CN113468811B - Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit - Google Patents
Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit Download PDFInfo
- Publication number
- CN113468811B CN113468811B CN202110763793.2A CN202110763793A CN113468811B CN 113468811 B CN113468811 B CN 113468811B CN 202110763793 A CN202110763793 A CN 202110763793A CN 113468811 B CN113468811 B CN 113468811B
- Authority
- CN
- China
- Prior art keywords
- prediction error
- power generation
- new energy
- standby
- load
- 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 99
- 238000010248 power generation Methods 0.000 claims abstract description 162
- 238000009826 distribution Methods 0.000 claims abstract description 63
- 238000003860 storage Methods 0.000 claims abstract description 18
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 230000003827 upregulation Effects 0.000 claims description 25
- 230000003828 downregulation Effects 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 8
- 238000005520 cutting process Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 230000001932 seasonal effect Effects 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 230000035515 penetration Effects 0.000 description 3
- 238000002922 simulated annealing Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241000006411 Damias Species 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002222 downregulating effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000012421 spiking Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid 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]
Abstract
The invention discloses a power grid reserve capacity probabilistic dynamic assessment method, a system, a terminal and a readable storage medium containing a new energy unit. Firstly, analyzing probability characteristics of new energy power generation prediction errors and load prediction errors, clustering the new energy power generation and the load prediction errors based on an improved fuzzy C-means clustering algorithm, estimating the kernel density of the new energy power generation prediction errors of each type, fitting normal distribution of the load prediction error probability densities of each type, and establishing probability density models of the new energy power generation prediction errors and the load prediction errors; then, carrying out convolution integral on probability density of two prediction errors, and establishing an equivalent standby probability density model; and integrating the equivalent standby probability density to obtain a probability distribution model, solving a confidence coefficient optimization model based on the optimal cost, and obtaining the optimal confidence coefficient corresponding to each equivalent standby category, thereby realizing the determination of the optimal standby capacity.
Description
Technical Field
The invention belongs to the technical field of power system reserve capacity evaluation, and particularly relates to a power grid reserve capacity probabilistic dynamic evaluation method, a system, a terminal and a readable storage medium containing a new energy unit.
Background
With the rapid increase of new energy grid connection, the load shedding and machine shedding events caused by the uncertainty of new energy power generation threaten the stable operation of the power system. Because electric energy cannot be stored in a large quantity, a certain load reserve is added to the electric power system to meet the electric power market demand by considering the electric power demand of a user and the uncertainty of the new energy power generation prediction before the high-proportion new energy power generation is connected. The traditional power system adopts a deterministic method, namely, the maximum value of the daily electricity demand of 2% -5% or the maximum unit capacity is used as the lower limit of the load reserve, and the load reserve of the power system is determined without taking the uncertainty factor of new energy power generation into consideration, which is definitely specified in the technical guidelines of the power system. Although the deterministic method is easy to implement, without theoretical support, a reasonable standby value cannot be determined.
On one hand, with the rapid development of the installed capacity of new energy power generation, the deterministic method cannot solve the problem of electric energy shortage caused by the fact that the actual output of the new energy in the electric power system is less than a predicted value, so that the electric power system loses safety and stability; on the other hand, the deterministic method cannot solve the problem that the current reserve capacity standard is larger than the actually required reserve capacity because the actual output of the new energy is larger than the predicted value, thereby causing economic loss. Therefore, in the new energy high-duty ratio power grid, it is important to reserve reasonable and effective spare capacity, and the requirement can not only solve unbalanced power caused by new energy power generation grid connection, but also realize economy and environmental protection.
Most students determine spare capacity based on statistical methods, data driven and risk control methods. Document "Holttinen Hannele, milligan Michael, kirby Brendan, et al use Standard Deviation as a Measure of Increased Operational Reserve Requirement for Wind Power [ J ]. Wind Engineering,2008,32 (4): 355-377," statistical method based on Sigma (standard deviation) was used to evaluate the effect of Wind power generation on the backup capacity of an electrical system, applied to different time scales and time sequences. The literature "Ortega-Vazquez M.A., kirschen D.S. timing the Spinning Reserve Requirements in Systems With Significant Wind Power Generation Penetration [ J ]. IEEE Transactions on Power Systems,2009,24 (1): 114-124," uses a mixed integer programming method to determine spare capacity and uses Monte Carlo simulation. This approach predicts reserve capacity based on deterministic criteria, taking into account random errors. The literature Liu J.T., feng S.H., wang K., et al method to determine spinning reserve requirement for a grid with large-scale wind power penetration [ J ]. The Journal of Engineering,2017 (13): 1686-1691 ] adopts a probability model method to respectively establish a probability model of outage capacity, a probability model of equivalent load prediction error, a probability model of unbalanced power of the system and a reserve capacity optimization model, and evaluates the reserve requirement of the high-proportion new energy power system. Document "Muzhikyan Aramazd, farid Amro m., youcef-Toumi kamal.an a priori analytical method for the determination of operating reserve requirements [ J ]. International Journal of Electrical Power & Energy Systems,2017,86:1-17," proposes a formal mathematical framework, in combination with probability distributions, for determining three types of operating standby requirements, namely load tracking, ramping and regulation, a priori. The literature "Mousavi Agah S.Mohammad, flynn Damia. Image of modeling non-normality and stochastic dependence of variables on operating reserve determination of power Systems with high penetration of wind power [ J ]. International Journal of Electrical Power & Energy Systems,2018, 97:146-154" proposes a method for dynamically determining the operational reserve requirements of a wind power system by taking into account the uncertainty of wind power and the non-normative nature of the variability and its random dependence on wind power predictions, and quantifying the reserve requirements by taking into account the risk of uncertainty of load and wind power variability.
In summary, the existing reserve capacity standard cannot meet the requirement of the new energy high-duty power grid, and the current research directly aiming at the reserve capacity of the new energy high-duty power grid cannot well adapt to the fluctuation of new energy power generation and the consideration of lack of economy.
Disclosure of Invention
The invention aims to provide a power grid reserve capacity probabilistic dynamic assessment method, a system, a terminal and a readable storage medium containing a new energy unit, which are used for solving the inadaptation of the existing reserve capacity standard under a new energy high-duty ratio scene. The invention makes up the defect that the deterministic prediction can only give out the determined prediction information by utilizing the probability prediction, can reflect the prediction error characteristic, and simultaneously considers the influence of the new energy power generation prediction error and the load prediction error, thereby improving the accuracy of the determination of the reserve capacity; and the prediction errors and the load prediction errors of the corresponding new energy power generation in the history period are classified, so that different categories have different probability distributions of equivalent reserve, the predicted reserve capacity is more reliable, the prediction results of the different categories have differences, the dynamic evaluation of the reserve capacity is realized, the method can be more suitable for the randomness and the fluctuation of the new energy power generation, and the economic trend requirement is met.
On the one hand, the invention provides a power grid reserve capacity probabilistic dynamic assessment method containing a new energy unit, which comprises the following steps:
s1: acquiring power generation historical data and load historical data in a historical period in a power grid containing a new energy unit, and taking a new energy power generation prediction error and a load prediction error calculated based on the power generation historical data and the load historical data as samples;
s2: classifying the corresponding new energy power generation prediction error and load prediction error in the history period;
s3: respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
s4: calculating to obtain the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
the equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
S5: and selecting the confidence coefficient, and obtaining the spare capacity based on the selected confidence coefficient and the probability distribution of the equivalent spare of the category to which the confidence coefficient belongs.
The power grid reserve capacity probabilistic dynamic assessment method containing the new energy unit can be applied to dynamic assessment of the power grid reserve capacity containing the new energy, and has a particularly remarkable effect in the power grid with the high new energy occupancy rate. The probability characteristics of the new energy power generation prediction error and the load prediction error are analyzed, the defect that the deterministic prediction can only give out the determined prediction information is overcome by adopting a probabilistic method, and the influence of the new energy power generation prediction error and the load prediction error is considered, so that the reserve capacity can be determined more accurately. In particular, the invention classifies the corresponding new energy power generation prediction error and load prediction error in the history period, classifies similar data into one category by classification, classifies data with different characteristics into different categories, is more suitable for the timeliness and uncertainty of prediction, and realizes the dynamic evaluation of spare capacity.
Optionally, in step S2, when classifying the prediction error of new energy power generation corresponding to the history period, the method includes: classifying according to two or more time period lengths as units respectively; or simultaneously classifying by taking the predicted power data quantity as a standard and classifying by taking two or more time period lengths as units respectively;
The classification process taking the predicted power data quantity as a standard comprises the following steps:
sequencing new energy power generation prediction error samples according to the power generation prediction power value in the power generation history data in the history period;
equally dividing new energy power generation prediction error samples according to the sample data volume;
when classifying according to two or more time period lengths as units, respectively, a clustering algorithm is adopted for classifying.
When the prediction errors of the new energy power generation corresponding to the historical period are classified, the time period is taken as a unit to divide the classification result, so that the classification result has timeliness, different time periods correspond to different types of models, the standby capacity of the prediction time period is obtained by utilizing the probability distribution of the equivalent standby of the belonging type, the prediction result of different time periods is caused to have variability, and the dynamic evaluation is realized on a time axis.
In addition, the invention considers the correlation between the new energy power generation prediction error and the predicted power, segments the new energy power generation prediction error according to the data quantity, and can embody the predicted power characteristics of different prediction errors.
Optionally, when the units are classified according to at least two or more time periods, the selected time periods are tmin and 1 month, and tmin is a sampling interval of the power generation history data and the load history data;
The method comprises the following steps of adopting fuzzy C-means clustering to classify, taking average absolute error, standard deviation, average relative error value and average error value as clustering indexes, and taking a certain period length as a unit to classify the corresponding new energy power generation prediction error in a history period:
s2.2.1: extracting a clustering index of data in the same period, and constructing a clustering index sample set E= { E by using the clustering index 1 ,e 2 ,...，e j ,...，e n1 N1 is the number of time periods, any jth time period sample e j A one-dimensional vector composed of p cluster indexes;
s2.2.2: setting an upper limit value S of iteration times, a class number c (c is more than or equal to 2 and less than or equal to n 1), a minimum value epsilon of iteration termination and a weighting index m;
s2.2.3: initializing a cluster center C= { C 1 ,c 2 ,...,c i ,...,c c }，c i Is the cluster center of the i-th group;
s2.2.4: updating the membership matrix u= (U) according to the following membership formula and cluster center updating formula ij ) c×n1 Clustering the center C until the iteration termination condition is met;
wherein u is ij For the j-th index e j Membership to the cluster center of the i-th group,
and taking the class of the maximum membership degree in the membership degrees corresponding to the samples in the membership degree matrix after iteration is terminated as the class to which the samples belong.
Compared with classification, the method adopts fuzzy C-means clustering to segment the prediction error, and the clustering analysis is divided by the thought of 'the difference between classes is as large as possible and the difference between classes is as small as possible', and has no preset class, so that similar data can be divided into classes according to the characteristics of the data, and the data with different characteristics can be divided into different classes, so that the method is more suitable for the seasonal and time-interval segmentation of the prediction error. Compared with the common hard clustering, the fuzzy C-means clustering (FCM) provides the membership degree of each sample to the clustering center, and can obtain more flexible clustering results.
Optionally, the power generation history data includes a predicted power value P of power generation per day per tmin in the history period WFt (MW), actual Power Generation measurement value P WMt (MW) and installed Capacity P it (MW); the load history data includes a load predicted power value P per tmin in a history period LFt (MW), actual load measurement P LMt (MW)；
The new energy power generation prediction error and the load prediction error are expressed as follows:
e Lt ＝P LMt -P LFt
in the formula e Wtpu 、e Lt The new energy power generation prediction error and the load prediction error of tmin are respectively represented.
In the invention, the research of taking original data as a sample to prepare spare capacity can not meet the requirement of the change of the installed capacity in consideration of the rapid increase speed of the installed capacity of the new energy power generation, the calculation of the prediction error introduces the concept of 'output ratio', and the power value of the new energy power generation is normalized to be in the interval of [0,1 ].
Optionally, in step S3, the new energy power generation prediction error probability density model is established based on kernel density estimation in a non-parameter model, and the load prediction error probability density model is established based on normal distribution fitting.
If Gaussian kernel function is selected, the new energy power generation predicts the error probability densityExpressed as:
the load prediction error probability density f (e Lt ) Expressed as:
in the method, in the process of the invention,nuclear density estimation of predictive error output ratio for new energy power generation, P i Indicating the installed capacity of wind power, e W For the new energy power generation prediction error, n is the number of samples of the new energy power generation prediction error, and each new energy power generation prediction error sample corresponds to one e Wtpu Value h is window width, e Wpu Predicting error output ratio for new energy, wherein e is natural constant and sigma Lw For the standard deviation of the load prediction error sample in the corresponding category, mu Lw The average value of the error samples is predicted for the corresponding class of intra-class loads.
The method adopts a normal distribution fitting method to determine the load probability density distribution; the probability density distribution of the new energy power generation prediction error is determined by adopting a nuclear density estimation method, so that the method can be more suitable for the spike property, the multimodal property, the thick tail property and the bias property of the new energy power generation prediction error, and can obtain more accurate probability distribution.
Among them, the preferred window width h is selected by the average integral square error method (Mean Integrated Squared Error, MISE), which is not affected by individual samples and reflects the overall properties more than other methods.
Optionally, the process of obtaining the probability distribution of the equivalent reserve in any category in step S4 is:
convolving the new energy power generation prediction error probability density and the load prediction error probability density of the corresponding category to obtain equivalent standby probability density;
Integrating the probability density of the equivalent reserve to obtain probability distribution of the equivalent reserve;
wherein the probability density of the equivalent redundancy is expressed as:
R t ＝e Lt -e Wt
wherein f (R) t ) For variable being equivalent standby R t Probability density of equivalent reserve of (c).
Optionally, in step S5, the optimal confidence level is determined based on the confidence level optimization model with the smallest expected cost of the system standby, and the standby capacity of the prediction period is obtained based on the selected optimal confidence level and the probability distribution of the equivalent standby of the category to which the prediction period belongs;
if the expected cost of the system standby is selected as the sum of standby purchase cost and standby punishment cost, the standby purchase cost comprises up-regulation standby purchase cost UC and down-regulation standby purchase cost DC, and the standby punishment cost comprises invalid up-regulation standby punishment cost IURP, invalid down-regulation standby punishment cost IDRP, load shedding punishment cost CLPC and machine shedding punishment cost WAPC;
the objective function of the confidence optimization model is expressed as:
min(CLPC×(R epα -R mpα )+WAPC×(R enα -R mnα )+UC×R euα +DC×R edα +IURP×(R eiuα -R miuα )+IDRP×(R midα -R eidα ))
in CLPC× (R) epα -R mpα ) Punishment of the cost for cut-load under confidence of 1-2 alpha, R epα For switching load corresponding to up-regulation (MW), R mpα For cutting the load to correspond to the actual needed standby, alpha is a parameter set for describing the confidence coefficient;
WAPC×(R enα -R mnα ) Punishment cost for cutting machine under confidence of 1-2 alpha, R enα For correspondingly regulating down the cutting machine, R mnα The cutting machine is correspondingly and practically needed for standby;
UC×R euα and DC X R edα The standby purchase cost under the confidence coefficient of 1-2 alpha is R euα And R is edα Respectively carrying out up-regulation and down-regulation;
IURP×(R eiuα -R miuα ) For invalid up-regulation of penalty cost under confidence 1-2 alpha, R eiuα And R is miuα The up-regulation standby and the actual required standby corresponding to the invalid up-regulation are respectively carried out;
IDRP×(R midα -R eidα ) Penalty fee for invalid downregulation at confidence level 1-2 alpha, R eidα And R is midα Respectively performing the corresponding down-regulation standby and the actually required standby for the invalid down-regulation;
the confidence level selected also satisfies the following constraint:
1-2α≥C min
wherein C is min Is the preset minimum confidence.
The method determines the optimal confidence based on the confidence optimization model with the minimum cost, comprehensively considers the influence of the standby purchase cost and the standby punishment cost on the standby expected cost, considers the reliability and the economy, and can obtain more reasonable and feasible results. The method is applied to the reserve capacity evaluation of the power grid containing the new energy unit, is beneficial to reducing the probability of occurrence of the load shedding and the switching-off event of the new energy power generation fluctuation, and ensures the safe and economic operation of the power system.
In a second aspect, the present invention provides an evaluation system based on the above method, comprising:
The historical data acquisition module is used for acquiring power generation historical data and load historical data in a historical period in a power grid containing the new energy unit;
the preprocessing module takes the new energy power generation prediction error and the load prediction error calculated based on the power generation history data and the load history data as samples;
the classification module is used for classifying the new energy power generation prediction error and the load prediction error which correspond to the historical period;
the probability density model construction module is used for respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
the equivalent standby probability distribution construction module is used for calculating the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
the equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
The confidence coefficient selection module is used for selecting confidence coefficients;
and the standby capacity acquisition module is used for acquiring the standby capacity of the prediction period based on the selected confidence and the probability distribution of the equivalent standby of the category to which the prediction period belongs.
In a third aspect, the present invention provides a terminal comprising a processor and a memory, the memory storing a computer program, the processor invoking the computer program to implement:
a method for dynamically evaluating the probability of the reserve capacity of a power grid containing a new energy unit.
In a fourth aspect, the present invention provides a readable storage medium storing a computer program, the computer program being invoked by a processor to implement:
step of power grid reserve capacity probabilistic dynamic assessment method containing new energy unit
Advantageous effects
1. The method realizes the probabilistic dynamic evaluation of the power grid reserve capacity of the new energy unit based on the equivalent reserve model, overcomes the defect that deterministic prediction only can give out the determined prediction information, considers the influence of the new energy power generation prediction error and the load prediction error, and improves the accuracy of the reserve capacity determination.
Wherein, it is further preferable to determine probability density distribution by adopting a normal distribution fitting method for the load prediction error; for the new energy power generation prediction error, the probability density distribution is determined by adopting a nuclear density estimation method, so that the method disclosed by the invention can be more suitable for the spike property, the multimodal property, the thick tail property and the bias property of the prediction error, and can obtain more accurate probability distribution.
2. According to the method, the corresponding new energy power generation prediction errors and load prediction errors in the historical period are classified, similar data are classified according to the data characteristics, and different characteristic data are classified into different categories, so that different categories have different probability distributions of equivalent reserve, the predicted reserve capacity is more reliable, the prediction results of the different categories are different, and dynamic evaluation of the reserve capacity is realized.
The improved fuzzy C-means clustering is further preferably adopted to establish a prediction error segmentation model, time periods are used as units for classification, more preferably two or more time period lengths are used as units for classification respectively, and therefore the method is more suitable for seasonal and time period correlation researches of errors. Compared with the common hard clustering, the fuzzy C-means clustering provides the membership degree of each sample to the clustering center, and can obtain more flexible clustering results. The overall optimal clustering initial value can be determined by means of a genetic algorithm and a simulated annealing algorithm, and accuracy of a clustering result can be effectively improved.
3. In a further preferred scheme of the invention, the optimal confidence coefficient is determined by a confidence coefficient optimization model with the smallest expected cost of the system standby, and the influence of standby purchase cost and standby punishment cost on the expected cost of the standby is comprehensively considered, wherein the punishment cost can be used as an evaluation index of reliability, and meanwhile, in order to ensure certain operation reliability, reliability constraint conditions are set, reliability and economy are considered, and more reasonable and feasible results can be obtained.
4. The method can be applied to the reserve capacity evaluation of the power grid containing the new energy unit, is beneficial to reducing the probability of occurrence of the new energy power generation fluctuation load shedding and the power-off event, and ensures the safe and economic operation of the power system.
Drawings
FIG. 1 is a flowchart of an algorithm for determining an optimal initial cluster center;
FIG. 2 is a seasonal clustering result of wind power prediction errors;
FIG. 3 is a seasonal clustering result of load prediction errors;
FIG. 4 is a probability density distribution of wind power prediction errors (1, 5);
FIG. 5 is a class 1 probability density distribution of load prediction errors;
FIG. 6 is (1,5,5,1) equivalent standby probability density
FIG. 7 is a (1,5,5,1) equivalent standby probability distribution
FIG. 8 is an equivalent standby (1,5,5,1) of different confidence standby total cost;
FIG. 9 is a comparison of reserve capacities at 1 month 3, 12, 14, and 28 of 2021;
FIG. 10 is a comparison of 2021, 1,5, 17 days reserve capacity;
fig. 11 is a schematic flow chart of a method for dynamically evaluating the probability of the standby capacity of a power grid containing a new energy unit.
Detailed Description
The method for dynamically evaluating the probability of the reserve capacity of the power grid containing the new energy unit is suitable for a power grid system containing new energy, particularly has a remarkable effect on a new energy high-duty ratio system, and is used for dynamically evaluating the reserve capacity of the new energy high-duty ratio system, wherein the high-duty ratio of the new energy is set by common general knowledge or experience in the field, and meanwhile, the method is also suitable for other new energy systems with other duty ratios. In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. In addition, the embodiments of the present application and the features in the embodiments may be combined with each other without conflicting with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention and to take as an example a new energy high duty cycle system, however, the present invention may be practiced in other ways than within the scope of the description, and the scope of the invention is therefore not limited to the specific embodiments disclosed below.
Example 1:
in this embodiment, wind power is taken as a new energy source for illustration, and it should be understood that the invention is not limited to a power grid of wind power new energy source, and the embodiment provides a method for probabilistic dynamic evaluation of standby capacity of a power grid containing a new energy unit, which includes the following steps:
s1: and acquiring power generation historical data and load historical data in a historical period of the new energy high-duty power grid, and taking a new energy power generation prediction error and a load prediction error calculated based on the power generation historical data and the load historical data as samples.
The embodiment adopts 2020 wind power data and load data which are disclosed in a bureau network by an electric transmission system operator Elia in belgium, wherein the 2020 wind power data comprises a daily wind power predicted power value (MW), an actual wind power measured value (MW) and a installed capacity (MW), a load predicted power value (MW) and an actual load measured value (MW). The data were taken as sampling intervals of t=15 min for a total of 96 data per day and 35136 data throughout the year. In other possible embodiments, t=15min is a non-unique value, and the t value can be adaptively adjusted according to the actual working condition requirement, which is not specifically limited in the present invention.
When it should be noted that, in this embodiment, the phenomenon that the original data has data missing is found by considering the preliminary detection of the load data, and before the error is formally calculated, the missing data is subjected to lagrangian interpolation processing, so as to obtain a complete data set for calculation and analysis. In other possible embodiments, other interpolation algorithms may be selected for processing, which is not particularly limited by the present invention.
The wind power prediction error corresponding to the t period is as follows:
e Wt ＝P WMt -P WFt
wherein P is WMt Representing a t period actual wind power Measurement (MW); p (P) WFt The wind power predicted power value (MW) before the day of the t period is represented.
Considering that the growth speed of the wind power installed capacity is rapid, the research of taking the original data as a sample to serve as the spare capacity cannot meet the requirement of the change of the installed capacity, the concept of 'output ratio' is introduced, and the wind power value is normalized to be in the interval of [0,1], so that the calculation is simplified.
the actual wind power prediction error value for the t period is:
the actual wind power prediction power value used for calculation in the period t is as follows:
wherein P is it The wind power installation capacity (MW) is shown for period t.
the load prediction error corresponding to the t period is:
e Lt ＝P LMt -P LFt
wherein P is LMt Representing actual load Measurements (MW); p (P) LFt Representing the load predicted power value (MW).
S2: and classifying the corresponding new energy power generation prediction error and load prediction error in the history period. The step aims at classifying the data with similar characteristics into one class, classifying the data with different characteristics into different classes, and classifying ideas are performed according to probability characteristics of error data.
In this embodiment, the prediction error of new energy power generation is classified three times, which are respectively: classification is made based on the predicted power data amount, classification is made in units of the length of the t period, and classification is made in units of the month.
When the predicted power data amount is used as a standard for classification, considering the predicted power characteristic of wind power prediction errors, and sequencing new energy power generation prediction error samples according to the power generation prediction power value in the power generation historical data in a historical period; and classifying the new energy power generation prediction error samples according to the sample data volume. In this embodiment, the wind power prediction error sample is divided into 5 segments, so that the number of each segment is as equal as possible, and the number of each segment is as follows:
wherein i is the number of segments, where i=1, 2,3,4,5; n is the number of samples, where n= 35136. In other possible embodiments, the segmentation may be adjusted. The predicted power output ratio at the segmentation point is obtained in this embodiment: 0.0682,0.2036,0.4047,0.5952.
Taking months as a unit for classification, 2, taking the seasonality of wind power prediction errors into consideration, respectively calculating the average absolute error, standard deviation, average relative error value and average error value of wind power prediction of 12 months as clustering indexes, taking the number of clustering groups as 4, taking 2 as a weighting index, and clustering the wind power and the load prediction errors by adopting an improved fuzzy C-means clustering method to obtain respective categories.
When the t time period length is taken as a unit for classification, the average absolute error, standard deviation, average relative error value and average error value of wind power prediction of 96 time periods are respectively calculated to serve as clustering indexes.
In this embodiment, the load prediction error is also performed by taking months as a unit, and the average absolute error, standard deviation, average relative error value and average error value of the load prediction error of 12 months are calculated as the clustering indexes, and in other possible embodiments, other matched clustering indexes may be selected.
FIG. 1 is a flowchart of an algorithm for determining an optimal initial cluster center based on a genetic algorithm and a simulated annealing algorithm. The classification process by adopting the improved fuzzy C-means clustering method is as follows:
s2.2.1: extracting a clustering index of data in the same period, and constructing a clustering index sample set E= { E by using the clustering index 1 ,e 2 ,...，e j ,...，e n1 N1 is the number of time periods, any jth time period sample e j A one-dimensional vector composed of p cluster indexes;
s2.2.2: setting an upper limit value S of iteration times, a class number c (2 is more than or equal to c is less than or equal to n 1), a minimum value epsilon of iteration termination and a weighting index m to control the accuracy degree of a result, (m > 1);
s2.2.3: initializing a cluster center C= { C 1 ,c 2 ,...,c i ,...,c c }，c i Is the cluster center of the i-th group;
s2.2.4: updating the membership matrix u= (U) according to the following membership formula and cluster center updating formula ij ) c×n1 Clustering the center C until the iteration termination condition is met;
wherein u is ij For the j-th index e j Membership to the cluster center of the i-th group,
and taking the class of the maximum membership degree in the membership degrees corresponding to the samples in the membership degree matrix after iteration is terminated as the class to which the samples belong.
Classifying by adopting the improved fuzzy C-means clustering method to obtain clustering results of tables 1-3, wherein table 1 shows seasonal clustering results of wind power prediction errors, and fig. 2 shows clustering results of month wind power prediction errors by taking average absolute errors, standard deviations and relative error average values as coordinate components; table 2 shows the clustering results of wind power prediction error time periods. Table 3 shows seasonal clustering results of load prediction errors, and fig. 3 shows clustering results describing month load prediction errors with mean absolute error, standard deviation, and relative error mean as coordinate components.
TABLE 1 seasonal clustering results of wind power prediction errors
TABLE 2 wind power prediction error period clustering results
TABLE 3 seasonal clustering results of load prediction errors
In the embodiment, 4 types of wind power prediction error seasonal categories, 12 types of wind power prediction error period categories, 5 types of prediction power categories and 4 types of load prediction error seasonal categories are obtained based on the classification; error data belonging to the wind power prediction error season type 1, the period-related type 5, the predicted power type 5, and the load prediction error type 1 are represented by (1,5,5,1).
It should be noted that in other possible embodiments, adjustments may be made to the classification, such as the selection of time periods, such as without regard to the predicted amount of power data, etc., without departing from the inventive concepts.
S3: and respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories.
To fully illustrate the implementation of the present invention, the following will take the (1,5,5,1) class as an example. Wherein, the probability density of wind power prediction errors (1, 5) and the probability density of load prediction error class 1 are respectively calculated.
Let wind power prediction error output ratio be e Wpu (set as an argument), then the kernel density is estimated as:
wherein n is the number of samples of the wind power prediction error, and is determined according to the number of samples of each class, namely wind power prediction error sample data in the class of wind power prediction errors (1, 5), e Wtpu Is determined by the samples of the corresponding class, each sample i corresponds to one e Wtpu Values.
In the embodiment, a Gaussian kernel function is selected, and kernel density estimation is performed on wind power prediction error output ratio. Other kernel functions may be selected in other possible embodiments. The gaussian kernel function selected in this embodiment is:
thus, the kernel density estimation of the wind power prediction error output ratio under the Gaussian kernel function is:
the wind power prediction error kernel density is estimated as follows:
wherein P is i Representing the wind power installed capacity (MW).
The optimum window width is preferably determined using the mean integral squared error method (Mean Integrated Squared Error, MISE) in this embodiment.
S31: MISE is defined as:
s32: solving the above formula to obtain:
wherein d 2 ＝∫e d 2 K(e d )de d ，e d E when calculating wind power prediction error as independent variable in Gaussian kernel function d ＝e W ，For the kernel density estimate of error e, f (e) is the probability density actual of error e.
S33: removing the last term to obtain a progressive integral mean square error of:
S34: obtaining the optimum window width h by solving partial derivative to make the first order derivative zero AMISE The method comprises the following steps:
the normal distribution model fitting of the load prediction error probability density is as follows:
in sigma Lw Is of the w classStandard deviation (MW) of intra-load prediction error; mu (mu) Lw Is the average value (MW) of the w-class load prediction error. In this example, the w-class is the load prediction error class 1.
Fig. 4 shows probability density distribution of wind power prediction error (1, 5) kernel density estimation, and fig. 5 shows normal distribution fitting of load prediction error class 1 probability density. It can be seen that the nuclear density estimation can well reflect the spiking, multimodal, thick tailing and bias of wind power prediction error probability density distribution.
It should be appreciated that other types of wind power prediction error probability densities and load prediction error probability densities may be calculated in accordance with the concepts described above.
S4: and calculating the probability distribution of equivalent reserve of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model.
Wherein, defining equivalent reserve as the difference between wind power prediction error and load prediction error:
R t ＝(P LMt -P LFt )-(P WMt -P WFt )＝e Lt -e Wt
the probability density convolution for two prediction errors yields the probability density for equivalent spares:
Fig. 6 shows (1,5,5,1) an equivalent standby probability density distribution.
Integrating the probability density of equivalent reserve to obtain probability distribution of equivalent reserve, wherein the equivalent reserve with the confidence degree of 1-2 alpha is:
s5: and selecting the confidence coefficient, and obtaining the spare capacity based on the selected confidence coefficient and the probability distribution of the equivalent spare of the category to which the confidence coefficient belongs.
When the reserve capacity is predicted, the probability distribution of the equivalent reserve is determined according to the category to which the prediction period belongs, and the reserve capacity is obtained by using the probability distribution of the equivalent reserve of the corresponding category. That is, in the present embodiment, the reserve capacity of 8 a.m. 2021.06.30 is to be predicted for the prediction period, first, in accordance with the prediction period: the method comprises the steps of determining the class of 4 wind power prediction error seasonal class, 12 wind power prediction error period class, 5 wind power prediction power class and 4 load prediction error seasonal class, further determining the probability distribution of equivalent reserve of the corresponding class, and finally selecting confidence level to obtain reserve capacity. When judging 5 kinds of predicted power categories, determining the category according to the magnitude of the predicted power value of the power generation in the predicted period.
It should be further noted that, in this embodiment, in order to ensure reliability of the model, the cluster analysis is based on the historical data of the whole year of the last year, and the historical data of the corresponding month of the last year needs to be replaced after one month, so as to have stronger timeliness. Meanwhile, due to the game between the limited data and the timeliness, the situation that the predicted samples exceed the clustering range can occur, and the traditional standby method is adopted at the moment to ensure the safe operation of the power system. In other possible embodiments, the periodicity of the data substitution may be adaptively adjusted.
Fig. 7 shows (1,5,5,1) the equivalent standby probability distribution, with equivalent standby points with 95%, 90%, 85%, 80% confidence levels selected. It can be seen that when the confidence is 95%, the system requires an up-regulation reserve capacity of at least 989.3MW and a corresponding down-regulation reserve capacity of at least 411MW. For the same confidence increment, when the confidence level is close to 1, the system needs more up-turned spare capacity to meet the confidence increasing demand.
In order to determine a reasonable and effective spare capacity, the sum of spare purchasing cost and punishment cost is minimum as a standard for selecting an optimal confidence level, and the confidence corresponding to the minimum expected cost is selected as the optimal confidence, so that the load spare of each time period in the future is evaluated.
Setting CLPC as load shedding punishment cost, and WAPC as waste wind punishment cost; UC is the up-regulation standby purchase expense, DC is the down-regulation standby purchase expense; IURP is an invalid up-regulation standby penalty, IDRP is an invalid down-regulation standby penalty, and then the objective function of the confidence optimization model may be expressed as:
min(CLPC×(R epα -R mpα )+WAPC×(R enα -R mnα )+UC×R euα +DC×R edα +IURP×(R eiuα -R miuα )+IDRP×(R midα -R eidα ))
in CLPC× (R) epα -R mpα ) Punishment of the cost for cut-load under confidence of 1-2 alpha, R epα For switching load corresponding to up-regulation (MW), R mpα Standby (MW) required for load shedding corresponding to actual;
WAPC×(R enα -R mnα ) Punishment of the cost for the abandoned wind under the confidence coefficient of 1-2 alpha, R enα For the corresponding downregulation of the abandoned wind (MW), R mnα Corresponding to the actual required standby (MW) for the wind curtailment;
UC×R euα and DC X R edα The standby purchase cost under the confidence coefficient of 1-2 alpha is R euα And R is edα Up-regulation standby (MW) and down-regulation standby (MW), respectively;
IURP×(R eiuα -R miuα ) For invalid up-regulation of penalty cost under confidence 1-2 alpha, R eiuα And R is miuα Up-regulation reserve (MW) and actual required reserve (MW) corresponding to the ineffective up-regulation respectively;
IDRP×(R midα -R eidα ) Penalty fee for invalid downregulation at confidence level 1-2 alpha, R eidα And R is midα The corresponding down-regulation reserve (MW) and the actual required reserve (MW) are respectively ineffective down-regulation.
In order to ensure certain operation reliability, the reliability constraint conditions are set as follows:
1-2α≥C min
wherein C is min For minimum confidence, the reserve capacity requirement is determined by the actual power plant requirements.
It should be appreciated that other possible embodiments may choose other ways to determine the confidence level, such as empirically taking values, may also choose other cost functions for the expected cost of system spares in the confidence optimization model or add other costs to the spare purchase cost and spare penalty cost, which may be adjusted according to actual needs, which the present invention does not specifically limit.
Dynamic evaluation and optimization of future reserve of wind-powered electric power systems using documents Zhang Danning, xu Jian, sun Yuanzhang, et cetera [ J ]]Grid technology, 2019,43 (09): 3252-3260 "price standard, i.e. cut load penalty cost 5707USD/MW, waste wind penalty cost 931USD/MW; up-regulating the spare purchasing expense to be 15USD/MW, down-regulating the spare purchasing expense to be 5USD/MW; the penalty cost for the invalid up-regulation reserve is 425USD/MW, the penalty cost for the invalid down-regulation reserve is 104USD/MW, and the expected cost of the reserve under different confidence levels of the equivalent reserve (1,5,5,1) is calculated. FIG. 8 shows a trend of expected cost for backup with different confidence levels for equivalent backup (1,5,5,1), with a minimum confidence level of 85%, an optimal confidence level for equivalent backup (1,5,5,1) of 86% and corresponding expected cost of 4.542 ×10 8 USD. At this confidence level, the optimal up-regulation of the system was for 780.287MW and the optimal down-regulation was for-256.464 MW. And performing the calculation on each class of equivalent reserve, and obtaining the optimal confidence coefficient of each class and the corresponding optimal equivalent reserve. When the price standard and the minimum confidence are different, the optimal confidence is also different, and the corresponding optimal equivalent reserve is different.
The wind power data of Belgium in 2976 time periods in 2021 is taken as test data, the equivalent reserve in 2976 time periods in 2021 is determined based on the obtained optimal equivalent reserve, the actual required reserve is calculated to be used as verification, the reserve determined by a traditional method is calculated, and documents Zhang Nan, huang Yuehui, liu Dewei and the like.
According to the power system technical guidelines, the conventional method is chosen here with 5% of the daily maximum load as spare capacity.
The literature is based on wind power and load prediction error independence, and the principle of root mean square is applied, and the specific spare capacity calculation mode is as follows:
wherein P is LM For maximum load (MW) in a day, P WT For total capacity (MW), P of wind power installations IM Is the maximum installed capacity (MW) of a single unit.
FIG. 9 shows the evaluation results of the reserve capacities of 2021, 1, 3, 12, 14 and 28 days, the actual output of wind power is smaller than the predicted value and the predicted error is larger, and it can be seen that the reserve capacity requirement cannot be met by the conventional method, and the reserve capacity determined by the method is closer to the actual required reserve and the load shedding risk is lower than that of the conventional method and the literature method;
fig. 10 shows the evaluation results of the reserve capacities of 1 month 5 and 17 days 2021, wherein the actual wind power output is larger than the predicted value and the prediction error is larger in the two days, so that the reserve capacity determined by the method is closer to the actual required reserve, the ineffective up-regulation is less, the risk of wind abandoning is lower, and the reserve capacity requirement of the power system can be better adapted.
In order to further evaluate the effectiveness and rationality of the model, the expected cost, the coverage of the predicted interval and the average width of the predicted interval are selected as indexes for evaluating the economy, the reliability and the acuity of the model. The coverage rate of the prediction interval refers to the coverage condition of the prediction interval on the actual needed standby, and the higher the coverage rate is, the higher the reliability of the model is, the interval coverage rate p is c The method comprises the following steps:
in the psi- i To determine whether the actual value is within the prediction intervalIf the actual value is not within the prediction interval, ψ i Taking 0, if the actual value is within the prediction interval, ψ i Taking 1;is the actual value of the i-th period, +.>Is the lower boundary of the interval>For the upper boundary of the interval, n is the number of samples, here 2976 is taken.
The average width of the prediction interval is the average value of the width of the prediction interval, and the narrower the average width of the prediction is, the higher the prediction accuracy is. The computational expression is:
table 4 shows the evaluation indexes of the 2021 month 1 standby evaluation under three methods, namely the expected cost, the coverage of the predicted interval, and the average width of the predicted interval.
Table 4 evaluation index comparison
It can be seen that although the average width of the prediction interval is the smallest in the traditional method, the coverage rate of the interval is small, the reliable operation of the power system cannot be ensured, the standby expected cost is high, the operation economy of the power system cannot be ensured, and the method cannot meet the standby requirement of the high-proportion wind power system. The coverage rate of the equivalent standby interval determined by the equivalent standby model and the literature method provided by the invention is about 95%, but compared with the literature method, the equivalent standby expected cost and the average width of the predicted interval under the equivalent standby model are smaller, and the equivalent standby model has reliability and economy. The equivalent standby model provided by the invention is reasonable and effective, and can meet the standby requirement of a high-proportion wind power system.
Example 2:
the embodiment of the invention provides an evaluation system based on a power grid reserve capacity probabilistic dynamic evaluation method of a new energy unit, which comprises the following steps: the system comprises a historical data acquisition module, a preprocessing module, a classification module, a probability density model construction module, an equivalent standby probability distribution construction module, a confidence level selection module and a standby capacity acquisition module.
The historical data acquisition module is used for acquiring power generation historical data and load historical data in a historical period in a power grid containing the new energy unit.
The preprocessing module takes the new energy power generation prediction error and the load prediction error calculated based on the power generation history data and the load history data as samples.
The classification module is used for classifying the new energy power generation prediction error and the load prediction error which correspond to the historical period.
The probability density model construction module is used for respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories.
And the equivalent standby probability distribution construction module calculates the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model.
The equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
the confidence coefficient selection module is used for selecting confidence coefficients;
and the standby capacity acquisition module is used for acquiring the standby capacity of the prediction period based on the selected confidence and the probability distribution of the equivalent standby of the category to which the prediction period belongs.
In some possible manners, when the classification module classifies the new energy power generation prediction error and the load prediction error corresponding to the historical period, the classification module includes: classifying according to at least two or more time period lengths as units respectively; or both classification based on the predicted power data amount and classification based on at least two or more time period lengths, respectively. Such as t=15 min and sorting in month units.
In some possible modes, fuzzy C-means clustering is adopted for classification, and average absolute error, standard deviation, average relative error value and average error value are used as clustering indexes, and a certain period length is used as a unit to classify the corresponding new energy power generation prediction errors in the history period.
In some possible ways, the new energy power generation prediction error probability density model is established based on kernel density estimation in a non-parametric model, and the load prediction error probability density model is established based on normal distribution fitting.
In some possible ways, the optimal confidence is determined based on a confidence optimization model with the smallest expected cost of system spares, and the spare capacity of the predicted period is obtained based on the selected optimal confidence and the probability distribution of the equivalent spares of the class to which the predicted period belongs.
The specific implementation process of each unit module refers to the corresponding process of the method. It should be understood that, in the specific implementation process of the above unit module, reference is made to the method content, the present invention is not specifically described herein, and the division of the functional module unit is merely a division of a logic function, and there may be another division manner when actually implemented, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted or not performed. Meanwhile, the integrated units can be realized in a hardware form or a software functional unit form.
Example 3:
the embodiment of the invention provides a terminal, which comprises a processor and a memory, wherein the memory stores a computer program, and the processor calls the computer program to realize the following steps:
s1: acquiring power generation historical data and load historical data in a historical period in a power grid containing a new energy unit, and taking a new energy power generation prediction error and a load prediction error calculated based on the power generation historical data and the load historical data as samples;
s2: classifying the corresponding new energy power generation prediction error and load prediction error in the history period;
s3: respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
s4: calculating to obtain the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
the equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
S5: and selecting the confidence coefficient, and obtaining the spare capacity based on the selected confidence coefficient and the probability distribution of the equivalent spare of the category to which the confidence coefficient belongs.
In some implementations, the processor invoking the computer program is further to implement: when classifying the corresponding new energy power generation prediction errors in the history period, the method comprises the following steps: classifying according to at least two or more time period lengths as units respectively; or both classification based on the predicted power data amount and classification based on at least two or more time period lengths, respectively. In some implementations, the processor invoking the computer program is further to implement: the process of classifying by taking the predicted power data amount as a standard comprises the following steps:
sequencing new energy power generation prediction error samples according to the power generation prediction power value in the power generation history data in the history period;
classifying the new energy power generation prediction error samples according to the sample data volume;
when the classification is carried out according to at least two or more time period lengths as units, the classification is carried out by adopting a clustering algorithm.
In some implementations, the processor invoking the computer program is further to implement: and determining the optimal confidence coefficient based on a confidence coefficient optimization model with the minimum expected cost of the system standby, and obtaining the standby capacity of the prediction period based on the selected optimal confidence coefficient and the probability distribution of the equivalent standby of the category to which the prediction period belongs.
For a specific implementation of each step, please refer to the description of the foregoing method.
It should be appreciated that in embodiments of the present invention, the processor may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
Example 4:
an embodiment of the present invention provides a readable storage medium storing a computer program that is called by a processor to implement:
s1: acquiring power generation historical data and load historical data in a historical period in a power grid containing a new energy unit, and taking a new energy power generation prediction error and a load prediction error calculated based on the power generation historical data and the load historical data as samples;
S2: classifying the corresponding new energy power generation prediction error and load prediction error in the history period;
s3: respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
s4: calculating to obtain the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
the equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
s5: and selecting the confidence coefficient, and obtaining the spare capacity based on the selected confidence coefficient and the probability distribution of the equivalent spare of the category to which the confidence coefficient belongs.
In some implementations, the computer program is invoked by the processor to implement: when classifying the corresponding new energy power generation prediction errors in the history period, the method comprises the following steps: classifying according to at least two or more time period lengths as units respectively; or both classification based on the predicted power data amount and classification based on at least two or more time period lengths, respectively.
In some implementations, the computer program is invoked by the processor to implement: the process of classifying by taking the predicted power data amount as a standard comprises the following steps:
sequencing new energy power generation prediction error samples according to the power generation prediction power value in the power generation history data in the history period;
classifying the new energy power generation prediction error samples according to the sample data volume;
when the classification is carried out according to at least two or more time period lengths as units, the classification is carried out by adopting a clustering algorithm.
In some implementations, the computer program is invoked by the processor to implement: and determining the optimal confidence coefficient based on a confidence coefficient optimization model with the minimum expected cost of the system standby, and obtaining the standby capacity of the prediction period based on the selected optimal confidence coefficient and the probability distribution of the equivalent standby of the category to which the prediction period belongs.
The readable storage medium is a computer readable storage medium, which may be an internal storage unit of the controller according to any one of the foregoing embodiments, for example, a hard disk or a memory of the controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the controller. Further, the readable storage medium may also include both an internal storage unit and an external storage device of the controller. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been output or is to be output.
Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The power grid reserve capacity probability dynamic assessment method for the new energy unit can be applied to dynamic assessment of the power grid reserve capacity of the new energy unit. The invention adopts a probabilistic method, overcomes the defect that deterministic prediction can only give out the determined prediction information, considers the influence of the new energy power generation prediction error and the load prediction error, and can more accurately determine the reserve capacity. The method adopts a normal distribution fitting method to determine the load probability density distribution; the probability density distribution of the new energy power generation prediction error is determined by adopting a nuclear density estimation method, so that the method can be more suitable for the spike property, the multimodal property, the thick tail property and the bias property of the new energy power generation prediction error, and can obtain more accurate probability distribution. The invention establishes the predictive error segment model based on the improved fuzzy C-means clustering, is more suitable for the seasonal and time period correlation research of errors, can obtain more flexible clustering results, determines the globally optimal clustering initial value by means of a genetic algorithm and a simulated annealing algorithm, and can effectively improve the accuracy of the clustering results. The method determines the optimal confidence based on the confidence optimization model with the minimum cost, comprehensively considers the influence of the standby purchase cost and the standby punishment cost on the standby expected cost, considers the reliability and the economy, and can obtain more reasonable and feasible results. The method is applied to the reserve capacity evaluation of the power grid containing the new energy unit, is beneficial to reducing the probability of occurrence of the load shedding and the switching-off event of the new energy power generation fluctuation, and ensures the safe and economic operation of the power system.
It should be emphasized that the examples described herein are illustrative rather than limiting, and that this invention is not limited to the examples described in the specific embodiments, but is capable of other embodiments in accordance with the teachings of the present invention, as long as they do not depart from the spirit and scope of the invention, whether modified or substituted, and still fall within the scope of the invention.
Claims (9)
1. A power grid reserve capacity probability dynamic evaluation method containing a new energy unit is characterized by comprising the following steps of: the method comprises the following steps:
s1: acquiring power generation historical data and load historical data in a historical period in a power grid containing a new energy unit, and taking a new energy power generation prediction error and a load prediction error calculated based on the power generation historical data and the load historical data as samples;
s2: classifying the corresponding new energy power generation prediction error and load prediction error in the history period;
s3: respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
s4: calculating to obtain the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
The equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
s5: selecting the confidence coefficient, and obtaining spare capacity based on the selected confidence coefficient and the probability distribution of equivalent spare of the category to which the confidence coefficient belongs;
in step S5, determining the optimal confidence coefficient based on a confidence coefficient optimization model with the minimum expected cost of the system standby, and obtaining the standby capacity of the prediction period based on the selected optimal confidence coefficient and the probability distribution of the equivalent standby of the category to which the prediction period belongs;
if the expected cost of the system standby is selected as the sum of standby purchase cost and standby punishment cost, the standby purchase cost comprises up-regulation standby purchase cost UC and down-regulation standby purchase cost DC, and the standby punishment cost comprises invalid up-regulation standby punishment cost IURP, invalid down-regulation standby punishment cost IDRP, load shedding punishment cost CLPC and machine shedding punishment cost WAPC;
the objective function of the confidence optimization model is expressed as:
min(CLPC×(R epα -R mpα )+WAPC×(R enα -R mnα )+UC×R euα +DC×R edα +IURP×(R eiuα -R miuα )+IDRP×(R midα -R eidα ))
in CLPC× (R) epα -R mpα ) Punishment of the cost for cut-load under confidence of 1-2 alpha, R epα For switching load corresponding to up-regulation (MW), R mpα The load is cut for corresponding to the actual needed standby;
WAPC×(R enα -R mnα ) Punishment cost for cutting machine under confidence of 1-2 alpha, R enα For correspondingly regulating down the cutting machine, R mnα The cutting machine is correspondingly and practically needed for standby;
UC×R euα and DC X R edα The standby purchase cost under the confidence coefficient of 1-2 alpha is R euα And R is edα Respectively carrying out up-regulation and down-regulation;
IURP×(R eiuα -R miuα ) For invalid up-regulation of penalty cost under confidence 1-2 alpha, R eiuα And R is miuα The up-regulation standby and the actual required standby corresponding to the invalid up-regulation are respectively carried out;
IDRP×(R midα -R eidα ) Penalty fee for invalid downregulation at confidence level 1-2 alpha, R eidα And R is midα Respectively performing the corresponding down-regulation standby and the actually required standby for the invalid down-regulation;
the confidence level selected also satisfies the following constraint:
1-2α≥C min
wherein C is min Is the preset minimum confidence.
2. The method according to claim 1, characterized in that: in step S2, when classifying the prediction error of new energy power generation corresponding to the history period, the method includes: classifying according to two or more time period lengths as units respectively; or simultaneously comprises classifying by taking the predicted power data amount as a standard and classifying by taking two or more time period lengths as units respectively:
the classification process taking the predicted power data quantity as a standard comprises the following steps:
Sequencing new energy power generation prediction error samples according to the power generation prediction power value in the power generation history data in the history period;
equally dividing new energy power generation prediction error samples according to the sample data volume;
when classifying according to two or more time period lengths as units, respectively, a clustering algorithm is adopted for classifying.
3. The method according to claim 2, characterized in that: when the two or more time period lengths are used as units for classification, the selected time period lengths are tmin and 1 month respectively, and tmin is the sampling interval of the power generation historical data and the load historical data;
the method comprises the following steps of adopting fuzzy C-means clustering to classify, taking average absolute error, standard deviation, average relative error value and average error value as clustering indexes, and taking a certain period length as a unit to classify the corresponding new energy power generation prediction error in a history period:
s2.2.1: extracting a clustering index of data in the same period, and constructing a clustering index sample set E= { E by using the clustering index 1 ,e 2 ,…，e j ,…，e n1 N1 is the number of time periods, any jth time period sample e j A one-dimensional vector composed of p cluster indexes;
S2.2.2: setting an upper limit value S of iteration times, a category number c, a minimum value epsilon of iteration termination and a weighting index m, wherein c is more than or equal to 2 and less than or equal to n1;
s2.2.3: initializing a cluster center C= { C 1 ,c 2 ,…，,c i ,...,c c }，c i Is the cluster center of the i-th group;
s2.2.4: updating the membership matrix u= (U) according to the following membership formula and cluster center updating formula ij ) c×n1 Clustering the center C until the iteration termination condition is met;
wherein u is ij For the j-th index e j Clustering center c corresponding to ith group i Membership degree of (3);
and taking the class of the maximum membership degree in the membership degrees corresponding to the samples in the membership degree matrix after iteration is terminated as the class to which the samples belong.
4. The method according to claim 1, characterized in that: the power generation history data includes a predicted power value P of power generation before day per tmin in a history period WFt Actual power generation measurement value P WMt And installed capacity P it The units are MW; the load history data includes a load predicted power value P per tmin in a history period LFt Actual load measurement value P LMt The units are MW;
the new energy power generation prediction error and the load prediction error are expressed as follows:
e Lt ＝P LMt -P LFt
in the formula e Wtpu 、e Lt The new energy power generation prediction error and the load prediction error of tmin are respectively represented.
5. The method according to claim 1, characterized in that: in the step S3, the new energy power generation prediction error probability density model is established based on nuclear density estimation in a non-parameter model, and the load prediction error probability density model is established based on normal distribution fitting;
If Gaussian kernel function is selected, the new energy power generation predicts the error probability densityExpressed as:
the load prediction error probability density f (e Lt ) Expressed as:
in the method, in the process of the invention,nuclear density estimation of predictive error output ratio for new energy power generation, P i Indicating the installed capacity of wind power, e W For the new energy power generation prediction error, n is the number of samples of the new energy power generation prediction error, and each new energy power generation prediction error sample corresponds to one e Wtpu Value h is window width, e Wpu Predicting error output ratio for new energy, wherein e is natural constant and sigma Lw For the standard deviation of the load prediction error sample in the corresponding category, mu Lw E is the average value of the load prediction error samples in the corresponding category Lt Represents the load prediction error of tmin.
6. The method according to claim 1, characterized in that: the process of obtaining the probability distribution of the equivalent reserve of any category in the step S4 is as follows:
predicting the error probability density of the new energy power generation of the corresponding categoryAnd the load prediction error probability density f (e Lt ) Convoluting to obtain equivalent standby probability density;
integrating the probability density of the equivalent reserve to obtain probability distribution of the equivalent reserve;
wherein the probability density of the equivalent redundancy is expressed as:
R t ＝e Lt -e Wt
Wherein f (R) t ) For variable being equivalent standby R t Probability density of the equivalent reserve of e Lt Representing the load prediction error of tmin,e Wt and representing the wind power prediction error corresponding to tmin.
7. A system based on the method of any one of claims 1-6, characterized in that: comprising the following steps:
the historical data acquisition module is used for acquiring power generation historical data and load historical data in a historical period in a power grid containing the new energy unit;
the preprocessing module is used for taking the new energy power generation prediction error and the load prediction error calculated based on the power generation history data and the load history data as samples;
the classification module is used for classifying the new energy power generation prediction error and the load prediction error which correspond to the historical period;
the probability density model construction module is used for respectively constructing a new energy power generation prediction error probability density model and a load prediction error probability density model of the corresponding categories based on the new energy power generation prediction error samples and the load prediction error samples of the corresponding categories;
the equivalent standby probability distribution construction module is used for calculating the equivalent standby probability distribution of each category based on the new energy power generation prediction error probability density model and the load prediction error probability density model;
The equivalent reserve is the difference between the load prediction error and the new energy power generation prediction error, and the categories of the new energy power generation prediction error probability density model and the load prediction error probability density model are used for determining the category of the equivalent reserve;
the confidence coefficient selection module is used for selecting confidence coefficients;
and the standby capacity acquisition module is used for acquiring the standby capacity of the prediction period based on the selected confidence and the probability distribution of the equivalent standby of the category to which the prediction period belongs.
8. A terminal, characterized by: comprising a processor and a memory, said memory storing a computer program, said processor invoking said computer program to implement:
the method of any one of claims 1-6.
9. A readable storage medium, characterized by: a computer program is stored, which is called by a processor to implement:
the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763793.2A CN113468811B (en) | 2021-07-06 | 2021-07-06 | Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763793.2A CN113468811B (en) | 2021-07-06 | 2021-07-06 | Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113468811A CN113468811A (en) | 2021-10-01 |
| CN113468811B true CN113468811B (en) | 2024-03-08 |
Family
ID=77878845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110763793.2A Active CN113468811B (en) | 2021-07-06 | 2021-07-06 | Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468811B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114965441B (en) * | 2022-07-28 | 2022-12-06 | 中国科学院国家天文台 | Training method of element probabilistic prediction model and element probabilistic prediction method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303266A (en) * | 2015-11-23 | 2016-02-03 | 国网山东省电力公司经济技术研究院 | Method for accurately estimating wind power prediction error interval |
| CN109038686A (en) * | 2018-08-28 | 2018-12-18 | 国网山东省电力公司聊城供电公司 | A kind of rolling optimal dispatching method based on wind power output prediction error |
| CN110084426A (en) * | 2019-04-26 | 2019-08-02 | 华北电力大学（保定） | A kind of wind power interval prediction method based on industry and mining city |
| CN111049193A (en) * | 2019-12-16 | 2020-04-21 | 国家电网公司华中分部 | Standby demand dynamic evaluation method for multiple scheduling scenes of wind power system |
| CN111260116A (en) * | 2020-01-10 | 2020-06-09 | 河南理工大学 | Time-interval refined short-term load prediction method based on BOA-SVR and fuzzy clustering |
| CN111310789A (en) * | 2020-01-15 | 2020-06-19 | 云南电网有限责任公司大理供电局 | Wind power interval prediction method based on kernel density estimation and implementation system thereof |
| CN111401755A (en) * | 2020-03-19 | 2020-07-10 | 国电南瑞科技股份有限公司 | Multi-new-energy output scene generation method, device and system based on Markov chain |
| CN112104005A (en) * | 2020-08-25 | 2020-12-18 | 中国电力科学研究院有限公司 | Power grid dispatching method and system considering new energy prediction uncertainty |
| CN112186761A (en) * | 2020-09-30 | 2021-01-05 | 山东大学 | Wind power scene generation method and system based on probability distribution |
| CN112818604A (en) * | 2021-02-05 | 2021-05-18 | 河海大学 | Wind turbine generator risk degree assessment method based on wind power prediction |
-
2021
- 2021-07-06 CN CN202110763793.2A patent/CN113468811B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303266A (en) * | 2015-11-23 | 2016-02-03 | 国网山东省电力公司经济技术研究院 | Method for accurately estimating wind power prediction error interval |
| CN109038686A (en) * | 2018-08-28 | 2018-12-18 | 国网山东省电力公司聊城供电公司 | A kind of rolling optimal dispatching method based on wind power output prediction error |
| CN110084426A (en) * | 2019-04-26 | 2019-08-02 | 华北电力大学（保定） | A kind of wind power interval prediction method based on industry and mining city |
| CN111049193A (en) * | 2019-12-16 | 2020-04-21 | 国家电网公司华中分部 | Standby demand dynamic evaluation method for multiple scheduling scenes of wind power system |
| CN111260116A (en) * | 2020-01-10 | 2020-06-09 | 河南理工大学 | Time-interval refined short-term load prediction method based on BOA-SVR and fuzzy clustering |
| CN111310789A (en) * | 2020-01-15 | 2020-06-19 | 云南电网有限责任公司大理供电局 | Wind power interval prediction method based on kernel density estimation and implementation system thereof |
| CN111401755A (en) * | 2020-03-19 | 2020-07-10 | 国电南瑞科技股份有限公司 | Multi-new-energy output scene generation method, device and system based on Markov chain |
| CN112104005A (en) * | 2020-08-25 | 2020-12-18 | 中国电力科学研究院有限公司 | Power grid dispatching method and system considering new energy prediction uncertainty |
| CN112186761A (en) * | 2020-09-30 | 2021-01-05 | 山东大学 | Wind power scene generation method and system based on probability distribution |
| CN112818604A (en) * | 2021-02-05 | 2021-05-18 | 河海大学 | Wind turbine generator risk degree assessment method based on wind power prediction |
Non-Patent Citations (4)
| Title |
|---|
| Locational Marginal Pricing Mechanism for Uncertainty Management Based on Improved Multi-ellipsoidal Uncertainty Set;赵宗正，刘益鑫，郭力，白林泉，王成山;《JOURNALOFMODERNPOWERSYSTEMSANDCLEANENERGY》;20210507;第9卷(第4期);734-750 * |
| 基于聚类与非参数核密度估计的风电功率预测误差分析;张晓英;张晓敏;廖顺;陈伟;王晓兰;;太阳能学报(第12期);270-280 * |
| 基于误差分类的风电功率区间评估;韩丽，乔妍，景惠甜;《电力系统自动化》;第45卷(第1期);97-104 * |
| 风电场功率预测不确定性分析方法及其应用研究;阎洁;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第12期);C042-69 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113468811A (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kabir et al. | Neural network-based uncertainty quantification: A survey of methodologies and applications | |
| US20210056647A1 (en) | Method for multi-dimensional identification of flexible load demand response effect | |
| CN107506868B (en) | Method and device for predicting short-time power load | |
| US20030182250A1 (en) | Technique for forecasting market pricing of electricity | |
| Cheng et al. | Enhanced state estimation and bad data identification in active power distribution networks using photovoltaic power forecasting | |
| CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
| CN111489036A (en) | Resident load prediction method and device based on electrical appliance load characteristics and deep learning | |
| CN112149873A (en) | Low-voltage transformer area line loss reasonable interval prediction method based on deep learning | |
| CN113126019A (en) | Intelligent ammeter error remote estimation method, system, terminal and storage medium | |
| CN112001644A (en) | Power distribution network operation reliability detection method, device, terminal and storage medium | |
| CN115034485A (en) | Wind power interval prediction method and device based on data space | |
| CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
| CN113468811B (en) | Power grid reserve capacity probabilistic dynamic assessment method and system containing new energy unit | |
| CN114912716A (en) | Short-term power load prediction method and system based on bidirectional long-term and short-term memory network | |
| CN115600729A (en) | Grid load prediction method considering multiple attributes | |
| CN110084403B (en) | Multi-period joint probability density prediction method and system for current-carrying capacity of overhead conductor | |
| Park et al. | Demand power forecasting with data mining method in smart grid | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN112734274A (en) | Mining and comprehensive evaluation method for low-carbon power grid operation leading influence factors | |
| CN111060755A (en) | Electromagnetic interference diagnosis method and device | |
| CN111507507A (en) | Big data-based monthly water consumption prediction method | |
| CN116249186A (en) | Data processing method and device of wireless network equipment, storage medium and electronic equipment | |
| CN115796341A (en) | Carbon effect code-based collaborative measure method for enterprise low-carbon economic performance | |
| CN115828134A (en) | Electricity consumption data sample construction, model training and account category determination method and device | |
| Daraghmi et al. | Accurate and time‐efficient negative binomial linear model for electric load forecasting in IoE |
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 |