CN111310121A - New energy output probability prediction method and system - Google Patents
New energy output probability prediction method and system Download PDFInfo
- Publication number
- CN111310121A CN111310121A CN201911111802.9A CN201911111802A CN111310121A CN 111310121 A CN111310121 A CN 111310121A CN 201911111802 A CN201911111802 A CN 201911111802A CN 111310121 A CN111310121 A CN 111310121A
- Authority
- CN
- China
- Prior art keywords
- historical
- power
- new energy
- predicted
- powers
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention provides a new energy output probability prediction method and system, which comprises the steps of obtaining a new energy power prediction value based on a time step length, and determining an output state range by combining a preset state level; mining historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the new energy output predicted value; and calculating the probability that the new energy output actual power falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers. The probability prediction result obtained by the method is obviously improved in self-adaptability, the discrimination of different uncertainties is improved, the width of a probability interval is reduced by more than 10% compared with the current probability prediction taking errors as objects, and the presentation form of the probability prediction result is more suitable for scheduling application.
Description
Technical Field
The invention belongs to the technical field of new energy, and particularly relates to a new energy output probability prediction method and system.
Background
The new energy output probability prediction has an important effect on improving the consumption of new energy. However, the current new energy output probability prediction is mainly based on statistical analysis of historical prediction errors, and has the following limitations: 1) in order to improve the accuracy of the probability prediction model, an error characteristic identification method is adopted, the width of an error interval is reduced through conditional probability, the model is complex, and the engineering application difficulty is increased; 2) the probability prediction model has poor self-adaptive capacity, and after the power prediction model is adjusted, the probability prediction model needs to be modeled again in a delayed manner, so that the workload is increased; 3) the conditional resolution of the current probabilistic prediction result is not high due to the restriction of technical characteristics.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a new energy output probability prediction method, and the improvement is that the method comprises the following steps:
acquiring a new energy power predicted value based on the time step length, and determining an output state range by combining a preset state level;
mining historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the new energy output predicted value;
calculating the probability that the actual power of the new energy output falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
The first preferred technical solution provided by the present invention is improved in that the mining of historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the predicted value of new energy output includes:
acquiring historical actual power data and historical predicted power data based on time and correlating the historical actual power data and the historical predicted power data to obtain sample data;
and obtaining a plurality of historical predicted powers with values in the output state range based on the output state range matching sample data, and taking the historical predicted powers as a plurality of historical predicted powers corresponding to the new energy output predicted value.
The second preferred technical solution provided by the present invention is improved in that the calculating of the probability that the actual power of the new energy output falls into each power level interval includes:
respectively counting the number of historical actual power values associated with the historical predicted power in each power level interval in a plurality of historical predicted powers corresponding to the new energy output predicted value;
and calculating the probability that the actual power of the new energy output falls into each power level interval according to the number of the historical actual powers of the values in each power level interval.
The improvement of the third preferred technical scheme provided by the invention is that the calculation formula of the probability that the actual output power of the new energy falls into the power level interval is as follows:
px＝kx/m
wherein p isxRepresenting the probability that the actual power of the new energy output falls into the x-th power level interval, kxThe number of the historical actual powers in the x-th power level interval is shown, and m represents the total number of the historical actual powers in all the power level intervals.
In a fourth preferred aspect of the present invention, the improvement is that the calculation formula of the range of the xth power level interval is as follows:
[x·ΔT,x·ΔT+ΔT]
where Δ T represents the width of the power level interval.
In a fifth preferred technical solution provided by the present invention, the improvement is that the obtaining and associating historical actual power data and historical predicted power data based on time to obtain sample data includes:
acquiring historical actual power and historical predicted power of the new energy based on time;
normalizing the historical actual power and the historical predicted power based on the starting capacity;
and according to the time corresponding to the historical actual power and the historical predicted power, correlating the historical actual power with the historical predicted power to form sample data.
The improvement of the sixth preferred technical solution provided by the present invention is that the obtaining of the predicted value of the new energy power based on the time step and the determining of the output state range by combining the preset state level include:
and acquiring a new energy power predicted value based on the time step, taking the difference value of the new energy output predicted value and the preset state level as the lower limit of the output range, and taking the sum of the new energy output predicted value and the preset state level as the upper limit of the output range.
The improvement of the seventh preferred technical solution provided by the present invention is that after calculating the probability that the actual power of the new energy output falls into each power level interval, the method further includes:
obtaining the actual power distribution range of the new energy output according to the probability that the actual power of the new energy output falls into each power level interval and the preset risk level;
and making a new energy power generation operation plan according to the actual power distribution range of the new energy output.
Based on the same invention concept, the invention also provides a new energy output probability prediction system, which comprises: the device comprises a range determining module, a historical prediction power module and a probability prediction module;
the range determining module is used for acquiring a new energy power predicted value based on the time step length and determining an output state range by combining a preset state level;
the historical prediction power module is used for mining historical similar output state data based on the output state range to obtain a plurality of historical prediction powers corresponding to the new energy output prediction value;
the probability prediction module is used for calculating the probability that the actual output power of the new energy falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
In an eighth preferred aspect of the present invention, the improvement wherein the history prediction power module includes: a sample data unit and a historical predicted power unit;
the sample data unit is used for acquiring historical actual power data and historical predicted power data based on time and correlating the historical actual power data and the historical predicted power data to obtain sample data;
and the historical prediction power unit is used for obtaining a plurality of historical prediction powers with values in the output state range based on the output state range matching sample data, and the historical prediction powers are used as a plurality of historical prediction powers corresponding to the new energy output prediction value.
In a ninth preferred aspect of the present invention, the improvement wherein the probability prediction module comprises: a number statistical unit and a probability calculation unit;
the number counting unit is used for respectively counting the number of historical actual power values associated with the historical predicted power in each power level interval in a plurality of historical predicted powers corresponding to the new energy output predicted value;
and the probability calculating unit is used for calculating the probability that the actual power of the new energy output falls into each power level interval according to the number of the historical actual powers of the values in each power level interval.
Compared with the closest prior art, the invention has the following beneficial effects:
the invention provides a new energy output probability prediction method and system, which comprises the steps of obtaining a new energy power prediction value based on a time step length, and determining an output state range by combining a preset state level; mining historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the new energy output predicted value; and calculating the probability that the new energy output actual power falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers. The probability prediction result obtained by the method is obviously improved in self-adaptability, the discrimination of different uncertainties is improved, the width of a probability interval is reduced by more than 10% compared with the current probability prediction taking errors as objects, and the presentation form of the probability prediction result is more suitable for scheduling application.
Drawings
Fig. 1 is a schematic flow chart of a new energy output probability prediction method provided by the present invention;
FIG. 2 is a schematic diagram of a basic structure of a new energy output probability prediction system according to the present invention;
fig. 3 is a detailed structural diagram of a new energy output probability prediction system provided by the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Aiming at the problems in the prior art, the method abandons the idea that the traditional probability prediction method takes prediction errors as a research object, adopts a big data mining concept, directly faces to scene analysis of prediction results, obtains uncertainty intervals of each moment, improves the adaptivity of the probability prediction results, improves the uncertainty resolution capability of the prediction results aiming at different characteristic powers, can effectively reduce the modeling workload, and has high practicability.
Example 1:
the flow diagram of the new energy output probability prediction method provided by the invention is shown in fig. 1, and the method comprises the following steps:
step 1: acquiring a new energy power predicted value based on the time step length, and determining an output state range by combining a preset state level;
step 2: mining historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the new energy output predicted value;
and step 3: calculating the probability that the actual power of the new energy output falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
Specifically, a complete technical route of the new energy output probability prediction method is provided, and the complete technical route comprises data processing, output state determination, similar output state mining, output probability interval determination and the like.
1. Data processing
The data processing is mainly to construct calculation samples for subsequent probability interval determination. The data to be processed comprises historical actual power data and historical predicted power data, and the data length is at least 1 year. The method comprises the following processing steps:
1-1) sorting historical actual power data and historical predicted power data according to time sequence;
1-2) normalizing the historical actual power T and the historical predicted power F by the starting capacity C:
in the formula, i is a subscript, n is the total number of history samples, subscript r represents an actual value, and subscript f represents a predicted value.
1-3) according to time, the historical actual power Pr,iAnd historical predicted power Pf,iCorrelating, forming a sample { (P)f,i,Pr,i)}。
2. Force state determination
And determining the output state according to the state level delta P. The specific method comprises the following steps:
2-1) determining a proper state level delta P, wherein the smaller the state level, the better the state level, but the smaller the state level, the influence on the matching of state samples can be caused, and the state sample is generally 0.01;
2-2) predicting the power prediction result P of the target moment t by combining the probability according to the state level delta Pf,tDetermining the output state range: [ P ]f,t-ΔP,Pf,t+ΔP]。
3. Similar force state mining
Matching the similar state of the historical predicted power according to the output state range:
{Pf,j}＝{Pf,t-ΔP≤Pf,i≤Pf,t+ΔP},j＝1,…,m
in the formula, Pf,jPredicting the output state for the matched historical similarity, namely predicting the output state with the new energyf,tThe historical predicted power of the match, m being the number thereof, satisfies { P }f,j}∈{Pf,i}。
4. Force probability interval determination
Due to historical real power Pr,iAnd historical predicted power Pf,iIs associated according to Pf,jCan obtain { (P)f,j,Pr,j)}。
With { Pr,jDetermining an output probability interval for the object, wherein the specific method comprises the following steps:
4-1) selecting a proper interval width delta T according to application requirements, wherein the interval width delta T is generally 0.05;
4-2) determining the number of samples k within the intervalx：
kx＝#{x·ΔT≤Pr,j＜x·ΔT+ΔT},x＝0,…,1/ΔT
Wherein, # {. is a counting function used for counting the number of samples; and x is a section number.
4-3) calculating the occurrence probability:
px＝kx/m
the final probabilistic prediction result is then: { [ x. DELTA.T, x. DELTA.T + DELTA.T],px|Pf,t}，x＝0,…,1/ΔT。
5. Risk scheduling application
Aiming at the wind power prediction result of 72 hours in the future, a power prediction result value P is provided every 15 minutesf,tAccording to the power prediction result value, the corresponding actual power falling into different power level intervals [ x.delta T, x.delta T + delta T ] can be obtained by adopting the method of 5.1-5.4]Probability p ofxOn condition that the risk level α is determined, it should be satisfied that:
wherein x is1,x2∈[0,…,1/ΔT]. The corresponding actual power distribution range can then be obtained:
[x1·ΔT,x2·ΔT]
at the moment of load peak, the wind power operation plan is considered according to the lower limit of the possible occurrence interval of the actual power, namely x1Δ T; at the time of load valley, the wind power operation plan is considered according to the upper limit of the possible occurrence interval of the actual power, namely x2Δ T. Therefore, on the premise of controllable risk, the wind power consumption level is improved.
Example 2:
based on the same invention concept, the invention also provides a new energy output probability prediction system, and the principle of solving the technical problems of the devices is similar to the new energy output probability prediction method, so repeated parts are not repeated.
The basic structure of the system is shown in fig. 2, and comprises: the device comprises a range determining module, a historical prediction power module and a probability prediction module;
the range determining module is used for obtaining a new energy power predicted value based on the time step length and determining an output state range by combining a preset state level;
the historical prediction power module is used for mining historical similar output state data based on the output state range to obtain a plurality of historical prediction powers corresponding to the new energy output prediction value;
the probability prediction module is used for calculating the probability that the actual power of the new energy output falls into each power level interval based on the historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
The detailed structure of the new energy output probability prediction system is shown in fig. 3.
Wherein the historical predicted power module comprises: a sample data unit and a historical predicted power unit;
the sample data unit is used for acquiring historical actual power data and historical predicted power data based on time and correlating the historical actual power data and the historical predicted power data to obtain sample data;
and the historical prediction power unit is used for matching the sample data based on the output state range to obtain a plurality of historical prediction powers with values in the output state range, and the historical prediction powers are used as a plurality of historical prediction powers corresponding to the new energy output prediction value.
Wherein the probability prediction module comprises: a number statistical unit and a probability calculation unit;
the number counting unit is used for respectively counting the number of historical actual power values associated with the historical predicted power in each power level interval in a plurality of historical predicted powers corresponding to the new energy output predicted value;
and the probability calculation unit is used for calculating the probability that the actual power of the new energy output falls into each power level interval according to the number of the historical actual powers of the values in each power level interval.
The sample data unit comprises a historical data acquisition subunit, a normalization subunit and a sample data subunit;
the historical data acquisition subunit is used for acquiring historical actual power and historical predicted power of the new energy source based on time;
the normalization subunit is used for normalizing the historical actual power and the historical predicted power based on the starting capacity;
and the sample data subunit is used for associating the historical actual power with the historical predicted power according to the time corresponding to the historical actual power and the historical predicted power to form sample data.
Wherein, the new energy output probability prediction system further comprises: a plan making module; the planning module comprises: a distribution range unit and a plan making unit;
the distribution range unit is used for obtaining the actual power distribution range of the new energy output according to the probability that the actual power of the new energy output falls into each power level interval and the preset risk level;
and the plan making unit is used for making a new energy power generation operation plan according to the actual power distribution range of the new energy output.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present application and not for limiting the scope of protection thereof, and although the present application is described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present application, they can make various changes, modifications or equivalents to the specific embodiments of the application, but these changes, modifications or equivalents are all within the scope of protection of the claims to be filed.
Claims (11)
1. A new energy output probability prediction method is characterized by comprising the following steps:
acquiring a new energy power predicted value based on the time step length, and determining an output state range by combining a preset state level;
mining historical similar output state data based on the output state range to obtain a plurality of historical predicted powers corresponding to the new energy output predicted value;
calculating the probability that the actual power of the new energy output falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
2. The method of claim 1, wherein said mining historical similar output state data based on said range of output states to obtain a plurality of historical predicted powers corresponding to said predicted new energy output value comprises:
acquiring historical actual power data and historical predicted power data based on time and correlating the historical actual power data and the historical predicted power data to obtain sample data;
and obtaining a plurality of historical predicted powers with values in the output state range based on the output state range matching sample data, and taking the historical predicted powers as a plurality of historical predicted powers corresponding to the new energy output predicted value.
3. The method of claim 2, wherein calculating the probability that the new energy contribution actual power falls within each power level interval comprises:
respectively counting the number of historical actual power values associated with the historical predicted power in each power level interval in a plurality of historical predicted powers corresponding to the new energy output predicted value;
and calculating the probability that the actual power of the new energy output falls into each power level interval according to the number of the historical actual powers of the values in each power level interval.
4. The method of claim 3, wherein the probability that the new energy contribution actual power falls within the power level interval is calculated as follows:
px＝kx/m
wherein p isxRepresenting the probability that the actual power of the new energy output falls into the x-th power level interval, kxThe number of the historical actual powers in the x-th power level interval is shown, and m represents the total number of the historical actual powers in all the power level intervals.
5. The method of claim 4, wherein the range of the xth power level interval is calculated as follows:
[x·ΔT,x·ΔT+ΔT]
where Δ T represents the width of the power level interval.
6. The method of claim 2, wherein obtaining and correlating historical actual power data and historical predicted power data based on time to obtain sample data comprises:
acquiring historical actual power and historical predicted power of the new energy based on time;
normalizing the historical actual power and the historical predicted power based on the starting capacity;
and according to the time corresponding to the historical actual power and the historical predicted power, correlating the historical actual power with the historical predicted power to form sample data.
7. The method of claim 1, wherein obtaining the predicted new energy power value based on the time step and determining the output state range in combination with the predetermined state level comprises:
and acquiring a new energy power predicted value based on the time step, taking the difference value of the new energy output predicted value and the preset state level as the lower limit of the output range, and taking the sum of the new energy output predicted value and the preset state level as the upper limit of the output range.
8. The method of claim 1, wherein after calculating the probability that the new energy contribution actual power falls within each power level interval, further comprising:
obtaining the actual power distribution range of the new energy output according to the probability that the actual power of the new energy output falls into each power level interval and the preset risk level;
and making a new energy power generation operation plan according to the actual power distribution range of the new energy output.
9. A new energy output probability prediction system is characterized by comprising: the device comprises a range determining module, a historical prediction power module and a probability prediction module;
the range determining module is used for acquiring a new energy power predicted value based on the time step length and determining an output state range by combining a preset state level;
the historical prediction power module is used for mining historical similar output state data based on the output state range to obtain a plurality of historical prediction powers corresponding to the new energy output prediction value;
the probability prediction module is used for calculating the probability that the actual output power of the new energy falls into each power level interval based on the plurality of historical predicted powers and the correlation between the historical predicted powers and the historical actual powers;
wherein, each power level interval is divided according to the application requirement.
10. The system of claim 9, wherein the historical predicted power module comprises: a sample data unit and a historical predicted power unit;
the sample data unit is used for acquiring historical actual power data and historical predicted power data based on time and correlating the historical actual power data and the historical predicted power data to obtain sample data;
and the historical prediction power unit is used for obtaining a plurality of historical prediction powers with values in the output state range based on the output state range matching sample data, and the historical prediction powers are used as a plurality of historical prediction powers corresponding to the new energy output prediction value.
11. The system of claim 10, wherein the probability prediction module comprises: a number statistical unit and a probability calculation unit;
the number counting unit is used for respectively counting the number of historical actual power values associated with the historical predicted power in each power level interval in a plurality of historical predicted powers corresponding to the new energy output predicted value;
and the probability calculating unit is used for calculating the probability that the actual power of the new energy output falls into each power level interval according to the number of the historical actual powers of the values in each power level interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911111802.9A CN111310121A (en) | 2019-11-14 | 2019-11-14 | New energy output probability prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911111802.9A CN111310121A (en) | 2019-11-14 | 2019-11-14 | New energy output probability prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111310121A true CN111310121A (en) | 2020-06-19 |
Family
ID=71144792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911111802.9A Pending CN111310121A (en) | 2019-11-14 | 2019-11-14 | New energy output probability prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310121A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112202188A (en) * | 2020-11-09 | 2021-01-08 | 国网湖南省电力有限公司 | New energy automatic power generation control method and system considering output uncertainty |
| CN112651560A (en) * | 2020-12-28 | 2021-04-13 | 华润电力技术研究院有限公司 | Ultra-short-term wind power prediction method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015192613A1 (en) * | 2014-06-20 | 2015-12-23 | 国家电网公司 | Power system control method and device |
| CN107067099A (en) * | 2017-01-25 | 2017-08-18 | 清华大学 | Wind power probability forecasting method and device |
| CN108133279A (en) * | 2017-08-29 | 2018-06-08 | 甘肃省电力公司风电技术中心 | Wind power probability forecasting method, storage medium and equipment |
| CN108985965A (en) * | 2018-06-22 | 2018-12-11 | 华北电力大学 | A kind of photovoltaic power interval prediction method of combination neural network and parameter Estimation |
-
2019
- 2019-11-14 CN CN201911111802.9A patent/CN111310121A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015192613A1 (en) * | 2014-06-20 | 2015-12-23 | 国家电网公司 | Power system control method and device |
| CN107067099A (en) * | 2017-01-25 | 2017-08-18 | 清华大学 | Wind power probability forecasting method and device |
| CN108133279A (en) * | 2017-08-29 | 2018-06-08 | 甘肃省电力公司风电技术中心 | Wind power probability forecasting method, storage medium and equipment |
| CN108985965A (en) * | 2018-06-22 | 2018-12-11 | 华北电力大学 | A kind of photovoltaic power interval prediction method of combination neural network and parameter Estimation |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112202188A (en) * | 2020-11-09 | 2021-01-08 | 国网湖南省电力有限公司 | New energy automatic power generation control method and system considering output uncertainty |
| CN112202188B (en) * | 2020-11-09 | 2022-10-28 | 国网湖南省电力有限公司 | New energy automatic power generation control method and system considering output uncertainty |
| CN112651560A (en) * | 2020-12-28 | 2021-04-13 | 华润电力技术研究院有限公司 | Ultra-short-term wind power prediction method, device and equipment |
| CN112651560B (en) * | 2020-12-28 | 2023-04-25 | 华润电力技术研究院有限公司 | Ultra-short-term wind power prediction method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112686464A (en) | Short-term wind power prediction method and device | |
| CN110555785B (en) | Monthly plan safety and stability checking method and system | |
| CN111754024B (en) | Prediction method and system of power industry time series based on regression analysis | |
| CN111091196B (en) | Passenger flow data determination method and device, computer equipment and storage medium | |
| CN107067099B (en) | Wind power probability prediction method and device | |
| CN108074015B (en) | Ultra-short-term prediction method and system for wind power | |
| CN107909212B (en) | Climbing event prediction method based on mesoscale wind power development process serialization | |
| CN111310121A (en) | New energy output probability prediction method and system | |
| CN110110339B (en) | Japanese hydrologic forecast error correction method and system | |
| CN108334988A (en) | A kind of short-term Load Forecasting based on SVM | |
| CN114819374A (en) | Regional new energy ultra-short term power prediction method and system | |
| CN105956708A (en) | Grey correlation time sequence based short-term wind speed forecasting method | |
| CN116579884B (en) | Power user behavior analysis method and system | |
| CN111753461A (en) | Tidal water level correction method, target residual water level acquisition method, device and equipment | |
| Dos Santos et al. | Preprocessing in fuzzy time series to improve the forecasting accuracy | |
| CN115908051A (en) | Method for determining energy storage capacity of power system | |
| WO2022222230A1 (en) | Indicator prediction method and apparatus based on machine learning, and device and storage medium | |
| CN115392567A (en) | Power load prediction method, electronic equipment, device and readable storage medium | |
| CN112700050A (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
| Yang et al. | PSC ship-selecting model based on improved particle swarm optimization and support vector machine algorithm | |
| CN111222688A (en) | Daily load prediction method for commercial building | |
| CN110543724A (en) | Satellite structure performance prediction method for overall design | |
| CN108363789B (en) | Short-term missing repairing method and device for electricity consumption meter data of industrial and commercial users | |
| CN111382895A (en) | Seawater desalination load prediction method and system | |
| CN104021045A (en) | CPU load multi-step prediction method based on mode fusion |
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 |