CN110598947A - Load prediction method based on improved cuckoo-neural network algorithm - Google Patents

Load prediction method based on improved cuckoo-neural network algorithm Download PDF

Info

Publication number
CN110598947A
CN110598947A CN201910890297.6A CN201910890297A CN110598947A CN 110598947 A CN110598947 A CN 110598947A CN 201910890297 A CN201910890297 A CN 201910890297A CN 110598947 A CN110598947 A CN 110598947A
Authority
CN
China
Prior art keywords
load
neural network
algorithm
day
cuckoo
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
Application number
CN201910890297.6A
Other languages
Chinese (zh)
Inventor
康丽
金锋
刘国中
胡必武
黄沃杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongguan University of Technology
Original Assignee
Dongguan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dongguan University of Technology filed Critical Dongguan University of Technology
Priority to CN201910890297.6A priority Critical patent/CN110598947A/en
Publication of CN110598947A publication Critical patent/CN110598947A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • 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

Abstract

The invention discloses a load prediction method based on an improved cuckoo-neural network algorithm, which comprises the following steps: calculating the maximum influence factor: collecting local meteorological data and historical load power data recorded by a system by using a monitoring system arranged on a load side, and finding out the type of influence factor with the maximum load influence degree by using an average influence value algorithm (MIV); selecting similar days: selecting a similar day according to the maximum influence factor calculated in the step one; the invention has the beneficial effects that: finding the first n environmental factors with the largest influence on the load by adopting an average influence value algorithm (MIV), selecting a similar day by combining the optimal similarity, finally improving the traditional cuckoo algorithm, applying the improved algorithm to a BP (back propagation) neural network, and predicting the load; the improved cuckoo algorithm can avoid the algorithm from falling into a local optimal solution and has stronger global search capability.

Description

Load prediction method based on improved cuckoo-neural network algorithm
Technical Field
The invention belongs to the technical field of power systems and automation thereof, and particularly relates to a load prediction method based on an improved cuckoo-neural network algorithm.
Background
With the development of the world economy and the progress of the power electronic technology, the variety of loads is continuously increased, the power of the loads is continuously increased, the size of some loads is complicated due to required parameters, the physical process of the loads is difficult to describe through expressions, and at this time, the load prediction is carried out through intelligent algorithms, and the load prediction is scientific prediction of future loads based on the principles of comprehensibility, possibility, controllability and systematicness. Load prediction plays an important role in many aspects of the power system. The medium and long-term load prediction not only provides basic data for planning a power supply and a power grid, but also is a precondition for making an annual overhaul plan, determining an operation mode and the like. The short-term load prediction is of great significance to optimal combination of the units, arrangement of a shutdown plan and a power generation plan, real-time safety analysis and the like. The higher the load prediction precision is, the higher the load prediction.
At present, a great deal of research work is carried out on the load prediction theory and the load prediction method by a plurality of expert scholars at home and abroad, and great progress is made. The commonly used prediction methods: kalman filtering algorithm, linear trend extrapolation, and intelligent algorithm, the intelligent algorithm comprising: radial Basis Function (RBF) neural network algorithms, Elman algorithms, Support Vector Machine (SVM) algorithms, and the like. The prediction methods have certain defects more or less, such as nonlinearity and randomness of load are not considered by a Kalman filtering algorithm and a linear trend extrapolation method, while the BP neural network has the defects of easy falling into local optimum and poor universal capability on future samples, and the GA algorithm has the defects of complex coding and slow search speed, wherein the neural network algorithm prediction is one of the most intelligent algorithms used at present, but the BP neural network prediction method has slow convergence speed and is easy to fall into local extremum.
Disclosure of Invention
The invention aims to provide a load prediction method based on an improved cuckoo-neural network algorithm, so as to solve the problems that the existing prediction methods proposed in the background technology have certain defects more or less, such as the nonlinearity and randomness of the load are not considered by a Kalman filtering algorithm and a linear trend extrapolation method, a BP neural network has the defects of easiness in falling into local optimization and poor flooding capability on future samples, and a GA algorithm has the defects of complex coding and slow search speed, wherein the neural network algorithm prediction is one of the most intelligent algorithms used at present, but the BP neural network prediction method has a slow convergence speed and is easy to fall into a local extremum.
The load prediction method based on the improved cuckoo-neural network algorithm is based on the basic principle that various types of environmental factors influencing the load size are considered, historical output data and historical environmental data recorded by a monitoring system arranged on a load side are collected, firstly, the average influence value algorithm (MIV) is adopted to find the former n environmental factors influencing the load most, the optimal similarity is combined to select the similar days, finally, the traditional cuckoo algorithm is improved, the improved algorithm is applied to a BP neural network, and the load is predicted.
In order to achieve the purpose, the invention provides the following technical scheme: a load prediction method based on an improved cuckoo-neural network algorithm comprises the following steps:
the method comprises the following steps: calculating the maximum influence factor: collecting local meteorological data and historical load power data recorded by a system by using a monitoring system arranged on a load side, and finding out the type of influence factor with the maximum load influence degree by using an average influence value algorithm (MIV);
step two: selecting similar days: selecting a similar day according to the maximum influence factor calculated in the step one;
step three: improvement of cuckoo algorithm: weight, threshold sum of initializing neural networkUpdating the weight and the threshold of the neural network by using a cuckoo algorithm according to other parameter values, and searching for the optimal neural network parameter; the conventional cuckoo algorithm has the defect of slow convergence speed, but for abandoning the probability rho, in the initial stage of iteration, in order to increase the number of bird nest positions which are optimal in the initial stage, the rho needs to be kept large, and in the later stage of iteration, in order to accelerate the convergence of the algorithm, the rho needs to be a small value, and for the step factor, the rho has a small valueTo avoid trapping in locally optimal solutions early in the iteration, soA larger value is required, and a smaller value is required in order to enhance the capability of locally searching for the optimal solution in the later iteration period; so as to be directed to the step-size factor in the cuckoo algorithmThe drop probability ρ is improved according to the following equation:
in the formula:represents the maximum step size;represents a minimum step size; t is tmaxRepresenting the maximum number of iterations; t is tminRepresenting a minimum number of iterations;
in the formula: rhoa maxRepresenting a maximum probability of discovery; rhoa minRepresenting a minimum probability of discovery; t is tmaxRepresenting the maximum number of iterations; t is tminTo representThe minimum number of iterations;
the process of updating the weight and the threshold of the neural network by the improved cuckoo algorithm is as follows:
1) initializing the population and other related variables;
2) updating the position of the bird nest in a Levy flying manner, comparing the position with the fitness of the previous generation of bird nest, updating and replacing the poor bird nest to obtain a new bird nest with higher fitness;
in the formula: x is the number oft+1And xtThe positions of the t-th and t + 1-th generation bird nests respectively, Levy (beta) is a Levy random path,is the t generation step length factor, as shown in formula (1);
3) according to a certain probability rhoa(t) abandoning part of bird nest positions and randomly changing the bird nest positions, calculating the updated bird nest fitness, obtaining the bird nest position with higher fitness through comparison and update, wherein the probability is shown as a formula (2), and if the termination condition of the algorithm is met, outputting the bird nest position as a solution of the problem; otherwise, returning to 3) and continuing iteration;
step four: training a load prediction model: processing data of similar days, then putting main influence factors as input and historical load as output into a BP neural network based on an improved cuckoo algorithm for training;
step five: and (3) load prediction: and C, processing the data of the day to be predicted, putting the meteorological data into the prediction model obtained in the step four to predict the load of the day to be predicted, and finally processing the output value of the model to obtain the predicted value of the load of the day to be predicted.
In a preferred embodiment of the present invention, in the first step, the data of the local meteorological data and the historical load power recorded by the system are collected, and the data of the day to be predicted and the data of the day of 7:00-17:00 in two months are collected with every 30min as a sample.
As a preferable technical solution of the present invention, in the first step, the meteorological data includes cloud cover, temperature, humidity, wind speed, illumination, and precipitation.
As a preferred technical solution of the present invention, in the fourth step, the data of the similar day is normalized.
As a preferable technical solution of the present invention, in the fifth step, the data of the day to be predicted is normalized, and the normalized meteorological data is put into the prediction model obtained in the fourth step to predict the load of the day to be predicted.
As a preferable technical solution of the present invention, in the fifth step, the output value of the model is finally subjected to inverse normalization processing.
Compared with the prior art, the invention has the beneficial effects that:
finding the first n environmental factors with the largest influence on the load by adopting an average influence value algorithm (MIV), selecting a similar day by combining the optimal similarity, finally improving the traditional cuckoo algorithm, applying the improved algorithm to a BP (back propagation) neural network, and predicting the load; the improved cuckoo algorithm can avoid the algorithm from falling into a local optimal solution and has stronger global search capability.
Drawings
Fig. 1 is a flowchart of the load prediction method based on the improved cuckoo-neural network algorithm of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: a load prediction method based on an improved cuckoo-neural network algorithm comprises the following steps:
the method comprises the following steps: calculating the maximum influence factor: collecting local meteorological data and historical load power data recorded by a system by using a monitoring system arranged on a load side, taking every 30min as a sample, collecting data of a day to be predicted and data of 7:00-17:00 every day in two months, wherein the meteorological data comprises cloud cover, temperature, humidity, wind speed, illumination and precipitation, and finding out the type of influence factor with the largest influence degree on the load by using an average influence value algorithm (MIV);
step two: selecting similar days: selecting a similar day according to the maximum influence factor calculated in the step one;
step three: improvement of cuckoo algorithm: initializing a weight value, a threshold value and other parameter values of the neural network, updating the weight value and the threshold value of the neural network by using a cuckoo algorithm, and searching for an optimal neural network parameter; the conventional cuckoo algorithm has the defect of slow convergence speed, but for abandoning the probability rho, in the initial stage of iteration, in order to increase the number of bird nest positions which are optimal in the initial stage, the rho needs to be kept large, and in the later stage of iteration, in order to accelerate the convergence of the algorithm, the rho needs to be a small value, and for the step factor, the rho has a small valueTo avoid trapping in locally optimal solutions early in the iteration, soA larger value is required, and a smaller value is required in order to enhance the capability of locally searching for the optimal solution in the later iteration period; so as to be directed to the step-size factor in the cuckoo algorithmThe drop probability ρ is improved according to the following equation:
in the formula:represents the maximum step size;represents a minimum step size; t is tmaxRepresenting the maximum number of iterations; t is tminRepresenting a minimum number of iterations;
in the formula: rhoa maxRepresenting a maximum probability of discovery; rhoa minRepresenting a minimum probability of discovery; t is tmaxRepresenting the maximum number of iterations; t is tminRepresenting a minimum number of iterations;
the process of updating the weight and the threshold of the neural network by the improved cuckoo algorithm is as follows:
1) initializing the population and other related variables;
2) updating the position of the bird nest in a Levy flying manner, comparing the position with the fitness of the previous generation of bird nest, updating and replacing the poor bird nest to obtain a new bird nest with higher fitness;
in the formula: x is the number oft+1And xtThe positions of the t-th and t + 1-th generation bird nests respectively, Levy (beta) is a Levy random path,is the t generation step length factor, as shown in formula (1);
3) according to a certain probability rhoa(t) abandoning part of bird nest positions and randomly changing the bird nest positions, calculating the updated bird nest fitness, obtaining the bird nest position with higher fitness through comparison and update, wherein the probability is shown as a formula (2), and if the termination condition of the algorithm is met, outputting the bird nest positionAs a solution to the problem; otherwise, returning to 3) and continuing iteration;
step four: training a load prediction model: normalizing the data of similar days, then putting the main influence factors as input and the historical load as output into a BP neural network based on an improved cuckoo algorithm for training;
step five: and (3) load prediction: firstly, carrying out normalization processing on data of a day to be predicted, putting the normalized meteorological data into the prediction model obtained in the fourth step to predict the load of the day to be predicted, and finally carrying out reverse normalization processing on the output value of the model to obtain a load prediction value of the day to be predicted; the formula for denormalization is as follows: x ═ xmax-y.(xmax-xmin)。
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (6)

1. A load prediction method based on an improved cuckoo-neural network algorithm is characterized by comprising the following steps:
the method comprises the following steps: calculating the maximum influence factor: collecting local meteorological data and historical load power data recorded by a system by using a monitoring system arranged on a load side, and finding out the type of influence factor with the maximum load influence degree by using an average influence value algorithm (MIV);
step two: selecting similar days: selecting a similar day according to the maximum influence factor calculated in the step one;
step three: improvement of cuckoo algorithm: initializing a weight value, a threshold value and other parameter values of the neural network, updating the weight value and the threshold value of the neural network by using a cuckoo algorithm, and searching for an optimal neural network parameter;
step four: training a load prediction model: processing data of similar days, then putting main influence factors as input and historical load as output into a BP neural network based on an improved cuckoo algorithm for training;
step five: and (3) load prediction: and C, processing the data of the day to be predicted, putting the meteorological data into the prediction model obtained in the step four to predict the load of the day to be predicted, and finally processing the output value of the model to obtain the predicted value of the load of the day to be predicted.
2. The method for predicting the load based on the improved cuckoo-neural network algorithm according to claim 1, wherein: in the first step, local meteorological data and historical load power data recorded by the system are collected, and data of 7:00-17:00 of a day to be predicted and a day of two months of the day to be predicted are collected by taking each 30min as a sample.
3. The method for predicting the load based on the improved cuckoo-neural network algorithm according to claim 2, wherein: in the first step, the meteorological data comprise cloud cover, temperature, humidity, wind speed, illumination and precipitation.
4. The method for predicting the load based on the improved cuckoo-neural network algorithm according to claim 1, wherein: and in the fourth step, the data of the similar days are normalized.
5. The method for predicting the load based on the improved cuckoo-neural network algorithm according to claim 1, wherein: in the fifth step, firstly, the data of the day to be predicted is normalized, and the normalized meteorological data is put into the prediction model obtained in the fourth step to predict the load of the day to be predicted.
6. The method for predicting the load based on the improved cuckoo-neural network algorithm according to claim 1, wherein: and in the fifth step, performing inverse normalization processing on the output value of the model.
CN201910890297.6A 2019-09-20 2019-09-20 Load prediction method based on improved cuckoo-neural network algorithm Pending CN110598947A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910890297.6A CN110598947A (en) 2019-09-20 2019-09-20 Load prediction method based on improved cuckoo-neural network algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910890297.6A CN110598947A (en) 2019-09-20 2019-09-20 Load prediction method based on improved cuckoo-neural network algorithm

Publications (1)

Publication Number Publication Date
CN110598947A true CN110598947A (en) 2019-12-20

Family

ID=68861569

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910890297.6A Pending CN110598947A (en) 2019-09-20 2019-09-20 Load prediction method based on improved cuckoo-neural network algorithm

Country Status (1)

Country Link
CN (1) CN110598947A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111292124A (en) * 2020-01-18 2020-06-16 河北工程大学 Water demand prediction method based on optimized combined neural network
CN112100904A (en) * 2020-08-12 2020-12-18 国网江苏省电力有限公司南京供电分公司 ICOA-BPNN-based distributed photovoltaic power station active power virtual acquisition method
CN112307672A (en) * 2020-10-29 2021-02-02 上海电机学院 BP neural network short-term wind power prediction method based on cuckoo algorithm optimization

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104318329A (en) * 2014-10-20 2015-01-28 国家电网公司 Power load forecasting method of cuckoo search algorithm improved support vector machine
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
CN109034464A (en) * 2018-07-11 2018-12-18 南京联迪信息系统股份有限公司 A kind of method that short-term photovoltaic generating system power prediction and result are checked
CN110147908A (en) * 2019-05-22 2019-08-20 东莞理工学院 A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm
CN110222888A (en) * 2019-05-27 2019-09-10 深圳供电局有限公司 A kind of per day Methods of electric load forecasting based on BP neural network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104318329A (en) * 2014-10-20 2015-01-28 国家电网公司 Power load forecasting method of cuckoo search algorithm improved support vector machine
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
CN109034464A (en) * 2018-07-11 2018-12-18 南京联迪信息系统股份有限公司 A kind of method that short-term photovoltaic generating system power prediction and result are checked
CN110147908A (en) * 2019-05-22 2019-08-20 东莞理工学院 A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm
CN110222888A (en) * 2019-05-27 2019-09-10 深圳供电局有限公司 A kind of per day Methods of electric load forecasting based on BP neural network

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111292124A (en) * 2020-01-18 2020-06-16 河北工程大学 Water demand prediction method based on optimized combined neural network
CN112100904A (en) * 2020-08-12 2020-12-18 国网江苏省电力有限公司南京供电分公司 ICOA-BPNN-based distributed photovoltaic power station active power virtual acquisition method
CN112100904B (en) * 2020-08-12 2022-08-23 国网江苏省电力有限公司南京供电分公司 ICOA-BPNN-based distributed photovoltaic power station active power virtual acquisition method
CN112307672A (en) * 2020-10-29 2021-02-02 上海电机学院 BP neural network short-term wind power prediction method based on cuckoo algorithm optimization

Similar Documents

Publication Publication Date Title
CN110751318B (en) Ultra-short-term power load prediction method based on IPSO-LSTM
CN112001439A (en) GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment
CN110598947A (en) Load prediction method based on improved cuckoo-neural network algorithm
CN111461463B (en) Short-term load prediction method, system and equipment based on TCN-BP
Zhang et al. Wind speed prediction research considering wind speed ramp and residual distribution
CN112396234A (en) User side load probability prediction method based on time domain convolutional neural network
CN116596044B (en) Power generation load prediction model training method and device based on multi-source data
CN111915079B (en) Hybrid KNN wind power prediction method and system
Niu et al. Short-term wind speed hybrid forecasting model based on bias correcting study and its application
Ogawa et al. Application of evolutionary deep neural netwok to photovoltaic generation forecasting
Elhariri et al. H-ahead multivariate microclimate forecasting system based on deep learning
CN112801416A (en) LSTM watershed runoff prediction method based on multi-dimensional hydrological information
CN113052389A (en) Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks
CN116799796A (en) Photovoltaic power generation power prediction method, device, equipment and medium
Zaman et al. Wind speed forecasting using ARMA and neural network models
CN113128666A (en) Mo-S-LSTMs model-based time series multi-step prediction method
CN116595895A (en) Training method of short-time electric quantity prediction model and short-time electric quantity prediction method
CN114862032B (en) XGBoost-LSTM-based power grid load prediction method and device
CN109359671B (en) Classification intelligent extraction method for hydropower station reservoir dispatching rules
CN116663746A (en) Power load prediction method and device, computer equipment and storage medium
CN116167508A (en) Short-term photovoltaic output rapid prediction method and system based on meteorological factor decomposition
Yuan et al. A novel hybrid short-term wind power prediction framework based on singular spectrum analysis and deep belief network utilized improved adaptive genetic algorithm
CN113283638A (en) Load extreme curve prediction method and system based on fusion model
Mandal et al. Roll of membership functions in fuzzy logic for prediction of shoot length of mustard plant based on residual analysis
CN113723670A (en) Photovoltaic power generation power short-term prediction method with variable time window

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20191220