CN109961160B - Power grid future operation trend estimation method and system based on tide parameters - Google Patents
Power grid future operation trend estimation method and system based on tide parameters Download PDFInfo
- Publication number
- CN109961160B CN109961160B CN201711335875.7A CN201711335875A CN109961160B CN 109961160 B CN109961160 B CN 109961160B CN 201711335875 A CN201711335875 A CN 201711335875A CN 109961160 B CN109961160 B CN 109961160B
- Authority
- CN
- China
- Prior art keywords
- power grid
- data
- historical
- key features
- power flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000010248 power generation Methods 0.000 claims abstract description 14
- 230000005856 abnormality Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 63
- 238000012549 training Methods 0.000 claims description 46
- 238000010276 construction Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005283 ground state Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- 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
-
- 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
-
- 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]
-
- 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
Abstract
The invention relates to a power grid future operation trend prediction method and system based on tide parameters, which are used for collecting current power grid tide data and data corresponding to factors affecting the current power grid; inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid; the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features. According to the method, the influence of various uncertain factors on a safety and stability analysis conclusion in the power grid operation situation change process is analyzed, key characteristics of uncertain information such as new energy power generation fluctuation, bus load prediction errors, scheduling plan abnormality and the like are extracted, a power grid future operation trend parameter prediction method considering uncertainty is researched, and a power grid operation trend data online forming technology comprehensively considering operation situation uncertainty and control strategies is researched.
Description
Technical Field
The invention relates to the field of future power flow trend of a power grid and computer algorithm, in particular to a power grid future operation trend estimation method and system based on power flow parameters.
Background
The transmission section, also called the tidal current section. In an actual power system, system schedulers often select a plurality of lines connecting a power supply center and a load center as a power transmission section according to geographic positions only. The comparison specification is defined as follows: under a certain ground state tide, a set of power transmission lines with the same active power flow direction and similar electric distances is called a power transmission section.
The factors influencing the power grid section power flow are many, and are regular and regular with the actual power flow value of the power grid, but we do not know how much the factors have an actual influence on the power grid power flow, so that the future power flow trend of the power grid is inaccurately judged, and the power flow section accident is caused.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a power grid future operation trend prediction method and a power grid future operation trend prediction system based on power flow parameters, to research the power grid future operation trend power flow parameter prediction method considering uncertainty, and to research the power grid operation trend data online forming technology comprehensively considering operation situation uncertainty and control strategies.
The invention aims at adopting the following technical scheme:
the invention provides a power grid future operation trend estimation method based on tide parameters, which is characterized in that:
collecting current power grid tide data and data corresponding to factors affecting the current power grid;
inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid;
the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features.
Further: the pre-constructed model of the relation between the historical power grid power flow and the influence factors comprises the following steps:
collecting historical power grid tide data of each section of a power grid;
collecting data corresponding to key features of each section; the key features include: new energy power generation fluctuation, bus load prediction error or abnormal scheduling plan;
calculating historical power grid power flow data weight occupied by the key features according to the historical power grid power flow data and the key features;
training the historical power grid tide data weight occupied by the key characteristics to obtain an optimized parameter weight training result; and constructing a model of the relation between the power grid power flow and the influence factors based on the historical power grid power flow data, the key features and the historical power grid power flow data weight occupied by the key features.
Further: before calculating the historical power grid power flow data weight occupied by the key feature according to the historical power grid power flow data and the key feature, the method further comprises the following steps: storing historical power grid tide data and key characteristics;
the storing of the historical grid power flow data and the key features comprises:
integrating the collected historical power grid power flow data and key features, and integrating the key features and the historical power grid power flow data into a data file by taking a section as a unit, wherein the data file is used as an input file for parameter training;
and storing the integrated historical power grid tide data and key characteristics into a historical data file.
Further: training the historical power grid tide data weight occupied by the key features to obtain an optimized parameter weight training result, wherein the training result comprises the following steps:
acquiring historical power grid tide data and key characteristics from a historical data file;
training the historical power grid power flow data and the key features, calculating the weight of the historical power grid power flow data occupied by the key features, and optimizing the weight.
Further, the optimizing the weight includes: calculating weight values such that the risk function is minimized, comprising:
constructing a weight fitting function containing key features;
and constructing a risk function according to the fitting function, and calculating the maximum weight value containing key features of the residual error between the fitting function and the objective function in the risk function.
Further, the vector representation of the weight fitting function is:
the risk function is expressed as:
the minimized risk function is expressed as:
for each weight parameter θ in the minimized risk function J (θ) j Obtaining the partial derivative of the weight parameters theta j The corresponding gradient:
according to each weight parameter theta j To update each weight parameter theta j Expressed as:
wherein: h is a θ (x i ) Vector representation of a weight fitting function for inclusion of key features, θ T ＝[θ 0 ,θ 1 ,...,θ n ]N is the weight component number, m represents the key feature sample data, x i Representing the i-th key feature sample point,representing the ith key feature sample point x i Is the j-th weight component of (2); y is i The method comprises the steps of obtaining a preset actual correctness objective function; alpha is the step size of the variance of the weight parameter.
Further, the method further comprises the step of verifying the weights, wherein the step of verifying the weights by using part of data is performed, and whether the historical power grid power flow data and the actual power grid power flow data of the training result are consistent or not is judged, so that the success rate of the historical power grid power flow data and the key feature after training is obtained until the success rate meets a set threshold value.
Further: estimating the future running trend of the power grid based on the model of the relation between the power grid power flow and the influence factors, comprising:
and inputting key features of current new energy power generation fluctuation, bus load prediction errors and abnormal scheduling plans into a model of the relation between the power grid power flow and the influence factors, and estimating the future power flow trend of the power grid according to historical power grid power flow data and key features of which the success rate meets a set threshold.
The invention provides a power grid future operation trend estimation system based on tide parameters, which is characterized in that: comprising the following steps:
the acquisition module is used for acquiring current power grid tide data and data corresponding to factors affecting the current power grid;
the estimating module is used for inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid;
the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features.
Further: the system also comprises a construction module which is used for constructing a relation model between the historical power grid tide and the influence factors.
Further: the construction module comprises:
the acquisition sub-module is used for acquiring historical power grid tide data of each section of the power grid; collecting data corresponding to key features corresponding to each section; the key features include: new energy power generation fluctuation, bus load prediction error and abnormal scheduling plan;
the calculation sub-module is used for calculating the historical power grid power flow data weight occupied by the key features according to the historical power grid power flow data and the key features;
the training sub-module is used for training the historical power grid tide data weights occupied by the key features to obtain an optimized parameter weight training result;
and the building sub-module is used for building a model of the relation between the power grid power flow and the influence factors based on the historical power grid power flow data, the key characteristics and the historical power grid power flow data weight occupied by the key characteristics.
Further: the storage module is used for storing the historical power grid power flow data and the key features before the weight occupied by each feature under all power flow data is calculated according to the historical power grid power flow data and the key features; the memory module includes:
the integration sub-module is used for integrating the collected historical power grid power flow data with the key features, integrating the key features and the historical power grid power flow data into a data file by taking a section as a unit, and taking the key features and the historical power grid power flow data as input files of parameter training;
and the storage sub-module is used for storing the integrated historical power grid tide data and key characteristics into a historical data file.
Further: the calculating submodule is further used for calculating a weight value for minimizing a risk function, and the calculating submodule comprises:
the first construction unit is used for constructing a weight fitting function containing key features;
the second construction unit constructs a risk function according to the fitting function, and calculates a maximum weight value containing key features of a residual error between the fitting function and the objective function in the risk function.
Further: the system further comprises a verification unit, wherein the verification unit is used for verifying the weights by using part of data, judging whether the historical power grid power flow data of the training result is consistent with the actual power grid power flow data, and obtaining the success rate of the historical power grid power flow data and the key characteristics after training until the success rate meets a set threshold.
Further: the estimating module is further used for inputting key features of current new energy power generation fluctuation, bus load prediction errors and scheduling plan abnormality into a model of the relation between the power grid power flow and the influence factors, and estimating future power flow trend of the power grid according to historical power grid power flow data and key features of which the success rate meets a set threshold.
Compared with the closest prior art, the technical scheme provided by the invention has the beneficial effects that:
firstly, collecting a numerical value corresponding to a preset influence factor; collecting current power grid tide data and data corresponding to factors affecting the current power grid; the collected data are input into a pre-constructed relation model between the historical power grid power flow and influence factors, the future running trend of the power grid is estimated, the selected influence factors are accurate, and the accuracy of estimating the power grid section power flow condition is improved.
The power grid tide data and influence factors are accurate: the system can integrate and process the current power grid real-time data, store the current power grid real-time data according to time units to form an effective training data set, and train the weights of the characteristics through various uncertain influence factor characteristics.
The training of the weights is accurate: the data of the system is updated in real time, factor characteristic training is optimized according to the actual condition of the current time period, the estimated result of the trend is ensured to be more approximate to the actual value, partial data is extracted to verify the weight parameters, and the readiness of the estimated result is further ensured.
Drawings
FIG. 1 is a detailed flowchart of a power grid future operation trend estimation method based on tide parameters;
FIG. 2 is a block diagram of a power grid future operation trend estimation system based on tide parameters;
fig. 3 is a schematic flow chart of a power grid future operation trend estimation method based on tide parameters.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them. Other embodiments may involve structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in, or substituted for, those of others. The scope of embodiments of the invention encompasses the full ambit of the claims, as well as all available equivalents of the claims. These embodiments of the invention may be referred to herein, individually or collectively, by the term "invention" merely for convenience and without intending to voluntarily limit the scope of this application to any single invention or inventive concept if more than one is in fact disclosed.
According to the method, a model of the relation between the power grid power flow and various influencing factors is built, the model is trained through a large amount of collected historical data, and the model and parameters are optimized through data updated in real time, so that the numerical value of each influencing factor at a given time point can be obtained, and the power grid section power flow condition at the time can be estimated. The invention relates to a power grid future operation trend prediction method and a power grid future operation trend prediction system based on trend parameters, which are used for analyzing the influence of various uncertain factors on a safety and stability analysis conclusion in the power grid operation situation change process, extracting key characteristics of uncertain information such as new energy power generation fluctuation, bus load prediction errors, scheduling plan anomalies and the like, researching the power grid future operation trend parameter prediction method considering uncertainty, and researching the power grid operation trend data online formation technology comprehensively considering operation situation uncertainty and control strategies. Comprising the following steps: collecting and storing historical power grid tide data and key characteristics; training the parameter weight occupied by the key features according to the historical power grid tide data and the key features; and estimating the future running trend of the power grid through the parameter weight result trained by the historical data.
Embodiment 1,
The invention provides a power grid future operation trend estimation method based on tide parameters, wherein a flow chart is shown in figures 1 and 3, and the method comprises the following steps:
1) The data acquisition module acquires and stores historical power grid tide data and key characteristics;
2) The parameter training module trains the parameter weight occupied by the key feature according to the historical power grid tide data and the key feature;
3) And the trend estimation module estimates the future operation trend of the power grid according to the parameter weight result trained by the historical data.
Further, the step 1) includes the steps of:
step 101: the data acquisition module acquires the tide of each section of the power grid;
step 102: acquiring key characteristics of uncertain information such as new energy power generation fluctuation, bus load prediction error, scheduling plan abnormality and the like corresponding to each section through external input;
step 103: the collected data is stored in a historical data file.
Further, the step 2) includes the steps of:
step 201: a large amount of power flow data and key features are obtained from the historical data file.
Step 202: training the big data, calculating weights occupied by all features of all tide data, and continuously optimizing the weights; substituting partial data (such as 20% of the whole data amount) into the weight, judging whether the trend data of the training result is consistent with the actual trend data, and obtaining the success rate of the data training until the success rate of verification meets the requirement (for example, the success rate reaches 90%).
Step 203: and verifying the weights by using part of data, and judging the success rate of the data after training.
Step 204: steps 202 and 203 are repeatedly performed until the success rate of verification meets the requirements.
The algorithm is exemplified by:
the following algorithm is a gradient descent algorithm for machine learning linear regression, assuming the value of the feature is x, the weight of the feature is θ, and this h (θ) is our fitting function:
the representation can also be in the form of vectors:
h θ (x)＝θ T X
the following functions are risk functions that we need to optimize, each term h θ (x i )-y i All represent the residual between our fitting function and y on the existing training set, and calculate its square loss function as the risk function we construct:
m represents the data of the sample.
The objective is to minimize the risk function so that the fitting function can maximally fit the objective function y, namely:
according to conventional thinking, we need to work with each θ in the above risk functions j Obtaining each theta by obtaining partial derivative thereof j The corresponding gradient:
here, theRepresenting the i-th sample point x i Of (h), i.e. theta in h (theta) j x j 。
Next, since we want to minimize the risk function, we follow each parameter θ j To update each of the negative gradient directions
Further, the step 3) includes the steps of:
step 301: and inputting key characteristic data of uncertain information such as new energy power generation fluctuation, bus load prediction error, scheduling plan abnormality and the like corresponding to the section.
Step 302: and obtaining the training result, and calculating to obtain the estimated future power grid operation trend.
Embodiment II,
Based on the same inventive concept, the invention also provides a power grid future operation trend estimation system based on the tide parameter, the structure diagram of which is shown in fig. 2, comprising:
the acquisition module is used for acquiring current power grid tide data and data corresponding to factors affecting the current power grid;
the estimating module is used for inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid;
the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features.
Further: the system also comprises a construction module which is used for constructing a relation model between the historical power grid tide and the influence factors.
Further: the construction module comprises:
the acquisition sub-module is used for acquiring historical power grid tide data of each section of the power grid; collecting data corresponding to key features corresponding to each section; the key features include: new energy power generation fluctuation, bus load prediction error and abnormal scheduling plan;
the calculation sub-module is used for calculating the historical power grid power flow data weight occupied by the key features according to the historical power grid power flow data and the key features;
the training sub-module is used for training the historical power grid tide data weights occupied by the key features to obtain an optimized parameter weight training result;
and the building sub-module is used for building a model of the relation between the power grid power flow and the influence factors based on the historical power grid power flow data, the key characteristics and the historical power grid power flow data weight occupied by the key characteristics.
Further: the storage module is used for storing the historical power grid power flow data and the key features before the weight occupied by each feature under all power flow data is calculated according to the historical power grid power flow data and the key features; the memory module includes:
the integration sub-module is used for integrating the collected historical power grid power flow data with the key features, integrating the key features and the historical power grid power flow data into a data file by taking a section as a unit, and taking the key features and the historical power grid power flow data as input files of parameter training;
and the storage sub-module is used for storing the integrated historical power grid tide data and key characteristics into a historical data file.
Further: the calculating submodule is further used for calculating a weight value for minimizing a risk function, and the calculating submodule comprises:
the first construction unit is used for constructing a weight fitting function containing key features;
the second construction unit constructs a risk function according to the fitting function, and calculates a maximum weight value containing key features of a residual error between the fitting function and the objective function in the risk function.
Further: the calculation submodule further comprises a verification unit for verifying the weights by using part of data, judging whether the historical power grid power flow data of the training result is consistent with the actual power grid power flow data, and obtaining the success rate of the historical power grid power flow data and the key feature after training until the success rate meets a set threshold.
Further: the estimating module is further used for inputting key features of current new energy power generation fluctuation, bus load prediction errors and scheduling plan abnormality into a model of the relation between the power grid power flow and the influence factors, and estimating future power flow trend of the power grid according to historical power grid power flow data and key features of which the success rate meets a set threshold.
Firstly, collecting a numerical value corresponding to a preset influence factor; and estimating the power grid section power flow condition based on the acquired numerical value and a preset model of the relation between the power grid power flow and a plurality of influence factors. The model of the relation between the preset power grid power flow and various influencing factors comprises historical power grid power flow data and key characteristics, the selected influencing factors are accurate, and accuracy of power grid section power flow condition prediction is improved.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, one skilled in the art may make modifications and equivalents to the specific embodiments of the present invention, and any modifications and equivalents not departing from the spirit and scope of the present invention are within the scope of the claims of the present invention.
Claims (7)
1. A power grid future operation trend prediction method based on tide parameters is characterized by comprising the following steps of:
collecting current power grid tide data and data corresponding to factors affecting the current power grid;
inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid;
the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features;
the pre-constructed model of the relation between the historical power grid power flow and the influence factors comprises the following steps:
collecting historical power grid tide data of each section of a power grid;
collecting data corresponding to key features of each section; the key features include: new energy power generation fluctuation, bus load prediction error or abnormal scheduling plan;
calculating historical power grid power flow data weight occupied by the key features according to the historical power grid power flow data and the key features;
training the historical power grid tide data weight occupied by the key characteristics to obtain an optimized parameter weight training result;
constructing a model of the relation between the power grid power flow and the influence factors based on the historical power grid power flow data, the key features and the historical power grid power flow data weight occupied by the key features;
before calculating the historical power grid power flow data weight occupied by the key feature according to the historical power grid power flow data and the key feature, the method further comprises the following steps: storing historical power grid tide data and key characteristics;
the storing of the historical grid power flow data and the key features comprises:
integrating the collected historical power grid power flow data and key features, and integrating the key features and the historical power grid power flow data into a data file by taking a section as a unit, wherein the data file is used as an input file for parameter training;
storing the integrated historical power grid tide data and key characteristics into a historical data file;
training the historical power grid tide data weight occupied by the key features to obtain an optimized parameter weight training result, wherein the training result comprises the following steps:
acquiring historical power grid tide data and key characteristics from a historical data file;
training the historical power grid power flow data and the key features, calculating the weight of the historical power grid power flow data occupied by the key features, and optimizing the weight;
the optimizing the weight includes: calculating weight values such that the risk function is minimized, comprising:
constructing a weight fitting function containing key features;
constructing a risk function according to the fitting function, and calculating the maximum weight value containing key features of the residual error between the fitting function and the objective function in the risk function;
the vector representation of the weight fitting function is as follows:
the risk function is expressed as:
the minimized risk function is expressed as:
for each weight parameter θ in the minimized risk function J (θ) j Obtaining the partial derivative of the weight parameters theta j The corresponding gradient:
according to each parameter theta j To update each θ j Expressed as:
wherein: h is a θ (x i ) Vector representation of a weight fitting function for inclusion of key features, θ T ＝[θ 0 ，θ 1 ，....，θ n ]N is the weight component number, m represents the key feature sample data, x i Representing the i-th key feature sample point,representing the ith key feature sample point x i Is the j-th weight component, y i The method comprises the steps of obtaining a preset actual correctness objective function; alpha is the step size of the variance of the weight parameter.
2. The future operation trend prediction method of a power grid according to claim 1, further comprising verifying weights, including verifying the weights by using part of data, judging whether the historical power grid power flow data and the actual power grid power flow data of the training result are consistent, and obtaining a success rate after the historical power grid power flow data and the key feature are trained until the success rate meets a set threshold.
3. The future operation trend estimating method of a power grid according to claim 1, wherein: estimating the future running trend of the power grid based on the model of the relation between the power grid power flow and the influence factors, comprising:
and inputting key features of current new energy power generation fluctuation, bus load prediction errors and abnormal scheduling plans into a model of the relation between the power grid power flow and the influence factors, and estimating the future power flow trend of the power grid according to historical power grid power flow data and key features of which the success rate meets a set threshold.
4. A system based on the trend prediction method of the future operation of the power grid based on the tide parameters as claimed in any one of claims 1 to 3, characterized in that: comprising the following steps:
the acquisition module is used for acquiring current power grid tide data and data corresponding to factors affecting the current power grid;
the estimating module is used for inputting the acquired data into a pre-constructed relation model between the historical power grid power flow and the influence factors, and estimating the future running trend of the power grid;
the relation model between the historical power grid power flow and the influence factors comprises historical power grid power flow data weights occupied by key features;
the method also comprises a construction module: the method comprises the steps of constructing a relation model between historical power grid power flow and influence factors;
the construction module comprises:
the acquisition sub-module is used for acquiring historical power grid tide data of each section of the power grid; collecting data corresponding to key features corresponding to each section; the key features include: new energy power generation fluctuation, bus load prediction error and abnormal scheduling plan;
the calculation sub-module is used for calculating the historical power grid power flow data weight occupied by the key features according to the historical power grid power flow data and the key features;
the training sub-module is used for training the historical power grid tide data weights occupied by the key features to obtain an optimized parameter weight training result;
the building sub-module is used for building a model of the relation between the power grid power flow and the influence factors based on the historical power grid power flow data, the key features and the historical power grid power flow data weight occupied by the key features;
the storage module is used for storing the historical power grid power flow data and the key features before the weight occupied by each feature under all power flow data is calculated according to the historical power grid power flow data and the key features; the memory module includes:
the integration sub-module is used for integrating the collected historical power grid power flow data with the key features, integrating the key features and the historical power grid power flow data into a data file by taking a section as a unit, and taking the key features and the historical power grid power flow data as input files of parameter training;
and the storage sub-module is used for storing the integrated historical power grid tide data and key characteristics into a historical data file.
5. The grid future operating trend prediction system of claim 4, wherein: the calculating submodule is further used for calculating a weight value for minimizing a risk function, and the calculating submodule comprises:
the first construction unit is used for constructing a weight fitting function containing key features;
the second construction unit constructs a risk function according to the fitting function, and calculates a maximum weight value containing key features of a residual error between the fitting function and the objective function in the risk function.
6. The grid future operating trend prediction system of claim 5, wherein: the system further comprises a verification unit, wherein the verification unit is used for verifying the weights by using part of data, judging whether the historical power grid power flow data of the training result is consistent with the actual power grid power flow data, and obtaining the success rate of the historical power grid power flow data and the key characteristics after training until the success rate meets a set threshold.
7. The grid future operating trend prediction system of claim 4, wherein: the estimating module is further used for inputting key features of current new energy power generation fluctuation, bus load prediction errors and scheduling plan abnormality into a model of the relation between the power grid power flow and the influence factors, and estimating future power flow trend of the power grid according to historical power grid power flow data and key features of which the success rate meets a set threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711335875.7A CN109961160B (en) | 2017-12-14 | 2017-12-14 | Power grid future operation trend estimation method and system based on tide parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711335875.7A CN109961160B (en) | 2017-12-14 | 2017-12-14 | Power grid future operation trend estimation method and system based on tide parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961160A CN109961160A (en) | 2019-07-02 |
| CN109961160B true CN109961160B (en) | 2024-01-19 |
Family
ID=67017709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711335875.7A Active CN109961160B (en) | 2017-12-14 | 2017-12-14 | Power grid future operation trend estimation method and system based on tide parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961160B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131331B (en) * | 2020-01-15 | 2022-02-22 | 国网陕西省电力公司电力科学研究院 | Network vulnerability guided information attack-oriented moving target defense deployment optimization method |
| CN111952959B (en) * | 2020-07-14 | 2023-10-13 | 北京科东电力控制系统有限责任公司 | Method, device and storage medium for compressing power grid process simulation time |
| CN115344830A (en) * | 2022-08-02 | 2022-11-15 | 无锡致为数字科技有限公司 | Event probability estimation method based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008512A (en) * | 2014-06-12 | 2014-08-27 | 国家电网公司 | Online stability evaluation index system of electric power system |
| CN104600695A (en) * | 2014-12-29 | 2015-05-06 | 国家电网公司 | Trend load flow calculating method based on online status estimation and real-time scheduling plans |
| CN105071385A (en) * | 2015-08-10 | 2015-11-18 | 国家电网公司 | Power grid operating data real-time analysis system |
| CN106920123A (en) * | 2017-01-18 | 2017-07-04 | 广州大学 | A kind of dining room data analysis system based on machine learning and Internet of Things |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102545172B (en) * | 2011-12-28 | 2014-09-17 | 国电南瑞科技股份有限公司 | Equipment overload successive approximation adaptive control method based on centralized real-time decisions |
-
2017
- 2017-12-14 CN CN201711335875.7A patent/CN109961160B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008512A (en) * | 2014-06-12 | 2014-08-27 | 国家电网公司 | Online stability evaluation index system of electric power system |
| CN104600695A (en) * | 2014-12-29 | 2015-05-06 | 国家电网公司 | Trend load flow calculating method based on online status estimation and real-time scheduling plans |
| CN105071385A (en) * | 2015-08-10 | 2015-11-18 | 国家电网公司 | Power grid operating data real-time analysis system |
| CN106920123A (en) * | 2017-01-18 | 2017-07-04 | 广州大学 | A kind of dining room data analysis system based on machine learning and Internet of Things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961160A (en) | 2019-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN109598416B (en) | Dynamic scheduling system and scheduling method for composite material workshop | |
| CN109961160B (en) | Power grid future operation trend estimation method and system based on tide parameters | |
| CN106951695A (en) | Plant equipment remaining life computational methods and system under multi-state | |
| CN108121215B (en) | Process control loops method of evaluating performance and device based on full loop reconstruct emulation | |
| CN111754024B (en) | Prediction method and system of power industry time series based on regression analysis | |
| CN108133279B (en) | Wind power probability prediction method, storage medium and device | |
| CN107015875B (en) | Method and device for evaluating storage life of electronic complete machine | |
| US9928467B2 (en) | Apparatus for forecasting water demand | |
| US20130338841A1 (en) | Parallel Computation of Dynamic State Estimation for Power System | |
| CN105205326B (en) | A kind of power plant's Real-time Load on-line prediction method | |
| CN102521080A (en) | Computer data recovery method for electricity-consumption information collecting system for power consumers | |
| CN110096036A (en) | A kind of determination method, device and equipment of equipment state | |
| CN114066262A (en) | Method, system and device for estimating cause-tracing reasoning of abnormal indexes after power grid dispatching and storage medium | |
| CN115392037A (en) | Equipment fault prediction method, device, equipment and storage medium | |
| CN103514488B (en) | Power-system short-term load forecasting device and method based on combination forecasting | |
| CN117057785A (en) | Power equipment operation and maintenance scheduling method, system, electronic equipment and storage medium | |
| CN116227248B (en) | Digital twin body construction method and device of gravity energy storage system and electronic equipment | |
| CN116540546A (en) | Recommendation method, system, equipment and medium for control parameters of process control system | |
| CN109840308B (en) | Regional wind power probability forecasting method and system | |
| CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
| CN113341901B (en) | Multi-equipment integrated control method and system based on experimental process | |
| CN113408210A (en) | Deep learning based non-intrusive load splitting method, system, medium, and apparatus | |
| CN111291464A (en) | Dynamic equivalence method and device for power system | |
| CN116934041B (en) | Internet of things collaboration-based factory task management method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |