CN112600204A - Method and system for predicting electrical load of commercial complex air conditioning equipment - Google Patents

Method and system for predicting electrical load of commercial complex air conditioning equipment Download PDF

Info

Publication number
CN112600204A
CN112600204A CN202011519020.1A CN202011519020A CN112600204A CN 112600204 A CN112600204 A CN 112600204A CN 202011519020 A CN202011519020 A CN 202011519020A CN 112600204 A CN112600204 A CN 112600204A
Authority
CN
China
Prior art keywords
load
commercial complex
air conditioning
imf
predicting
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.)
Granted
Application number
CN202011519020.1A
Other languages
Chinese (zh)
Other versions
CN112600204B (en
Inventor
李昆明
郑海雁
祝永晋
李婵娟
谢林枫
尹飞
李新家
熊政
季聪
龙玲莉
张鸿鸣
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.)
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Nanjing University of Posts and Telecommunications
Jiangsu Fangtian Power Technology Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Nanjing University of Posts and Telecommunications
Jiangsu Fangtian Power Technology Co Ltd
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 State Grid Corp of China SGCC, State Grid Jiangsu Electric Power Co Ltd, Nanjing University of Posts and Telecommunications, Jiangsu Fangtian Power Technology Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202011519020.1A priority Critical patent/CN112600204B/en
Publication of CN112600204A publication Critical patent/CN112600204A/en
Application granted granted Critical
Publication of CN112600204B publication Critical patent/CN112600204B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
    • 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
    • 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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Power Engineering (AREA)
  • Air Conditioning Control Device (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method for forecasting electric load of commercial complex air conditioning equipment, which comprises the steps of dividing the electric load of a commercial complex into functional areas; collecting power utilization information system data and business complex data of each functional area; decomposing the original load sequence of each functional area into a limited number of components with different characteristics; the method has the advantages that the prediction model is respectively established for predicting the power load aiming at each characteristic component, the power utilization characteristics of the air-conditioning equipment of the high-rise commercial complex are brought into consideration, the prediction precision is further improved compared with that of the traditional method, and meanwhile, the calculation efficiency is improved.

Description

Method and system for predicting electrical load of commercial complex air conditioning equipment
Technical Field
The invention belongs to the technical field of land leveler operation, and particularly relates to a method for predicting electrical load of commercial complex air conditioning equipment.
Background
The high-rise commercial complex has large height, multiple layers, complex functions and dense population. High-rise commercial complexes typically include businesses, restaurants, parking, recreational fitness facilities, office buildings, hotels, apartments, and the like, with large numbers of standing and floating people. Along with the continuous improvement of people to the requirement of indoor environment travelling comfort level, simultaneously in order to satisfy the inside diversified functional demand of building, high-rise commercial complex has all installed a large amount of intelligent electrical control system usually, has integrateed simultaneously and has supplied a plurality of subsystems such as distribution system, fire extinguishing system, lighting system, motor system of dragging, air conditioning system and water supply and drainage system. Some high-level and high-modernization high-rise commercial complexes are also provided with building automation systems, communication automation systems and office, security and fire-fighting automation systems. The excellent design scheme and control management of various systems are the basis of the intelligent, safe, comfortable and economic operation management of the electrical system of the high-rise building and are also important components of the energy-saving work of the high-rise commercial integrated body.
A large amount of data shows that when the high-rise commercial complex operates, the energy consumption cost mainly comprises energy consumption costs of various electromechanical devices, a central air conditioning system, a lighting system, a water supply and drainage system, an elevator system and the like in a building. The total energy consumption of the air conditioning system, the lighting system, the elevator system and the like accounts for about more than 2/3 of the whole high-rise building, particularly the air conditioning system. The energy consumption distribution of the complex with different use functions is slightly different. With the progress of urbanization, the proportion of the electric energy consumption of the high-rise commercial complex is expected to be further improved, particularly in China. Accurate prediction of electricity consumption of high-rise commercial complexes is crucial to optimizing the operating economy of the use of energy devices inside buildings. And by knowing the internal energy consumption condition of the high-rise commercial comprehensive body, support can be provided for formulating a reasonable energy-saving strategy.
To the energy consumption of traditional commercial building, the scholars at home and abroad adopt different mathematical models to carry out short-term prediction of power consumption load, including: the system comprises a prediction model based on a mathematical statistics theory, a time series model, a Kalman filtering prediction model, a linear regression prediction model, an autoregressive moving average model and the like. With the updating and upgrading of the acquisition equipment, the conditions of personnel in the building can be easily obtained at present. The quantity of mobile personnel in the building and the load electricity consumption data have certain correlation, scholars explore the influence of mobile stream on the energy consumption of commercial buildings, and functional relations between indoor stream data and equipment energy consumption are built based on Monte Carlo simulation and Markov chain models and are predicted. In addition to the above, there are also a variety of intelligent algorithms applied to the prediction of electrical loads. For example, a multilayer perceptron is used as a model prediction frame, a plurality of external factors such as temperature, rainfall, wind speed and the like are input into an input layer of an artificial neural network ANN, the numerical value of a final output layer is used as the power consumption at a future moment, and the neural network parameters are optimized through a particle swarm optimization PSO algorithm; adopting a BP-Adaboost algorithm to predict the building power utilization load; selecting characteristics by adopting a principal component analysis method, and simplifying a prediction mode; and based on an ensemble learning method, meteorological data, building mobile people flow and intelligent electric meter data are fused to predict the power load.
TABLE 1 energy consumption of electrical equipment in traditional commercial buildings
Figure BDA0002848381010000021
At present, a large number of prediction methods exist for the traditional building electrical load. The high-rise commercial complex is influenced by factors such as air temperature, rainfall, weather factors, holidays, social activities, policy activities, the number of users and the like, and has the characteristics of strong nonlinearity and randomness. Socioeconomic and policy adjustments also have a certain indirect impact on the load in the corresponding time period.
However, the existing high-level business complex has the conditions of multiple devices, complex structure, large personnel mobility, complicated personnel and the like, and a good method for predicting the load is not provided.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a high-rise commercial complex which can predict the air conditioning load under complex conditions for realizing the purpose, and the technical scheme is as follows:
in a first aspect, a method for predicting an electrical load of a commercial complex air conditioning device is provided, which includes:
dividing the functional area of the electric load of the commercial complex;
collecting power utilization information system data and business complex data of each functional area;
decomposing the original load sequence of each functional area into a limited number of components with different characteristics;
and respectively establishing a prediction model for each characteristic component to predict the power load.
Further in conjunction with the first aspect, the functional zone partitioning of the electrical load to the business complex is embodied as a business, a restaurant, an entertainment, an office building, a hotel, an apartment, and others.
With reference to the first aspect, the acquiring the electricity consumption information system data and the business complex data of each functional area specifically includes:
the measured loads of each functional area are sampled at intervals of 15 minutes, and the commercial complex data are sampled at the same time, wherein the commercial complex data comprise data of a meteorological parameter table, an indoor temperature table and a machine room parameter table.
With reference to the first aspect, further, the decomposing the original load sequence of each functional region into a limited number of components with different characteristics specifically includes:
decomposing original load sequence of each functional area into K modal components, namely IMF components by adopting a VMD method1、IMF2、IMF3、...IMFK(ii) a Wherein IMFKRepresenting the K-th modal component.
With reference to the first aspect, further, the method for determining the optimal value of K includes:
respectively calculating information entropies of the K modal components, and representing the difference between the modal components of the VMD decomposed signal by adopting a difference coefficient C;
Figure BDA0002848381010000031
in the formula (I), the compound is shown in the specification,
Figure BDA0002848381010000032
is the mean value of the entropy of the information of K modal components, S1、S2...SKInformation entropies corresponding to the K modal components respectively;
error between original signal and reconstruction preference according to equation (2):
Δ＝sum[abs(y-IMF1-IMF2-…-IMFK)] (2)
wherein y is the original input signal;
the decomposition quality factor is obtained according to equation (3):
Q＝C/Δ (3)
wherein Q is a decomposition quality factor, and Delta represents an error between an original signal and a reconstructed signal;
and selecting the value within the value range of K, wherein the K value corresponding to the maximum decomposition quality factor is the optimal value.
With reference to the first aspect, further, the respectively establishing a prediction model for each feature component includes:
a prediction model is constructed by adopting an extreme learning machine network, the input layer node is set to be 14, the output layer node is set to be 1, and the number range of the hidden layer neuron nodes is set to be 30-40.
With reference to the first aspect, further, the predicted power consumption load is specifically: and superposing the prediction results of the frequency sequences obtained by decomposition according to the established prediction model, and taking the superposed result as the final prediction result.
In a second aspect, there is provided a system for predicting electrical load for a commercial complex air conditioning unit, comprising:
a function division module: the system is used for carrying out functional zone division on the electric load of the commercial complex;
an acquisition module: the system is used for acquiring the electricity utilization information system data and the commercial complex data of each functional area;
decomposing a module course: the system comprises a load analysis module, a load analysis module and a load analysis module, wherein the load analysis module is used for decomposing an original load sequence of each functional area into a limited number of components with different characteristics;
a prediction module: and the method is used for establishing a prediction model for each characteristic component to predict the power load.
Has the advantages that: the method brings the electricity utilization characteristics of the air conditioning equipment of the high-rise commercial complex into consideration, further improves the prediction precision compared with the traditional method, and simultaneously improves the calculation efficiency.
Drawings
FIG. 1 is a diagram showing the basic components of an electrical system of a high-rise commercial complex according to the present invention;
FIG. 2 is a flow chart of the air conditioning load prediction of the high-rise commercial complex according to the present invention;
FIG. 3 is a diagram of a model of an extreme learning machine for air conditioning load prediction in a high-rise commercial complex.
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 to 3, the present invention provides a technical solution: a method for predicting the electrical load of air conditioning equipment of a commercial complex,
1. the method comprises the steps of firstly, carrying out function division on the load of the high-rise commercial complex, dividing the load into 7 parts in total, namely commercial, catering, entertainment, office buildings, hotels, apartments and others, respectively predicting and reconstructing the load of an air conditioner based on data of an electricity utilization information acquisition system, and further determining the whole air conditioning equipment of the high-rise commercial complex and the electricity utilization information of the load of the air conditioning equipment.
2. Based on the data of the electricity utilization information acquisition system, the actual measurement load values of 7 functional areas of the high-rise commercial complex at a certain day are sampled: the data sampling interval is 15min, and the sampling time is 0: 00-24: 00 a day; and simultaneously, collecting data of a high-rise commercial complex, wherein the data mainly comprises a meteorological parameter table, an indoor temperature table and a machine room parameter table. The method specifically comprises the following steps: comprehensive outdoor temperature, comprehensive outdoor humidity, comprehensive indoor temperature, water supply temperature of a machine room, return water temperature, supply and return temperature difference, instantaneous heat of the machine room, pump power and the like.
3. Decomposing the original load sequence of each functional area by adopting a VMD method, decomposing the original load sequence into a finite number of components with different characteristics, and aiming at each functional areaAnd (3) respectively establishing a prediction model for each characteristic component, so that pure datamation of a load sequence is avoided, and the prediction precision is improved. Decomposing the original load sequence of each functional area into K sub-modal components, namely IMF1、IMF2、IMF3...IMFK. Where K is the number of VMD modal components IMF. The value of K directly influences the decomposition effect of the signal sequence, and the determination of the value is particularly important. If the value of K is larger, the signal is over-decomposed; if the value of K is too small, under-decomposition will occur. Considering the condition of the air-conditioning load characteristics of high-rise commercial buildings, limiting the range of the K value to be intervals (3-8), respectively calculating and comparing by adopting an enumeration method, and determining an optimal value, wherein the specific operation steps are as follows:
a) the decomposition is performed successively by an enumeration method. And respectively calculating the information entropy of the K components, and representing the difference between the IMF components of the VMD decomposed signal by adopting a difference coefficient C.
Figure BDA0002848381010000051
In the formula (I), the compound is shown in the specification,
Figure BDA0002848381010000052
is the information entropy mean of the K IMF components. S1、S2...SKThe information entropy corresponding to the K IMFs is obtained.
b) The error between the original signal and the reconstructed signal is represented by delta, and the smaller the value of delta, the closer the reconstructed signal after decomposition is to the original voltage signal. The expression is
Δ＝sum[abs(y-IMF1-IMF2-…-IMFK)] (2)
Where y is the original input signal.
c) The decomposition quality factor Q of the VMD is defined by the difference coefficient and the error coefficient.
Q＝C/Δ (3)
And selecting the maximum quality factor Q in the interval range, and determining the optimal modal decomposition number K, wherein the optimal modal decomposition number K contains the main detailed characteristics of the original sequence so as to inhibit modal aliasing among signals. And according to the center frequency of the modal components after decomposition, each modal component conforms to the decomposition principle.
4. And constructing a prediction extreme learning machine model. The specific operation steps are as follows: a) firstly, determining a network model structure, wherein the key point of establishing the extreme learning machine network lies in determining the number of the hidden neurons, and the determination of the number of the hidden neurons does not have a fixed method or formula so far. When the number of the hidden layer nerves is selected, the hidden layer nerves are selected from a small value and gradually increased, the increased upper limit is the number of samples, and according to the theorem of the extreme learning machine, when the number of the samples is equal to the number of the hidden neurons, the extreme learning machine can approximately fit the training samples without error, and the number of nodes does not need to be increased.
b) Determination of input layer nodes: the input nodes are selected according to the periodicity of the air conditioning load, the day type and the air temperature influence, and comprise: a load value at the same time 7 days in the last week from the prediction date, and load values at the last 7 times from the prediction time point; the attribute of the predicted day, namely the day type; the comprehensive outdoor maximum temperature on the same day, the comprehensive outdoor minimum temperature on the same day, the comprehensive outdoor humidity, the water supply temperature of the machine room, the water return temperature, the temperature difference between the supply and the return, the instantaneous heat of the machine room and the pump power. The input variables amount to 14 dimensions, so that the input level nodes are 14.
c) In the selection of the nodes of the output layer, because the load values at the same moment in the last 7 days corresponding to each moment are different, furthermore, the load prediction is a rolling prediction, that is, the load value at the next moment is predicted by using the load values at the last 7 moments from the prediction time point, and the last 7 moment values at the next moment comprise the last 6 measured load values and the predicted load value at the last moment. Therefore, each prediction point needs to establish extreme learning machine prediction independently, and the output layer node is 1.
d) Determination of the number of implicit neuron nodes: the number of nodes, the computational accuracy requirements and the computational power of the input layer are taken into account. And setting the range of the number of the neuron nodes in the hidden layer to be (30-40), and analyzing and comparing by adopting an enumeration method to determine the optimal number of the nodes. The average relative error is controlled to be less than 4 percent, and the average absolute error is controlled to be less than 6 percent.
f) The output layer node takes 1.
5. And merging and reconstructing the prediction results of each component to obtain the final prediction result.
The invention principle is as follows:
the electricity consumption of the high-rise commercial complex is influenced by factors such as air temperature, rainfall, weather factors, holidays, social activities, policy activities, the number of users and the like, has the characteristics of strong nonlinearity and randomness, and has the characteristics of more functional partitions, complex structure, large personnel mobility, complicated situations and the like. According to the method, according to different electricity utilization characteristics, the overall function of a high-rise commercial complex is divided firstly, the original load sequence of each functional area is decomposed based on the data of an electricity utilization information acquisition system, the original load sequence is decomposed into components with different characteristics by adopting an improved variational modal decomposition algorithm, a prediction model is respectively established for each characteristic component, the pure datamation of the load sequence is avoided, and meanwhile, the prediction precision is improved. The variational modal decomposition is a signal decomposition estimation method. In the process of obtaining the decomposition components, the method determines the frequency center and the bandwidth of each component by iteratively searching the optimal solution of the variation model, thereby being capable of adaptively realizing the frequency domain subdivision of the signal and the effective separation of each component. In order to solve the variation problem, an alternative direction multiplier method is adopted, each mode and the center frequency thereof are continuously updated, each mode is demodulated to a corresponding base frequency band step by step, and finally, each mode, namely the corresponding center frequency, is extracted together. Assuming that each sub-signal is mainly centered around a center frequency, the center frequency will be determined with the decomposition. Assuming the original input signal is f (t), the VMD decomposes f (t) into K eigenmode functions u through adaptive quasi-orthogonal transformationk(t) of the formula：
uk(t)＝Ak(t)cos(φk(t))k＝1,2…,K (4)
Wherein: a. thek(t) is uk(t) magnitude; phi is ak′(t)＝ωk(t)，ωk(t) is uk(t) instantaneous frequency characterization.
And simultaneously, collecting the operating environment data of the high-rise commercial complex, wherein the operating environment data mainly comprises a meteorological parameter table, an indoor temperature table, a machine room parameter table and the like. And determining and selecting a proper input set according to the temperature, the time type (working day/holiday/special date) and the load value at the historical similar moment, and constructing an Extreme Learning Machine (ELM) -based load prediction model. Compared with other methods, the extreme learning machine is a novel learning algorithm provided based on a single hidden layer feedforward neural network, the training process is simple, input weights and threshold values are randomly generated, model training can be completed by obtaining output weights of SLFNs through a generalized inverse matrix, and the training speed and the generalization capability are greatly improved. And finally, reconstructing the established high-rise commercial complex air conditioning equipment and the electric load prediction model thereof so as to determine the prediction result.
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 (8)

1. A method for predicting the electrical load of a commercial complex air conditioning device is characterized by comprising the following steps:
dividing the functional area of the electric load of the commercial complex;
collecting power utilization information system data and business complex data of each functional area;
decomposing the original load sequence of each functional area into a limited number of components with different characteristics;
and respectively establishing a prediction model for each characteristic component to predict the power load.
2. The method of predicting an electrical load for a commercial complex air conditioning apparatus as set forth in claim 1, wherein: the functional zone partitioning of the electrical load to the business complex is particularly the partitioning of the business complex into businesses, restaurants, entertainment, office buildings, hotels, apartments and others.
3. The method of predicting an electrical load for a commercial complex air conditioning apparatus as set forth in claim 2, wherein: the collecting of the electricity utilization information system data and the commercial complex data of each functional area specifically comprises the following steps:
the measured loads of each functional area are sampled at intervals of 15 minutes, and the commercial complex data are sampled at the same time, wherein the commercial complex data comprise data of a meteorological parameter table, an indoor temperature table and a machine room parameter table.
4. The method of predicting an electrical load for a commercial complex air conditioning apparatus as set forth in claim 1, wherein: the decomposing of the original load sequence of each functional area into a finite number of components with different characteristics is specifically as follows:
decomposing original load sequence of each functional area into K modal components, namely IMF components by adopting a VMD method1、IMF2、IMF3、...IMFK(ii) a Wherein IMFKRepresenting the K-th modal component.
5. The method of predicting an electrical load for a commercial complex air conditioning apparatus as set forth in claim 4, wherein: the optimal value determination method of K comprises the following steps:
respectively calculating information entropies of the K modal components, and representing the difference between the modal components of the VMD decomposed signal by adopting a difference coefficient C;
Figure FDA0002848379000000011
in the formula (I), the compound is shown in the specification,
Figure FDA0002848379000000012
is the mean value of the entropy of the information of K modal components, S1、S2...SKInformation entropies corresponding to the K modal components respectively;
error between original signal and reconstruction preference according to equation (2):
Δ＝sum[abs(y-IMF1-IMF2-…-IMFK)] (2)
wherein y is the original input signal;
the decomposition quality factor is obtained according to equation (3):
Q＝C/Δ (3)
wherein Q is a decomposition quality factor, and Delta represents an error between an original signal and a reconstructed signal;
and selecting the value within the value range of K, wherein the K value corresponding to the maximum decomposition quality factor is the optimal value.
6. The method of predicting an electrical load for a commercial complex air conditioning apparatus as set forth in claim 1, wherein: the respectively establishing a prediction model for each feature component includes:
a prediction model is constructed by adopting an extreme learning machine network, the input layer node is set to be 14, the output layer node is set to be 1, and the number range of the hidden layer neuron nodes is set to be 30-40.
7. The method of predicting the electrical load of a commercial complex air conditioning device according to claim 6, wherein the predicted electrical load is specifically: and superposing the prediction results of the frequency sequences obtained by decomposition according to the established prediction model, and taking the superposed result as the final prediction result.
8. A system for predicting an electrical load for a commercial complex air conditioning unit, comprising:
a function division module: the system is used for carrying out functional zone division on the electric load of the commercial complex;
an acquisition module: the system is used for acquiring the electricity utilization information system data and the commercial complex data of each functional area;
decomposing a module course: the system comprises a load analysis module, a load analysis module and a load analysis module, wherein the load analysis module is used for decomposing an original load sequence of each functional area into a limited number of components with different characteristics;
a prediction module: and the method is used for establishing a prediction model for each characteristic component to predict the power load.
CN202011519020.1A 2020-12-21 2020-12-21 Electric load prediction method and system for commercial integrated air conditioning equipment Active CN112600204B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011519020.1A CN112600204B (en) 2020-12-21 2020-12-21 Electric load prediction method and system for commercial integrated air conditioning equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011519020.1A CN112600204B (en) 2020-12-21 2020-12-21 Electric load prediction method and system for commercial integrated air conditioning equipment

Publications (2)

Publication Number Publication Date
CN112600204A true CN112600204A (en) 2021-04-02
CN112600204B CN112600204B (en) 2023-06-13

Family

ID=75199702

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011519020.1A Active CN112600204B (en) 2020-12-21 2020-12-21 Electric load prediction method and system for commercial integrated air conditioning equipment

Country Status (1)

Country Link
CN (1) CN112600204B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106127360A (en) * 2016-06-06 2016-11-16 国网天津市电力公司 A kind of multi-model load forecasting method analyzed based on user personality
CN111950793A (en) * 2020-08-17 2020-11-17 浙江工业大学 Comprehensive energy system load prediction method considering multivariate load coupling characteristics

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106127360A (en) * 2016-06-06 2016-11-16 国网天津市电力公司 A kind of multi-model load forecasting method analyzed based on user personality
CN111950793A (en) * 2020-08-17 2020-11-17 浙江工业大学 Comprehensive energy system load prediction method considering multivariate load coupling characteristics

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
任鹏: "大型商业建筑空调负荷预测方法的研究", 《中国优秀硕士论文工程科技Ⅱ辑》 *

Also Published As

Publication number Publication date
CN112600204B (en) 2023-06-13

Similar Documents

Publication Publication Date Title
CN107942960B (en) A kind of intelligentized information processing system
CN115249094B (en) Building energy efficiency management and optimization method based on big data
Li et al. Reinforcement learning of room temperature set-point of thermal storage air-conditioning system with demand response
CN104484715A (en) Neural network and particle swarm optimization algorithm-based building energy consumption predicting method
Kim et al. Sequence-to-sequence deep learning model for building energy consumption prediction with dynamic simulation modeling
Lin et al. Short-term forecast model of cooling load using load component disaggregation
CN114239972A (en) Campus energy efficiency and electrical safety management method and system based on artificial intelligence technology
CN116739562A (en) LSTM-based power distribution network stability operation and maintenance method
Song et al. An indoor temperature prediction framework based on hierarchical attention gated recurrent unit model for energy efficient buildings
CN115423301A (en) Intelligent electric power energy management and control method, device and system based on Internet of things
Wang et al. A review of load forecasting of the distributed energy system
CN111401658B (en) Parallel cold load prediction method based on building space unit
CN116205425A (en) Low-carbon park cold-hot electric load prediction method based on typical database
Zhao et al. Heating load prediction of residential district using hybrid model based on CNN
CN115545415A (en) Urban regional energy system load prediction method in planning stage
Han et al. Physical-data fusion modeling method for energy consumption analysis of smart building
Zhao et al. Data-driven online energy management framework for HVAC systems: An experimental study
CN110110388A (en) Building air conditioning load forecasting method based on data pre-processing and wavelet decomposition
Kumar et al. Forecasting indoor temperature for smart buildings with ARIMA, SARIMAX, and LSTM: A fusion approach
Yu et al. Impact of window and air-conditioner operation behaviour on cooling load in high-rise residential buildings
CN112600204B (en) Electric load prediction method and system for commercial integrated air conditioning equipment
Zhang et al. Improving the accuracy of load forecasting for campus buildings based on federated learning
CN111144628A (en) Distributed energy supply type cooling, heating and power load prediction model system and method
CN115906396A (en) Passive building energy management system and use method thereof
CN113837665B (en) Regional electric heating load prediction method based on intelligent body modeling

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