CN111177278A - Grid user short-term load prediction real-time processing tool - Google Patents
Grid user short-term load prediction real-time processing tool Download PDFInfo
- Publication number
- CN111177278A CN111177278A CN201911318383.6A CN201911318383A CN111177278A CN 111177278 A CN111177278 A CN 111177278A CN 201911318383 A CN201911318383 A CN 201911318383A CN 111177278 A CN111177278 A CN 111177278A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- user
- time
- real
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000005065 mining Methods 0.000 abstract description 3
- 230000009466 transformation Effects 0.000 abstract description 3
- 238000010223 real-time analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 230000005611 electricity Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a grid user short-term load prediction real-time processing tool, which executes the following steps: step S1: automatically identifying a user or a power station; step S2: establishing a data warehouse; step S3: preprocessing, namely preprocessing load data, wherein abnormal load data comprise noise and missing values; step S4: standardization processing, namely performing linear transformation on the original data to enable the result to fall into a [0,1] interval; step S5: training a model and checking errors; step S6: and displaying the predicted data of the database on line. The invention adopts a big data ODPS engine and an artificial intelligence technology to process large-scale data, so as to realize real-time processing, real-time mining, real-time analysis, real-time learning and modeling and give a prediction result in real time.
Description
Technical Field
The invention belongs to the technical field of power informatization, and particularly relates to a load prediction technology.
Background
Due to the non-storable nature of electrical energy, the size and nature of the load can significantly affect the design and operation of the electrical power system. The load prediction of the power system can affect the abundance assessment, the power price formulation and the power utilization condition of users of the power system. Accurate power system load prediction can enhance the safety and reliability of the operation of the power supply network.
With the increasing of load randomness and uncertainty, the traditional method of purely relying on mechanism modeling is difficult to meet the requirement of prediction precision, a new solution needs to be explored, and with the development of scientific technology, the acquisition and processing cost of data is reduced year by year, and the acquisition of massive historical data becomes possible; with the development of the artificial intelligence technology, the data consumption capability of the model is gradually enhanced, and the rules contained in the data can be effectively learned by adopting a proper data driving model.
In the current society, along with the rapid development of sensor technology, real-time monitoring and data storage technology, the electric power data volume and complexity also increase exponentially, and the phenomenon is particularly prominent at the user side. How to dig the value of mass data at the user side and efficiently and reasonably apply the mass data becomes a problem to be solved urgently under the current smart grid era. The load prediction is based on the historical data of the power load, and the method is used for exploring the development law of the load by researching the relevance and the change condition of the load data, social conditions and the internal relation among other natural conditions (such as temperature, rainfall and wind speed), so as to predict the load data of a certain period of time in the future. The traditional load prediction method has difficulty in coping with larger data volume and stronger randomness.
(1) The precision is low. The load prediction has a plurality of influence factors, and the prediction accuracy is low because only the influence of a single variable on the load is considered. The traditional method cannot mine the influence on load change under multi-factor multivariable. A more refined load prediction model cannot be established.
(2) The efficiency is low. The traditional load prediction technology has long time for large-scale data processing and mining analysis and slow load prediction speed.
(3) The cost is high. In the traditional load prediction, a large amount of research work is required by experts, so that the cost is particularly high due to the dependence on a large amount of human and material resources.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a grid user short-term load prediction real-time processing tool, so that the load of the next several days can be predicted in real time based on an ODPS engine, and the prediction efficiency and accuracy are improved.
In order to solve the technical problems, the invention adopts the following technical scheme: a grid user short-term load prediction real-time processing tool executes the following steps:
step S1: automatically identifying a user or a power station, and automatically identifying the longitude and latitude and basic information of an area where the user or the power station is located according to the input user or the power station;
step S2: establishing a data warehouse, acquiring corresponding load historical data from the basic information of the user or the power station through a corresponding data interface to a marketing system, a power utilization information acquisition system and a distribution network system, acquiring local population density and economic condition data, acquiring corresponding historical weather condition and future weather condition forecast data from a weather station, and importing the data into an ODPS data warehouse;
step S3: preprocessing, namely preprocessing load data, wherein abnormal load data comprise noise and missing values;
step S4: normalization, linear transformation of the raw data to bring the result to [0,1]Interval, the transfer function is as follows:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
step S5: training a model and checking errors, judging whether the user or the power station is trained for the first time, if not, loading the stored training model, if so, randomly initializing a weight and a threshold matrix, then inputting a sample, performing training through short-term load prediction of a neural network, verifying whether the generated errors are in an allowed range, if so, storing model parameters and outputting results to a database, otherwise, correcting the weights through a dam optimizer, and repeating the execution until the conditions are met;
step S6: and displaying the predicted data of the database on line.
Preferably, a preprocessing model on a time series is established for the abnormal value types:
wherein y (t) represents the current load sequence, x (t) represents the load sequence without abnormal value, n is the number of abnormal values, ω I and α (j) represent the influence factors of the abnormal value of the load, and It(T) represents the pulse function at time T.
Preferably, for the missing value in the data warehouse, the average value of the loads at the same time points on two adjacent days and the loads at two time points before and after the current time is calculated according to the fluctuation cycle characteristics of the power load, and the load change rate method of the day before and after is used, and the missing value is filled by adding the load change amount to the average value.
Preferably, in step S5, the error is verified by a root mean square error and an average absolute error.
By adopting the technical scheme, the invention has the following beneficial effects:
(1) the influences of local weather conditions (temperature, cloud conditions, humidity and wind speed), local economic conditions, population density and other factors on the load are combined, a multi-factor multivariable load prediction refinement model is established, and the accuracy of load prediction is obviously improved.
(2) The large-scale data are processed by adopting a large-data ODPS engine and an artificial intelligence technology, so that real-time processing, real-time mining, real-time analysis, real-time learning and modeling are realized, and a prediction result is given in real time.
(3) The working mode of original personnel is changed, and the investigation workload of the personnel in the power system is greatly reduced. Part of daily manual work is finished by the tool by a computer, so that the prediction workload is remarkably reduced, the working efficiency is obviously improved, and the prediction cost is reduced.
The following detailed description of the present invention will be provided in conjunction with the accompanying drawings.
Drawings
The invention is further described with reference to the accompanying drawings and the detailed description below:
FIG. 1 is a flow chart of the operation of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention selects a certain user or power station as parameter input, and refers to a grid user short-term load prediction real-time processing tool shown in figure 1, and the following steps are executed:
in a first step, a user or a power station is automatically identified. And automatically identifying the longitude and latitude and the basic information of the area where the user or the power station is located according to the input user or power station by adopting an automatic identification algorithm.
For basic information, if the power station can identify the type of the power station (such as a thermal power station, a hydropower station, a photovoltaic power station and the like), capacity. If the user is the user, the user type (such as a special transformer user, a public transformer user and the like), the electricity utilization type (commercial electricity utilization, residential electricity utilization, industrial electricity utilization and the like) can be identified.
And secondly, establishing a data warehouse. And the basic information of the user or the power station is sent to a marketing system, a power utilization information acquisition system and a distribution network system through corresponding data interfaces to obtain corresponding load historical data. The marketing system acquires historical load data of users, and the electricity utilization information acquisition system acquires historical load data of the transformer substation and the power station. The data obtained is needed to be active and reactive. Meanwhile, local population density and economic condition data are obtained, and the data of the corresponding historical weather conditions and the temperature, wind direction, wind speed, humidity and the like forecasted by the future weather conditions are obtained by the weather-out bureau and are imported into an ODPS data warehouse.
And thirdly, preprocessing, namely preprocessing all the original data, active data, reactive data, temperature data, wind direction data, wind speed data, humidity data, population density data and economic condition data. Since the acquired data may be abnormal and the format of the data is not uniform, a preprocessing process is required. The abnormal load data mainly comprises noise and missing values, so a preprocessing model on a time sequence needs to be established for the abnormal value types:
wherein y (t) represents the current load sequence, x (t) represents the load sequence without abnormal value, n is the number of abnormal values, ω I and α (j) represent the influence factors of the abnormal value of the load, and It(T) represents the pulse function at time T. For the missing value in the data warehouse, according to the fluctuation cycle characteristic of the electric load, calculating the load of the same time point on the two adjacent days and the average value of the load of the two time points on the two adjacent days before and after the current time, and filling the missing value by adding the load variation quantity to the average value by a load variation rate method of the day before and after.
And fourthly, standardizing. And constructing a training sample set according to the input basic information of the user or the power station, corresponding historical load data and relevant data such as local population density, economic conditions, urbanization conditions, whether the data are holidays and the like. The training sample set is a set of data, i.e. a multidimensional array. That is, the data are arranged in time series, for example [ [0.87,0.67,0.87], [0.34,0.46,0.65], [0.75,0.67,0.87] ]. Such as [ active value array ], [ rainfall value array ], [ temperature value array ] ]).
And fifthly, carrying out standardization processing on the training sample set. In a multi-index evaluation system, the evaluation indexes are different in size and magnitude due to different properties. When the levels of the indexes are greatly different, if the original index values are directly used for analysis, the function of the indexes with higher numerical values in the comprehensive analysis is highlighted, and the function of the indexes with lower numerical levels is relatively weakened. Therefore, in order to ensure the reliability of the result, the raw index data needs to be standardized. I.e. a linear transformation of the original data, with the result falling to 0,1]Interval, the transfer function is as follows:
where max is the maximum value of the sample data and min is the minimum value of the sample data.
And sixthly, training a model and checking errors. And judging whether the user or the power station is trained for the first time, if not, loading the stored model, and if so, randomly initializing the weight and the threshold matrix. Then inputting a sample, training by short-term load prediction of a neural network, verifying whether the generated error is in an allowed range, if so, saving the model parameters and outputting the result to a database, otherwise, correcting the weight by a dam optimizer, and repeating the execution until the condition is met. The error is mainly verified by Root Mean Square Error (RMSE), Mean Absolute Error (MAE).
(1)RMSE：
Root Mean Square Error, which is the Square Root of the ratio of the sum of the squares of the deviations of the observed and true values to the number of observations m, is a measure of the deviation of the observed and true values.
(2)MAE
Mean Absolute Error, the average Absolute Error is the Mean of Absolute errors that better reflects the actual situation of the predicted value Error.
And seventhly, displaying on line. And displaying the predicted data of the database for reference of related personnel.
The prediction data of the database can be further imported into a power dispatching automation system, and automatic dispatching is carried out according to the prediction data, such as power output adjustment of a generator, load distribution adjustment, capacitor switching, a reactor switching and the like, so that continuous safe and stable operation of a power grid is ensured.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that the invention is not limited thereto, and may be embodied in other forms without departing from the spirit or essential characteristics thereof. Any modification which does not depart from the functional and structural principles of the present invention is intended to be included within the scope of the claims.
Claims (4)
1. A grid user short term load prediction real time processing tool, characterized by: the following steps are carried out:
step S1: automatically identifying a user or a power station, and automatically identifying the longitude and latitude and basic information of an area where the user or the power station is located according to the input user or the power station;
step S2: establishing a data warehouse, acquiring corresponding load historical data from the basic information of the user or the power station through a corresponding data interface to a marketing system, a power utilization information acquisition system and a distribution network system, acquiring local population density and economic condition data, acquiring corresponding historical weather condition and future weather condition forecast data from a weather station, and importing the data into an ODPS data warehouse;
step S3: preprocessing, namely preprocessing load data, wherein abnormal load data comprise noise and missing values;
step S4: normalization process, linearity of raw dataChange over so that the result falls to [0,1]]Interval, the transfer function is as follows:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
step S5: training a model and checking errors, judging whether the user or the power station is trained for the first time, if not, loading the stored training model, if so, randomly initializing a weight and a threshold matrix, then inputting a sample, performing training through short-term load prediction of a neural network, verifying whether the generated errors are in an allowed range, if so, storing model parameters and outputting results to a database, otherwise, correcting the weights through a dam optimizer, and repeating the execution until the conditions are met;
step S6: and displaying the predicted data of the database on line.
2. The grid user short term load prediction real time processing tool of claim 1, wherein: establishing a preprocessing model on a time sequence for the abnormal value types:
wherein y (t) represents the current load sequence, x (t) represents the load sequence without abnormal value, n is the number of abnormal values, ω I and α (j) represent the influence factors of the abnormal value of the load, and It(T) represents the pulse function at time T.
3. The grid user short term load prediction real time processing tool of claim 1, wherein: for the missing value in the data warehouse, according to the fluctuation cycle characteristic of the electric load, calculating the load of the same time point on the two adjacent days and the average value of the load of the two time points on the two adjacent days before and after the current time, and filling the missing value by adding the load variation quantity to the average value by a load variation rate method of the day before and after.
4. The grid user short term load prediction real time processing tool of claim 1, wherein: in step S5, the error is verified by the root mean square error and the average absolute error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318383.6A CN111177278A (en) | 2019-12-19 | 2019-12-19 | Grid user short-term load prediction real-time processing tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318383.6A CN111177278A (en) | 2019-12-19 | 2019-12-19 | Grid user short-term load prediction real-time processing tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111177278A true CN111177278A (en) | 2020-05-19 |
Family
ID=70622385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911318383.6A Pending CN111177278A (en) | 2019-12-19 | 2019-12-19 | Grid user short-term load prediction real-time processing tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111177278A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756049A (en) * | 2020-06-18 | 2020-10-09 | 国网浙江省电力有限公司电力科学研究院 | Data-driven reactive power optimization method considering loss of real-time measurement information of power distribution network |
| CN113435663A (en) * | 2021-07-15 | 2021-09-24 | 国网冀北电力有限公司唐山供电公司 | CNN-LSTM combined load prediction method considering electric vehicle charging load influence |
| CN114221329A (en) * | 2021-12-01 | 2022-03-22 | 国网浙江省电力有限公司营销服务中心 | Power grid load management method and system based on big data |
| CN117039850A (en) * | 2023-07-12 | 2023-11-10 | 湖北华中电力科技开发有限责任公司 | Abnormal electricity consumption analysis method and system based on space-time ground feature characteristics |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270309A (en) * | 2011-07-27 | 2011-12-07 | 华北电力大学 | Short-term electric load prediction method based on ensemble learning |
| CN104537429A (en) * | 2014-12-11 | 2015-04-22 | 国家电网公司 | Short-term load forecasting method and device based on data warehouse and data mining technology |
| CN108960520A (en) * | 2018-07-12 | 2018-12-07 | 南方电网科学研究院有限责任公司 | Power load prediction method, system, computer equipment and medium |
| CN110210670A (en) * | 2019-06-03 | 2019-09-06 | 辽宁工程技术大学 | A kind of prediction technique based on power-system short-term load |
| CN110348592A (en) * | 2019-05-21 | 2019-10-18 | 华电电力科学研究院有限公司 | A kind of load model prediction technique and forecasting system based on artificial neural network |
-
2019
- 2019-12-19 CN CN201911318383.6A patent/CN111177278A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270309A (en) * | 2011-07-27 | 2011-12-07 | 华北电力大学 | Short-term electric load prediction method based on ensemble learning |
| CN104537429A (en) * | 2014-12-11 | 2015-04-22 | 国家电网公司 | Short-term load forecasting method and device based on data warehouse and data mining technology |
| CN108960520A (en) * | 2018-07-12 | 2018-12-07 | 南方电网科学研究院有限责任公司 | Power load prediction method, system, computer equipment and medium |
| CN110348592A (en) * | 2019-05-21 | 2019-10-18 | 华电电力科学研究院有限公司 | A kind of load model prediction technique and forecasting system based on artificial neural network |
| CN110210670A (en) * | 2019-06-03 | 2019-09-06 | 辽宁工程技术大学 | A kind of prediction technique based on power-system short-term load |
Non-Patent Citations (1)
| Title |
|---|
| 杨波: "基于支持向量机的电力系统短期负荷预测" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111756049A (en) * | 2020-06-18 | 2020-10-09 | 国网浙江省电力有限公司电力科学研究院 | Data-driven reactive power optimization method considering loss of real-time measurement information of power distribution network |
| CN113435663A (en) * | 2021-07-15 | 2021-09-24 | 国网冀北电力有限公司唐山供电公司 | CNN-LSTM combined load prediction method considering electric vehicle charging load influence |
| CN114221329A (en) * | 2021-12-01 | 2022-03-22 | 国网浙江省电力有限公司营销服务中心 | Power grid load management method and system based on big data |
| CN114221329B (en) * | 2021-12-01 | 2024-08-02 | 国网浙江省电力有限公司营销服务中心 | Big data-based power grid load management method and system |
| CN117039850A (en) * | 2023-07-12 | 2023-11-10 | 湖北华中电力科技开发有限责任公司 | Abnormal electricity consumption analysis method and system based on space-time ground feature characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN110222882A (en) | A kind of prediction technique and device of electric system Mid-long Term Load | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN110880789A (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
| Liu et al. | Photovoltaic generation power prediction research based on high quality context ontology and gated recurrent neural network | |
| CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
| Mayer et al. | Probabilistic modeling of future electricity systems with high renewable energy penetration using machine learning | |
| CN112653198A (en) | Wind power output scene generation method and system based on prediction box | |
| CN118487276B (en) | Power grid safety dynamic management and control method and system for power guarantee object | |
| CN115859099A (en) | Sample generation method and device, electronic equipment and storage medium | |
| Shendryk et al. | Decision Support System for Efficient Energy Management of MicroGrid with Renewable Energy Sources | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| Wang et al. | A Comprehensive Review on the Development of Data-Driven Methods for Wind Power Prediction and AGC Performance Evaluation in Wind-Thermal Bundled Power Systems | |
| CN112330017A (en) | Power load prediction method, power load prediction device, electronic device, and storage medium | |
| CN117200352A (en) | Photovoltaic power generation regulation and control method and system based on cloud edge fusion | |
| Huang et al. | Power prediction method of distributed photovoltaic digital twin system based on GA-BP | |
| CN115313377B (en) | Power load prediction method and system | |
| Zim et al. | Short-term Weather Forecasting for Wind Energy Generation using A Deep Learning Technique | |
| CN105633946B (en) | A kind of high wind-powered electricity generation of extraction penetrates the modeling method of busbar day net active power Random-fuzzy feature | |
| Shendryk et al. | Decision Support System for Efficient Energy Management of Hybrid Power Grid | |
| Lin et al. | Research on Operation Strategy of User-side Energy System Based on Data Driving | |
| Xiong et al. | Graph Convolutional Network based Electricity Demand Forecasting in Power Distribution Networks | |
| Wang et al. | Intraday net load reserve demand assessment based on catboost and kernel density estimation | |
| RongQi et al. | Research of flexible load analysis of distribution network based on big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |
|
| RJ01 | Rejection of invention patent application after publication |