CN110119842B - Micro-grid short-term load prediction method - Google Patents
Micro-grid short-term load prediction method Download PDFInfo
- Publication number
- CN110119842B CN110119842B CN201910363565.9A CN201910363565A CN110119842B CN 110119842 B CN110119842 B CN 110119842B CN 201910363565 A CN201910363565 A CN 201910363565A CN 110119842 B CN110119842 B CN 110119842B
- Authority
- CN
- China
- Prior art keywords
- sequence
- coefficient
- variation
- mutation
- micro
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000035772 mutation Effects 0.000 claims abstract description 34
- 230000002068 genetic effect Effects 0.000 claims abstract description 11
- 238000002922 simulated annealing Methods 0.000 claims abstract description 10
- 230000006835 compression Effects 0.000 claims abstract description 6
- 238000007906 compression Methods 0.000 claims abstract description 6
- 230000010355 oscillation Effects 0.000 claims description 24
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000010248 power generation Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000003915 air pollution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Water Supply & Treatment (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to a micro-grid short-term load prediction method, which comprises the following steps: s1, acquiring load history data, and improving the data quality of a singular value interval by adopting a cubic spline difference value; s2, establishing a gray variation coefficient model based on amplitude compression, and introducing an improved human comfort index as an influence factor in the modeling process; s3, calculating a predicted parameter sequence of the accumulated mutation coefficient sequence and the mutation coefficient sequence; s4, optimizing the predicted parameter sequence by using a genetic simulated annealing algorithm to obtain optimal matching parameters; s5, reconstructing the optimal matching parameters to obtain an optimal variation coefficient sequence; s6, reversely solving to obtain a load predicted value, and controlling the working state of the distributed power supply. Compared with the prior art, the invention introduces the air quality condition into the human body comfort index, establishes the gray variation coefficient model, solves the problem based on the genetic simulated annealing algorithm, and has the advantages of high prediction speed and high prediction precision.
Description
Technical Field
The invention relates to the technical field of load prediction, in particular to a micro-grid short-term load prediction method.
Background
The micro-grid is a small power generation and distribution system connected to the user side, can realize self control, protection and management, and has the characteristics of low cost, low voltage, small pollution and the like. The micro-grid short-term load prediction is an important precondition for realizing efficient energy saving and optimized operation of the micro-grid, and the accurate prediction of short-term load change has important significance for the arrangement of power generation and supply plans of a power system and the benefit of a power market. Compared with a large power grid, the load of the micro-grid at the user side has the characteristics of large fluctuation, strong uncertainty and low similarity of historical load curves. The load fluctuation of the micro-grid at the user side has a plurality of influencing factors, such as climate conditions, resident electricity habits and economic development degree, wherein the influence of the meteorological factors is obvious.
The prediction method commonly adopted by the micro-grid short-term load comprises a traditional prediction method such as a time sequence method, a similar day method and the like, a modern prediction method such as a gray model, a support vector machine, a neural network and the like, and various combined prediction methods. Most of the methods do not consider or only consider the influence of certain meteorological factors in modeling, so that the accuracy of a prediction result is low, a human body comfort index is introduced for the influence of the meteorological factors on the load, a short-term load prediction method based on the human body comfort index is provided, the human body comfort index in the prior art generally comprises temperature, humidity and wind speed, however, as the industrialization process is accelerated, the urban air pollution situation is serious, the air pollution can bring serious harm to the human body, therefore, the use amount of household appliances, such as a dehumidifier and an air purifier, for improving the living environment is greatly increased, and the load change of a user side micro-grid is further influenced, so that the air quality condition is particularly important to be included in the human body comfort index.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a micro-grid short-term load prediction method based on an improved human comfort index and a gray model, which can rapidly and accurately predict the short-term load of a micro-grid at a user side.
The aim of the invention can be achieved by the following technical scheme: a micro-grid short-term load prediction method, comprising the steps of:
s1, acquiring load history data, and improving the data quality of a singular value interval by adopting a cubic spline difference value;
s2, establishing a gray variation coefficient model based on amplitude compression, and introducing an improved human comfort index considering the air quality condition as an influence factor in the modeling process;
s3, calculating a predicted parameter sequence of the accumulated mutation coefficient sequence and the mutation coefficient sequence;
s4, optimizing the predicted parameter sequence by using a genetic simulated annealing algorithm to obtain optimal matching parameters;
s5, reconstructing the optimal matching parameters to obtain an optimal variation coefficient sequence;
and S6, reversely solving to obtain a load predicted value, and controlling the working state of each distributed power supply of the micro-grid according to the load predicted value.
Preferably, the data quality improvement in step S1 is represented by an original time sequence as a first-order lagrangian interpolation polynomial:
wherein x is an independent variable, x i-1 、x i Is the independent variable of the adjacent non-abnormal value in the abnormal value interval i, f i ′(x i-1 )、f i ′(x i ) For the first derivative value of the adjacent non-outlier value over outlier interval i, f i "x" is the second derivative value of the adjacent non-outlier on outlier interval i, x i+1 Is an independent variable of a non-outlier over the outlier interval i.
Preferably, the improving the human comfort index in the step S2 includes temperature, relative humidity, wind speed and air quality conditions, and the step S2 specifically includes the following steps:
s21, setting a random oscillation sequence;
s22, introducing influencing factors for improving the human comfort index, and establishing a gray variation coefficient model.
Preferably, the random oscillation sequence in step S21 is as follows:
X (0) =(x (0) (1),x (0) (2),…x (0) (n))
X (0) D=(x (0) (1)d,x (0) (2)d,…x (0) (n)d)
wherein X is (0) For randomly oscillating sequences, sequence X (0) D is random oscillation sequence X (0) Is the smoothed sequence of (2), D is the sequence X (0) Is a first order smoothness operator of (a), (0) (k) d is the smoothed sequence X (0) D is an element, k is a constant, D is an element in D, and T is an amplitude.
Preferably, the gray variation coefficient in the step S22 is:
where CV is the coefficient of variation, σ is the standard deviation, and μ is the arithmetic mean.
Preferably, the step S3 specifically includes the following steps:
s31, acquiring an original sequence of a historical variation coefficient, and calculating an oscillation sequence of the historical variation coefficient;
s32, acquiring an original sequence of the mutation variation coefficient, and calculating an oscillation sequence of the mutation variation coefficient.
Preferably, in the step S31, the original sequence of the historical variation coefficient is:
wherein CV 1 (m) is the historical variation coefficient of the previous m time data, sigma m Standard deviation, mu, of the data at the previous m time m Is the expectation of the previous m-time data;
the smoothed sequence of the historical coefficient of variation oscillation sequence is:
CV 1 (0) D=(CV 1 (0) (1)d,CV 1 (0) (2)d,…CV 1 (0) (n)d)。
wherein CV 1 (0) For historical coefficient of variation sequences, the sequences CV 1 (0) D is oscillation sequence CV 1 (0) Is the smoothed sequence of (2), D is the sequence CV 1 (0) D is the element in D.
Preferably, the original sequence of the mutation coefficient of variation in the step S32 is:
CV 2 (0) =(CV 2 (0) (1),CV 2 (0) (2),…,CV 2 (0) (t))
wherein CV 2 (0) The original sequence of the mutation coefficient of variation is shown, and t is a constant;
the smooth sequence of the mutation coefficient of variation oscillation sequence is as follows:
CV 2 (0) D=(CV 2 (0) (1)d,CV 2 (0) (2)d,…,CV 2 (0) (n)d)
wherein the sequence CV 2 (0) D is oscillation sequence CV 2 (0) Is the smoothed sequence of (2), D is the sequence CV 2 (0) D is the element in D.
Preferably, the step S4 specifically includes the following steps:
s41, randomly generating initial groups according to the predicted parameter sequences of the accumulated mutation coefficient sequence and the mutation coefficient sequence respectively;
s42, evaluating the fitness of individuals in the population;
s43, performing a genetic simulated annealing process: sequentially performing crossing and mutation operations on individuals, and receiving new individuals according to the Metropolis probability to generate next generation new individuals;
s44, judging whether a termination condition is met, executing a step S45 if the termination condition is met, otherwise, returning to the step S42;
s45, outputting the optimal matching parameters.
Compared with the prior art, the invention has the following advantages:
1. the method adopts a method of cubic spline difference value to carry out data quality improvement on the singular value interval, carries out quality improvement on the data set with abnormal values, and reduces the problems of precision deviation and iteration non-convergence caused by data quality by effectively removing the singular values in the load historical data.
2. The invention improves the human comfort index, introduces the index of the air quality condition, is more in line with the use condition of the current micro-grid load, and can effectively reflect the weak change of the initial stage of the load data by adopting the variation coefficient, thereby further improving the accuracy of load prediction.
3. The invention combines the advantages of genetic algorithm and gray model, improves the prediction effect of the historical load sequence with obvious change for short period, can ensure the precision and speed of the load prediction of the micro-grid at the user side, and has excellent practical application value.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a human comfort index model of the present invention;
FIG. 3 is a schematic flow chart of the genetic simulated annealing algorithm of the present invention;
fig. 4 is a graph comparing short-term load prediction results.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples.
As shown in fig. 1, a micro-grid short-term load prediction method includes the following steps:
s1, acquiring load history data, and improving the data quality of a singular value interval by adopting a cubic spline difference value;
s2, establishing a gray variation coefficient model based on amplitude compression, and introducing an improved human comfort index considering the air quality condition as an influence factor in the modeling process;
s3, calculating a predicted parameter sequence of the accumulated mutation coefficient sequence and the mutation coefficient sequence;
s4, optimizing the predicted parameter sequence by using a genetic simulated annealing algorithm to obtain optimal matching parameters;
s5, reconstructing the optimal matching parameters to obtain an optimal variation coefficient sequence;
and S6, reversely solving to obtain a load predicted value, and controlling the working state of each distributed power supply of the micro-grid according to the load predicted value.
In step S1, the embodiment obtains load history data within 100 days of a residential area of a certain micro-grid project in the Shanghai, and then uses a cubic spline difference value to perform the data quality improvement on a singular value interval, specifically, the original time sequence is expressed as a first-order lagrangian interpolation polynomial:
wherein x is an independent variable, x i-1 、x i Is the independent variable of the adjacent non-abnormal value in the abnormal value interval i, f i ′(x i-1 )、f i ′(x i ) For the first derivative value of the adjacent non-outlier value over outlier interval i, f i And (x) is a second derivative value of a non-abnormal value adjacent to the abnormal value interval i, and is obtained after further derivation:
wherein x is i+1 Is an independent variable of a non-outlier over the outlier interval i.
In the step S2 and the step S3, a gray variation coefficient model based on amplitude compression is established, and an improved human comfort index considering the air quality condition is introduced as an influence factor in the modeling process, so as to obtain a predicted parameter sequence of an accumulated variation coefficient sequence and an abrupt variation coefficient sequence.
First, a random oscillation sequence with an amplitude T is set as follows:
X (0) =(x (0) (1),x (0) (2),…x (0) (n))
in the formula, the sequence X (0) D=(x (0) (1)d,x (0) (2)d,…x (0) (n) D) D is the sequence X (0) First order smoothness operator of (a), sequence X (0) D is random oscillation sequence X (0) Is a smooth sequence of (2);
in the method, in the process of the invention,x (0) (k) d is the smoothed sequence X (0) D is an element, k is a constant, D is an element in D, and T is an amplitude.
Then, a gray coefficient of variation model based on amplitude compression is established, and an improved human body comfort index considering the air quality condition is introduced as an influence factor in the modeling process, and fig. 2 shows the improved human body comfort index model including temperature, relative humidity, wind speed and air quality condition.
Wherein, the coefficient of variation formula is:
wherein CV is a coefficient of variation, sigma is a standard deviation, and mu is an arithmetic mean;
finally, a predicted parameter sequence of the accumulated mutation coefficient sequence and the mutation coefficient sequence is obtained:
let the original sequence of the historical coefficient of variation be CV 1 (m) then there are
In CV 1 (m) is the historical variation coefficient of the previous m time data, sigma m Standard deviation, mu, of the data at the previous m time m Is the expectation of the previous m-time data;
the smoothed sequence of the historical coefficient of variation oscillation sequence is:
CV 1 (0) D=(CV 1 (0) (1)d,CV 1 (0) (2)d,…CV 1 (0) (n)d)
in CV 1 (0) For historical coefficient of variation sequences, the sequences CV 1 (0) D is oscillation sequence CV 1 (0) Is the smoothed sequence of (2), D is the sequence CV 1 (0) D is the element in D.
Let the mutation coefficient of variation sequence be CV 2 (0) CV for effectively reflecting short-period fluctuation of equipment 2 (0) The sliding window principle is adopted to input data in a fixed length, the length of the sliding window is selected to be 3 in consideration of the correlation of the time sequence, and then the original sequence of the mutation coefficient of variation is
CV 2 (0) =(CV 2 (0) (1),CV 2 (0) (2),…,CV 2 (0) (t))
In CV 2 (0) The original sequence of the mutation coefficient of variation is shown, and t is a constant;
the smooth sequence of the mutation coefficient of variation oscillation sequence is as follows:
CV 2 (0) D=(CV 2 (0) (1)d,CV 2 (0) (2)d,…,CV 2 (0) (n)d)
in the formula, the sequence CV 2 (0) D is oscillation sequence CV 2 (0) Is the smoothed sequence of (2), D is the sequence CV 2 (0) D is the element in D.
In step S4, optimizing the obtained parameter sequence by using a genetic simulated annealing algorithm to obtain optimal matching parameters, and firstly, randomly generating initial groups by using the obtained prediction parameter sequences of the accumulated variation coefficient sequence and the mutation variation coefficient sequence respectively; secondly, evaluating the fitness of individuals in the population; then, the individuals are crossed and mutated, and new individuals are accepted according to the Metropolis probability to generate next generation new individuals; and finally, judging whether the termination condition is met or not until the optimal matching parameters are output. As shown in fig. 3, the method specifically comprises the following steps:
s41, randomly generating initial groups according to the predicted parameter sequences of the accumulated mutation coefficient sequence and the mutation coefficient sequence respectively;
s42, evaluating the fitness of individuals in the population;
s43, performing a genetic simulated annealing process: sequentially performing crossing and mutation operations on individuals, and receiving new individuals according to the Metropolis probability to generate next generation new individuals;
s44, judging whether a termination condition is met, executing a step S45 if the termination condition is met, otherwise, returning to the step S42;
s45, outputting the optimal matching parameters.
In step S5 and step S6, the optimal variation coefficient sequence is obtained by reconstructing the optimal matching parameters, the load predicted value is obtained by solving in an inverse way, the predicted result is compared with the predicted result and the actual value of the traditional gray model, the comparison effect is shown in figure 4, no matter the electric load peak period or the electric load valley period is used, compared with the traditional gray model, the predicted result obtained by adopting the method is closer to the actual value, the accuracy of the method for short-term load prediction is verified, and the working state of each distributed power supply is controlled by the micro-grid control system according to the short-term load predicted value obtained by the method, including power generation and scheduling control, so that the high-efficiency energy conservation and the optimal operation of the micro-grid are ensured.
Claims (4)
1. A micro-grid short-term load prediction method, comprising the steps of:
s1, acquiring load history data, and improving the data quality of a singular value interval by adopting a cubic spline difference value;
s2, establishing a gray variation coefficient model based on amplitude compression, and introducing an improved human comfort index considering the air quality condition as an influence factor in the modeling process;
s3, calculating a predicted parameter sequence of the accumulated mutation coefficient sequence and the mutation coefficient sequence;
s4, optimizing the predicted parameter sequence by using a genetic simulated annealing algorithm to obtain optimal matching parameters;
s5, reconstructing the optimal matching parameters to obtain an optimal variation coefficient sequence;
s6, reversely solving to obtain a load predicted value, and making a micro-grid power generation and scheduling plan by a micro-grid control system according to the load predicted value;
the improvement of the human body comfort index in the step S2 comprises the following steps of temperature, relative humidity, wind speed and air quality condition, wherein the step S2 specifically comprises the following steps:
s21, setting a random oscillation sequence;
s22, introducing influencing factors for improving the human comfort index, and establishing a gray variation coefficient model;
the random oscillation sequence in the step S21 is as follows:
X (0) =(x (0) (1),x (0) (2),…x (0) (n))
X (0) D=(x (0) (1)d,x (0) (2)d,…x (0) (n)d)
wherein X is (0) For randomly oscillating sequences, sequence X (0) D is random oscillation sequence X (0) Is the smoothed sequence of (2), D is the sequence X (0) Is a first order smoothness operator of (a), (0) (k) d is the smoothed sequence X (0) The element of D, k is a constant, D is the element in D, and T is the amplitude;
the gray variation coefficient in step S22 is as follows:
wherein CV is a coefficient of variation, σ is a standard deviation, and μ is an arithmetic mean;
the step S3 specifically comprises the following steps:
s31, acquiring an original sequence of a historical variation coefficient, and calculating an oscillation sequence of the historical variation coefficient;
s32, acquiring an original sequence of the mutation variation coefficient, and calculating an oscillation sequence of the mutation variation coefficient;
the step S4 specifically includes the following steps:
s41, randomly generating initial groups according to the predicted parameter sequences of the accumulated mutation coefficient sequence and the mutation coefficient sequence respectively;
s42, evaluating the fitness of individuals in the population;
s43, performing a genetic simulated annealing process: sequentially performing crossing and mutation operations on individuals, and receiving new individuals according to the Metropolis probability to generate next generation new individuals;
s44, judging whether a termination condition is met, executing a step S45 if the termination condition is met, otherwise, returning to the step S42;
s45, outputting the optimal matching parameters.
2. The method according to claim 1, wherein the data quality improvement in step S1 is represented by a first-order lagrangian interpolation polynomial:
wherein x is an independent variable, x i-1 、x i Is the independent variable of the adjacent non-abnormal value in the abnormal value interval i, f i ′(x i-1 )、f i ′(x i ) For the first derivative value of the adjacent non-outlier value over outlier interval i, f i "x" is the second derivative value of the adjacent non-outlier on outlier interval i, x i+1 Is an independent variable of a non-outlier over the outlier interval i.
3. The method for predicting short-term load of a micro-grid according to claim 1, wherein the original sequence of the historical variation coefficients in step S31 is:
wherein CV 1 (m) is the historical variation coefficient of the previous m time data, sigma m Standard deviation, mu, of the data at the previous m time m Is the expectation of the previous m-time data;
the smoothed sequence of the historical coefficient of variation oscillation sequence is:
CV 1 (0) D=(CV 1 (0) (1)d,CV 1 (0) (2)d,…CV 1 (0) (n)d)
wherein CV 1 (0) For historical coefficient of variation sequences, the sequences CV 1 (0) D is oscillation sequence CV 1 (0) Is the smoothed sequence of (2), D is the sequence CV 1 (0) D is the element in D.
4. The method for predicting short-term load of a micro-grid according to claim 1, wherein the original sequence of mutation coefficient of variation in step S32 is:
CV 2 (0) =(CV 2 (0) (1),CV 2 (0) (2),…,CV 2 (0) (t))
wherein CV 2 (0) The original sequence of the mutation coefficient of variation is shown, and t is a constant;
the smooth sequence of the mutation coefficient of variation oscillation sequence is as follows:
CV 2 (0) D=(CV 2 (0) (1)d,CV 2 (0) (2)d,…,CV 2 (0) (n)d)
wherein the sequence CV 2 (0) D is oscillation sequence CV 2 (0) Is the smoothed sequence of (2), D is the sequence CV 2 (0) First order of (2)And a smoothness operator, wherein D is an element in D.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910363565.9A CN110119842B (en) | 2019-04-30 | 2019-04-30 | Micro-grid short-term load prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910363565.9A CN110119842B (en) | 2019-04-30 | 2019-04-30 | Micro-grid short-term load prediction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110119842A CN110119842A (en) | 2019-08-13 |
CN110119842B true CN110119842B (en) | 2023-09-26 |
Family
ID=67520338
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910363565.9A Active CN110119842B (en) | 2019-04-30 | 2019-04-30 | Micro-grid short-term load prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110119842B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111092875B (en) * | 2019-12-12 | 2022-05-24 | 南京国电南自电网自动化有限公司 | Transmission and transformation operation and inspection platform Internet of things edge information transmission compression method and system |
CN114580168A (en) * | 2022-03-03 | 2022-06-03 | 山东瑞智飞控科技有限公司 | Method for fusion display of unmanned aerial vehicle monitoring atmospheric pollution data and three-dimensional GIS |
CN114626631A (en) * | 2022-03-29 | 2022-06-14 | 华东交通大学 | Short-time wind speed prediction method based on non-stationary and non-Gaussian smooth interpolation preprocessing technology |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105913175A (en) * | 2016-04-07 | 2016-08-31 | 哈尔滨理工大学 | Intelligent power grid short period load prediction method based on improved nerve network algorithm |
CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学(保定) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
CN107239849A (en) * | 2017-04-17 | 2017-10-10 | 西安电子科技大学 | One kind is based on improved exponential smoothing gray model Methods of electric load forecasting |
CN108876054A (en) * | 2018-07-06 | 2018-11-23 | 国网河南省电力公司郑州供电公司 | Short-Term Load Forecasting Method based on improved adaptive GA-IAGA optimization extreme learning machine |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103259285B (en) * | 2013-05-03 | 2015-04-29 | 国家电网公司 | Method for optimizing short running of electric power system comprising large-scale wind power |
-
2019
- 2019-04-30 CN CN201910363565.9A patent/CN110119842B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学(保定) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
CN105913175A (en) * | 2016-04-07 | 2016-08-31 | 哈尔滨理工大学 | Intelligent power grid short period load prediction method based on improved nerve network algorithm |
CN107239849A (en) * | 2017-04-17 | 2017-10-10 | 西安电子科技大学 | One kind is based on improved exponential smoothing gray model Methods of electric load forecasting |
CN108876054A (en) * | 2018-07-06 | 2018-11-23 | 国网河南省电力公司郑州供电公司 | Short-Term Load Forecasting Method based on improved adaptive GA-IAGA optimization extreme learning machine |
Also Published As
Publication number | Publication date |
---|---|
CN110119842A (en) | 2019-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110119842B (en) | Micro-grid short-term load prediction method | |
CN113112077B (en) | HVAC control system based on multi-step prediction deep reinforcement learning algorithm | |
CN104638644B (en) | Acquiring method for dynamic random optimal power flow of power system for wind-containing power field | |
CN104598985B (en) | Methods of electric load forecasting | |
CN109102155B (en) | Ultra-short-term node marginal electricity price probability prediction method and system | |
CN110212592B (en) | Thermal power generating unit load regulation maximum rate estimation method and system based on piecewise linear expression | |
CN111783947A (en) | Energy consumption prediction method based on LSTM neural network | |
CN112418495A (en) | Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network | |
CN115907176A (en) | Power transmission side carbon emission prediction method based on federal learning | |
CN109146131A (en) | A kind of wind-power electricity generation prediction technique a few days ago | |
CN116596139A (en) | Short-term load prediction method and system based on Elman neural network | |
CN113344273B (en) | Regional power distribution network peak-valley difference adjustment optimization method and system based on building energy | |
CN110874802A (en) | Electricity consumption prediction method based on ARMA and SVM model combination | |
CN114266187A (en) | Office building electricity utilization network optimization method and system | |
CN108108837A (en) | A kind of area new energy power supply structure optimization Forecasting Methodology and system | |
CN112348236A (en) | Abnormal daily load demand prediction system and method for intelligent power consumption monitoring terminal | |
CN117277346A (en) | Energy storage frequency modulation method, device and equipment based on multi-agent system | |
Molina et al. | Approach to multivariable predictive control applications in residential HVAC direct load control | |
CN116227883A (en) | Intelligent household energy management system prediction decision-making integrated scheduling method based on deep reinforcement learning | |
CN115967092A (en) | Data-driven non-parameter probability optimal power flow prediction-analysis integrated method for new energy power system | |
CN113298308B (en) | Parameter self-adaptive power consumption prediction method and system | |
CN111079996B (en) | Virtual seat system based on BP neural network power load prediction | |
CN112327046B (en) | Non-invasive load monitoring method based on fuzzy clustering and support vector regression | |
Foster et al. | Short-term load forecasting with high levels of distributed renewable generation | |
Wang et al. | A novel approach to forecast electricity consumption based on fractional grey model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |