CN104318318A - Power grid loss influence quantization model by charge, network and source coordination control-based factors - Google Patents
Power grid loss influence quantization model by charge, network and source coordination control-based factors Download PDFInfo
- Publication number
- CN104318318A CN104318318A CN201410530418.3A CN201410530418A CN104318318A CN 104318318 A CN104318318 A CN 104318318A CN 201410530418 A CN201410530418 A CN 201410530418A CN 104318318 A CN104318318 A CN 104318318A
- Authority
- CN
- China
- Prior art keywords
- layer
- model
- loss
- network
- grid 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
- 238000013139 quantization Methods 0.000 title abstract 2
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000003062 neural network model Methods 0.000 claims abstract description 5
- 210000002569 neuron Anatomy 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 240000002853 Nelumbo nucifera Species 0.000 claims description 7
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 7
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000001537 neural effect Effects 0.000 claims description 3
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
- 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
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power grid loss influence quantization model by charge, network and source coordination control-based factors. the featured steps comprises: model data are prepared; a BP neural network model is built; the neural network is trained by input data; influences of each grid loss factor on power grid loss is quantized; and the model can be additionally used for predication of power grid predication. The specific implementation steps can be seen as figures in the abstract. Influences of grid influence factors on the grid loss can be quantized, and evidence is provided for a power grid department to make effective loss reduction measures.
Description
Technical field
The invention belongs to electric system Losses Analysis field, particularly relating to a kind of factor pair grid loss based on lotus, net, source cooperation control affects quantitative model.
Background technology
Grid loss and operation of power networks economy are closely related, and network loss is associated with many factors, is also no lack of contact and affects between factor and factor, and this makes network loss research become a urgently problem for complexity.Carry out in-depth analysis to the concrete impact of the every factor of influence of network loss on network loss to be conducive to effectively falling damage, improve operation of power networks economic benefit.The research network loss factor is much, but further the research work that the impact of each network loss factor pair grid loss is carried out quantizing but is not seen report.
Factor pair grid loss based on lotus, net, source cooperation control affects quantitative model and falls on the basis of damage potentiality at excavation power system load, electrical network self and the mutual cooperation control of power supply, neural network is used to carry out sensitivity analysis on each influence factor for the impact of network loss, and using quantized value that sensitivity value affects as this factor network loss.This model algorithm is simply different in nature, and calculated amount is little, and concurrency is strong, Real-time Network can be utilized to undermine network loss factor statistics data and effectively quantize network loss impact each factor, provides reliable basis for damage falls in further efficient electrical network.In addition this model can also be used to carry out effective network loss prediction, the planning value in given each influence factor future, just can make a prediction to following network loss, no matter whether this be take reducing loss measure necessary future for decision-making, or all significant for the validity of assessment reducing loss measure.
Summary of the invention
The object of the invention is to, provide a kind of factor pair grid loss based on lotus, net, source cooperation control to affect quantitative model, be used for assessing the importance that every network loss influence factor affects network loss, provide foundation for electrical network department takes measures effectively to fall damage.
Its feature comprises:
1, model data prepares
Statistics grid loss factor data and corresponding grid loss amount, as mode input after can carrying out nondimensionalization and normalization to it.The acceptable error range of setting model.
2, BP neural network model is created
The neuron number of hidden layer quantity and each layer in the middle of setting neural network, the transport function type of each layer of setting neural network.
3, to input data neural network training
The input of model trained as training set the neural network created, training process comprises the reverse makeover process of forward calculation process and weights and threshold.In forward calculation process, input quantity successively calculates from input layer through hidden layer, and is transmitted to output layer, and every layer of neuronic state only affects the neuronic state of lower one deck.As output layer can not obtain the output of expectation, then proceed to error back propagation process, error signal returns along original interface channel, successively the weights and threshold of each layer of regulating networks, until arrive input layer, then repeats forward calculation.These two processes are carried out successively repeatedly, and constantly the weights and threshold of each layer of adjustment, makes network error reach the model error scope of setting.Now neural metwork training completes, and each layer weights and threshold setting suitably.
4, the impact of each network loss factor pair grid loss is quantized
On each layer each neuron weights basis, the neural network susceptibility calculating each factor pair grid loss affects quantized value as it to grid loss.Below provide with input layer (neuron number and network loss factor of influence number are for N), hidden layer (neuron number is L), the neural network of output layer (neuron number is 1) each one deck is that the factor i of example affects quantized value to grid loss
computing formula:
Wherein
for the connection weight between the input layer factor and hidden layer,
for the connection weight between hidden layer and output layer.
5, model can add and predict for grid loss
This model also has the auxiliary function of grid loss prediction, inputs the planned value in each factor future, the neural network model trained can be used to carry out following network loss prediction.
Accompanying drawing explanation
Fig. 1 is the factor pair grid loss impact quantification model flow figure based on lotus, net, source cooperation control.
embodiment
Below in conjunction with accompanying drawing, preferred embodiment is elaborated.It is emphasized that following explanation is only exemplary, instead of in order to limit the scope of the invention and apply.
Fig. 1 is the factor pair grid loss impact quantification model flow figure based on lotus, net, source cooperation control.
Step 1: statistical history network loss data and corresponding reactive-load compensation amount, high energy input amount, trend section power etc.And setting model allows relative error to be within 5%.
Step 2: create one containing an input layer (4 neurons), 3 hidden layers (5 neurons), the BP neuroid of an input layer (1 neuron).Random setting initial weight and threshold value.
Step 3: train the BP neuroid set up by input data, knows and meets error setting.
Step 4: begin the compilation of program writing and calculate reactive-load compensation amount, high energy input amount, trend section power, to the neural sensitivity degree of network loss, affects the quantized value of size on network loss as it.
Claims (1)
1. the factor pair grid loss based on lotus, net, source cooperation control affects quantitative model, it is characterized in that:
1, model data prepares
Statistics grid loss factor data and corresponding grid loss amount, as mode input after can carrying out nondimensionalization and normalization to it; The acceptable error range of cover half type;
2, BP neural network model is created
The neuron number of hidden layer quantity and each layer in the middle of setting neural network, the transport function type of each layer of setting neural network;
3, to input data neural network training
The input of model trained as training set the neural network created, training process comprises the reverse makeover process of forward calculation process and weights and threshold; To in computation process, input quantity successively calculates from input layer through hidden layer, and is transmitted to output layer, and every layer of neuronic state only affects the neuronic state of lower one deck; Output layer can not obtain the output expected, then proceed to error back propagation process, error signal returns along original interface channel, successively the weights and threshold of each layer of regulating networks, until arrive input layer, then repeats forward calculation; Two processes are carried out successively repeatedly, and constantly the weights and threshold of each layer of adjustment, makes network error reach the model error scope of setting; Time neural metwork training complete, the setting of each layer weights and threshold is suitably;
4, the impact of each network loss factor pair grid loss is quantized
On each layer each neuron weights basis, the neural network susceptibility calculating each factor pair grid loss affects quantized value as it to grid loss; Under provide with input layer (neuron number and network loss factor of influence number are for N), hidden layer (neuron number is L), the neural network of output layer (neuron number is 1) each one deck is that the factor i of example affects quantized value to grid loss
computing formula:
Wherein
for the connection weight between the input layer factor and hidden layer,
for the connection weight between hidden layer and output layer;
5, model can add and predict for grid loss
This model also has the auxiliary function of grid loss prediction, inputs the planned value in each factor future, the neural network model trained can be used to carry out following network loss prediction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410530418.3A CN104318318A (en) | 2014-10-10 | 2014-10-10 | Power grid loss influence quantization model by charge, network and source coordination control-based factors |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410530418.3A CN104318318A (en) | 2014-10-10 | 2014-10-10 | Power grid loss influence quantization model by charge, network and source coordination control-based factors |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104318318A true CN104318318A (en) | 2015-01-28 |
Family
ID=52373546
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410530418.3A Pending CN104318318A (en) | 2014-10-10 | 2014-10-10 | Power grid loss influence quantization model by charge, network and source coordination control-based factors |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104318318A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636009A (en) * | 2018-11-22 | 2019-04-16 | 中国电力科学研究院有限公司 | It is a kind of to establish the method and system for determining the neural network model of grid line loss |
CN109858663A (en) * | 2018-11-19 | 2019-06-07 | 中国农业大学 | Distribution network failure power failure INFLUENCING FACTORS analysis based on BP neural network |
CN111552911A (en) * | 2020-03-17 | 2020-08-18 | 东南大学 | Multi-scene generation-based quantitative analysis method for technical line loss influence factors |
-
2014
- 2014-10-10 CN CN201410530418.3A patent/CN104318318A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109858663A (en) * | 2018-11-19 | 2019-06-07 | 中国农业大学 | Distribution network failure power failure INFLUENCING FACTORS analysis based on BP neural network |
CN109636009A (en) * | 2018-11-22 | 2019-04-16 | 中国电力科学研究院有限公司 | It is a kind of to establish the method and system for determining the neural network model of grid line loss |
CN109636009B (en) * | 2018-11-22 | 2022-07-01 | 中国电力科学研究院有限公司 | Method and system for establishing neural network model for determining line loss of power grid |
CN111552911A (en) * | 2020-03-17 | 2020-08-18 | 东南大学 | Multi-scene generation-based quantitative analysis method for technical line loss influence factors |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sachan et al. | Optimizing basic COCOMO model using simplified genetic algorithm | |
CN105844367A (en) | Sensitivity factor based calculating method for power grid node marginal pricing | |
CN103489038A (en) | Photovoltaic ultra-short-term power prediction method based on LM-BP neural network | |
CN109445935A (en) | A kind of high-performance big data analysis system self-adaption configuration method under cloud computing environment | |
Zhang et al. | A novel ensemble system for short-term wind speed forecasting based on Two-stage Attention-Based Recurrent Neural Network | |
Shuran et al. | Applying BP neural network model to forecast peak velocity of blasting ground vibration | |
Mustafa et al. | Reactive power tracing in pool-based power system utilising the hybrid genetic algorithm and least squares support vector machine | |
CN104318318A (en) | Power grid loss influence quantization model by charge, network and source coordination control-based factors | |
CN102880908A (en) | Method for calculating remanufactured part environmental loss based on back propagation (BP) neural network | |
CN102737285A (en) | Back propagation (BP) neural network-based appropriation budgeting method for scientific research project | |
Wang et al. | A hybrid intelligent framework for forecasting short-term hourly wind speed based on machine learning | |
CN101860025A (en) | Predictor-corrector technology-based power loss calculation method of grid in future operation mode | |
Chi et al. | Comparison of two multi-step ahead forecasting mechanisms for wind speed based on machine learning models | |
Ghadertootoonchi et al. | Long-and Short-term Prediction of Bitcoin Energy Consumption | |
KR102229209B1 (en) | Apparatus and method for power demand forecasting | |
Ahmadzadeh et al. | Application of multi regressive linear model and neural network for wear prediction of grinding mill liners | |
CN111210051A (en) | User electricity consumption behavior prediction method and system | |
Litao et al. | Short-term load forecasting model for metro power supply system based on echo state neural network | |
Guo et al. | Short-Term Photovoltaic Power-Forecasting based on Machine Learning | |
Sike et al. | Electric vehicle charging load time-series prediction based on broad learning system | |
Peng et al. | LITHIUM‐ION BATTERY REMAINING USEFUL LIFE ESTIMATION BASED ON ENSEMBLE LEARNING WITH LS‐SVM ALGORITHM | |
Zhang et al. | Short-Term Electrical Load Forecasting Based on Attention-GRU Networks | |
Ban | Energy decision making of steel company based on energy management system | |
Yu et al. | Convolutional Neural Network for Subsurface Flow Prediction | |
Cheng et al. | Adaptive combination forecasting model based on area correlation degree with application to China’s energy consumption |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150128 |