CN111415068A - Power distribution decision modeling method based on relevance of transformation measures and loss load index - Google Patents
Power distribution decision modeling method based on relevance of transformation measures and loss load index Download PDFInfo
- Publication number
- CN111415068A CN111415068A CN202010130943.1A CN202010130943A CN111415068A CN 111415068 A CN111415068 A CN 111415068A CN 202010130943 A CN202010130943 A CN 202010130943A CN 111415068 A CN111415068 A CN 111415068A
- Authority
- CN
- China
- Prior art keywords
- investment
- power distribution
- load
- distribution network
- loss
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 135
- 230000009466 transformation Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 230000006872 improvement Effects 0.000 claims abstract description 22
- 230000008901 benefit Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000004048 modification Effects 0.000 claims description 15
- 238000012986 modification Methods 0.000 claims description 15
- 238000005065 mining Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000010219 correlation analysis Methods 0.000 claims description 9
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 239000003637 basic solution Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000008685 targeting Effects 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 2
- 238000012827 research and development Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000007418 data mining Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000000611 regression analysis Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000009420 retrofitting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of power systems, and provides a multi-year investment planning decision modeling technology based on the relevance of power distribution network transformation measures and power grid load loss indexes, aiming at solving the problem of complex power flow calculation related to traditional power distribution network investment decision modeling and considering the improvement of the operational reliability indexes of the existing power distribution network. The modeling technology improves the investment decision model through a data mining technology, has great advantages in the aspects of finding problem potential rules, improving the calculation efficiency and the like, can avoid a complex load flow calculation process, and effectively improves the calculation efficiency. A training sample set is formed by loss load indexes and transformation measures, and corresponding incidence relation rules can be obtained through offline learning of sample data and serve as the basis of a multi-year investment decision model. In practical application, when a scheme for configuring the transformation measures is given, the deep confidence network model can quickly give a load loss index result as a constraint condition of a subsequent power distribution network investment decision model.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a power distribution decision modeling method based on relevance between modification measures and load loss indexes.
Background
The national energy agency issues a power distribution network construction transformation action plan (2015-2020) in 2015 at 8 months, and the plan requires China to accelerate the construction of modern power distribution networks, so that the power supply reliability is further improved. Therefore, how to scientifically utilize the transformation fund and reasonably make a transformation scheme is one of the key problems concerned in the field of power distribution at present. The underlying task of a power distribution network is to provide users with a safe, stable, high quality supply of power. Compared with a power transmission network, the power distribution network has numerous nodes and a complex structure, and has a large influence on the power supply reliability, so that the evaluation of performance indexes such as reliability, economy and the like is one of core problems of the research in the power distribution field. In recent years, the rapid development of intermittent renewable energy power Generation represented by wind power and photovoltaic power Generation has increased the permeability of Distributed Generation (DG) in an active power distribution network, increased the types and number of active elements, increasingly complex network structure of the active power distribution network, increasingly prominent system distribution characteristics, and new requirements for optimization investment decision of the power distribution network.
In order to establish an accurate investment decision model and ensure the operation reliability of the power distribution network, the relationship between active power distribution network modification measures and the power grid load loss indexes is of great importance. However, the related analysis in the traditional investment decision modeling involves power flow calculation, and the analysis process of the physical model is very complex, which is not beneficial to the current power distribution network planning investment decision. Therefore, applying the data association mining method to the correlation analysis of the two is a better choice. General data association mining methods include regression analysis, feature analysis, variation and deviation analysis, association rule mining, neural network methods, network data mining, fuzzy grey association degree and other chemical methods. Considering the implicit association relation between the 'transformation measures-loss load indexes' of the power distribution network, the data fitting based on regression analysis cannot meet the association analysis, and therefore the method of machine learning is adopted for solving. The machine learning has great advantages in the aspects of finding problem latent rules, improving the calculation efficiency and the like. And analyzing the association rule between the technical path configuration and the investment benefit and the applicable operation condition thereof by analyzing large-scale index data and analyzing a data mining method such as regression analysis and machine learning.
Disclosure of Invention
The invention provides a multi-year investment planning decision-making modeling technical method based on the relevance of power distribution network modification measures and power grid load loss indexes, which aims to solve the problem of complex load flow calculation involved in the traditional power distribution network investment decision-making modeling and consider the improvement of the reliability indexes of the existing power distribution network. The modeling technology improves the great advantages of the investment decision model in the aspects of finding potential rules of problems, improving the calculation efficiency and the like through a data mining technology based on a deep confidence network, can avoid a complex load flow calculation process, and can effectively improve the calculation efficiency. And forming a training sample set by the loss load amount index and the transformation measure, and obtaining a corresponding incidence relation rule by off-line learning of sample data to be used as the basis of an investment decision model. Therefore, in practical application, when a resource allocation scheme is given, the power distribution network correlation analysis model based on the deep belief network can quickly give a result of a corresponding load loss index as a constraint condition of a subsequent power distribution network investment decision model.
In order to achieve the purpose, the technical scheme of the invention is as follows: the power distribution decision modeling method based on the relevance of the transformation measures and the load loss indexes is characterized by comprising the following steps of:
s1: determining implicit relations between different configuration schemes and the power grid load loss amount indexes; determining the influence degree of the investment decision scheme on the reliability index of the system load loss amount; determining a correlation rule between investment improvement measure configuration under different operating conditions and investment benefits improved by the loss load index;
s2: optimizing the implicit relationship, the degree of influence and the association rule in the step S1 based on a Nadam optimizer;
s3: providing a power distribution network multi-year investment decision model for correlation analysis of the transformation measures and the power distribution network load loss indexes, providing a power distribution network load loss index evaluation model based on the correlation analysis, providing a correlation relation between various transformation measures of the power distribution network and the load loss indexes, and providing a traditional power distribution network planning model; wherein the content of the first and second substances,
improving a first multi-year investment decision model with the maximum target according to the loss load index of the power distribution network;
a second multi-year investment decision model aiming at minimizing the investment cost of the power distribution network;
s4: and solving the first multi-year investment decision model and the second multi-year investment decision model to obtain an optimal power distribution network investment planning decision.
Preferably, in step S1, the degree of influence of the investment decision scheme on the reliability index of the system load capacity is characterized by the load loss index of the power grid based on an association rule obtained by statistical analysis or mathematical learning.
Preferably, in step S1, the association rule between the investment improvement measure configuration under different operating conditions and the loss of the load amount and the investment benefit specifically includes: and mining by using the sample data of the loss load capacity index of the power distribution network through a research and development algorithm, and dynamically updating investment benefits along with the change of a configuration scheme so as to obtain an accurate investment aid decision result.
Preferably, in step S2, the step of optimizing based on the Nadam optimizer is a generative model, which is formed by stacking a plurality of restricted boltzmann machines, has good nonlinear mapping capability, can learn and adapt to unknown information, and has a structure formed by an input and output layer and a plurality of hidden layers.
Preferably, the power distribution network multi-year investment decision model for relevance analysis of the transformation measures and the power distribution network load loss indexes in the step S3 belongs to a complex nonlinear programming problem, and a direct mapping between the power distribution network transformation measures and the load loss indexes is constructed by utilizing the nonlinear mapping capability based on the Nadam optimizer;
the model can quickly estimate the loss load value under the transformation measures when the scene of the transformation measures of the power distribution network changes, so that the influence degree of implementation of different transformation measures of the power distribution network on reliability indexes such as the loss load of the power distribution network is judged, the influence degree is used as a relevance constraint condition of later-stage power distribution network investment decision, and the time consumption of time domain simulation is saved; adopting a deep confidence network to carry out relevance mining and obtain a corresponding power grid load loss index, wherein the process comprises the following steps:
step 1: obtaining sample data of time sequence simulation in medium and long-term operation, and initially training to determine a basic solution space of each parameter of the deep confidence network;
step 2: establishing an input and output vector of a deep belief network, and determining a neural network model and a learning mode;
and step 3: calculating the input and output of each unit of the hidden layer and the output layer of the deep belief network, namely finishing the preliminary learning of the deep belief network;
and 4, step 4: adjusting the weight and the threshold of the controlled deep belief network performance by adopting a Nadam optimizer, and optimizing the convergence speed and the convergence effect of deep belief network learning;
and 5: continuously updating the learning mode and the learning times;
step 6: repeating the step 5, and continuously carrying out deep belief network training until a cutoff condition is met, namely the maximum learning times;
and 7: and (3) applying a deep confidence network association rule, inputting data such as node load, voltage, line power, distributed power supply output and telemechanical device installation under a certain transformation scheme, and calling the deep confidence network to obtain a corresponding power grid load loss index result.
Preferably, in the traditional power distribution network investment model, the voltage, power and phase angle parameters of the network are obtained through load flow calculation, and then the technical and economic index values of the network are obtained through calculation, wherein the investment decision model is as follows:
Xi∈{0,1} (3)
in the model, the maximum improvement of the loss load index representing the investment benefit of the power distribution network is an objective function, as shown in formula (1); the total investment of the power distribution network, the independence of the transformation measures and the correlation relationship between the transformation measures and the load loss index are taken as constraints, and the constraint is shown as a formula (2-4); i and
respectively representing the loss load indexes, X, of the power distribution network before and after the implementation of the reconstruction measuresiRepresenting a different type of modification, K (X)i) Representative reconstruction measureApplication of XiThe cost of (2);
representing the incidence relation between the modification measures and the load loss index; wherein y represents the vector of parameters related to power flow and grid structure in the network, such as voltage, power and phase angle; as shown in the formula (4), in the traditional investment model, the relationship between the reconstruction measures and the load loss indexes needs to be expressed by depending on the power flow parameters;
wherein, the loss load reliability index in the model can be expressed as follows; the power supply reliability index is as follows: the reliability index is generally used for evaluating the influence degree of the power failure phenomenon of the power distribution network on users; according to the difference of the power failure time, the users can be classified into 3 types after power failure: 1) if the user is located in the upstream section of the fault area, the power failure time is the sum of the inter-section fault positioning time and the fault isolation time and is recorded as T1; 2) if the user is located in the downstream section of the fault area and can be supplied through the standby supply channel, the power failure time is the sum of T1 and the fault supply time and is recorded as T2; 3) if the user is located in the downstream section of the fault area and can not be supplied through the standby supply channel, or the user is located in the fault area, the power failure time comprises inter-section fault positioning time, intra-section fault positioning time and fault repairing time, and is recorded as T3; on the basis, a plurality of reliability evaluation indexes widely used in the international range can be calculated; the calculation formula of the user average power failure time SAIDI, the expected power shortage EENS of the system and the power supply reliability RS-3 index related in the text is shown as formulas (2), (3) and (4);
ID＝λF(β1T1+β2T2+β3T3) (5)
IE＝IDPL(6)
in the formula: i isD、IE、IRSAIDI, EENS and RS-3 indexes of the feeder line are respectively; lambda [ alpha ]FThe total failure rate of the feeder line is; pLβ is the total load of the feeder line1、β2、β3For the distribution coefficient of the power failure users, the average distribution proportion of the above 3 types of users is respectively expressed when any equipment in the feeder line fails.
Preferably, the first multi-year investment decision model with the maximum target for the maximum increase of the distribution network loss load index comprises a structure similar to that of the traditional investment decision model, wherein the structure of the first multi-year investment decision model with the maximum target for the maximum increase of the distribution network loss load index is just that a constraint condition formula (4) in the traditional investment decision model is replaced by a formula (10), and a related constraint condition is modified into a total constraint of multiple years; therefore, the annual investment decision model with the maximum target of the maximum improvement of the loss load index of the power distribution network can be expressed as follows:
in the above formula, NepRepresenting the total investment cycle, equation (8) as the investment targetRepresenting the total improvement amount of the reliability index of the power distribution network in the total investment period, wherein XepFor each investment measure in an investment cycle,. DELTA.IepRepresenting the variation of the reliability index in each investment period; formula (9) is investment amount constraint, CmaxTo an upper limit value of the investment amount, Cep(Xep) Representing the amount of investment for each investment measure in each investment period; the formula (10) is the associated rule constraint condition of the investment transformation measure and the reliability index,kthe method comprises the following steps of (1) providing an interaction strategy set of energy storage and flexible load, wherein phi is an association rule function, and omega and b respectively represent training parameters of an association rule; formula (11) represents the investment measure library constraint of the ep investment period, and psi is the investment measure library; the formula (12) is the upper and lower limit constraint of the investment reconstruction measures,
and
is XepiAt the lower and upper limits of the ep period, for example, formula (13),
and
the upper limit of the number of the two-remote device and the three-remote device in the ep period and the upper limit of the capacity of the distributed power supply in the ep period are respectively,
and
is XepiLower and upper limits within the total investment period; the formula (14) shows that the total amount of investment measures in the whole investment period also needs to meet the requirements of upper and lower limits.
The above formula replaces the parameter vector y related to the power flow calculation in the formula (4) with the threshold and weight parameters for deep belief network learning, i.e. the power flow constraint is converted into the relevance constraint based on the deep belief network.
8. The power distribution decision modeling method based on transformation measures and loss load index correlation according to claim 1, wherein the second multi-year investment decision model targeting power distribution network investment cost minimization comprises the following steps:
in the model, the minimum total investment cost of the power grid is taken as a target, the lower limit of the increase of the loss load index is taken as a constraint, and the rest constraint conditions are the same as the perennial investment decision model with the maximum increase of the loss load index of the power distribution network, and are all based on the association rule of the transformation measures of the power distribution network and the loss load index for modeling; wherein, Delta IsetSet value representing improvement of reliability index, Cinvest_epAnd CEENS_epRespectively representing the fixed investment amount and the lost load compensation amount, and the sum of the fixed investment amount and the lost load compensation amount is the total investment amount of the reconstruction measures.
Compared with the prior art, the invention has the beneficial effects that: compared with the traditional investment decision modeling technology for the power distribution network, the investment decision modeling technology based on the relevance can convert an investment decision model originally related to complex nonlinear power flow calculation into a simple linear power distribution network investment decision model based on data relevance, and can consider the influence of complex and diverse power distribution network transformation measures on the load loss index of the power distribution network, so that the accurate investment planning decision of the power distribution network can be realized more quickly and efficiently. In addition, the relevance mining technology applied in the patent has great advantages in the aspects of finding problem potential rules, improving the calculation efficiency and the like, not only can the complex load flow calculation process be avoided, but also the calculation efficiency can be effectively improved.
Drawings
FIG. 1 is a deep belief network architecture of the present invention;
FIG. 2 is a model for evaluating the loss load index of the power distribution network based on correlation analysis according to the present invention;
FIG. 3 is a flow chart of the correlation analysis based on the deep belief network of the present invention;
FIG. 4 is a decision diagram of a multi-year investment planning of a power distribution network based on the relevance of a modification measure and a load loss index.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
A power distribution network investment planning decision modeling method based on a deep belief network comprises the following steps:
analyzing a recessive relation between different investment transformation measure configuration schemes and the distribution network load loss index;
describing the influence degree of the investment decision scheme on the operation reliability such as the load loss of the power distribution system;
digging a correlation rule between technical path configuration under different operating conditions and investment benefit improvement by using a power grid load loss index;
constructing a direct mapping between a power distribution network modification measure and a load loss index;
establishing a power grid load loss index;
establishing a power distribution network load loss index evaluation model based on relevance analysis;
training a deep confidence network for the loss load index of the power distribution network and various predicted reconstruction measures;
(1) analyzing a recessive relation between different configuration schemes and the power grid load loss index;
under the consideration of a differentiated operation strategy, according to a power distribution network modification measure and load loss index association rule provided by early power distribution network interaction medium-long time operation time sequence simulation and deep confidence network training, a recessive relation between different configuration schemes and power grid load loss indexes is analyzed from the aspects of statistical analysis and data learning;
(2) describing the influence degree of the investment decision scheme on the operation reliability such as the system load loss and the like;
based on the correlation rule obtained by the statistical analysis or the mathematical learning, the influence degree of the investment decision scheme on the system operation reliability is described by the loss load index of the power distribution network.
(3) Digging a correlation rule between investment modification measure configuration under different operating conditions and investment benefit improvement by using a power grid load loss index;
and mining association rules between the technical path configuration and the investment benefits under different operating conditions by using a deep belief network algorithm, and dynamically updating the investment benefits along with the change of a configuration scheme so as to obtain accurate investment aid decisions. Since an investment decision model containing correlation analysis of 'transformation measures-power grid load loss indexes' belongs to a complex nonlinear programming problem, the direct mapping between the transformation measures of the power distribution network and the load loss indexes is constructed by utilizing the nonlinear mapping capability of a deep confidence network. The deep confidence network based on the optimization of the Nadam optimizer is a generation model, is formed by stacking a plurality of restricted Boltzmann machines, has good nonlinear mapping capability, can learn and self-adapt unknown information, and is a common relevance analysis algorithm based on data mining.
The process of performing relevance mining by adopting the deep belief network and obtaining the corresponding power grid load loss index is as follows:
step 1: obtaining sample data of time sequence simulation in medium and long-term operation, and initially training to determine a basic solution space of each parameter of the deep confidence network;
step 2: establishing an input and output vector of a deep belief network, and determining a neural network model and a learning mode;
and step 3: calculating the input and output of each unit of the hidden layer and the output layer of the deep belief network, namely finishing the preliminary learning of the deep belief network;
and 4, step 4: adjusting the weight and the threshold of the controlled deep belief network performance by adopting a Nadam optimizer, and optimizing the convergence speed and the convergence effect of deep belief network learning;
and 5: continuously updating the learning mode and the learning times;
step 6: and (5) repeating the step 5, and continuously carrying out deep belief network training until a cutoff condition (maximum learning times) is met.
And 7: and (3) applying a deep confidence network association rule, inputting data such as node load, voltage, line power, distributed power supply output and telemechanical device installation under a certain transformation scheme, and calling the deep confidence network to obtain a corresponding power grid load loss index result.
(4) Establishing a power distribution network multi-year investment decision model based on relevance analysis
Traditional power distribution network investment models; the method comprises the following steps of obtaining parameters such as voltage, power and phase angle of a network through load flow calculation in a traditional power distribution network investment model, and further obtaining a technical and economic index value of the network through calculation, wherein an investment decision model is as follows:
Xi∈{0,1} (3)
in the model, the maximum improvement of the loss load index representing the investment benefit of the power distribution network is an objective function, as shown in formula (1); the total investment of the power distribution network, the independence of the transformation measures and the correlation relationship between the transformation measures and the load loss index are taken as constraints, and the constraint is shown as a formula (2-4). I and
respectively representing the distribution before and after the implementation of the retrofitting measuresNet loss load index, XiRepresenting a different type of modification, K (X)i) Representative reconstruction measure XiThe cost of (2).
Representing the incidence relation between the modification measures and the loss load index. Wherein y represents the vector of parameters related to power flow and grid structure in the network, such as voltage, power, phase angle and the like. As can be seen from the formula (4), in the traditional investment model, the relationship between the reconstruction measures and the load loss indexes needs to be expressed by means of the power flow parameters.
The load loss reliability index in the model can be expressed as follows. The power supply reliability index is as follows: the reliability index is generally used for evaluating the influence degree of the power distribution network power failure phenomenon on users. According to the difference of the power failure time, the users can be classified into 3 types after power failure: 1) if the user is located in the section upstream of the fault area, the power failure time is the sum of the inter-section fault locating time and the fault isolating time, and is recorded as T1. 2) If the user is located in the downstream section of the fault area and can transfer the power through the backup channel, the power failure time is the sum of the power failure time T1 and the fault transfer time, and is recorded as T2. 3) If the user is located in the downstream section of the fault area and cannot be supplied through the backup channel, or if the user is located in the fault area, the power outage time includes inter-section fault location time, intra-section fault location time, and fault repair time, which is denoted as T3. On the basis, a plurality of reliability evaluation indexes widely used in the international range can be calculated. The calculation formulas of the user average power failure time (SAIDI), the expected power shortage amount (EENS) of the system and the power supply reliability (RS-3) indexes related to the method are shown in the formulas (2), (3) and (4).
ID＝λF(β1T1+β2T2+β3T3) (5)
IE＝IDPL(6)
In the formula: i isD、IE、IRSAIDI, EENS and RS-3 indexes of the feeder line are respectively; lambda [ alpha ]FThe total failure rate of the feeder line is; pLβ is the total load of the feeder line1、β2、β3For the distribution coefficient of the power failure users, the average distribution proportion of the above 3 types of users is respectively expressed when any equipment in the feeder line fails.
The power distribution decision modeling method based on the correlation between the reconstruction measures and the loss load indexes is characterized in that the multi-year investment decision model with the maximum target of the maximum improvement of the loss load indexes of the power distribution network comprises a structure similar to that of the traditional investment decision model, wherein the structure of the multi-year investment decision model with the maximum target of the maximum improvement of the loss load indexes of the power distribution network is only that a constraint condition formula (4) in the traditional investment decision model is replaced by a formula (10), and related constraint conditions are modified into total constraint for many years. Therefore, the annual investment decision model with the maximum target of the maximum improvement of the loss load index of the power distribution network can be expressed as follows:
in the above formula, NepExpressing the total investment period, and expressing the reliability index promotion total amount of the power distribution network in the total investment period by using a formula (8) as an investment target, wherein XepFor each investment measure in an investment cycle,. DELTA.IepRepresenting the variation of the reliability index in each investment period; formula (9) is investment amount constraint, CmaxTo an upper limit value of the investment amount, Cep(Xep) Representing the amount of investment for each investment measure in each investment period; the formula (10) is the associated rule constraint condition of the investment transformation measure and the reliability index,kthe method comprises the following steps of (1) providing an interaction strategy set of energy storage and flexible load, wherein phi is an association rule function, and omega and b respectively represent training parameters of an association rule; formula (11) represents the investment measure library constraint of the ep investment period, and psi is the investment measure library; the formula (12) is the upper and lower limit constraint of the investment reconstruction measures,
and
is XepiAt the lower and upper limits of the ep period, for example, formula (13),
and
the upper limit of the number of the two-remote device and the three-remote device in the ep period and the upper limit of the capacity of the distributed power supply in the ep period are respectively,
and
is XepiLower and upper limits within the total investment period; the formula (14) shows that the total amount of investment measures in the whole investment period also needs to meet the upper and lower limitsAnd (6) obtaining.
The above formula replaces the parameter vector y related to the power flow calculation in the formula (4) with the threshold and weight parameters for deep belief network learning, i.e. the power flow constraint is converted into the relevance constraint based on the deep belief network.
8. The power distribution decision modeling method based on transformation measures and loss load index correlation according to claim 1, wherein the second multi-year investment decision model targeting power distribution network investment cost minimization comprises the following steps:
in the model, the minimum total investment cost of the power grid is taken as a target, the lower limit of the increase of the loss load index is taken as a constraint, and the rest constraint conditions are the same as the perennial investment decision model with the maximum increase of the loss load index of the power distribution network, and are all based on the association rule of the transformation measures of the power distribution network and the loss load index for modeling; wherein, Delta IsetSet value representing improvement of reliability index, Cinvest_epAnd CEENS_epRespectively representing the fixed investment amount and the lost load compensation amount, and the sum of the fixed investment amount and the lost load compensation amount is the total investment amount of the reconstruction measures.
Compared with the prior art, the invention has the beneficial effects that: compared with the traditional investment decision modeling technology for the power distribution network, the relevance-based investment decision-making multi-year modeling technology provided by the patent can convert an original investment decision model related to complex nonlinear power flow calculation into a simple linear power distribution network investment decision-making model based on data relevance, and can consider the influence of complex and diverse power distribution network transformation measures on the load loss index of the power distribution network, so that the accurate investment planning decision of the power distribution network can be realized more quickly and efficiently. In addition, the relevance mining technology applied in the patent has great advantages in the aspects of finding problem potential rules, improving the calculation efficiency and the like, not only can the complex load flow calculation process be avoided, but also the calculation efficiency can be effectively improved.
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.
Claims (8)
1. The power distribution decision modeling method based on the relevance of the transformation measures and the load loss indexes is characterized by comprising the following steps of:
s1: determining implicit relations between different configuration schemes and the power grid load loss amount indexes; determining the influence degree of the investment decision scheme on the reliability index of the system load loss amount; determining a correlation rule between investment improvement measure configuration under different operating conditions and investment benefits improved by the loss load index;
s2: optimizing the implicit relationship, the degree of influence and the association rule in the step S1 based on a Nadam optimizer;
s3: providing a power distribution network multi-year investment decision model for correlation analysis of the transformation measures and the power distribution network load loss indexes, providing a power distribution network load loss index evaluation model based on the correlation analysis, providing a correlation relation between various transformation measures of the power distribution network and the load loss indexes, and providing a traditional power distribution network planning model; wherein the content of the first and second substances,
improving a first multi-year investment decision model with the maximum target according to the loss load index of the power distribution network;
a second multi-year investment decision model aiming at minimizing the investment cost of the power distribution network;
s4: and solving the first multi-year investment decision model and the second multi-year investment decision model to obtain an optimal power distribution network investment planning decision.
2. The power distribution decision modeling method based on the correlation between the improvement measure and the loss load index as claimed in claim 1, wherein in step S1, the degree of influence of the investment decision scheme on the reliability index of the system load is characterized by the loss load index of the power grid based on the correlation rule obtained by statistical analysis or mathematical learning.
3. The power distribution decision modeling method based on modification measure and loss load index correlation according to claim 1, wherein in step S1, the rule of correlation between the configuration of the modification measure for investment under different operating conditions and the investment benefit of the loss load specifically includes: and mining by using the sample data of the loss load capacity index of the power distribution network through a research and development algorithm, and dynamically updating investment benefits along with the change of a configuration scheme so as to obtain an accurate investment aid decision result.
4. The power distribution decision modeling method based on the correlation between the improvement measure and the loss load index as claimed in claim 1, wherein in step S2, the optimization step based on the Nadam optimizer is a generative model, and is formed by stacking a plurality of restricted boltzmann machines, has good nonlinear mapping capability, can learn and adapt to unknown information, and has a structure formed by an input and output layer and a plurality of hidden layers.
5. The power distribution decision modeling method based on the correlation of reformulation measures and loss load indicators as recited in claim 1,
the power distribution network multi-year investment decision model for relevance analysis of the transformation measures and the power distribution network load loss indexes in the step S3 belongs to the problem of complex nonlinear programming, and a direct mapping between the power distribution network transformation measures and the load loss indexes is constructed by utilizing the nonlinear mapping capability based on a Nadam optimizer;
the model can quickly estimate the loss load value under the transformation measures when the scene of the transformation measures of the power distribution network changes, so that the influence degree of implementation of different transformation measures of the power distribution network on reliability indexes such as the loss load of the power distribution network is judged, the influence degree is used as a relevance constraint condition of later-stage power distribution network investment decision, and the time consumption of time domain simulation is saved; adopting a deep confidence network to carry out relevance mining and obtain a corresponding power grid load loss index, wherein the process comprises the following steps:
step 1: obtaining sample data of time sequence simulation in medium and long-term operation, and initially training to determine a basic solution space of each parameter of the deep confidence network;
step 2: establishing an input and output vector of a deep belief network, and determining a neural network model and a learning mode;
and step 3: calculating the input and output of each unit of the hidden layer and the output layer of the deep belief network, namely finishing the preliminary learning of the deep belief network;
and 4, step 4: adjusting the weight and the threshold of the controlled deep belief network performance by adopting a Nadam optimizer, and optimizing the convergence speed and the convergence effect of deep belief network learning;
and 5: continuously updating the learning mode and the learning times;
step 6: repeating the step 5, and continuously carrying out deep belief network training until a cutoff condition is met, namely the maximum learning times;
and 7: and (3) applying a deep confidence network association rule, inputting data such as node load, voltage, line power, distributed power supply output and telemechanical device installation under a certain transformation scheme, and calling the deep confidence network to obtain a corresponding power grid load loss index result.
6. The power distribution decision modeling method based on the correlation between the improvement measures and the loss load index according to claim 1 is characterized in that in a traditional power distribution network investment model, voltage, power and phase angle parameters of a network are obtained through load flow calculation, and then technical and economic index values of the network are obtained through calculation, wherein the investment decision model is as follows:
Xi∈{0,1} (3)
in the model, the maximum improvement of the loss load index representing the investment benefit of the power distribution network is an objective function, as shown in formula (1); the total investment of the power distribution network, the independence of the transformation measures and the correlation relationship between the transformation measures and the load loss index are taken as constraints, and the constraint is shown as a formula (2-4); i and
respectively representing the loss load indexes, X, of the power distribution network before and after the implementation of the reconstruction measuresiRepresenting a different type of modification, K (X)i) Representative reconstruction measure XiThe cost of (2);
representing the incidence relation between the modification measures and the load loss index; wherein y represents the vector of parameters related to power flow and grid structure in the network, such as voltage, power and phase angle; as shown in the formula (4), in the traditional investment model, the relationship between the reconstruction measures and the load loss indexes needs to be expressed by depending on the power flow parameters;
wherein, the loss load reliability index in the model can be expressed as follows; the power supply reliability index is as follows: the reliability index is generally used for evaluating the influence degree of the power failure phenomenon of the power distribution network on users; according to the difference of the power failure time, the users can be classified into 3 types after power failure: 1) if the user is located in the upstream section of the fault area, the power failure time is the sum of the inter-section fault positioning time and the fault isolation time and is recorded as T1; 2) if the user is located in the downstream section of the fault area and can be supplied through the standby supply channel, the power failure time is the sum of T1 and the fault supply time and is recorded as T2; 3) if the user is located in the downstream section of the fault area and can not be supplied through the standby supply channel, or the user is located in the fault area, the power failure time comprises inter-section fault positioning time, intra-section fault positioning time and fault repairing time, and is recorded as T3; on the basis, a plurality of reliability evaluation indexes widely used in the international range can be calculated; the calculation formula of the user average power failure time SAIDI, the expected power shortage EENS of the system and the power supply reliability RS-3 index related in the text is shown as formulas (2), (3) and (4);
ID＝λF(β1T1+β2T2+β3T3) (5)
IE＝IDPL(6)
in the formula: i isD、IE、IRSAIDI, EENS and RS-3 indexes of the feeder line are respectively; lambda [ alpha ]FThe total failure rate of the feeder line is; pLβ is the total load of the feeder line1、β2、β3For the distribution coefficient of the power failure users, the average distribution proportion of the above 3 types of users is respectively expressed when any equipment in the feeder line fails.
7. The power distribution decision modeling method based on the correlation between the improvement measure and the loss load index according to claim 1 is characterized in that the first multi-year investment decision model with the maximum target of the increase of the loss load index of the power distribution network is similar to the traditional investment decision model in structure, except that the constraint condition formula (4) in the traditional investment decision model is replaced by the following formula (10), and the related constraint condition is modified into the total constraint of many years; therefore, the first multi-year investment decision model with the maximum target for increasing the loss load index of the power distribution network can be expressed as follows:
in the above formula, NepExpressing the total investment period, and expressing the reliability index promotion total amount of the power distribution network in the total investment period by using a formula (8) as an investment target, wherein XepFor each investment measure in an investment cycle,. DELTA.IepRepresenting the variation of the reliability index in each investment period; formula (9) is investment amount constraint, CmaxTo an upper limit value of the investment amount, Cep(Xep) Representing the amount of investment for each investment measure in each investment period; the formula (10) is the associated rule constraint condition of the investment transformation measure and the reliability index,kthe method comprises the following steps of (1) providing an interaction strategy set of energy storage and flexible load, wherein phi is an association rule function, and omega and b respectively represent training parameters of an association rule; formula (11) represents the investment measure library constraint of the ep investment period, and psi is the investment measure library; the formula (12) is the upper and lower limit constraint of the investment reconstruction measures,
and
is XepiAt the lower and upper limits of the ep period, for example, formula (13),
and
the upper limit of the number of the two-remote device and the three-remote device in the ep period and the upper limit of the capacity of the distributed power supply in the ep period are respectively,
and
is XepiLower and upper limits within the total investment period; the formula (14) shows that the total amount of investment measures in the whole investment period also needs to meet the requirements of upper and lower limits.
The above formula replaces the parameter vector y related to the power flow calculation in the formula (4) with the threshold and weight parameters for deep belief network learning, i.e. the power flow constraint is converted into the relevance constraint based on the deep belief network.
8. The power distribution decision modeling method based on transformation measures and loss load index correlation according to claim 1, wherein the second multi-year investment decision model targeting power distribution network investment cost minimization comprises the following steps:
in the model, the minimum total investment cost of the power grid is taken as a target, the lower limit of the increase of the loss load index is taken as a constraint, and the rest constraint conditions are the same as the perennial investment decision model with the maximum increase of the loss load index of the power distribution network, and are all based on the association rule of the transformation measures of the power distribution network and the loss load index for modeling; wherein, Delta IsetSet value representing improvement of reliability index, Cinvest_epAnd CEENS_epRespectively representing the fixed investment amount and the lost load compensation amount, and the sum of the fixed investment amount and the lost load compensation amount is the total investment amount of the reconstruction measures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130943.1A CN111415068A (en) | 2020-02-28 | 2020-02-28 | Power distribution decision modeling method based on relevance of transformation measures and loss load index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130943.1A CN111415068A (en) | 2020-02-28 | 2020-02-28 | Power distribution decision modeling method based on relevance of transformation measures and loss load index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111415068A true CN111415068A (en) | 2020-07-14 |
Family
ID=71494063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010130943.1A Pending CN111415068A (en) | 2020-02-28 | 2020-02-28 | Power distribution decision modeling method based on relevance of transformation measures and loss load index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111415068A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100784A (en) * | 2020-09-22 | 2020-12-18 | 四川大学 | Power distribution network planning method based on clustering net rack topology and reliability estimation association model |
| CN113393051A (en) * | 2021-06-30 | 2021-09-14 | 四川大学 | Power distribution network investment decision method based on deep migration learning |
| CN113793077A (en) * | 2021-11-17 | 2021-12-14 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing power failure influence of power distribution network user fault |
| CN117076573A (en) * | 2023-10-16 | 2023-11-17 | 深圳博十强志科技有限公司 | Data processing analysis system based on big data technology |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018014774A (en) * | 2016-07-19 | 2018-01-25 | 株式会社日立製作所 | System optimization calculation device and system optimization calculation method of power distribution system |
| CN109359837A (en) * | 2018-09-29 | 2019-02-19 | 国网四川省电力公司经济技术研究院 | A kind of assessment of active distribution network technical economic benefit and investment decision method |
| CN110009181A (en) * | 2019-01-25 | 2019-07-12 | 国网福建省电力有限公司 | Distribution network transform measure and mistake load figureofmerit relevance method for digging and device |
| CN110059938A (en) * | 2019-03-29 | 2019-07-26 | 四川大学 | A kind of distribution network planning method based on correlation rule driving |
| CN110264112A (en) * | 2019-07-17 | 2019-09-20 | 国网河南省电力公司开封供电公司 | Bidirectional weighted gray correlation-based power distribution network reliability influence factor analysis method |
-
2020
- 2020-02-28 CN CN202010130943.1A patent/CN111415068A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018014774A (en) * | 2016-07-19 | 2018-01-25 | 株式会社日立製作所 | System optimization calculation device and system optimization calculation method of power distribution system |
| CN109359837A (en) * | 2018-09-29 | 2019-02-19 | 国网四川省电力公司经济技术研究院 | A kind of assessment of active distribution network technical economic benefit and investment decision method |
| CN110009181A (en) * | 2019-01-25 | 2019-07-12 | 国网福建省电力有限公司 | Distribution network transform measure and mistake load figureofmerit relevance method for digging and device |
| CN110059938A (en) * | 2019-03-29 | 2019-07-26 | 四川大学 | A kind of distribution network planning method based on correlation rule driving |
| CN110264112A (en) * | 2019-07-17 | 2019-09-20 | 国网河南省电力公司开封供电公司 | Bidirectional weighted gray correlation-based power distribution network reliability influence factor analysis method |
Non-Patent Citations (2)
| Title |
|---|
| BIN CHEN ET AL.: "An Investment Decision Model of Distribution Network Planning Based on Correlation Mining of Reconstruction Measures and Performance Indexes", 《2018 CHINA INTERNATIONAL CONFERENCE ON ELECTRICITY DISTRIBUTION (CICED)》 * |
| YUE XIANG ET AL.: "Correlation-based Investment Decision-Making for Distribution Network Reconstruction", 《2019 IEEE INNOVATIVE SMART GRID TECHNOLOGIES - ASIA (ISGT ASIA)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100784A (en) * | 2020-09-22 | 2020-12-18 | 四川大学 | Power distribution network planning method based on clustering net rack topology and reliability estimation association model |
| CN113393051A (en) * | 2021-06-30 | 2021-09-14 | 四川大学 | Power distribution network investment decision method based on deep migration learning |
| CN113393051B (en) * | 2021-06-30 | 2023-07-18 | 四川大学 | Power distribution network investment decision-making method based on deep migration learning |
| CN113793077A (en) * | 2021-11-17 | 2021-12-14 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing power failure influence of power distribution network user fault |
| CN113793077B (en) * | 2021-11-17 | 2022-03-15 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing power failure influence of power distribution network user fault |
| CN117076573A (en) * | 2023-10-16 | 2023-11-17 | 深圳博十强志科技有限公司 | Data processing analysis system based on big data technology |
| CN117076573B (en) * | 2023-10-16 | 2024-01-05 | 深圳博十强志科技有限公司 | Data processing analysis system based on big data technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111415068A (en) | Power distribution decision modeling method based on relevance of transformation measures and loss load index | |
| Sözen et al. | Prediction of net energy consumption based on economic indicators (GNP and GDP) in Turkey | |
| CN104573875B (en) | A kind of method of the power generating facilities and power grids optimization planning of low-carbon | |
| Wang et al. | Two-stage stochastic planning for integrated energy systems accounting for carbon trading price uncertainty | |
| CN107909253A (en) | Intelligent distribution network scheduling controlling effect evaluation method based on interval based AHP | |
| CN110910026B (en) | Cross-provincial power transmission line loss intelligent management and decision method and system | |
| Zang et al. | A robust state estimator for integrated electrical and heating networks | |
| CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
| CN105528668A (en) | Dynamic environment and economy scheduling method of grid-connected wind power system | |
| CN115877312A (en) | Electric energy meter informatization evaluation calibration model based on station area electric energy conservation | |
| CN112070395A (en) | Energy internet reliability evaluation system, model establishing method and evaluation method | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| CN108108837A (en) | A kind of area new energy power supply structure optimization Forecasting Methodology and system | |
| CN112100784A (en) | Power distribution network planning method based on clustering net rack topology and reliability estimation association model | |
| Jiang et al. | A bottom-up method for probabilistic short-term load forecasting based on medium voltage load patterns | |
| CN116415708B (en) | Power grid robust planning method considering confidence level | |
| Zhang et al. | Energy economy and energy structure optimization countermeasures based on big data mining | |
| CN115907198A (en) | Long-distance heat supply load intelligent prediction system | |
| CN115456205A (en) | Large-scale multi-target unit maintenance optimization method | |
| Fu et al. | Study on wind power consumption capacity of power grid considering risk and unit commitment | |
| Zhang et al. | Forecasting model of total import and export based on ARIMA algorithm optimized by BP neural network | |
| Xie et al. | Vector ordinal optimization theory based large‐scale multi‐objective unit commitment considering stochastic wind power | |
| Ghods et al. | Long-term peak demand forecasting by using radial basis function neural networks | |
| Wang et al. | Distribution Network Monthly Line Loss Calculate and Improvement with Convolutional Neural Network | |
| Tang | Natural Gas Load Forecasting Based on Improved Genetic Algorithm and BP Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200714 |