CN111709554A - Method and system for joint prediction of net loads of power distribution network - Google Patents
Method and system for joint prediction of net loads of power distribution network Download PDFInfo
- Publication number
- CN111709554A CN111709554A CN202010439761.2A CN202010439761A CN111709554A CN 111709554 A CN111709554 A CN 111709554A CN 202010439761 A CN202010439761 A CN 202010439761A CN 111709554 A CN111709554 A CN 111709554A
- Authority
- CN
- China
- Prior art keywords
- load
- power
- renewable energy
- historical data
- prediction
- 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
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method and a system for joint prediction of net load of a power distribution network, wherein the method comprises the following steps: respectively acquiring historical data of an electric load and historical data of renewable energy sources through different electric power information acquisition ports; preprocessing and normalizing the historical data of the power load and the historical data of the renewable energy; obtaining a user side load prediction result through calculation based on an improved generalized regression short-term load prediction model; the method comprises the steps that based on an EMD-LSTM photovoltaic power generation output prediction model, a renewable energy output prediction result is obtained through calculation; and superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network. In the implementation of the method, the user side load and the power generation output of the renewable energy are respectively predicted, and then the net load of the power distribution network is superposed for joint prediction, so that the operation safety of the power grid is ensured.
Description
Technical Field
The invention relates to the technical field of net load prediction of a power distribution network, in particular to a method and a system for joint prediction of net load of the power distribution network.
Background
The change of the load on the user side has obvious periodicity, the future power demand can be predicted according to the historical data of the load on the user side, and the scheduling decision of the power grid is made on the basis. However, when the renewable energy is connected to the power distribution network, the power flow in the power distribution network flows in two directions, so that the load characteristics are changed. The output of the renewable energy has strong randomness and volatility, and is easily influenced by weather conditions, so that the output changes greatly under different weather conditions, and the operation of the power distribution network is greatly influenced. Therefore, a method and a system for predicting the net load of the power distribution network are needed to ensure the safety of the operation of the power grid.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method and a system for joint prediction of net load of a power distribution network.
In order to solve the technical problem, an embodiment of the present invention provides a method for jointly predicting a net load of a power distribution network, where the method includes:
respectively acquiring historical data of an electric load and historical data of renewable energy sources through different electric power information acquisition ports;
preprocessing the historical data of the power load and the historical data of the renewable energy sources, and normalizing the historical data of the power load and the historical data of the renewable energy sources to obtain normalized power load data and renewable energy source data;
based on an improved generalized regression short-term load prediction model, obtaining a user side load prediction result through calculation according to the normalized power load data;
based on the photovoltaic power generation output prediction model of EMD-LSTM, according to the renewable energy data after normalization processing, calculating to obtain a renewable energy output prediction result;
and superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
Optionally, the respectively acquiring historical data of the electrical load and historical data of the renewable energy source through different power information acquisition ports includes:
acquiring historical data of the electric load through an electric power information acquisition port of the electric load;
and acquiring historical data of the renewable energy source through a power information acquisition port of the renewable energy source.
Optionally, the preprocessing the historical data of the power load and the historical data of the renewable energy source includes: and preprocessing the historical data of the power load and the historical data of the renewable energy sources by default values and abnormal values.
Optionally, the obtaining, by calculation, a user-side load prediction result according to the normalized power load data based on the improved generalized regression short-term load prediction model includes:
acquiring historical legal holiday information, historical power load data and corresponding meteorological factors at historical moments;
classifying the historical legal holiday information according to a historical daily load curve based on a K-means clustering algorithm;
checking the validity of said classification and specifying the date type of the historical data and future forecast date;
obtaining coefficients of each item in the improved generalized regression short-term load prediction model from the data through generalized multiple linear regression;
and acquiring meteorological data related to a future prediction date, and predicting the load of the user side according to the improved generalized regression short-term load prediction model.
Optionally, the classifying, according to the historical daily load curve, the historical legal holiday information based on the K-means clustering algorithm includes:
carrying out normalization processing on the daily load curve;
selecting k daily load curves from the daily load curves as clustering centers;
classifying the rest daily load curves into clusters where existing clustering centers are located according to Euclidean distances;
calculating to obtain a new clustering center;
judging whether the new clustering center and the existing clustering center are clustered less than a specified threshold value;
if yes, defining a holiday qualitative variable according to the clustering result;
and if not, returning to classify the rest daily load curves into the cluster where the existing cluster center is located according to the Euclidean distance.
Optionally, the photovoltaic power generation output prediction model based on the EMD-LSTM may obtain the renewable energy output prediction result by calculation according to the renewable energy data after the normalization processing, where the renewable energy output prediction result includes:
screening related variables and carrying out standardization processing on related influence historical data;
performing EMD decomposition on the photovoltaic power generation power historical sequence, and determining the number of decomposed intrinsic mode function subsequences according to the specific condition of historical data;
predicting each subsequence based on an LSTM model to obtain a predicted value of each subsequence;
and obtaining a final result of photovoltaic power generation power prediction through the prediction values of the subsequences.
Optionally, the step of superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network includes:
the user side load prediction result is
The renewable energy output prediction result is
Obtaining the predicted value according to the net load of the power distribution network as
In addition, an embodiment of the present invention further provides a system for jointly predicting a net load of a power distribution network, where the system includes:
a historical data acquisition module: the system comprises a power information acquisition port, a power load management port, a power information acquisition port and a power information acquisition port, wherein the power information acquisition port is used for acquiring historical data of a power load and historical data of renewable energy sources respectively;
a preprocessing and normalization module: the system comprises a power load, a renewable energy source, a power load, a renewable energy source and a power load, wherein the power load is used for generating power load historical data;
a user side load calculation module: the system is used for obtaining a user side load prediction result through calculation according to the normalized power load data based on an improved generalized regression short-term load prediction model;
renewable energy output calculation module: the photovoltaic power generation output prediction model is used for obtaining a renewable energy output prediction result through calculation according to the renewable energy data after normalization processing based on the EMD-LSTM;
and a result superposition module: and the system is used for superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
In the implementation of the method, the load on the user side is predicted based on the improved generalized regression short-term load prediction model, the renewable energy output is predicted based on the photovoltaic power generation output prediction model of the EMD-LSTM, and then the renewable energy output is superposed to obtain the predicted value according to the net load of the power distribution network, so that the prediction precision is improved, meanwhile, the net load of the power distribution network is effectively predicted, and the operation safety of the power distribution network is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for joint prediction of net loads of a power distribution network in an embodiment of the present invention;
FIG. 2 is a schematic structural composition diagram of a system for joint prediction of net loads of a power distribution network in an embodiment of the present invention;
FIG. 3 is a flow chart of an improved generalized regression short term load prediction for a converged date type in an embodiment of the present invention;
FIG. 4 is a flow chart of an EMD-LSTM based photovoltaic process prediction model in an embodiment 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. 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.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for jointly predicting a net load of a power distribution network according to an embodiment of the present invention.
As shown in fig. 1, a method for joint prediction of net load of a power distribution network includes:
s11: respectively acquiring historical data of an electric load and historical data of renewable energy sources through different electric power information acquisition ports;
in a specific implementation process of the present invention, the acquiring historical data of the electrical load and historical data of the renewable energy through different power information acquisition ports respectively includes: acquiring historical data of the electric load through an electric power information acquisition port of the electric load; and acquiring historical data of the renewable energy source through a power information acquisition port of the renewable energy source.
S12: preprocessing the historical data of the power load and the historical data of the renewable energy sources, and normalizing the historical data of the power load and the historical data of the renewable energy sources to obtain normalized power load data and renewable energy source data;
in a specific implementation process of the present invention, the preprocessing the historical data of the electrical load and the historical data of the renewable energy source includes: and preprocessing the historical data of the power load and the historical data of the renewable energy sources by default values and abnormal values.
In addition, the historical data of the electrical load and the historical data of the renewable energy source are normalized or normalized, and in this embodiment, the historical data of the electrical load and the historical data of the renewable energy source are normalized.
S13: based on an improved generalized regression short-term load prediction model, obtaining a user side load prediction result through calculation according to the normalized power load data;
in a specific implementation process of the present invention, as shown in fig. 3, the obtaining, by calculation, a user-side load prediction result according to the normalized power load data based on the improved generalized regression short-term load prediction model includes: acquiring historical legal holiday information, historical power load data and corresponding meteorological factors at historical moments; classifying the historical legal holiday information according to a historical daily load curve based on a K-means clustering algorithm; checking the validity of said classification and specifying the date type of the historical data and future forecast date; obtaining coefficients of each item in the improved generalized regression short-term load prediction model from the data through generalized multiple linear regression; and acquiring meteorological data related to a future prediction date, and predicting the load of the user side according to the improved generalized regression short-term load prediction model. The specific formula of the improved generalized regression short-term load prediction model is as follows:
Y＝Ttrend+β0+β1M+β2M×t+β3M×t2+
β4M×t3+β5H×t+β6H×t2+β7H×t3+
β8W×H+β9D×H；
wherein Y is predicted value of power load, M, W, H, D is historical data of corresponding month, week, hour and date type, β0～β9Is a regression coefficient; wherein D represents the influence of legal holidays, and different legal holidays are classified to obtain the accurate number of the date types.
Specifically, the algorithm based on K-means clustering, according to a historical daily load curve, classifying the historical legal holiday information includes: carrying out normalization processing on the daily load curve; selecting k daily load curves from the daily load curves as clustering centers; classifying the rest daily load curves into clusters where existing clustering centers are located according to Euclidean distances; calculating to obtain a new clustering center; judging whether the new clustering center and the existing clustering center are clustered less than a specified threshold value; if yes, defining a holiday qualitative variable according to the clustering result; and if not, returning to classify the rest daily load curves into the cluster where the existing cluster center is located according to the Euclidean distance.
Note that, in order to reflect the influence of holidays on the user-side load in the load prediction model, a date type variable is introduced. Besides defining the variables of the month, the week and the hour as qualitative variables, the influence of holidays and rest on load characteristics is also considered, and dates are divided into different types and are added into a load prediction model as qualitative variables through cluster analysis on a load curve. Common clustering algorithms comprise K-means clustering, hierarchical clustering, self-organizing mapping neural network clustering, fuzzy clustering methods and the like, and the load curves can be classified efficiently and reasonably by selecting a proper clustering method according to the data types and the clustering purposes. The K-means algorithm has high efficiency, can overcome the problems of local optimal solution, linear separation among categories and the like after improvement, and is suitable for classifying load curves.
S14: based on the photovoltaic power generation output prediction model of EMD-LSTM, according to the renewable energy data after normalization processing, calculating to obtain a renewable energy output prediction result;
in a specific implementation process of the present invention, as shown in fig. 4, the obtaining of the prediction result of the renewable energy output by calculating according to the renewable energy data after the normalization processing by the photovoltaic power generation output prediction model based on the EMD-LSTM includes: screening related variables and carrying out standardization processing on related influence historical data; performing EMD decomposition on the photovoltaic power generation power historical sequence, and determining the number of decomposed intrinsic mode function subsequences according to the specific condition of historical data; predicting each subsequence based on an LSTM model to obtain a predicted value of each subsequence; and obtaining a final result of photovoltaic power generation power prediction through the prediction values of the subsequences.
Specifically, in the first step, relevant variables are screened, and relevant influence factor historical data are standardized to avoid influences caused by different dimensions and different magnitudes, so that characteristics of different metrics are comparable, and a standardized formula is as follows:
wherein μ represents the mean of the samples; σ is the standard deviation of the sample;
secondly, performing EMD decomposition on the photovoltaic power generation power historical sequence, and determining the number of decomposed intrinsic mode function subsequences according to the specific condition of historical data; analyzing the characteristic of the eigenmode function subsequence, removing the high-frequency eigenmode function subsequence with smaller value, and reserving the rest eigenmode function subsequence and the residual sequence;
thirdly, respectively predicting each subsequence by using an LSTM model, inputting weather related factor data with variables of each subsequence and corresponding time points, and outputting a predicted value of each subsequence;
and fourthly, obtaining a final result of photovoltaic power generation power prediction by superposing the predicted values of the subsequences.
S15: and superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
In a specific implementation process of the present invention, the step of superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network includes: the user side load prediction result is
The renewable energy output prediction result is
Obtaining the predicted value according to the net load of the power distribution network as
In the implementation of the method, the load on the user side is predicted based on the improved generalized regression short-term load prediction model, the renewable energy output is predicted based on the photovoltaic power generation output prediction model of the EMD-LSTM, and then the renewable energy output is superposed to obtain the predicted value according to the net load of the power distribution network, so that the prediction precision is improved, meanwhile, the net load of the power distribution network is effectively predicted, and the operation safety of the power distribution network is ensured.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a system for jointly predicting a net load of a power distribution network according to an embodiment of the present invention.
As shown in fig. 2, a system for joint prediction of net load of a distribution network includes:
the historical data acquisition module 11: the system comprises a power information acquisition port, a power load management port, a power information acquisition port and a power information acquisition port, wherein the power information acquisition port is used for acquiring historical data of a power load and historical data of renewable energy sources respectively;
the preprocessing and normalization module 12: the system comprises a power load, a renewable energy source, a power load, a renewable energy source and a power load, wherein the power load is used for generating power load historical data;
the user side load calculation module 13: the system is used for obtaining a user side load prediction result through calculation according to the normalized power load data based on an improved generalized regression short-term load prediction model;
renewable energy output calculation module 14: the photovoltaic power generation output prediction model is used for obtaining a renewable energy output prediction result through calculation according to the renewable energy data after normalization processing based on the EMD-LSTM;
the result superposition module 15: and the system is used for superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
Specifically, the working principle of the system related function module according to the embodiment of the present invention may refer to the description related to the first method embodiment, and is not described herein again.
In the implementation of the method, the load on the user side is predicted based on the improved generalized regression short-term load prediction model, the renewable energy output is predicted based on the photovoltaic power generation output prediction model of the EMD-LSTM, and then the renewable energy output is superposed to obtain the predicted value according to the net load of the power distribution network, so that the prediction precision is improved, meanwhile, the net load of the power distribution network is effectively predicted, and the operation safety of the power distribution network is ensured.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
In addition, the method and the system for jointly predicting the net load of the power distribution network provided by the embodiment of the invention are described in detail, a specific embodiment is adopted to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A method for joint prediction of net loads of a power distribution network is characterized by comprising the following steps:
respectively acquiring historical data of an electric load and historical data of renewable energy sources through different electric power information acquisition ports;
preprocessing the historical data of the power load and the historical data of the renewable energy sources, and normalizing the historical data of the power load and the historical data of the renewable energy sources to obtain normalized power load data and renewable energy source data;
based on an improved generalized regression short-term load prediction model, obtaining a user side load prediction result through calculation according to the normalized power load data;
based on the photovoltaic power generation output prediction model of EMD-LSTM, according to the renewable energy data after normalization processing, calculating to obtain a renewable energy output prediction result;
and superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
2. The method for joint prediction of net loads of power distribution networks according to claim 1, wherein the step of collecting historical data of electric loads and historical data of renewable energy sources through different power information collection ports respectively comprises the steps of:
acquiring historical data of the electric load through an electric power information acquisition port of the electric load;
and acquiring historical data of the renewable energy source through a power information acquisition port of the renewable energy source.
3. The method of joint prediction of net loads on a power distribution network according to claim 1, wherein the preprocessing of historical data of the power loads and historical data of the renewable energy sources comprises: and preprocessing the historical data of the power load and the historical data of the renewable energy sources by default values and abnormal values.
4. The method for jointly predicting the net loads of the power distribution network according to claim 1, wherein the step of obtaining the user-side load prediction result through calculation according to the normalized power load data based on the improved generalized regression short-term load prediction model comprises the following steps:
acquiring historical legal holiday information, historical power load data and corresponding meteorological factors at historical moments;
classifying the historical legal holiday information according to a historical daily load curve based on a K-means clustering algorithm;
checking the validity of said classification and specifying the date type of the historical data and future forecast date;
obtaining coefficients of each item in the improved generalized regression short-term load prediction model from the data through generalized multiple linear regression;
and acquiring meteorological data related to a future prediction date, and predicting the load of the user side according to the improved generalized regression short-term load prediction model.
5. The method for jointly predicting the net load of the power distribution network according to claim 4, wherein the classifying the historical legal holiday information according to a historical daily load curve by the K-means cluster-based algorithm comprises:
carrying out normalization processing on the daily load curve;
selecting k daily load curves from the daily load curves as clustering centers;
classifying the rest daily load curves into clusters where existing clustering centers are located according to Euclidean distances;
calculating to obtain a new clustering center;
judging whether the new clustering center and the existing clustering center are clustered less than a specified threshold value;
if yes, defining a holiday qualitative variable according to the clustering result;
and if not, returning to classify the rest daily load curves into the cluster where the existing cluster center is located according to the Euclidean distance.
6. The method for jointly predicting the net load of the power distribution network according to claim 1, wherein the obtaining of the prediction result of the renewable energy output through calculation according to the renewable energy data after the normalization processing by the photovoltaic power generation output prediction model based on the EMD-LSTM comprises:
screening related variables and carrying out standardization processing on related influence historical data;
performing EMD decomposition on the photovoltaic power generation power historical sequence, and determining the number of decomposed intrinsic mode function subsequences according to the specific condition of historical data;
predicting each subsequence based on an LSTM model to obtain a predicted value of each subsequence;
and obtaining a final result of photovoltaic power generation power prediction through the prediction values of the subsequences.
7. The method of claim 1, wherein the step of superposing the user-side load prediction result and the renewable energy output prediction result to obtain the prediction value according to the net load of the power distribution network comprises:
the user side load prediction result is
The renewable energy output prediction result is
Obtaining the predicted value according to the net load of the power distribution network as
8. A system for joint prediction of net load of a power distribution network, the system comprising:
a historical data acquisition module: the system comprises a power information acquisition port, a power load management port, a power information acquisition port and a power information acquisition port, wherein the power information acquisition port is used for acquiring historical data of a power load and historical data of renewable energy sources respectively;
a preprocessing and normalization module: the system comprises a power load, a renewable energy source, a power load, a renewable energy source and a power load, wherein the power load is used for generating power load historical data;
a user side load calculation module: the system is used for obtaining a user side load prediction result through calculation according to the normalized power load data based on an improved generalized regression short-term load prediction model;
renewable energy output calculation module: the photovoltaic power generation output prediction model is used for obtaining a renewable energy output prediction result through calculation according to the renewable energy data after normalization processing based on the EMD-LSTM;
and a result superposition module: and the system is used for superposing the user side load prediction result and the renewable energy output prediction result to obtain a prediction value according to the net load of the power distribution network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010439761.2A CN111709554A (en) | 2020-05-22 | 2020-05-22 | Method and system for joint prediction of net loads of power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010439761.2A CN111709554A (en) | 2020-05-22 | 2020-05-22 | Method and system for joint prediction of net loads of power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111709554A true CN111709554A (en) | 2020-09-25 |
Family
ID=72538619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010439761.2A Pending CN111709554A (en) | 2020-05-22 | 2020-05-22 | Method and system for joint prediction of net loads of power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709554A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383069A (en) * | 2020-11-05 | 2021-02-19 | 国网山东省电力公司电力科学研究院 | Dynamic prediction method for primary frequency modulation compensation capability of generator set |
| CN112598155A (en) * | 2020-11-23 | 2021-04-02 | 国网浙江海宁市供电有限公司 | Load increase and decrease estimation method and system for transformer substation |
| CN113139675A (en) * | 2021-03-08 | 2021-07-20 | 深圳职业技术学院 | Comprehensive electrical load interval prediction method for park comprehensive energy system |
| CN113505943A (en) * | 2021-07-30 | 2021-10-15 | 广东电网有限责任公司 | Method, system, equipment and medium for predicting short-term load of power grid |
| CN115081902A (en) * | 2022-06-30 | 2022-09-20 | 国网北京市电力公司 | Comprehensive planning method, device, equipment and medium based on source network load-storage cooperation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948845A (en) * | 2019-03-15 | 2019-06-28 | 国网江苏省电力有限公司经济技术研究院 | A kind of distribution network load shot and long term Memory Neural Networks prediction technique |
| CN110112783A (en) * | 2019-05-23 | 2019-08-09 | 深圳市建筑科学研究院股份有限公司 | Photovoltaic storage battery micro-capacitance sensor dispatch control method |
-
2020
- 2020-05-22 CN CN202010439761.2A patent/CN111709554A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948845A (en) * | 2019-03-15 | 2019-06-28 | 国网江苏省电力有限公司经济技术研究院 | A kind of distribution network load shot and long term Memory Neural Networks prediction technique |
| CN110112783A (en) * | 2019-05-23 | 2019-08-09 | 深圳市建筑科学研究院股份有限公司 | Photovoltaic storage battery micro-capacitance sensor dispatch control method |
Non-Patent Citations (2)
| Title |
|---|
| 朱玥等: "基于EMD-LSTM的光伏发电预测模型", 《电力工程技术》 * |
| 王凌谊等: "融合日期类型的改进线性回归短期负荷预测模型", 《广东电力》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383069A (en) * | 2020-11-05 | 2021-02-19 | 国网山东省电力公司电力科学研究院 | Dynamic prediction method for primary frequency modulation compensation capability of generator set |
| CN112598155A (en) * | 2020-11-23 | 2021-04-02 | 国网浙江海宁市供电有限公司 | Load increase and decrease estimation method and system for transformer substation |
| CN113139675A (en) * | 2021-03-08 | 2021-07-20 | 深圳职业技术学院 | Comprehensive electrical load interval prediction method for park comprehensive energy system |
| CN113139675B (en) * | 2021-03-08 | 2023-02-28 | 深圳职业技术学院 | Comprehensive electrical load interval prediction method for park comprehensive energy system |
| CN113505943A (en) * | 2021-07-30 | 2021-10-15 | 广东电网有限责任公司 | Method, system, equipment and medium for predicting short-term load of power grid |
| CN113505943B (en) * | 2021-07-30 | 2023-05-30 | 广东电网有限责任公司 | Method, system, equipment and medium for predicting short-term load of power grid |
| CN115081902A (en) * | 2022-06-30 | 2022-09-20 | 国网北京市电力公司 | Comprehensive planning method, device, equipment and medium based on source network load-storage cooperation |
| CN115081902B (en) * | 2022-06-30 | 2024-04-09 | 国网北京市电力公司 | Comprehensive planning method, device, equipment and medium based on source network load storage cooperation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709554A (en) | Method and system for joint prediction of net loads of power distribution network | |
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| CN112561156A (en) | Short-term power load prediction method based on user load mode classification | |
| CN111724278A (en) | Fine classification method and system for power multi-load users | |
| CN110750524A (en) | Method and system for determining fault characteristics of active power distribution network | |
| CN112330078B (en) | Power consumption prediction method and device, computer equipment and storage medium | |
| CN115775045A (en) | Photovoltaic balance prediction method based on historical similar days and real-time multi-dimensional study and judgment | |
| CN113408548A (en) | Transformer abnormal data detection method and device, computer equipment and storage medium | |
| CN113569462A (en) | Distribution network fault level prediction method and system considering weather factors | |
| CN115660182A (en) | Photovoltaic output prediction method based on maximum expected sample weighted neural network model | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN106846170B (en) | Generator set trip monitoring method and monitoring device thereof | |
| CN108846505B (en) | Multidimensional checking method and equipment for renewable energy grid-connected consumption information | |
| CN113689079A (en) | Transformer area line loss prediction method and system based on multivariate linear regression and cluster analysis | |
| CN111967919A (en) | System and method for analyzing electricity consumption behavior of residents based on autoregressive and adaptive boosting algorithm | |
| CN114372835B (en) | Comprehensive energy service potential customer identification method, system and computer equipment | |
| CN115718861A (en) | Method and system for classifying power users and monitoring abnormal behaviors in high-energy-consumption industry | |
| CN115204698A (en) | Real-time analysis method for power supply stability of low-voltage transformer area | |
| Ma | The Research of Stock Predictive Model based on the Combination of CART and DBSCAN | |
| CN112069633B (en) | Power distribution network data preprocessing method based on particle swarm principle and adopting big data clustering | |
| CN115292361A (en) | Method and system for screening distributed energy abnormal data | |
| CN114707739A (en) | Wind-solar output prediction and market risk management and control method and system based on big data | |
| CN112365081A (en) | Photovoltaic power station power generation capacity prediction method and device | |
| CN111783827A (en) | Enterprise user classification method and device based on load 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200925 |