CN103440370A - Transmission and transformation project construction cost assessment method and device - Google Patents
Transmission and transformation project construction cost assessment method and device Download PDFInfo
- Publication number
- CN103440370A CN103440370A CN2013103674919A CN201310367491A CN103440370A CN 103440370 A CN103440370 A CN 103440370A CN 2013103674919 A CN2013103674919 A CN 2013103674919A CN 201310367491 A CN201310367491 A CN 201310367491A CN 103440370 A CN103440370 A CN 103440370A
- Authority
- CN
- China
- Prior art keywords
- particle swarm
- transformation project
- model
- sample data
- support vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000009466 transformation Effects 0.000 title claims abstract description 74
- 230000005540 biological transmission Effects 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000010276 construction Methods 0.000 title abstract description 54
- 239000002245 particle Substances 0.000 claims abstract description 99
- 238000012843 least square support vector machine Methods 0.000 claims abstract description 36
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 230000000739 chaotic effect Effects 0.000 claims description 64
- 238000011156 evaluation Methods 0.000 claims description 39
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 36
- 238000012706 support-vector machine Methods 0.000 description 29
- 238000013210 evaluation model Methods 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 16
- 238000011160 research Methods 0.000 description 16
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000013528 artificial neural network Methods 0.000 description 12
- 238000012795 verification Methods 0.000 description 10
- 238000013461 design Methods 0.000 description 7
- 230000003068 static effect Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 244000003416 Asparagus officinalis Species 0.000 description 1
- 235000005340 Asparagus officinalis Nutrition 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a transmission and transformation project construction cost assessment method and device. The transmission and transformation project construction cost assessment method comprises the following steps: input historical sample data of a transmission and transformation project are received; iterations, inertia weight, learning factors, particle velocity of a chaos particle swarm and the population size of the particle swarm are initialized to build a chaos particle swarm model; according to the chaos particle swarm optimization, parameters of the chaos particle swarm model are optimized; according to the historical sample data and the optimized chaos particle swarm model, optimal values of the iterations, inertia weight and learning factors of the chaos particle swarm model are determined; according to the determined optimal values of the iterations, inertia weight and learning factors, penalty coefficients, insensitive coefficients and kernel function parameters of a least square support vector machine model are determined respectively to build the least square support vector machine model; input actual sample data of the transmission and transformation project are received; according to the actual sample data of the transmission and transformation project and the built least square support vector machine model, a construction cost assessment result of the transmission and transformation project is generated.
Description
Technical Field
The invention relates to the technical field of power transmission and transformation projects, in particular to a method and a device for evaluating the construction cost of a power transmission and transformation project.
Background
The construction of the power transmission and transformation project generally has the characteristics of huge project investment amount, multiple related fields, complex influence factors and the like, so that the control of the construction cost of the power transmission and transformation project is always a difficult problem. The control of the construction cost of the power transmission and transformation project is to strictly calculate, regulate and monitor all the costs in the construction cost forming process according to the established construction cost target of the calculated and determined construction cost and investment cost, reveal the deviation, correct in time and ensure the realization of the construction cost target. Therefore, to improve the utilization efficiency of resources, optimizing the resource allocation must start from the goal of control, namely, evaluating the construction cost.
With the development of science and technology, many cost estimation methods have appeared in the domestic engineering cost field, including: an estimation index method, an approximate quota method, an exponential smoothing method, a specific weight method, a fuzzy mathematical calculation method, a gray relevance meter algorithm, a neural network model method, an empirical estimation method and the like. The methods can solve the problem of quick estimation of the construction cost in a certain specific historical period and the process of engineering project development, but the general defects of the methods are that the most active factors in competition are fixed, the method is difficult to adapt to the requirements of a market economic system, the time value of capital is neglected, the method is lack of dynamics, the separation of technology and economy is caused, the estimation cost error is too large, and the actual requirements of the engineering construction in the market economic development are still difficult to meet.
In the 90 s of the 20 th century, the machine learning theory research of small sample data is gradually mature, a relatively perfect theoretical system, namely a statistical learning theory, is formed, and on the basis, Vapnik in 1995 proposes a new machine learning method, namely a support vector machine technology. The support vector machine technology provides an effective theoretical analysis basis for the learning of small sample data, is successfully applied in many fields, and becomes a new research hotspot of small sample learning. However, in practical research, it is found that it is still difficult to obtain a stable and good learning effect by simply relying on the support vector machine technology to perform small sample data learning, so that the technology starts with the artificial intelligence technology, searches for a proper theoretical technical algorithm, improves the small sample data learning method based on the support vector machine technology, designs a scientific and reasonable small sample data intelligent learning improvement algorithm, applies the improvement algorithm to the rapid estimation of the construction cost of the power transmission and transformation project, and meets the requirements of construction cost control and bid-bid activity implementation in the construction process of the power transmission and transformation project.
At present, the research on the project cost estimation method is less, and the project cost estimation method is researched mainly by using fuzzy mathematics, grey correlation degree, artificial neural network, support vector machine and other methods except the commonly used rated budget estimate cost estimation and list pricing method.
(1) Fuzzy mathematics based cost estimation
The Wangzhen Zhen obviously teaches that the construction cost of the construction is an inexact number at first in the whole country, has the idea of ambiguity, and combines the practical application of the fuzzy mathematics method to the engineering practice, and provides a new method for quickly estimating the construction cost. According to the probability theory and the fuzzy mathematic principle, the method for determining the random-fuzzy mathematic feature statistics is proposed by the methods of the dawn Yang and the like, the sub-project cost is estimated by applying the fuzzy mathematic closeness concept, and the possible value of the total project cost is formed by overlapping the sub-project cost. Subsequently, the application research of the fuzzy mathematics in the cost estimation is further researched by Song Hongbin, Jiangdeli, Richeng, and the like respectively.
(2) Cost estimation based on grey correlation
The Qianyong peak firstly proposes a generation function method of a gray system, and makes up the defect of uncertainty of an adjustment coefficient in a fuzzy mathematical cost estimation model. Zhang Quoqin and Qianyangfeng estimate the construction cost by using the gray system theory, but only roughly consider the engineering characteristics and do not consider the weights of the partial engineering, so the estimated cost is low in accuracy and difficult to popularize and apply. The Asparagus, Yunhua, decomposes the pre-estimated project and similar project, uses the subsection project as the calculation starting point, combines the subsection project characteristic and the cost to calculate the degree of association, makes up the deficiency in the model establishment of Zhangouqiu and Qianyangfeng, and improves the accuracy of the estimation result. Then Zhangyi friend, Huang Baozhen, Liao dynasty and the like respectively combine the fuzzy closeness and the grey correlation degree, improve the previous estimation model and further improve the estimation accuracy.
(3) Cost estimation based on artificial neural network
The shore cheng and the high forest introduce an artificial neural network estimation model and artificial intelligent estimation system software of engineering cost through the research on the basic principle of the neural network, and analyze the examples of the well lane engineering in the mine project construction. Subsequently, more experts and scholars use the neural network to research the estimation of different construction engineering construction costs, and the strong mountain and the like research the estimation of the hydropower engineering construction costs, so that the application of the neural network in the hydropower engineering is developed. Shenjinshan, Zhaoxin, Yangyi and Fuhong are used to establish engineering cost estimating model. Silver waves and the like research the application of a neural network in a cost estimation method of power transmission engineering. In recent years, researches for improving the network learning ability by combining theories such as a neural network, a clustering technology and a genetic algorithm appear. The Denghin and Lichi space are combined with fuzzy mathematics and BP neural network to design fast estimation model of engineering cost. The Wangyang design combines a soft computing method, a clustering technology and a fuzzy neural network theory to design a power line engineering cost prediction model. The panda utilizes a genetic algorithm to combine with a BP neural network theory to design a construction engineering cost estimation model.
(4) Cost estimation based on support vector machine
Wejuntao has studied the application of the support vector machine in the cost estimation method of the power transmission project. Jiang LiNa adopts a rough set and support vector machine method to form an intelligent prediction system, and the problem of low construction cost prediction efficiency of construction engineering is solved. The Hahewang and the like propose a construction project cost prediction method based on a fuzzy least square support vector machine. The Wuxiajuan uses a system prediction method of a support vector machine, combines the trend and the characteristics of the construction cost of a thermal power engineering project, and establishes a thermal power plant engineering construction cost prediction model. And respectively evaluating the road engineering cost by utilizing the support vector machine, such as Wangjinxiang, Xie Ying and the like. Pengliu provides an improved algorithm for intelligently learning small sample data based on a parameter optimization regression support vector machine, and the algorithm is applied to quick estimation of engineering cost.
The disadvantage of fuzzy mathematics is that the complex problem description for the engineering cost estimation is too simple, and therefore the estimation result is naturally coarser. The grey correlation theory has the defects that the cost similarity of different projects is over-estimated, the calculation error is large, and the accuracy requirement of the current project cost estimation within 10 percent is difficult to meet. The disadvantage of the neural network is that learning requires a large training sample size to ensure the robustness and convergence of the algorithm. The support vector machine has the disadvantages of low convergence speed, long running time and sensitivity and dependence on experience of parameters on external change.
Most of the cost estimation methods still stay in shallow-level discussion, or the algorithm is applied in a single aspect, or the method is lack of systematicness, or the method is only suitable for the engineering field with large scale of historical engineering data, and the cost estimation method of small sample engineering data is basically not discussed deeply.
Disclosure of Invention
The embodiment of the invention provides a power transmission and transformation project cost evaluation method, which comprises the following steps:
receiving input historical sample data of the power transmission and transformation project;
initializing iteration times, inertia weight, learning factors, particle speed and the population scale of the chaotic particle swarm to establish a chaotic particle swarm model;
optimizing the parameters of the chaotic particle swarm model according to the chaotic particle swarm optimization algorithm;
determining the optimal values of the iteration times, the inertia weight and the learning factors of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
respectively determining a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model according to the determined iteration times, the inertia weight and the optimal value of the learning factor to establish the least square support vector machine model;
receiving input actual sample data of the power transmission and transformation project;
and generating a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
The invention also provides a power transmission and transformation project cost evaluation device, which comprises:
the data input module is used for receiving input historical sample data and actual sample data of the power transmission and transformation project;
the chaotic particle swarm model initialization module is used for initializing the iteration times, the inertia weight, the learning factor, the particle speed and the swarm scale of the chaotic particle swarm to establish a chaotic particle swarm model;
the optimization module is used for optimizing the chaotic particle swarm model parameters according to the chaotic particle swarm optimization algorithm;
the optimal value determining module is used for determining the optimal values of the iteration times, the inertia weight and the learning factors of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
the least square support vector machine module is used for respectively determining a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model according to the determined iteration times, the inertia weight and the optimal value of the learning factor to establish the least square support vector machine model;
and the evaluation module is used for generating a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
The invention not only can enable the investor to accurately estimate the construction cost of a newly-built project in the early feasibility research stage of project construction, but also can assist the general calculation examiner to carry out reasonable and rapid construction cost examination in the initial design stage so as to achieve the aim of providing a basis for investment decision, and can help project construction units to rapidly determine the enterprise quotation range in the bidding activities, optimize the quotation strategy on the premise of ensuring the enterprise benefits and maximally improve the success rate of winning bid.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flow chart of a power transmission and transformation project cost evaluation method provided by an embodiment of the invention;
FIG. 2 is a block diagram of a power transmission and transformation project cost evaluation apparatus according to the present invention;
FIG. 3 is a flow chart of the chaos particle swarm least square support vector machine evaluation model construction in the embodiment of the invention
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for estimating a cost of a power transmission and transformation project, where the method includes:
step S101, receiving input historical sample data and actual sample data of the power transmission and transformation project;
step S102, initializing iteration times, inertia weight, learning factors, particle speed and population scale of the chaotic particle swarm to establish a chaotic particle swarm model;
step S103, optimizing the chaotic particle swarm model parameters according to a chaotic particle swarm optimization algorithm;
step S104, determining the optimal values of the iteration times, the inertia weight and the learning factors of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
step S105, substituting the determined iteration times, the inertia weight and the optimal value of the learning factor into a corresponding formula, determining a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model, and finally establishing the least square support vector machine model;
and S106, generating a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
Preferably, in the embodiment of the present invention, the population size of the chaotic particle swarm is set according to the sample capacity of the historical sample data.
Preferably, in the embodiment of the present invention, the particle velocity is initialized by multiplying the magnitude of the iteration number, the inertia weight, and the learning factor by the corresponding coefficient.
Preferably, in the embodiment of the present invention, principal component analysis is performed on the sample data to determine the influencing factors.
In addition, as shown in fig. 2, the present invention also provides a power transmission and transformation project cost evaluation device, which includes:
the data input module 201 is configured to receive input historical sample data and actual sample data of the power transmission and transformation project;
the chaotic particle swarm model initialization module 202 is used for initializing the iteration times, the inertia weight, the learning factor, the particle speed and the swarm scale of the chaotic particle swarm to establish a chaotic particle swarm model;
the optimization module 203 is used for optimizing the chaotic particle swarm model parameters according to the chaotic particle swarm optimization algorithm;
an optimal value determining module 204, configured to determine optimal values of the iteration times, the inertia weight, and the learning factor of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
the least square support vector machine module 205 is configured to determine a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model according to the determined iteration number, the inertia weight and the optimal value of the learning factor to establish the least square support vector machine model;
and the evaluation module 206 is configured to generate a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
The chaos particle swarm least square support vector machine evaluation model in the embodiment of the invention provides a background:
the support vector machine has many specific advantages in solving the machine learning problems of small samples, nonlinearity and high dimension, however, it is still difficult to obtain a stable and good learning effect by simply relying on the support vector machine technology to perform small sample data learning. Therefore, the technology applies a novel improved algorithm, namely a least square support vector machine, on the basis of the original support vector machine theory, and the greatest difference between the improved algorithm and the support vector machine algorithm is as follows: the improved algorithm introduces a least square linear system into the support vector machine, and replaces the traditional support vector machine to solve the problem of function estimation by adopting a quadratic programming method. Therefore, the complexity of the model is reduced, the construction process of the model is simplified, and the accuracy of the learning result is improved.
With the continuous deepening of a least squares support vector machine evaluation model in engineering application, some inevitable defects are exposed, most prominently, problems of selection and optimization of model parameters are solved, in the parameter selection aspect, the accuracy of the model is inevitably influenced in practical application by means of an expert system or blind search by setting an initial value, and the like. The defects are specifically shown as follows:
the penalty coefficient C determines the complexity of the model and the penalty degree of the fitting deviation larger than epsilon according to the characteristics of sample data. Too large a value (> 100) or too small a value (< 10) of C may degrade the generalization performance of the system due to over-learning or under-learning.
And the insensitive coefficient epsilon shows the expectation of the system on the error of the estimation function on sample data, the larger the epsilon value is, the fewer the number of support vectors is, the more sparse the expression of the solution is, but the accuracy of regression estimation can be reduced by the overlarge epsilon.
And thirdly, the kernel function parameter sigma accurately defines the structure of the high-dimensional characteristic space phi (x), so that the complexity of a final solution is controlled, and if the sigma value is too large or too small, the generalization performance of the system is deteriorated.
How to select reasonable parameters becomes a problem in the application process of the support vector machine algorithm, and is also the key point of the current application research. The conventional cross validation trial calculation method is time-consuming and unclear in search purpose, so that resources are wasted, time and labor are consumed, and parameters cannot be effectively optimized. Therefore, a new method needs to be found, which can reasonably and efficiently optimize the parameters of the least square support vector machine model, so that the estimation model is flexible and intelligent and meets the requirements of modeling of the actual power transmission and transformation project.
The particle swarm optimization algorithm is simple to implement, but has the defects of weak local searching capability, easy falling into a local optimal point, low convergence speed in the later evolution stage and the like. Because the chaotic motion has the characteristics of ergodicity, randomness, sensitivity to initial conditions and the like, the chaotic idea is introduced into the basic particle swarm optimization algorithm, the diversity of the swarm and the ergodicity of particle search are improved, the capability of the particle swarm optimization algorithm to get rid of local extreme points is improved, and the convergence speed and the precision of the basic particle swarm optimization algorithm are improved. Based on the method, the chaotic particle swarm optimization algorithm is used for optimizing the parameter setting in the model. The basic idea of the chaotic particle swarm optimization algorithm is as follows: 1) the chaotic sequence is adopted to initialize the position and the speed of the particles, the randomness essence of the particle swarm optimization algorithm during initialization is not changed, meanwhile, the chaotic characteristic can be well utilized to improve the diversity of the population and the ergodicity of particle search, and the initial population is selected and selected on the basis of generating a large number of initial populations. 2) And generating a new chaotic sequence on the basis of the optimal position searched by the current whole particle swarm, and replacing the position of one particle in the current particle swarm by the optimal position particle in the chaotic sequence. And introducing a search algorithm of the chaotic sequence to generate a plurality of local optimal neighborhood points in iteration so as to help inert particles to escape from local minimum points, thereby quickly searching the optimal solution.
The chaotic particle swarm least square support vector machine evaluation model in the embodiment of the invention is constructed, and as shown in fig. 3, the chaotic particle swarm least square support vector machine evaluation model in the embodiment of the invention is constructed by the following flow chart:
firstly, initializing and setting the size M of a particle swarm, the maximum allowable iteration number L, the inertia weight W, a learning factor D and the speed of initializing each particle. It should be noted that since L, W and D are optimized simultaneously, the values of the 3 parameters are generally not on the same order of magnitude, and the corresponding coefficients should be multiplied when initializing the particle velocity.
Chaotic initialization of particle positions. Randomly generating a vector of which the value of each component is between 0 and 1 in 3 dimensions, obtaining N vectors which are initial groups, then respectively carrying the components to a value range of L, W, D parameters, finally calculating an adaptive value of a particle swarm, selecting M solutions with better performance from the N initial groups as initial solutions, and randomly generating N initial speeds.
And thirdly, if the fitness of the particles is superior to the individual extreme value, setting the adaptive value of the particle swarm to be a new position.
And fourthly, the fitness of the particles is superior to the global extreme value, and the global extreme value is set as a new position.
Updating the speed and position of the particle.
And sixthly, performing chaotic optimization on the optimal position. And mapping the global extreme value to a domain of a Logistic equation, then performing iteration by using the Logistic equation to generate a chaotic variable sequence, and returning the generated chaotic variable sequence to an original solution space through inverse mapping. And calculating an adaptive value of each feasible solution experienced by the chaotic variable in the original solution space to obtain a feasible solution with the best performance.
And seventhly, replacing the position of any one particle in the current population by the best feasible solution.
If the maximum iteration times are met, stopping searching, wherein the global optimal position is a parameter vector (L, W, D); otherwise, returning to the third step.
Ninthly, constructing the sample mean square error e for the parameters C, epsilon and sigma needing to be optimizedRMSEAnd when the root mean square error of a sample of the least square support vector machine is minimum, corresponding C, epsilon and sigma are optimal parameters, and finally, a least square support vector machine evaluation model optimized by chaotic particle swarm is established.
The present invention is further illustrated in detail below with reference to specific examples:
in the project-oriented north electric power company 500kv transformation project cost stage, an evaluation model is established, wherein the evaluation model needs to be established for 8 items of installation project cost of an electric part of a main production project, equipment purchase cost of the electric part, construction project cost of the main production project, equipment purchase cost of an auxiliary production project, construction project cost of the auxiliary production project, construction project cost of a single project related to a station site, other cost and static investment respectively, and the evaluation model is established by taking static investment cost as an example. Input sample is x1: rated voltage, x, on the medium voltage side2: low side rated voltage, x3: substation type, x4: seismic intensity, x5: whether heating zone, x6: station area, x7: area of main control building, x8: amount of scaffold, x9: basic quantity, x10: amount of excavation, x11: main transformer with or without load regulation, x12: number of main transformers, x13: volume of this period, x14: number of high-voltage side outgoing lines, x15: number of medium voltage side outlets, x16: number of outlets on low voltage side, x17: high-voltage side connection type, x18: medium voltage side wiring pattern, x19: low voltage side wiring pattern, x20: number of reactors, x21: number of capacitors, x22: number of isolating switches, x23: number of transformers, x24: number of lightning arresters, x25: number of switch cabinets, x26: high-side switchgear type, x27: medium voltage side switchgear type, x28: low side switchgear type, x29: power cable, x30: and controlling the cable, wherein the 30 influence factors form 9 main component new indexes. Since the historical sample capacity of the power transformation project is 29, the population size of the particle swarm is set to 29, the maximum iteration number L is 1000, binary coding is adopted for two parameters W and D, wherein the search range of W is set to be 0, 100]And the search range of D is set to [0.1, 100 ]]. The initial velocity of the particles was 2. The kernel functions commonly used by the least square support vector machine include a radial basis function, a polynomial function, a linear function and the like, and research shows that the radial basis function has strong generalization capability, so that the radial basis kernel function is selected to obtain an optimal evaluation model. Meanwhile, according to the input historical samples, the optimal parameters C, epsilon and sigma are found. The optimal parameters obtained by calculation are respectively as follows: c =23, e =520, σ =1.24, the corresponding evaluation results are shown in table 1:
TABLE 1 comparison of prediction results for different parameters
Wherein,wherein
And y (i) are predicted and actual values, respectively, and the parameters in Table 1 are in fitness function eRMSEMinimum value.
As can be seen from table 1, when C =23, e =520, and σ =1.24, the error between the static investment of the power transformation project and the real static investment of the power transformation project derived from the evaluation model is the smallest. Therefore, the power transmission and transformation project cost evaluation model based on the chaotic particle swarm least square support vector machine is established by using the parameters C =23, epsilon =520 and sigma = 1.24. The kernel functions commonly used by the least square support vector machine include a radial basis function, a polynomial function, a linear function, and the like, and research shows that the radial basis function has strong generalization capability, so the radial basis kernel function is selected to obtain an optimal evaluation model in the embodiment.
The following is sample verification for cost evaluation by adopting the scheme:
1. 500kv power transformation project approximate calculation stage sample verification
(1) Static investment
The static investment evaluation index group in the approximate calculation stage of the 500kv power transformation project consists of 9 indexes, a total of 29 sample data are combined with 19 actual project samples and 10 typical case samples, based on the support vector machine principle, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring and calculating samples, and the obtained evaluation model verification result is as follows:
static investment evaluation result in approximate calculation stage of table 2500 kv power transformation project
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 34780 | 34430 | 1.01% |
| Qinhuangzao Changli 500kV transformer substation | 39810 | 37120 | 6.76% |
(2) Engineering cost for installation of electrical parts
The evaluation index group of the installation project cost of the electrical part in the approximate calculation stage of 500kv power transformation project consists of 7 indexes, and by combining 19 actual project samples and 10 typical case samples, 29 sample data are combined, based on the principle of a support vector machine, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring and calculating samples, and the obtained evaluation model verification results are as follows:
table 3500 kv transformation project approximate calculation stage electric part installation project cost evaluation result
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 2706.946 | 2614.242 | 3.42% |
| Qinhuangzao Changli 500kV transformer substation | 2938.705 | 2697.542 | 8.21% |
(3) Purchase fee of electric part equipment
The evaluation index group of the purchase cost of the electrical part equipment in the approximate calculation stage of 500kv power transformation engineering is composed of 7 indexes, and by combining 19 actual engineering samples and 10 typical case samples, 29 sample data are combined, based on the principle of a support vector machine, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measurement samples, and the obtained evaluation model verification results are as follows:
table 4500 kv transformation project approximate calculation stage electric part equipment purchase cost evaluation result
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 20950.211 | 21835.432 | 4.23% |
| Qinhuangzao Changli 500kV transformer substation | 24786.166 | 23097.748 | 6.81% |
(4) Construction cost of main production engineering
The evaluation index group of the construction project expense of the main production project in the approximate calculation stage of the 500kv power transformation project is composed of 4 indexes, a total of 29 sample data are combined with 19 actual project samples and 10 typical case samples, based on the principle of a support vector machine, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring and calculating samples, and the obtained evaluation model verification result is as follows:
table 5500 kv transformation project approximate calculation stage main production project construction project cost evaluation result
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 3066.131 | 2778.681 | 9.38% |
| Qinhuangzao Changli 500kV transformer substation | 2347.506 | 2135.341 | 9.04% |
(5) Auxiliary production engineering equipment purchase fee
The 500kv transformer project approximate calculation stage auxiliary production engineering equipment purchase cost evaluation index group is composed of 7 indexes, a total of 29 sample data are combined with 19 actual engineering samples and 10 typical case samples, based on the support vector machine principle, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring samples, and the obtained evaluation model verification result is as follows:
table 6500 kv transformation project approximate calculation stage auxiliary production project equipment purchase cost evaluation result
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 90.136 | 96.686 | 7.26% |
| Qinhuangzao Changli 500kV transformer substation | 105.041 | 112.556 | 7.15% |
(6) Auxiliary production engineering construction cost
The evaluation index group of the construction project expense of the auxiliary production project in the approximate calculation stage of the 500kv power transformation project is composed of 4 indexes, a total of 29 sample data are combined with 19 actual project samples and 10 typical case samples, based on the principle of a support vector machine, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring and calculating samples, and the obtained evaluation model verification result is as follows:
auxiliary production engineering construction project expense evaluation result in table 7500 kv power transformation engineering approximate calculation stage
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 563.120 | 595.184 | 5.69% |
| Qinhuangzao Changli 500kV transformer substation | 845.683 | 785.563 | 7.11% |
(7) Site-related single project construction cost
The evaluation index group of the single project construction project cost related to the station site in the approximate calculation stage of the 500kv transformation project is composed of 4 indexes, is combined with 19 actual project samples and 10 typical case samples, totally 29 sample data, is based on the support vector machine principle, is programmed by using Matlab software, takes 27 samples as learning samples, and takes the other 2 samples as measurement and calculation samples, and the obtained evaluation model verification result is as follows:
evaluation result of single project construction cost related to station site in table 8500 kv power transformation project approximate calculation stage
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 694.832 | 656.205 | 5.55% |
| Qinhuangzao Changli 500kV transformer substation | 841.952 | 785.098 | 6.75% |
(8) Other costs
The approximate calculation stage of 500kv transformation engineering and other cost evaluation index groups are composed of 2 indexes, a total of 29 sample data are combined with 19 actual engineering samples and 10 typical case samples, based on the support vector machine principle, Matlab software programming is applied, 27 samples are used as learning samples, the other 2 samples are used as measuring and calculating samples, and the obtained evaluation model verification results are as follows:
table 9500 kv power transformation project approximate calculation stage other cost evaluation result
| Sample(s) | Actual value (Wanyuan) | Calculation value (Wanyuan) | Deviation of |
| 500kV transformer substation engineering of ampere times | 3381.612 | 3628.81 | 7.31% |
| Qinhuangzao Changli 500kV transformer substation | 6811.763 | 6330.626 | 7.06% |
Determination of safety interval of new cost index of power transformation project
By combining the research contents, the safety interval for obtaining the cost indexes corresponding to 2 learning samples in the approximate calculation stage of the 500kv power transformation project is as follows:
safety interval of indicator in approximate calculation stage of table 10500 kv power transformation project
The technical scheme of the invention brings beneficial effects
(1) Starting from an artificial intelligence technology, the particle swarm optimization algorithm, the chaos optimization algorithm, the nonlinear kernel principal component analysis and the related concepts and algorithms of the support vector machine technology are expanded and improved, and the intelligent learning algorithm of the small sample data is beneficially improved.
(2) In the field of engineering cost, the technology aims to provide a systematic engineering cost rapid estimation method on the basis of a small sample data intelligent learning improvement algorithm by combining engineering historical cost data and through links such as data preprocessing, data clustering, data classification learning and the like. The technology can not only enable an investor to accurately estimate the construction cost of a newly-built project in the early feasibility research stage of project construction, but also assist approximate calculation examiners to carry out reasonable and rapid construction cost examination in the initial design stage, so as to achieve the aim of providing basis for investment decision, help project construction units to rapidly determine the enterprise quotation range in bidding activities, optimize quotation strategies on the premise of ensuring enterprise benefits, and improve the success rate of winning bid to the maximum extent.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A power transmission and transformation project cost assessment method is characterized by comprising the following steps:
receiving input historical sample data of the power transmission and transformation project;
initializing iteration times, inertia weight, learning factors, particle speed and the population scale of the chaotic particle swarm to establish a chaotic particle swarm model;
optimizing the parameters of the chaotic particle swarm model according to a chaotic particle swarm optimization algorithm;
determining the optimal values of the iteration times, the inertia weight and the learning factors of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
respectively determining a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model according to the determined iteration times, the inertia weight and the optimal value of the learning factor to establish the least square support vector machine model;
receiving input actual sample data of the power transmission and transformation project;
and generating a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
2. The power transmission and transformation project cost evaluation method according to claim 1, wherein the initializing population size of the chaotic particle swarm comprises: and setting the population scale of the chaotic particle swarm according to the sample capacity of the historical sample data.
3. The power transmission and transformation project cost evaluation method according to claim 1, wherein the initializing the particle velocity of the chaotic particle swarm comprises: and multiplying the particle speed by a corresponding coefficient according to the iteration times, the inertia weight and the magnitude of the learning factor.
4. The power transmission and transformation project cost evaluation method according to claim 1, wherein the method further comprises: and carrying out principal component analysis on the sample data to determine influence factors.
5. The electric transmission and transformation project cost evaluation device is characterized in that the method comprises the following steps:
the data input module is used for receiving input historical sample data and actual sample data of the power transmission and transformation project;
the chaotic particle swarm model initialization module is used for initializing the iteration times, the inertia weight, the learning factor, the particle speed and the swarm scale of the chaotic particle swarm to establish a chaotic particle swarm model;
the optimization module is used for optimizing the chaotic particle swarm model parameters according to the chaotic particle swarm optimization algorithm;
the optimal value determining module is used for determining the optimal values of the iteration times, the inertia weight and the learning factors of the chaotic particle swarm model according to the historical sample data and the optimized chaotic particle swarm model;
the least square support vector machine module is used for respectively determining a penalty coefficient, an insensitive coefficient and a kernel function parameter of the least square support vector machine model according to the determined iteration times, the inertia weight and the optimal value of the learning factor to establish the least square support vector machine model;
and the evaluation module is used for generating a power transmission and transformation project cost evaluation result according to the actual sample data of the power transmission and transformation project and the established least square support vector machine model.
6. The electric transmission and transformation project cost evaluation device according to claim 5, wherein the initializing population size of the chaotic particle swarm comprises: and setting the population scale of the chaotic particle swarm according to the sample capacity of the historical sample data.
7. The electric transmission and transformation project cost evaluation device according to claim 5, wherein the initializing the particle velocity of the chaotic particle swarm comprises: and multiplying the particle speed by a corresponding coefficient according to the iteration times, the inertia weight and the magnitude of the learning factor.
8. The electric transmission and transformation project cost evaluation apparatus of claim 5, wherein said apparatus further comprises: and the principal component analysis module is used for carrying out principal component analysis on the sample data to determine influence factors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103674919A CN103440370A (en) | 2013-08-21 | 2013-08-21 | Transmission and transformation project construction cost assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103674919A CN103440370A (en) | 2013-08-21 | 2013-08-21 | Transmission and transformation project construction cost assessment method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103440370A true CN103440370A (en) | 2013-12-11 |
Family
ID=49694063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013103674919A Pending CN103440370A (en) | 2013-08-21 | 2013-08-21 | Transmission and transformation project construction cost assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103440370A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103972908A (en) * | 2014-05-23 | 2014-08-06 | 国家电网公司 | Multi-target reactive power optimization method based on adaptive chaos particle swarm algorithm |
| CN104021272A (en) * | 2014-05-06 | 2014-09-03 | 国网上海市电力公司 | Method for extracting project budgetary estimate influence factors based on principal component analysis |
| CN105046374A (en) * | 2015-08-25 | 2015-11-11 | 华北电力大学 | Power interval predication method based on nucleus limit learning machine model |
| CN105243608A (en) * | 2015-10-29 | 2016-01-13 | 国家电网公司 | Line project cost estimation method based on power transmission and transformation project cost design elements |
| CN105354371A (en) * | 2015-10-21 | 2016-02-24 | 江苏省电力公司 | GA-WNN based power transmission and transformation project construction cost prediction method |
| CN106780120A (en) * | 2016-12-06 | 2017-05-31 | 广东电网有限责任公司电网规划研究中心 | Project of transmitting and converting electricity cost index processing method and device |
| CN107169157A (en) * | 2017-04-07 | 2017-09-15 | 上海电气集团股份有限公司 | A kind of structural thermal analysis finite element modeling method |
| CN108764639A (en) * | 2018-04-26 | 2018-11-06 | 国网浙江省电力有限公司经济技术研究院 | Project of transmitting and converting electricity construction cost assessment method based on space-time big data |
| CN109146235A (en) * | 2018-07-05 | 2019-01-04 | 国网内蒙古东部电力有限公司经济技术研究院 | Method for evaluating influence factors of construction cost of transformer substation and computing equipment |
| CN109902390A (en) * | 2018-12-13 | 2019-06-18 | 中国石油大学(华东) | A kind of Favorable Reservoir development area prediction technique expanded based on small sample |
| CN109993346A (en) * | 2019-02-22 | 2019-07-09 | 南京邮电大学 | Micro-capacitance sensor voltage safety evaluation method based on chaos time sequence and neural network |
| CN110807490A (en) * | 2019-11-04 | 2020-02-18 | 国网四川省电力公司经济技术研究院 | Intelligent prediction method for construction cost of power transmission line based on single-base tower |
| CN111222669A (en) * | 2018-11-27 | 2020-06-02 | 国网新疆电力有限公司经济技术研究院 | Overhead line cost prediction method and device |
| CN111311096A (en) * | 2020-02-17 | 2020-06-19 | 杭州电子科技大学 | QFD and KANO model-based multi-yield quality optimization method |
| CN112214851A (en) * | 2020-09-29 | 2021-01-12 | 国网福建省电力有限公司 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
| CN112508512A (en) * | 2020-11-26 | 2021-03-16 | 国网河北省电力有限公司经济技术研究院 | Power grid engineering cost data management method and device and terminal equipment |
| CN115760249A (en) * | 2022-11-07 | 2023-03-07 | 国网宁夏电力有限公司经济技术研究院 | Line loss-considered power transmission and transformation project cost evaluation method, medium and equipment |
| CN116308579A (en) * | 2023-02-23 | 2023-06-23 | 葛洲坝集团交通投资有限公司 | Particle swarm-SVM-based engineering cost determination method, system and product |
| CN117454225A (en) * | 2023-11-13 | 2024-01-26 | 承德市工程建设造价管理站 | Engineering cost data management system |
| CN118537052A (en) * | 2024-07-22 | 2024-08-23 | 宁波运筹科技有限公司 | International freight logistics cost intelligent estimation method and device based on large model |
-
2013
- 2013-08-21 CN CN2013103674919A patent/CN103440370A/en active Pending
Non-Patent Citations (4)
| Title |
|---|
| LIANG XINHENG等: "Improved CPSO-LSSVM in Predicting Financial", 《2010 SECOND LITA INTERNATIONAL CONFERENCE ON GEOSCIENCE AN REMOTE SENSING》 * |
| 刘丽霞: "基于小波理论与LSSVM的模拟集成电路故障诊断方法", 《万方数据》 * |
| 司海涛: "有小样本数据特征的输变电工程造价估算与灵敏度研究", 《万方数据》 * |
| 王棉斌等: "基于概率分析方法的输变电工程造价风险评估模型", 《电网技术》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021272A (en) * | 2014-05-06 | 2014-09-03 | 国网上海市电力公司 | Method for extracting project budgetary estimate influence factors based on principal component analysis |
| CN103972908A (en) * | 2014-05-23 | 2014-08-06 | 国家电网公司 | Multi-target reactive power optimization method based on adaptive chaos particle swarm algorithm |
| CN105046374B (en) * | 2015-08-25 | 2019-04-02 | 华北电力大学 | A kind of power interval prediction technique based on core extreme learning machine model |
| CN105046374A (en) * | 2015-08-25 | 2015-11-11 | 华北电力大学 | Power interval predication method based on nucleus limit learning machine model |
| CN105354371A (en) * | 2015-10-21 | 2016-02-24 | 江苏省电力公司 | GA-WNN based power transmission and transformation project construction cost prediction method |
| CN105243608A (en) * | 2015-10-29 | 2016-01-13 | 国家电网公司 | Line project cost estimation method based on power transmission and transformation project cost design elements |
| CN106780120A (en) * | 2016-12-06 | 2017-05-31 | 广东电网有限责任公司电网规划研究中心 | Project of transmitting and converting electricity cost index processing method and device |
| CN107169157A (en) * | 2017-04-07 | 2017-09-15 | 上海电气集团股份有限公司 | A kind of structural thermal analysis finite element modeling method |
| CN108764639A (en) * | 2018-04-26 | 2018-11-06 | 国网浙江省电力有限公司经济技术研究院 | Project of transmitting and converting electricity construction cost assessment method based on space-time big data |
| CN109146235A (en) * | 2018-07-05 | 2019-01-04 | 国网内蒙古东部电力有限公司经济技术研究院 | Method for evaluating influence factors of construction cost of transformer substation and computing equipment |
| CN111222669A (en) * | 2018-11-27 | 2020-06-02 | 国网新疆电力有限公司经济技术研究院 | Overhead line cost prediction method and device |
| CN109902390A (en) * | 2018-12-13 | 2019-06-18 | 中国石油大学(华东) | A kind of Favorable Reservoir development area prediction technique expanded based on small sample |
| CN109902390B (en) * | 2018-12-13 | 2023-10-24 | 中国石油大学(华东) | Method for predicting development area of favorable reservoir based on small sample expansion |
| CN109993346A (en) * | 2019-02-22 | 2019-07-09 | 南京邮电大学 | Micro-capacitance sensor voltage safety evaluation method based on chaos time sequence and neural network |
| CN109993346B (en) * | 2019-02-22 | 2020-09-11 | 南京邮电大学 | Micro-grid voltage safety evaluation method based on chaotic time sequence and neural network |
| CN110807490A (en) * | 2019-11-04 | 2020-02-18 | 国网四川省电力公司经济技术研究院 | Intelligent prediction method for construction cost of power transmission line based on single-base tower |
| CN111311096B (en) * | 2020-02-17 | 2022-05-31 | 杭州电子科技大学 | QFD and KANO model-based multi-yield quality optimization method |
| CN111311096A (en) * | 2020-02-17 | 2020-06-19 | 杭州电子科技大学 | QFD and KANO model-based multi-yield quality optimization method |
| CN112214851A (en) * | 2020-09-29 | 2021-01-12 | 国网福建省电力有限公司 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
| CN112214851B (en) * | 2020-09-29 | 2022-06-07 | 国网福建省电力有限公司 | Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm |
| CN112508512A (en) * | 2020-11-26 | 2021-03-16 | 国网河北省电力有限公司经济技术研究院 | Power grid engineering cost data management method and device and terminal equipment |
| CN115760249A (en) * | 2022-11-07 | 2023-03-07 | 国网宁夏电力有限公司经济技术研究院 | Line loss-considered power transmission and transformation project cost evaluation method, medium and equipment |
| CN115760249B (en) * | 2022-11-07 | 2024-10-08 | 国网宁夏电力有限公司经济技术研究院 | Transmission and transformation project cost assessment method, medium and equipment considering line loss |
| CN116308579A (en) * | 2023-02-23 | 2023-06-23 | 葛洲坝集团交通投资有限公司 | Particle swarm-SVM-based engineering cost determination method, system and product |
| CN117454225A (en) * | 2023-11-13 | 2024-01-26 | 承德市工程建设造价管理站 | Engineering cost data management system |
| CN117454225B (en) * | 2023-11-13 | 2024-05-14 | 承德市工程建设造价管理站 | Engineering cost data management system |
| CN118537052A (en) * | 2024-07-22 | 2024-08-23 | 宁波运筹科技有限公司 | International freight logistics cost intelligent estimation method and device based on large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103440370A (en) | Transmission and transformation project construction cost assessment method and device | |
| Liu et al. | A novel hybrid methodology for short-term wind power forecasting based on adaptive neuro-fuzzy inference system | |
| Tian et al. | A novel wind speed forecasting system based on hybrid data preprocessing and multi-objective optimization | |
| Zhao et al. | An optimized grey model for annual power load forecasting | |
| Cai et al. | A hybrid CPSO–SQP method for economic dispatch considering the valve-point effects | |
| Wang et al. | An innovative hybrid approach for multi-step ahead wind speed prediction | |
| CN103489038A (en) | Photovoltaic ultra-short-term power prediction method based on LM-BP neural network | |
| CN103985058B (en) | Available transfer capability calculation method based on improved multiple centrality-correction interior point method | |
| Aly | A novel approach for harmonic tidal currents constitutions forecasting using hybrid intelligent models based on clustering methodologies | |
| CN102938562B (en) | Prediction method of total wind electricity power in area | |
| CN103136585A (en) | Weighting Voronoi diagram substation planning method based on chaotic and genetic strategy | |
| CN106786977B (en) | Charging scheduling method of electric vehicle charging station | |
| CN105303250A (en) | Wind power combination prediction method based on optimal weight coefficient | |
| Mustafa et al. | Reactive power tracing in pool-based power system utilising the hybrid genetic algorithm and least squares support vector machine | |
| Rueda et al. | Heuristic optimization based approach for identification of power system dynamic equivalents | |
| CN113300380A (en) | Load curve segmentation-based power distribution network reactive power optimization compensation method | |
| Chang | Short-term load forecasting using radial basis function neural network | |
| CN115714382A (en) | Active power distribution network real-time scheduling method and device based on security reinforcement learning | |
| Mc Namara et al. | Weight optimisation for iterative distributed model predictive control applied to power networks | |
| CN106557832A (en) | A kind of micro-capacitance sensor addressing constant volume method | |
| CN104915788B (en) | A method of considering the Electrical Power System Dynamic economic load dispatching of windy field correlation | |
| CN105634018A (en) | Random response surface method and interior point method based wind-power-plant-contained random optimal power flow solving method | |
| CN116796911A (en) | Medium-voltage distribution network optimization regulation and control method and system based on typical scene generation and on-line scene matching | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN107292434A (en) | A kind of intelligent Forecasting of wind power output |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131211 |
|
| RJ01 | Rejection of invention patent application after publication |