation management system based on Internet of things | |
| CN117977587B (en) | Power load prediction system and method based on deep neural network | |
| CN113505923A (en) | Regional power grid short-term load prediction method and system | |
| CN112183877A (en) | Photovoltaic power station fault intelligent diagnosis method based on transfer learning | |
| CN111027768A (en) | Data processing method and device and application platform | |
| CN115730749A (en) | Electric power dispatching risk early warning method and device based on fused electric power data | |
| CN115238854A (en) | Short-term load prediction method based on TCN-LSTM-AM | |
| Malik et al. | Multi-step ahead time-series wind speed forecasting for smart-grid application | |
| CN112911533B (en) | Temperature detection system based on remove end App | |
| Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
| CN116109018B (en) | Photovoltaic power station power prediction method, device and related equipment | |
| CN117113202A (en) | Power loop energy consumption detection method and equipment based on joint error stacking model |
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 |