CN110414034B - Method, system and equipment for early warning of power load climbing - Google Patents

Method, system and equipment for early warning of power load climbing Download PDF

Info

Publication number
CN110414034B
CN110414034B CN201910486670.1A CN201910486670A CN110414034B CN 110414034 B CN110414034 B CN 110414034B CN 201910486670 A CN201910486670 A CN 201910486670A CN 110414034 B CN110414034 B CN 110414034B
Authority
CN
China
Prior art keywords
power
skewness
determining
time series
value
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
Application number
CN201910486670.1A
Other languages
Chinese (zh)
Other versions
CN110414034A (en
Inventor
曾凯文
万杰
刘嘉宁
王海柱
姚坤
王�琦
郭钰锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd, Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN201910486670.1A priority Critical patent/CN110414034B/en
Publication of CN110414034A publication Critical patent/CN110414034A/en
Application granted granted Critical
Publication of CN110414034B publication Critical patent/CN110414034B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06Electricity, gas or water supply
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00Circuit arrangements for ac mains or ac distribution networks
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70Smart grids as climate change mitigation technology in the energy generation sector
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The application discloses a method for early warning of power load climbing, which comprises the following steps: acquiring power grid load data; determining a time sequence of power skewness according to the power grid load data; determining the optimal forecast length according to the time sequence of the power skewness; and establishing a forecasting model corresponding to the optimal forecasting length by using the BP neural network, and forecasting the power skewness by using the forecasting model to finish the early warning of the power load climbing. According to the method and the device, the specific power skewness index parameter is utilized to quantitatively depict the power load climbing event, so that uncertainty of prediction of the power load climbing event is converted into quantitative prediction of the power skewness value, the prediction difficulty is greatly reduced, the power system can use the uncertainty as reference to carry out risk assessment, a reasonable scheduling margin is determined, and safe, stable and efficient operation of the power system is ensured. The application also provides a system, equipment and computer readable storage medium for the power load climbing early warning, and the system, the equipment and the computer readable storage medium have the beneficial effects.

Description

Method, system and equipment for early warning of power load climbing
Technical Field
The present application relates to the field of electrical engineering, and in particular, to a method, a system, a device, and a computer-readable storage medium for early warning of power load climbing.
Background
The power load prediction has a very important influence on the system operation and production cost, and is mainly used for unit optimization combination, economic power flow control, water, fire and electricity coordination and the like. The accurate load prediction can economically and reasonably arrange the start-up and the maintenance of the generator set in the power grid, maintain the safety and the stability of the operation of the power grid, reduce the unnecessary rotary reserve capacity, reasonably arrange the maintenance plan of the generator set, ensure the normal production and the life of the society, effectively reduce the power generation cost and improve the economic benefit and the social benefit. Therefore, existing research efforts have been mainly developed around the load prediction method and its accuracy.
Load maximum prediction is generally a major concern in short-term prediction. Meanwhile, with the continuous development and change of the structure form of the power grid and the like, the abrupt change of the power in a short time affects the safe operation of the power system; especially during peak and valley periods of the load, such load climbing events are more threatening. For regional power grids, impact influence caused by actual power load climbing events needs to be more emphasized.
Therefore, how to early warn the power load climbing is a technical problem that needs to be solved by those skilled in the art at present.
Disclosure of Invention
The application aims to provide a method, a system, equipment and a computer readable storage medium for early warning of power load climbing, which are used for early warning of power load climbing.
In order to solve the technical problem, the application provides a method for warning power load climbing, which comprises the following steps:
acquiring power grid load data;
determining a time sequence of power skewness according to the power grid load data; wherein the power skewness is used to represent the degree of deviation of the electrical load from a normal central value;
determining an optimal forecast length according to the time sequence of the power skewness;
and establishing a forecasting model corresponding to the optimal forecasting length by using a BP neural network, and forecasting the power skewness by using the forecasting model to finish early warning of power load climbing.
Optionally, determining a time sequence of power skewness according to the power grid load data includes:
according to the formulaDetermining a time series of the power skewness;
wherein p isw,tFor the time series of the power skewness, p (i x Δ t) is a power load discrete time series, N is a total number of samples, Δ t is a sampling time interval,is the mean value of the power in the sampling time, prmsIs the rms value of the power over the sampling time.
Optionally, determining an optimal prediction length of the power skew according to the time series of the power skewness includes:
according to the formulaCalculating the covariance after delaying k step lengths;
according to the formulaCalculating an autocorrelation coefficient;
determining a k value corresponding to an autocorrelation coefficient closest to a first preset value as the optimal forecast length of the power skewness;
where k is the delay step, n is the length of the time series of power skews,is the mean of the time series of the power skewness, pw,t+kA time series p of said power skewnessw,tA time series obtained by delaying k steps, γ (k) is a covariance after delaying k steps, γ (0) is a covariance when delay step k is 0, and ρ (k) is an autocorrelation obtained by delaying k stepsAnd (4) the coefficient.
Optionally, the forecasting model is used to forecast the power skew, so as to complete the early warning of the power load climbing, including:
calculating a power distortion value within the optimal forecast length using the forecast model;
and sending out an alarm when the absolute value of the power distortion value exceeds a second preset value.
The application also provides a system for power load climbing early warning, and the system comprises:
the acquisition module is used for acquiring power grid load data;
the first determining module is used for determining a time sequence of power skewness according to the power grid load data; wherein the power skewness is used to represent the degree of deviation of the electrical load from a normal central value;
a second determining module, configured to determine an optimal prediction length according to the time series of power skewness;
and the forecasting module is used for establishing a forecasting model corresponding to the optimal forecasting length by using a BP (back propagation) neural network, forecasting the power skewness by using the forecasting model and finishing early warning on the power load climbing.
Optionally, the first determining module includes:
a first determining submodule for determining a first equationDetermining a time series of the power skewness;
wherein p isw,tFor the time series of the power skewness, p (i x Δ t) is a power load discrete time series, N is a total number of samples, Δ t is a sampling time interval,is the mean value of the power in the sampling time, prmsIs the rms value of the power over the sampling time.
Optionally, the second determining module includes:
first meterAn operator module for calculating a formulaCalculating the covariance after delaying k step lengths;
a second calculation submodule for calculating according to a formulaCalculating an autocorrelation coefficient;
the second determining submodule is used for determining that the k value corresponding to the autocorrelation coefficient closest to the first preset value is the optimal forecast length of the power skewness;
where k is the delay step, n is the length of the time series of power skews,is the mean of the time series of the power skewness, pw,t+kA time series p of said power skewnessw,tIn the time series obtained by delaying k steps, γ (k) is a covariance after delaying k steps, γ (0) is a covariance when delay step k is 0, and ρ (k) is an autocorrelation coefficient obtained by delaying k steps.
Optionally, the forecasting module includes:
a third computing submodule for computing a power distortion value within the optimal forecast length using the forecast model;
and the alarm submodule is used for sending out an alarm when the absolute value of the power skew value exceeds a second preset value.
The application also provides a power load climbing early warning device, and this power load climbing early warning device includes:
a memory for storing a computer program;
a processor for implementing the steps of the method for power load hill climbing warning as described in any one of the above when the computer program is executed.
The present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the method for power load climbing warning according to any one of the above embodiments.
The application provides a method for early warning of power load climbing, which comprises the following steps: acquiring power grid load data; determining a time sequence of power skewness according to the power grid load data; wherein, the power skewness is used for representing the deviation degree of the power load from the normal central value; determining the optimal forecast length according to the time sequence of the power skewness; and establishing a forecasting model corresponding to the optimal forecasting length by using the BP neural network, and forecasting the power skewness by using the forecasting model to finish the early warning of the power load climbing.
According to the technical scheme provided by the application, the specific power skewness index parameter is utilized to quantitatively depict the power load climbing event, so that the uncertainty of prediction of the power load climbing event is converted into quantitative prediction of the power skewness value, and the prediction difficulty is greatly reduced; meanwhile, the optimal prediction length is determined according to the time sequence of the power distortion, a BP neural network is further utilized to establish a prediction model, the power distortion is predicted by utilizing the prediction model, and the power system can perform risk assessment by taking the prediction model as a reference, determine a reasonable scheduling margin and ensure the safe, stable and efficient operation of the power system. The application also provides a system, equipment and computer readable storage medium for power load climbing early warning, which have the beneficial effects and are not repeated herein.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for warning a power load climbing according to an embodiment of the present disclosure;
fig. 2 is a flowchart of an actual representation of S103 in the method for warning a power load climbing as provided in fig. 1;
fig. 3 is a structural diagram of a system for warning a power load climbing according to an embodiment of the present disclosure;
fig. 4 is a block diagram of another system for warning of power load climbing according to an embodiment of the present disclosure;
fig. 5 is a structural diagram of an electric load climbing early warning device according to an embodiment of the present application.
Detailed Description
The core of the application is to provide a method, a system, equipment and a computer readable storage medium for early warning of power load climbing, which are used for early warning of power load climbing.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.
Referring to fig. 1, fig. 1 is a flowchart of a method for warning of power load climbing according to an embodiment of the present disclosure.
The method specifically comprises the following steps:
s101: acquiring power grid load data;
with the continuous development and change of the structure form of the power grid and the like, the abrupt change of the power in a short time influences the safe operation of the power system; especially during peak and valley periods of the load, such load climbing events are more threatening. For regional power grids, impact influence caused by actual power load climbing events needs to be more emphasized.
Therefore, the application provides a method for early warning of power load climbing, which quantitatively describes a power load climbing event by using a specific 'power skewness' index parameter so as to predict the power load climbing event.
S102: determining a time sequence of power skewness according to the power grid load data;
the power skewness mentioned here is used for representing the deviation degree of the power load from a normal central value, and the purpose of the method is to convert the uncertainty of prediction of the power load climbing event into quantitative prediction of the power skewness value, so as to reduce the prediction difficulty;
optionally, the determining a time series of power skewness according to the grid load data may specifically be:
according to the formulaDetermining a time series of power skewness;
wherein p isw,tFor the time series of power skewness, p (i x Δ t) is the discrete time series of the power load, N is the total number of samples, Δ t is the sampling time interval,the average value of the power in the sampling time can be calculated according to the formulaCalculating; p is a radical ofrmsThe RMS value of the power in the sampling time can be expressed according to the formulaCalculating;
according to the calculation method, the skewness index is a three-order moment statistical average of signals, is a dimensionless relative value and can reflect the asymmetry of the vibration signals; taking the vibration signal as an example, if there is friction or collision in a certain direction, resulting in asymmetry of the vibration waveform, the distortion index will increase. Similarly, when the power load climbing event occurs, the waveform of the normal power signal is also asymmetric;
therefore, the power distortion pwMay indicate a condition in which the electrical load deviates from a normal center value over a period of time; when climbing occursWhen the value is constant, the value will increase or decrease; wherein, negative climbing (load drop) corresponding to negative value; the positive value corresponds to positive climbing (load is steep rise), so that the parameter of power skewness can be used for quantitatively depicting and describing a load climbing event;
optionally, since 4 hours and 24 hours are two key scheduling time scales of the power system, respectively, the selected index time scale (number of samples) may also be selected to be 4 hours and 24 hours. And, the hourly power for 4 hours is phwThe power distortion per day is p for 24 hoursdw
S103: determining the optimal forecast length according to the time sequence of the power skewness;
the power system needs to guarantee the balance of energy supply and demand, in order to guarantee the safe and stable operation of the system, the power system needs to provide enough rotation reserve by means of load prediction, if relevant prediction information related to the occurrence of a load climbing event can be provided in advance, an important reference value is provided for the power system to make a scheduling plan, the optimal forecast length is determined according to the time sequence of power skewness, and the purpose is to analyze the forecastability of the time sequence of the power skewness on the basis of the step S101;
alternatively, the steps may be specifically the steps shown in fig. 2, and the following description is made with reference to fig. 2.
Referring to fig. 2, fig. 2 is a flowchart illustrating an actual representation manner of S103 in the method for warning a power load climbing as provided in fig. 1.
The method specifically comprises the following steps:
s201: according to the formulaCalculating the covariance after delaying k step lengths;
s202: according to the formulaCalculating an autocorrelation coefficient;
s203: and determining the k value corresponding to the autocorrelation coefficient closest to the first preset value as the optimal forecast length of the power skewness.
Where k is the delay step, n is the length of the time series of power skews,is the mean value of a time series of power skews, pw,t+kAs a time sequence p of power skewsw,tA time series obtained by delaying k steps, wherein gamma (k) is a covariance after delaying k steps, gamma (0) is a covariance when a delay step k is equal to 0, and rho (k) is an autocorrelation coefficient obtained by delaying k steps;
the embodiment of the application utilizes a Pearson autocorrelation analysis method to research the predictability of the time series of the power skewness pw,tDelayed by a time sequence p of k stepsw,t+kThe autocorrelation coefficient between the two signals represents the correlation degree of the two signals, the larger the autocorrelation coefficient is, the stronger dependence relationship exists between the two signals, and the hidden rule in the data can be mined by a statistical method to realize the prediction of future data. The k steps at this time represent the autocorrelation length, i.e., the optimal prediction length of the power skew.
Preferably, the autocorrelation coefficients have a decreasing trend as the autocorrelation length increases. Moreover, the autocorrelation coefficient is 0.5-0.8, which indicates that strong correlation exists between the data, so that the first preset value can be set to be 0.6. A strong dependence exists between the autocorrelation coefficient and the signal in the autocorrelation time range which is closest to 0.6, and the time scale is the optimal prediction length; furthermore, a statistical method can be adopted to predict the power distortion in the future optimal forecast length time by using the historical power distortion;
alternatively, the same method may be used to predict both the hourly power distortion and the daily power distortion and determine the optimal prediction length.
S104: and establishing a forecasting model corresponding to the optimal forecasting length by using the BP neural network, and forecasting the power skewness by using the forecasting model to finish the early warning of the power load climbing.
The BP neural network is a multilayer feedforward network trained according to error back propagation (error back propagation for short), the algorithm is called BP algorithm, the basic idea is a gradient descent method, a gradient search technology is utilized, so that the mean square error of the error between the actual output value and the expected output value of the network is minimum, the BP neural network is utilized to establish a forecasting model corresponding to the optimal forecasting length, the BP neural network has strong nonlinear mapping capability and a flexible network structure, the number of middle layers of the network and the number of neurons of each layer can be set randomly according to specific conditions, and the performance of the BP neural network is different along with the difference of the structure.
The purpose of establishing a forecasting model corresponding to the optimal forecasting length by using the BP neural network and forecasting the power skewness by using the forecasting model is that the power system can make a more reasonable and economic dispatching plan according to the forecasting result of the power skewness, provide more rotary standby in the time period of predicting the occurrence of a large power load climbing event and ensure the safe, efficient and stable operation of the regional power system;
optionally, the forecasting of the power skew by using the forecasting model mentioned here is performed to finish the early warning of the power load climbing, and specifically, the method may also be:
calculating a power distortion value within the optimal prediction length by using a prediction model;
and sending out an alarm when the absolute value of the power distortion value exceeds a second preset value.
Based on the technical scheme, the method for early warning of the power load climbing provided by the application quantitatively describes the power load climbing event by using the specific power skewness index parameter, so that the uncertainty of prediction of the power load climbing event is converted into quantitative prediction of the power skewness value, and the prediction difficulty is greatly reduced; meanwhile, the optimal prediction length is determined according to the time sequence of the power distortion, a BP neural network is further utilized to establish a prediction model, the power distortion is predicted by utilizing the prediction model, and the power system can perform risk assessment by taking the prediction model as a reference, determine a reasonable scheduling margin and ensure the safe, stable and efficient operation of the power system.
Referring to fig. 3, fig. 3 is a structural diagram of a system for warning a power load climbing according to an embodiment of the present disclosure.
The system may include:
an obtaining module 100, configured to obtain power grid load data;
a first determining module 200, configured to determine a time series of power skewness according to the grid load data; wherein, the power skewness is used for representing the deviation degree of the power load from the normal central value;
a second determining module 300, configured to determine an optimal prediction length according to the time series of power skewness;
the forecasting module 400 is configured to establish a forecasting model corresponding to the optimal forecasting length by using the BP neural network, and forecast power skewness by using the forecasting model to complete early warning of power load climbing.
Referring to fig. 4, fig. 4 is a structural diagram of another power load climbing warning system according to an embodiment of the present disclosure.
The first determining module 200 may include:
a first determining submodule for determining a first equationDetermining a time series of power skewness;
wherein p isw,tFor the time series of power skewness, p (i x Δ t) is the discrete time series of the power load, N is the total number of samples, Δ t is the sampling time interval,is the mean value of the power in the sampling time, prmsIs the rms value of the power over the sampling time.
The second determining module 300 may include:
a first calculation submodule for calculating according to a formulaAfter calculating the delay of k stepsThe covariance of (a);
a second calculation submodule for calculating according to a formulaCalculating an autocorrelation coefficient;
the second determining submodule is used for determining the k value corresponding to the autocorrelation coefficient closest to the first preset value as the optimal forecast length of the power skewness;
where k is the delay step, n is the length of the time series of power skews,is the mean value of a time series of power skews, pw,t+kAs a time sequence p of power skewsw,tIn the time series obtained by delaying k steps, γ (k) is a covariance after delaying k steps, γ (0) is a covariance when delay step k is 0, and ρ (k) is an autocorrelation coefficient obtained by delaying k steps.
The forecasting module 400 may include:
a third calculation submodule for calculating a power distortion value within the optimum forecast length using the forecast model;
and the alarm submodule is used for sending out an alarm when the absolute value of the power skew value exceeds a second preset value.
The various components of the above system may be practically applied in the following embodiments:
the acquisition module acquires power grid load data; the first determining submodule is based on formulaDetermining a time series of power skewness; the first calculation submodule is based on formulaCalculating the covariance after delaying k step lengths; the second calculation submodule is based on formulaComputingAn autocorrelation coefficient;
the second determining submodule determines the k value corresponding to the autocorrelation coefficient closest to the first preset value as the optimal forecast length of the power skewness; the third calculation submodule calculates a power distortion value within the optimal forecast length by using the forecast model; the alarm sub-module issues an alarm when the absolute value of the power skew value exceeds a second preset value.
Referring to fig. 5, fig. 5 is a structural diagram of an electric load climbing warning device according to an embodiment of the present disclosure.
The power load climbing warning device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 522 (e.g., one or more processors) and a memory 532, one or more storage media 530 (e.g., one or more mass storage devices) storing applications 542 or data 544. Memory 532 and storage media 530 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a sequence of instruction operations for the device. Still further, the central processor 522 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the power load climbing warning device 500.
The power load climb warning device 500 may also include one or more power supplies 525, one or more wired or wireless network interfaces 550, one or more input-output interfaces 558, and/or one or more operating systems 541, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
The steps in the method for warning the power load climbing described above with reference to fig. 1 to 2 are implemented by the power load climbing warning device based on the structure shown in fig. 5.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a function calling device, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
A method, a system, a device and a computer readable storage medium for power load climbing warning provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Claims (10)

1. A method for early warning of power load climbing is characterized by comprising the following steps:
acquiring power grid load data;
determining a time sequence of power skewness according to the power grid load data; wherein the power skewness is used to represent the degree of deviation of the electrical load from a normal central value;
determining an optimal forecast length according to the time sequence of the power skewness;
and establishing a forecasting model corresponding to the optimal forecasting length by using a BP neural network, and forecasting the power skewness by using the forecasting model to finish early warning of power load climbing.
2. The method of claim 1, wherein determining a time series of power skewness from the grid load data comprises:
according to the formulaDetermining a time series of the power skewness;
wherein p isw,tFor the time series of the power skewness, p (i Δ @)t) For a discrete time series of power loads, N is the total number of samples, ΔtIn order to sample the time interval between the samples,is the mean value of the power in the sampling time, prmsIs the rms value of the power over the sampling time.
3. The method of claim 1, wherein determining an optimal forecast length for the power distortion based on the time series of power distortions comprises:
according to the formulaCalculating the covariance after delaying k step lengths;
according to the formulaCalculating an autocorrelation coefficient;
determining a k value corresponding to an autocorrelation coefficient closest to a first preset value as the optimal forecast length of the power skewness;
where k is the delay step, n is the length of the time series of power skews,is the mean of the time series of the power skewness, pw,t+kA time series p of said power skewnessw,tIn the time series obtained by delaying k steps, γ (k) is a covariance after delaying k steps, γ (0) is a covariance when delay step k is 0, and ρ (k) is an autocorrelation coefficient obtained by delaying k steps.
4. The method of claim 1, wherein forecasting the power skewness using the forecasting model to complete pre-warning of power load climbing comprises:
calculating a power distortion value within the optimal forecast length using the forecast model;
and sending out an alarm when the absolute value of the power distortion value exceeds a second preset value.
5. A system for early warning of power load climbing, comprising:
the acquisition module is used for acquiring power grid load data;
the first determining module is used for determining a time sequence of power skewness according to the power grid load data; wherein the power skewness is used to represent the degree of deviation of the electrical load from a normal central value;
a second determining module, configured to determine an optimal prediction length according to the time series of power skewness;
and the forecasting module is used for establishing a forecasting model corresponding to the optimal forecasting length by using a BP (back propagation) neural network, forecasting the power skewness by using the forecasting model and finishing early warning on the power load climbing.
6. The system of claim 5, wherein the first determining module comprises:
a first determining submodule for determining a first equationDetermining a time series of the power skewness;
wherein p isw,tFor the time series of the power skewness, p (i Δ @)t) For a discrete time series of power loads, N is the total number of samples, ΔtIn order to sample the time interval between the samples,is the mean value of the power in the sampling time, prmsIs the rms value of the power over the sampling time.
7. The system of claim 5, wherein the second determining module comprises:
a first calculation submodule for calculating according to a formulaCalculating the covariance after delaying k step lengths;
a second calculation submodule for calculating according to a formulaCalculating an autocorrelation coefficient;
the second determining submodule is used for determining that the k value corresponding to the autocorrelation coefficient closest to the first preset value is the optimal forecast length of the power skewness;
where k is the delay step, n is the length of the time series of power skews,is the mean of the time series of the power skewness, pw,t+kA time series p of said power skewnessw,tA time series obtained by delaying k steps, where γ (k) is a covariance after delaying k steps, γ (0) is a covariance when delay step k is 0,ρ (k) is an autocorrelation coefficient obtained by delaying by k steps.
8. The system of claim 5, wherein the forecasting module comprises:
a third computing submodule for computing a power distortion value within the optimal forecast length using the forecast model;
and the alarm submodule is used for sending out an alarm when the absolute value of the power skew value exceeds a second preset value.
9. An electric load climbing early warning device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of power load hill climbing warning as claimed in any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, having a computer program stored thereon, which, when being executed by a processor, carries out the steps of the method for power load hill climbing warning according to any one of claims 1 to 4.
CN201910486670.1A 2019-06-05 2019-06-05 Method, system and equipment for early warning of power load climbing Active CN110414034B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910486670.1A CN110414034B (en) 2019-06-05 2019-06-05 Method, system and equipment for early warning of power load climbing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910486670.1A CN110414034B (en) 2019-06-05 2019-06-05 Method, system and equipment for early warning of power load climbing

Publications (2)

Publication Number Publication Date
CN110414034A CN110414034A (en) 2019-11-05
CN110414034B true CN110414034B (en) 2021-06-29

Family

ID=68358230

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910486670.1A Active CN110414034B (en) 2019-06-05 2019-06-05 Method, system and equipment for early warning of power load climbing

Country Status (1)

Country Link
CN (1) CN110414034B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103400039A (en) * 2013-07-31 2013-11-20 武汉大学 Wind power climbing prediction model switching method based on gale weather classification
US8696104B1 (en) * 2012-10-16 2014-04-15 Xerox Corporation Motion quality improvement by feed-forward torque control of imaging drum
CN105262117A (en) * 2015-11-12 2016-01-20 四川大学 Wind power climbing optimization control method
CN106786736A (en) * 2016-12-20 2017-05-31 国家电网公司 Wind-powered electricity generation energy storage source power and capacity configuration optimizing method based on economic load dispatching
CN106897789A (en) * 2017-01-03 2017-06-27 内蒙古电力(集团)有限责任公司 A kind of active power for wind power climbing event detecting method and device
CN108764738A (en) * 2018-05-31 2018-11-06 四川大学 A kind of city power transmission network safe probability appraisal procedure considering elastic nargin
CN109658006A (en) * 2018-12-30 2019-04-19 广东电网有限责任公司 A kind of large-scale wind power field group auxiliary dispatching method and device
CN109829624A (en) * 2018-12-29 2019-05-31 华北电力大学 A kind of wind-powered electricity generation cooperative game climbing control method and device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8696104B1 (en) * 2012-10-16 2014-04-15 Xerox Corporation Motion quality improvement by feed-forward torque control of imaging drum
CN103400039A (en) * 2013-07-31 2013-11-20 武汉大学 Wind power climbing prediction model switching method based on gale weather classification
CN105262117A (en) * 2015-11-12 2016-01-20 四川大学 Wind power climbing optimization control method
CN106786736A (en) * 2016-12-20 2017-05-31 国家电网公司 Wind-powered electricity generation energy storage source power and capacity configuration optimizing method based on economic load dispatching
CN106897789A (en) * 2017-01-03 2017-06-27 内蒙古电力(集团)有限责任公司 A kind of active power for wind power climbing event detecting method and device
CN108764738A (en) * 2018-05-31 2018-11-06 四川大学 A kind of city power transmission network safe probability appraisal procedure considering elastic nargin
CN109829624A (en) * 2018-12-29 2019-05-31 华北电力大学 A kind of wind-powered electricity generation cooperative game climbing control method and device
CN109658006A (en) * 2018-12-30 2019-04-19 广东电网有限责任公司 A kind of large-scale wind power field group auxiliary dispatching method and device

Also Published As

Publication number Publication date
CN110414034A (en) 2019-11-05

Similar Documents

Publication Publication Date Title
Zheng et al. Prediction of wind farm power ramp rates: A data-mining approach
US9020874B2 (en) Short-term load forecast using support vector regression and feature learning
WO2014176930A1 (en) Short-term operation optimization method for electric power system having large-scale wind power
US9792568B2 (en) Generating a capacity schedule for a facility
CN103283104A (en) Power control system and method for controlling power
EP3200316B1 (en) Electric power system monitoring device and electric power system monitoring system
CN103683277A (en) Calculation method for transient-stability load-shedding control validity evaluation indexes of power system
US20180054059A1 (en) System stabilization control device and power system control system
CN103679282B (en) The Forecasting Methodology of wind power climbing
Yuan et al. Adaptive hybrid model for long term load prediction in computational grid
CN110414034B (en) Method, system and equipment for early warning of power load climbing
Tang et al. Hybrid prediction approach based on weekly similarities of traffic flow for different temporal scales
JP2017169289A (en) Power prediction system, power prediction method, and program
Wang et al. Dynamic heat supply prediction using support vector regression optimized by particle swarm optimization algorithm
CN108520170A (en) A kind of computational methods and device of wire breaking and tower falling probabilistic model
Xu et al. Calculating reserve power requirements from wind–power forecasts
CN111680841A (en) Short-term load prediction method and system based on principal component analysis and terminal equipment
CN109799864B (en) Method and device for predicting overall generated power of regional small hydropower station
JP2019216534A (en) Electric power system monitoring system, electric power system monitoring method, and program
JP2020092533A (en) Power supply and demand planning device
JP5833267B1 (en) Power generation amount predicting control device, power generation amount prediction method, and power generation amount prediction program
Prakash et al. Modified interval‐based generator scheduling for PFR adequacy under uncertain PV generation
Zhou et al. Wind power forecasting based on econometrics theory
WO2017149617A1 (en) Control device, supply/demand adjustment control device, power storage device, output control device, supply/demand adjustment system, control method, supply/demand adjustment method, and program
CN107332237B (en) Optimization method and device for direct current channel power transmission plan

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