CN114881506A - Heat supply demand load assessment method and system based on room temperature and IBA-LSTM - Google Patents
Heat supply demand load assessment method and system based on room temperature and IBA-LSTM Download PDFInfo
- Publication number
- CN114881506A CN114881506A CN202210567906.6A CN202210567906A CN114881506A CN 114881506 A CN114881506 A CN 114881506A CN 202210567906 A CN202210567906 A CN 202210567906A CN 114881506 A CN114881506 A CN 114881506A
- Authority
- CN
- China
- Prior art keywords
- indoor temperature
- heat supply
- lstm
- parameters
- demand load
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 238000011156 evaluation Methods 0.000 claims abstract description 24
- 238000013210 evaluation model Methods 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 230000004927 fusion Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 14
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000010438 heat treatment Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 13
- 238000009529 body temperature measurement Methods 0.000 claims description 10
- 230000035945 sensitivity Effects 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 241000288673 Chiroptera Species 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/08—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"
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a heat supply demand load assessment method and system based on room temperature and IBA-LSTM, comprising the following steps: setting a plurality of indoor temperature measuring points for different heat users in a heat supply system, and acquiring indoor temperature measuring values at a plurality of moments in a preset period; assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measuring point; analyzing various influence factors influencing the heat supply demand load evaluation by adopting a sensitivity analysis method, and screening out important influence factors; carrying out parameter optimization on the LSTM network algorithm by adopting an improved bat algorithm IBA; and constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm, and evaluating the load demand of the heat supply system. According to the invention, the weight coefficient of each room temperature measuring point is determined to determine the indoor temperature fusion value, and the IBA-LSTM is adopted to construct the heat supply demand load evaluation model, so that the model training speed can be increased, and the model evaluation precision is high.
Description
Technical Field
The invention belongs to the technical field of intelligent heat supply, and particularly relates to a heat supply demand load assessment method based on room temperature and IBA-LSTM.
Background
With the rapid development of informatization technology and intelligent heat supply, a large amount of heat supply data can be stored, effective information is mined from historical data, a reasonable and appropriate heat supply load prediction model is constructed, and the method has great significance for improving heat supply quality and heat supply efficiency of heat supply enterprises. The load prediction is mainly realized by analyzing the change characteristic of the heating heat load and combining the influence factors influencing the change of the load, thereby realizing the accurate prediction process of the heat load. The timely and accurate heat load prediction can not only ensure the heat demand of users, but also ensure the benefits of heat supply enterprises, and realize the balance of supply and demand. Therefore, the heat load prediction is an important basis for the operation decision of the heat supply enterprises, and is a necessary basis for the heat supply enterprises to reduce energy waste and realize the efficient management and the economic operation of the centralized heat supply system.
Because long-term stable indoor temperature data is difficult to obtain, most load evaluation only considers the influence of factors such as outdoor temperature, historical heating load and the like, and does not consider the influence of indoor temperature; in practice, after the building type, the human behavior, the heat supply standard and the like are determined, under a certain meteorological condition, the heat supply load theoretically has a fixed value, the heat supply amount can be infinite, different indoor temperatures can correspond to different heat supply amounts, and if the indoor temperatures are ignored, the accuracy of a prediction model cannot be guaranteed; in addition, the number of input variables of the load evaluation model is large, the more the input variables are, the longer the model training time is, and for the numerous algorithms of load evaluation, how to combine the actual engineering data, comprehensively consider the evaluation accuracy of the model, and select an applicable evaluation method is also a problem faced at present.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a heat supply demand load assessment method and system based on room temperature and IBA-LSTM, the weight coefficient of each room temperature measuring point is determined, and finally an indoor temperature fusion value is determined, wherein the indoor temperature fusion value can effectively and accurately represent the indoor temperature, and the heat supply demand load assessment model construction accuracy is facilitated; and the improved intelligent optimization algorithm is adopted to carry out parameter optimization on the LSTM network algorithm, and the heat supply demand load assessment model is constructed based on the optimized LSTM network algorithm, so that the model training speed can be increased, the model training error can be reduced, the model assessment precision is higher, and the heat supply demand load can be better assessed.
In order to solve the technical problems, the technical scheme of the invention is as follows:
the invention provides a heat supply demand load assessment method based on room temperature and IBA-LSTM, which comprises the following steps:
s1, setting a plurality of indoor temperature measuring points for different heat users in the heating system, and acquiring indoor temperature measuring values at a plurality of moments in a preset period;
step S2, assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measuring point;
s3, analyzing various influence factors influencing heat supply demand load evaluation by adopting a sensitivity analysis method, and screening out important influence factors;
s4, optimizing parameters of the LSTM network algorithm by adopting an improved intelligent optimization algorithm;
and S5, constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm, and evaluating the load demand of the heat supply system.
Further, the step S1 includes: setting the measuring point position of each layer of users according to the area, the orientation and the layout of each layer of user house type and the position relation of the wall surface and the window; a plurality of indoor temperature measuring points are arranged in rooms of a bottom layer user, a top layer user and a middle layer user of one unit.
Further, the step S2 includes:
acquiring historical heat supply load data and a preset heat supply indoor temperature target value, and performing heat supply analysis on a heat user by using an AHP (analytic hierarchy process) analysis method to obtain a weight coefficient of each indoor temperature monitoring point;
calculating an indoor temperature fusion value according to the indoor temperature measurement value of each indoor temperature monitoring point and the corresponding weight coefficient, wherein the calculation formula is as follows:
n is the number of indoor temperature monitoring points;wherein i is 1,2,3, …, and n is the indoor temperature measured value of the ith indoor temperature monitoring point at the time k; c. C i Wherein i is 1,2,3, …, n, c 1 +c 2 +c 3 +…+c n 1 is the weight coefficient of each indoor temperature monitoring point;
the weight coefficient calculation formula is expressed as:
is the arithmetic mean value of each indoor temperature measurement value, and r is an adjustment coefficient.
Further, the step S3 includes:
setting an output function Y (f) (x) of the heat supply demand load evaluation model 1 ,x 2 ,…,x z ) Comprising z influencing parameters; the parameter influencing factors include: indoor temperature, heat supply historical parameters, building thermal characteristic parameters, meteorological parameters and social parameters;
the heat supply historical parameters comprise return water temperature, flow, pressure and heat supply load;
the building thermal characteristic parameters include type, age, geographic location and orientation of the building;
the meteorological parameters comprise outdoor temperature, wind speed and solar radiation; social parameters include holidays and holidays.
And mapping the value range of each parameter to [0,1] according to the probability distribution obeyed by each parameter, discretizing the parameter by a preset sampling level p, and randomly sampling each parameter once on p sampling levels to generate a vector X.
Preferably, the step S3 of screening out important influencing factors includes:
in the process of generating a sample, a base sample point X is generated 1 Adding disturbance variable, and sequentially generating other sample points X i After different sample points are generated, z +1 sample points are obtained, and the basic effect value of each parameter is calculated as follows:
by calculating the mean value mu of the effect value of each parameter i And standard deviation σ i Determining the degree of importance or sensitivity of the parameter, mean μ i And standard deviation σ i The calculation is expressed as:
wherein d is i,e (X) is X i The e basic effect value, N is the sample capacity;
the average value represents the sensitivity of the parameters, and the larger the value is, the more important the parameters are, so as to determine the sensitivity sequence of the parameters; the standard deviation characterizes the degree of interaction between the parameters, indicating that the parameters interact strongly with other parameters if the standard deviation is large, and that the parameters interact weakly with other parameters if the standard deviation is small.
Further, the step S4 includes the following steps:
s401, setting basic parameters of the bat population, including the total number m of individuals of the bat population, the dimension d of the population, and the maximum value f of the pulse emission frequency max Minimum value f min Emissivity of pulse wave r i Pulse rate increase and decrease coefficient gamma and loudness A i Loudness reduction factor alpha and maximum number of iterations N max ;
S402, setting speed and position coordinates of the bat individual, including the position x of the bat individual i (h, η, n) and the flying velocity v i And the frequency f of the transmission of the pulses i (ii) a h is the number of hidden layer neurons, eta is the learning rate of the LSTM, and n is the iteration frequency when the LSTM loss function meets the requirement;
s403, correcting a calculation formula of the position and the flight speed of the bat individual;
s404, checking the random number rand obtained by random flight, when rand is more than r i Then, acquiring a new solution by performing non-directional disturbance on the position of the current optimal solution;
s405, in the process of optimizing the LSTM by the bat algorithm, adopting a root mean square error as a fitness function;
s406, checking the acquired random numberAnd the new solution obtained in S403, such as satisfying the condition rand < A i And f (x) i )<f(x * ) Said f (x) i ) To be at position x i The pulse transmission frequency of (3); f (x) * ) To correct the optimal position x * The pulse transmission frequency of (2). x is the number of * The optimal position is calculated after all bat positions are compared; the selection acceptance obtains a new solution, and at the same time r is increased i A is decreased by i A value of (d);
s407, comparing the obtained new solution with the global optimal solution, and if the new solution is better than the global optimal solution, correcting the optimal solution and the optimal position of the bat individual;
s408, judging whether the iteration frequency meets the requirement of the maximum iteration frequency or not, if not, searching a new solution in the neighborhood of the current optimal solution by adopting a gradient descent method, and when the position of the new solution is better than that of the current optimal solution, replacing the optimal solution with a newly calculated solution; if yes, the optimal solution is unchanged, and S402 is switched to repeat execution;
and S409, if the iteration times are met, outputting the found optimal solution, namely obtaining the optimal solution of the number of hidden layer neurons, the LSTM learning rate and the iteration times.
Preferably, in the step S403, the calculation formula for correcting the position and flight speed of the individual bats is expressed as:
f i =f min +(f max -f min )β;
wherein, beta is ∈ [0,1]]Satisfying uniform distribution, x * The optimal position is calculated after all bat positions are compared; maximum value f of pulse transmission frequency max Minimum value f min And the frequency f of the transmission of the pulses i ; The flight speeds at the time t and the time t +1 respectively;the time t and the time t +1 are the positions.
Preferably, in step S406, r is increased i A is decreased by i The values of (a) are specifically:
the bat can continuously adjust the loudness of sound waves and the emissivity of pulse waves according to the direction of prey to improve the predation efficiency; the acoustic loudness and pulse wave emissivity of bats are calculated as:
is the initial pulse wave emissivity of the bat;the pulse wave emissivity of the bat at the time t is shown;the sound wave loudness of the bat at the time t and the time t +1 are respectively.
Further, the step S5 includes:
collecting historical data of relevant important influence factors of a heat supply system as sample data, and carrying out data preprocessing on the sample data;
dividing the preprocessed data into a training set and a test set according to a preset proportion;
inputting data of a training set into the LSTM network algorithm after parameter optimization for training, generating a heat supply demand load evaluation model, and evaluating the trained model on a test set;
and inputting the data to be evaluated into the trained heat supply demand load evaluation model to obtain a heat supply demand load evaluation value.
A room temperature and IBA-LSTM based heating demand load assessment system comprising:
a room temperature measuring point setting module: the system comprises a plurality of indoor temperature measuring points, a plurality of indoor temperature measuring points and a plurality of indoor temperature measuring values, wherein the indoor temperature measuring points are used for setting a plurality of indoor temperature measuring points for different heat users in a heating system and acquiring the indoor temperature measuring values at a plurality of moments in a preset period;
a measuring point weight calculating module: the indoor temperature measuring points are used for assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating indoor temperature fusion values of the indoor temperature measuring points;
a sensitivity analysis module: the method is used for analyzing various influence factors influencing the heat supply demand load evaluation by adopting a sensitivity analysis method and screening out important influence factors;
LSTM algorithm optimization module: the LSTM network optimization method is used for optimizing parameters of an LSTM network algorithm by adopting an improved intelligent optimization algorithm;
an evaluation model construction module: the method is used for constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm and evaluating the load demand of the heat supply system.
The invention has the beneficial effects that:
(1) the method comprises the steps of setting a plurality of indoor temperature measuring points for different heat users in a heat supply system, and obtaining indoor temperature measuring values at a plurality of moments in a preset period; assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measuring point; the weight coefficient can be dynamically adjusted, the weight coefficient of each room temperature measuring point can be determined, and finally an indoor temperature fusion value is determined, wherein the indoor temperature fusion value can effectively and accurately represent the indoor temperature, and the accuracy of building a heat supply demand load evaluation model is facilitated;
(2) according to the invention, a sensitivity analysis method is adopted to analyze various influence factors influencing heat supply demand load evaluation, so that important influence factors can be screened out, less sensitive factors are ignored, and the efficiency of subsequent evaluation model construction is improved;
(3) the LSTM network algorithm is optimized through the improved bat algorithm IBA, the number of neurons of hidden layers of the LSTM model, the learning rate and the iteration times are optimized through the improved bat algorithm, descending gradient optimization is used as interference, the bat algorithm is assisted to jump out of an extreme value, and the optimal solution is searched out more efficiently and rapidly; and optimizing LSTM parameters by adopting the improved bat algorithm, and constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm, so that the model training speed can be increased, the model training error can be reduced, the model evaluation precision is higher, and the heat supply demand load can be better evaluated.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for evaluating heat demand load based on room temperature and IBA-LSTM according to the present invention;
FIG. 2 is a schematic structural diagram of a heating demand load assessment system based on room temperature and IBA-LSTM.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings: in order to clearly explain the technical features of the present invention, the present invention will be explained in detail by the following embodiments and the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
In an embodiment of the present invention, as shown in fig. 1, this embodiment 1 provides a heating demand load assessment method based on room temperature and IBA-LSTM, including:
s1, setting a plurality of indoor temperature measuring points for different heat users in the heating system, and acquiring indoor temperature measuring values at a plurality of moments in a preset period;
step S2, assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measuring point;
s3, analyzing various influence factors influencing heat supply demand load evaluation by adopting a sensitivity analysis method, and screening out important influence factors;
s4, optimizing parameters of the LSTM network algorithm by adopting an improved intelligent optimization algorithm;
and S5, constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm, and evaluating the load demand of the heat supply system.
In this embodiment, in step S1, setting a plurality of indoor temperature measurement points for different heat consumers in the heating system, and acquiring indoor temperature measurement values at a plurality of times within a preset period includes: a plurality of indoor temperature measuring points are arranged in the rooms of a bottom layer user, a top layer user and a middle layer user of one unit; the measuring point positions of each layer of users are set according to the area, the orientation and the layout of each layer of user house type and the position relation of the wall surface and the window.
In this embodiment, in step S2, assigning different weight coefficients to multiple indoor temperature measurement points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measurement point, includes:
according to a plurality of indoor temperature measuring points of different heat users, collecting corresponding indoor temperature measuring values at a plurality of moments, acquiring corresponding historical heat supply load data and preset heat supply indoor temperature target values, and performing heat supply analysis on the heat users by using an AHP hierarchical analysis method to obtain weight coefficients of all indoor temperature monitoring points;
and calculating an indoor temperature fusion value according to the indoor temperature measurement value of each indoor temperature monitoring point and the corresponding weight coefficient, wherein the indoor temperature fusion value is expressed as:
n is the number of indoor temperature monitoring points;wherein i is 1,2,3, …, n is the indoor temperature measured value of the ith indoor temperature monitoring point at the time k; c. C i Wherein i is 1,2,3, …, n, c 1 +c 2 +c 3 +…+c n 1 is the weight coefficient of each indoor temperature monitoring point;
the weight coefficient is dynamically adjusted along with the time change, and is a dynamic weighting factor, and the calculation formula is expressed as follows:
is the arithmetic mean of the measured values of the room temperatures, r is the adjustment factor, andthe self error of the sensor for measuring the indoor temperature is related to the average value and the fusion value of the indoor temperature of different indoor temperature monitoring points at different moments.
In this embodiment, in step S3, a sensitivity analysis method is used to analyze multiple influence factors affecting the heat supply demand load evaluation, and an important influence factor is screened out, which specifically includes:
setting an output function Y (f) (x) of the heat supply demand load evaluation model 1 ,x 2 ,…,x z ) Including z influencing parameters, and then mapping the value range of each parameter to [0,1] according to the probability distribution obeyed by each parameter]Discretizing the sampling level by a preset sampling level p to make each parameter take the value ofRandomly taking values in the vector, and randomly taking values of each parameter on p sampling points to generate a vector X (X ═ X) 1 ,x 2 ,…,x z ) (ii) a Wherein the influence parameters at least comprise indoor temperature, heat supply historical parameters, building thermal characteristic parameters, meteorological parameters and social parameters; the heat supply historical parameters comprise supply and return water temperature, flow, pressure and heat supply load; the building thermal characteristic parameters include the type, age, geographic location and orientation of the building; meteorological parameters including outdoor temperature, wind speed and solar radiation; social parameters include holidays and holidays;
in the process of generating a sample, a base sample point X is generated 1 Then adding disturbance variable to generate other sample points X in turn i After different sample points are generated, z +1 sample points are obtained, and the basic effect value of each parameter is calculated as follows:
by calculating the mean value mu of the effect value of each parameter i And standard deviation σ i Determining the degree of importance or sensitivity of the parameter, mean μ i And standard deviation σ i The calculation is expressed as:
wherein d is i,e (X) is X i The e basic effect value, N is the sample capacity; the mean value characterizes the sensitivity of the parameters, and the larger the value is, the more important the parameters are, so as to determine the sensitivity ranking of the parameters, specifically: more important and more sensitive, the larger the value and the higher the sensitivity, indicating that the parameter is more important; the standard deviation characterizes the degree of interaction between the parameters, indicating that the parameters interact strongly with other parameters if the standard deviation is large, and that the parameters interact weakly with other parameters if the standard deviation is small.
It should be noted that the sensitivity analysis is to study the effect of different changes (or variability) of the model input parameters on the variability of the model output. Generally, the sensitivity analysis method mainly comprises the following steps:
(1) selecting model parameters, and defining independent and interdependent parameters of the model;
(2) setting the value range of the parameters and the probability density function (or prior distribution) of the parameters;
(3) selecting a proper parameter sampling design method, such as MC sampling, LHS sampling, M-OAT sampling and the like, to generate a parameter sample;
(4) applying a parameter sample operation model, and calculating a corresponding output objective function value to form an objective function set;
(5) and evaluating the degree of the correlation between the model parameters and the output and the internal interaction of the parameters by a certain method.
In this embodiment, in step S4, performing parameter optimization on the LSTM network algorithm by using an improved intelligent optimization algorithm specifically includes:
s401, setting basic parameters of bat population including total number m and species of bats in the populationDimension d of the group, maximum value f of the pulse transmission frequency max Minimum value f min Emissivity of pulse wave r i Pulse rate increase and decrease coefficient gamma and loudness A i Loudness reduction coefficient alpha and maximum number of iterations N max ;
S402, setting speed and position coordinates of the bat individual, including the position x of the bat individual i (h, η, n) and the flying velocity v i And the frequency f of the transmission of the pulses i (ii) a Wherein h is the number of hidden layer neurons, η is the learning rate of the LSTM, and n is the iteration number when the LSTM loss function meets the requirement;
s403, correcting the position and flight speed of the bat individual;
s404, checking the random number rand obtained by random flight, when rand is more than r i Then, acquiring a new solution by performing non-directional disturbance on the position of the current optimal solution;
s405, in the process of optimizing the LSTM by the bat algorithm, the root mean square error is adopted as a fitness function, and the more reasonable fitness function is selected to directly influence the prediction precision of the optimized model;
s406, checking the acquired random number and the new solution acquired in the S403, if the condition rand < A is met i And f (x) i )<f(x * ) Said f (x) i ) To be at position x i The pulse transmission frequency of (3); f (x) * ) To correct the optimal position x * The pulse transmission frequency of (2). x is a radical of a fluorine atom * The optimal position is calculated after all bat positions are compared; the selection acceptance obtains a new solution, and at the same time r is increased i A is decreased by i A value of (d);
s407, comparing the obtained new solution with the global optimal solution, and if the new solution is better than the global optimal solution, correcting the optimal solution and the optimal position of the bat individual;
s408, judging whether the iteration number meets the requirement of the maximum iteration number, if not, searching a new solution in the neighborhood of the current optimal solution by adopting a gradient descent method, and when the position of the new solution is better than that of the current optimal solution, replacing the optimal solution with a newly calculated solution, otherwise, keeping the optimal solution unchanged, and turning to S402 to be repeatedly executed;
and S409, if the iteration times are met, outputting the found optimal solution, namely obtaining the optimal solution of the number of hidden layer neurons, the LSTM learning rate and the iteration times.
It should be noted that, when the LSTM is used to evaluate the heating demand load, the following problems exist: firstly, determining the number of hidden layer neurons; secondly, determining the LSTM learning rate; and thirdly, determining the iteration number. The number of hidden layer neurons can influence the fitting effect of the whole LSTM model on heat supply demand load, too few can cause poor fitting effect, and too much can influence the prediction efficiency and the training and learning speed; the learning rate and the iteration number can affect the learning rate and the final prediction effect of the model. The optimal solution is difficult to obtain by subjectively selecting the model parameters, and the subjective trial method takes much time, so that the optimal solution of the LSTM model parameters is found by adopting an improved bat algorithm.
The improved bat algorithm is based on the bat algorithm, and takes the gradient descent algorithm as noise, so that the search speed of the optimal solution of the bat algorithm in the region range is increased, and the probability of the bat algorithm falling into the extreme value in the region range is reduced. The improved bat algorithm can be regarded as a combination of the bat algorithm in a global optimal solution search and a gradient descent algorithm in a neighborhood search, each pair of global optimal solutions is searched once, so that the positions of all bat individuals in the population are updated once, and after the update is completed once, a descent gradient method is adopted to calculate a new position x, x * =x * -μf′(x * ),f′(x * ) Is the derivative of the objective function at the current optimal position, mu is the correction coefficient of the gradient descent algorithm, if the new position is the optimal solution, the new solution is retained, otherwise the original optimal solution is retained.
In this embodiment, in S403, the calculation formula for correcting the position and the flight speed of the individual bats is expressed as:
f i =f min +(f max -f min )β;
wherein, beta is ∈ [0,1]]Satisfying uniform distribution, x * Is the calculated optimal position after comparing all bat positions. Maximum value f of pulse transmission frequency max Minimum value f min And the frequency f of the transmission of the pulses i ; The flight speeds at the time t and the time t +1 respectively;the time t and the time t +1 are the positions, respectively.
Preferably, in step S406, r is increased i A is decreased by i The values of (a) are specifically:
the bat can continuously adjust the loudness of sound waves and the emissivity of pulse waves according to the direction of prey to improve the predation efficiency; the acoustic loudness and pulse wave emissivity of bats are calculated as:
is the initial pulse wave emissivity of the bat;the pulse wave emissivity of the bat at the time t is shown;the sound wave loudness of the bat at the time t and the time t +1 are respectively.
In this embodiment, in step S5, a heat supply demand load assessment model is constructed based on the optimized LSTM network algorithm, and the load demand of the heat supply system is assessed, which specifically includes:
collecting historical data of relevant important influence factors of a heat supply system as sample data, and carrying out data preprocessing on the sample data;
dividing the preprocessed data into a training set and a test set according to a preset proportion;
inputting data of a training set into the LSTM network algorithm after parameter optimization for training, generating a heat supply demand load evaluation model, and evaluating the trained model on a test set;
and inputting the data to be evaluated into the trained heat supply demand load evaluation model to obtain a heat supply demand load evaluation value.
In this embodiment, the preprocessing sample data includes:
removing abnormal values of the data by adopting a 3 sigma principle of a Lauda criterion;
filling the data with a vacancy value by adopting one of an averaging method, a previous moment value method, an accumulated value method and a similarity calculation method;
and (4) normalizing the data by adopting a data normalization method.
In this embodiment, after obtaining the estimated value of the heating demand load, the method further includes: measuring the fitting degree of the evaluation value and the true value by using the performance evaluation index; the performance evaluation indexes comprise mean square error MSE, mean square error RMSE, mean absolute error MAE and mean relative error MAPE.
In one embodiment of the present invention, as shown in fig. 2, this embodiment 2 proposes a heating demand load evaluation system based on room temperature and IBA-LSTM, the heating demand load evaluation system including:
a room temperature measuring point setting module: the system comprises a plurality of indoor temperature measuring points, a plurality of indoor temperature measuring points and a plurality of indoor temperature measuring values, wherein the indoor temperature measuring points are used for setting a plurality of indoor temperature measuring points for different heat users in a heating system and acquiring the indoor temperature measuring values at a plurality of moments in a preset period;
a measuring point weight calculating module: the indoor temperature measuring points are used for assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating indoor temperature fusion values of the indoor temperature measuring points;
a sensitivity analysis module: the method is used for analyzing various influence factors influencing the heat supply demand load evaluation by adopting a sensitivity analysis method and screening out important influence factors;
LSTM algorithm optimization module: the LSTM network optimization method is used for optimizing parameters of an LSTM network algorithm by adopting an improved intelligent optimization algorithm;
an evaluation model construction module: the method is used for constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm and evaluating the load demand of the heat supply system.
In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. The system embodiments described above are merely illustrative, and the flowcharts and block diagrams in the figures, for example, illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. A heating demand load assessment method based on room temperature and IBA-LSTM is characterized by comprising the following steps:
s1, setting a plurality of indoor temperature measuring points for different heat users in the heating system, and acquiring indoor temperature measuring values at a plurality of moments in a preset period;
step S2, assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating an indoor temperature fusion value of each indoor temperature measuring point;
s3, analyzing various influence factors influencing heat supply demand load evaluation by adopting a sensitivity analysis method, and screening out important influence factors;
s4, optimizing parameters of the LSTM network algorithm by adopting an improved intelligent optimization algorithm;
and S5, constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm, and evaluating the load demand of the heat supply system.
2. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 1, wherein said step S1 includes:
setting the measuring point position of each layer of users according to the area, the orientation and the layout of each layer of user house type and the position relation of the wall surface and the window;
a plurality of indoor temperature measuring points are arranged in rooms of a bottom layer user, a top layer user and a middle layer user of one unit.
3. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 1, wherein said step S2 includes:
acquiring historical heat supply load data and a preset heat supply indoor temperature target value, and performing heat supply analysis on a heat user by using an AHP (analytic hierarchy process) analysis method to obtain a weight coefficient of each indoor temperature monitoring point;
calculating an indoor temperature fusion value according to the indoor temperature measurement value of each indoor temperature monitoring point and the corresponding weight coefficient, wherein the calculation formula is as follows:
n is the number of indoor temperature monitoring points;wherein i is 1,2,3, …, and n is the thindoor temperature measurement values of i indoor temperature monitoring points at the time k; c. C i Wherein i is 1,2,3, …, n, c 1 +c 2 +c 3 +…+c n 1 is the weight coefficient of each indoor temperature monitoring point;
the weight coefficient calculation formula is expressed as:
4. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 1, wherein said step S3 includes:
setting an output function Y (f) (x) of the heat supply demand load evaluation model 1 ,x 2 ,…,x z ) Comprising z influencing parameters; the parameter influencing factors include: indoor temperature, heat supply historical parameters, building thermal characteristic parameters, meteorological parameters and social parameters;
the heat supply historical parameters comprise return water temperature, flow, pressure and heat supply load;
the building thermal characteristic parameters include type, age, geographic location and orientation of the building;
the meteorological parameters comprise outdoor temperature, wind speed and solar radiation; social parameters include holidays and holidays;
and mapping the value range of each parameter to [0,1] according to the probability distribution obeyed by each parameter, discretizing the parameter by a preset sampling level p, and randomly sampling each parameter once on p sampling levels to generate a vector X.
5. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 4, wherein said screening out important influencing factors in step S3 comprises:
in the process of generating a sample, a base sample point X is generated 1 Adding disturbance variable, and sequentially generating other sample points X i After different sample points are generated, z +1 sample points are obtained, and the basic effect value of each parameter is calculated as follows:
by calculating the mean value mu of the effect value of each parameter i And standard deviation σ i Judging the importance or sensitivity of the parameters, the mean value mu i And standard deviation σ i The calculation is expressed as:
wherein d is i,e (X) is X i The e basic effect value, N is the sample capacity;
the average value represents the sensitivity of the parameters, and the larger the value is, the more important the parameters are, so as to determine the sensitivity sequence of the parameters; the standard deviation characterizes the degree of interaction between the parameters, indicating that the parameters interact strongly with other parameters if the standard deviation is large, and that the parameters interact weakly with other parameters if the standard deviation is small.
6. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 1, wherein said step S4 includes the steps of:
s401, setting basic parameters of the bat population, including the total number m of individuals of the bat population, the dimension d of the population, and the maximum value f of the pulse emission frequency max Minimum, isValue f min Emissivity of pulse wave r i Pulse rate increase and decrease coefficient gamma and loudness A i Loudness reduction factor alpha and maximum number of iterations N max ;
S402, setting speed and position coordinates of the bat individual, including the position x of the bat individual i (h, η, n) and the flying velocity v i And the frequency f of the transmission of the pulses i (ii) a h is the number of hidden layer neurons, eta is the learning rate of the LSTM, and n is the iteration frequency when the LSTM loss function meets the requirement;
s403, correcting a calculation formula of the position and the flight speed of the bat individual;
s404, checking the random number rand obtained by random flight, when rand is more than r i Then, acquiring a new solution by performing non-directional disturbance on the position of the current optimal solution;
s405, in the process of optimizing the LSTM by the bat algorithm, adopting a root mean square error as a fitness function;
s406, checking the acquired random number and the new solution acquired in the S403, if the condition rand < A is met i And f (x) i )<f(x * ) Said f (x) i ) To be at position x i The pulse transmission frequency of (3); f (x) * ) To correct the optimal position x * Pulse transmission frequency of (x) * The optimal position is calculated after all bat positions are compared; the selection acceptance obtains a new solution, and at the same time r is increased i A is decreased by i A value of (d);
s407, comparing the obtained new solution with the global optimal solution, and if the new solution is better than the global optimal solution, correcting the optimal solution and the optimal position of the bat individual;
s408, judging whether the iteration frequency meets the requirement of the maximum iteration frequency or not, if not, searching a new solution in the neighborhood of the current optimal solution by adopting a gradient descent method, and when the position of the new solution is better than that of the current optimal solution, replacing the optimal solution with a newly calculated solution; if yes, the optimal solution is unchanged, and the step is switched to S402 to be executed repeatedly;
and S409, if the iteration times are met, outputting the found optimal solution, namely obtaining the optimal solution of the number of hidden layer neurons, the LSTM learning rate and the iteration times.
7. The heating demand load assessment method based on room temperature and IBA-LSTM as set forth in claim 6, wherein in said step S403, the calculation formula of correcting the position and flight speed of the individual bats is expressed as:
f i =f min +(f max -f min )β;
β∈[0,1]satisfying uniform distribution, x * The optimal position is calculated after all bat positions are compared; maximum value f of pulse transmission frequency max Minimum value f min And the frequency f of the transmission of the pulses i ;The flight speeds at the time t and the time t +1 respectively;the time t and the time t +1 are the positions.
8. The method for assessing heating demand load based on room temperature and IBA-LSTM as claimed in claim 6, wherein in step S406, r is increased i A is decreased by i The values of (a) are specifically:
the bat can continuously adjust the loudness of sound waves and the emissivity of pulse waves according to the direction of prey to improve the predation efficiency; the acoustic loudness and pulse wave emissivity of bats are calculated as:
9. A heating demand load evaluation method according to claim 1, wherein the step S5 includes:
collecting historical data of relevant important influence factors of a heat supply system as sample data, and carrying out data preprocessing on the sample data;
dividing the preprocessed data into a training set and a test set according to a preset proportion;
inputting data of a training set into the LSTM network algorithm after parameter optimization for training, generating a heat supply demand load evaluation model, and evaluating the trained model on a test set;
and inputting the data to be evaluated into the trained heat supply demand load evaluation model to obtain a heat supply demand load evaluation value.
10. A heating demand load assessment system based on room temperature and IBA-LSTM, the heating demand load assessment system comprising:
a room temperature measuring point setting module: the system comprises a plurality of indoor temperature measuring points, a plurality of indoor temperature measuring points and a plurality of indoor temperature measuring values, wherein the indoor temperature measuring points are used for setting a plurality of indoor temperature measuring points for different heat users in a heating system and acquiring the indoor temperature measuring values at a plurality of moments in a preset period;
a measuring point weight calculating module: the indoor temperature measuring points are used for assigning different weight coefficients to a plurality of indoor temperature measuring points of different hot users, and calculating indoor temperature fusion values of the indoor temperature measuring points;
a sensitivity analysis module: the method is used for analyzing various influence factors influencing the heat supply demand load evaluation by adopting a sensitivity analysis method and screening out important influence factors;
LSTM algorithm optimization module: the LSTM network optimization method is used for optimizing parameters of an LSTM network algorithm by adopting an improved intelligent optimization algorithm;
an evaluation model construction module: the method is used for constructing a heat supply demand load evaluation model based on the optimized LSTM network algorithm and evaluating the load demand of the heat supply system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210567906.6A CN114881506A (en) | 2022-05-24 | 2022-05-24 | Heat supply demand load assessment method and system based on room temperature and IBA-LSTM |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210567906.6A CN114881506A (en) | 2022-05-24 | 2022-05-24 | Heat supply demand load assessment method and system based on room temperature and IBA-LSTM |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114881506A true CN114881506A (en) | 2022-08-09 |
Family
ID=82678524
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210567906.6A Pending CN114881506A (en) | 2022-05-24 | 2022-05-24 | Heat supply demand load assessment method and system based on room temperature and IBA-LSTM |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114881506A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117078047A (en) * | 2023-10-16 | 2023-11-17 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106096781A (en) * | 2016-06-07 | 2016-11-09 | 哈尔滨工业大学 | Heating demand forecasting procedure based on integrated temperature |
CN107390521A (en) * | 2017-06-27 | 2017-11-24 | 西安建筑科技大学 | The method and test platform that a kind of optimal measuring point of air-conditioning system indoor temperature is asked for |
CN108240679A (en) * | 2018-02-22 | 2018-07-03 | 烟台科创捷能机电工程有限公司 | A kind of heat supply method based on building heating load prediction, device and system |
KR20180121213A (en) * | 2017-04-28 | 2018-11-07 | (주)가교테크 | Building control apparatus based on load prediction based on building energy efficiency rating |
CN109376961A (en) * | 2018-12-06 | 2019-02-22 | 国网河北能源技术服务有限公司 | A kind of heating load prediction technique and system |
CN110738380A (en) * | 2018-07-18 | 2020-01-31 | 浙江盾安节能科技有限公司 | Thermal load control method, device and system |
CN110991749A (en) * | 2019-12-06 | 2020-04-10 | 国网冀北电力有限公司电力科学研究院 | Heat supply load prediction method and device |
CN111473407A (en) * | 2020-04-10 | 2020-07-31 | 浙江大学 | Model-based centralized heating system on-demand accurate regulation and control method |
CN112128841A (en) * | 2020-09-29 | 2020-12-25 | 河北工业大学 | Whole-network balance adjusting method based on load prediction and room temperature feedback correction |
CN114239991A (en) * | 2021-12-24 | 2022-03-25 | 西安交通大学 | Building heat supply load prediction method, device and equipment based on data driving |
-
2022
- 2022-05-24 CN CN202210567906.6A patent/CN114881506A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106096781A (en) * | 2016-06-07 | 2016-11-09 | 哈尔滨工业大学 | Heating demand forecasting procedure based on integrated temperature |
KR20180121213A (en) * | 2017-04-28 | 2018-11-07 | (주)가교테크 | Building control apparatus based on load prediction based on building energy efficiency rating |
CN107390521A (en) * | 2017-06-27 | 2017-11-24 | 西安建筑科技大学 | The method and test platform that a kind of optimal measuring point of air-conditioning system indoor temperature is asked for |
CN108240679A (en) * | 2018-02-22 | 2018-07-03 | 烟台科创捷能机电工程有限公司 | A kind of heat supply method based on building heating load prediction, device and system |
CN110738380A (en) * | 2018-07-18 | 2020-01-31 | 浙江盾安节能科技有限公司 | Thermal load control method, device and system |
CN109376961A (en) * | 2018-12-06 | 2019-02-22 | 国网河北能源技术服务有限公司 | A kind of heating load prediction technique and system |
CN110991749A (en) * | 2019-12-06 | 2020-04-10 | 国网冀北电力有限公司电力科学研究院 | Heat supply load prediction method and device |
CN111473407A (en) * | 2020-04-10 | 2020-07-31 | 浙江大学 | Model-based centralized heating system on-demand accurate regulation and control method |
CN112128841A (en) * | 2020-09-29 | 2020-12-25 | 河北工业大学 | Whole-network balance adjusting method based on load prediction and room temperature feedback correction |
CN114239991A (en) * | 2021-12-24 | 2022-03-25 | 西安交通大学 | Building heat supply load prediction method, device and equipment based on data driving |
Non-Patent Citations (6)
Title |
---|
JIHOON JANG等: ""Prediction of heating energy consumption with operation pattern variables for non-residential buildings using LSTM networks"", 《ENERGY & BUILDINGS》, vol. 255, 5 November 2021 (2021-11-05), pages 1 - 13 * |
候阿婷: ""空调系统数字仿真及室内温度最佳测点研究"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, no. 7, 15 July 2018 (2018-07-15), pages 038 - 717 * |
吴玉利等: ""用热影响参数对热力站日供热量预测的影响"", 《煤气与热力》, vol. 42, no. 5, 15 May 2022 (2022-05-15), pages 10 - 13 * |
李万程: ""居住建筑热负荷模型分步校准和案例研究"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, no. 6, 15 June 2020 (2020-06-15), pages 038 - 401 * |
李振虎: ""燃气锅炉运行气候补偿初步研究与应用"", 《价值工程》, vol. 37, 28 November 2018 (2018-11-28), pages 255 - 258 * |
郭锴: ""基于树模型与神经网络模型的住宅建筑供暖负荷预测的研究"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, no. 1, 15 January 2022 (2022-01-15), pages 038 - 1353 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117078047A (en) * | 2023-10-16 | 2023-11-17 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
CN117078047B (en) * | 2023-10-16 | 2024-02-23 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109858647B (en) | Regional flood disaster risk evaluation and estimation method coupled with GIS and GBDT algorithm | |
CN108320016B (en) | Short-term prediction method for building energy consumption | |
CN110110912B (en) | Photovoltaic power multi-model interval prediction method | |
Xiao et al. | Impacts of data preprocessing and selection on energy consumption prediction model of HVAC systems based on deep learning | |
CN104091216A (en) | Traffic information predication method based on fruit fly optimization least-squares support vector machine | |
CN110413657B (en) | Average response time evaluation method for seasonal non-stationary concurrency | |
Li et al. | Calibration of dynamic building energy models with multiple responses using Bayesian inference and linear regression models | |
US20180248370A1 (en) | Methods and systems for energy use normalization and forecasting | |
CN113469426A (en) | Photovoltaic output power prediction method and system based on improved BP neural network | |
CN112182720A (en) | Building energy consumption model evaluation method based on building energy management application scene | |
CN109981749A (en) | A kind of cloud workflow task running time prediction method promoted based on limit gradient | |
CN112884012A (en) | Building energy consumption prediction method based on support vector machine principle | |
CN115374995A (en) | Distributed photovoltaic and small wind power station power prediction method | |
Li et al. | A generic approach to calibrate building energy models under uncertainty using bayesian inference | |
CN111931983A (en) | Precipitation prediction method and system | |
CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
Bolbasova et al. | The application of machine learning to predictions of optical turbulence in the surface layer at Baikal Astrophysical Observatory | |
CN113762387A (en) | Data center station multi-load prediction method based on hybrid model prediction | |
CN114881506A (en) | Heat supply demand load assessment method and system based on room temperature and IBA-LSTM | |
CN114897264A (en) | Photovoltaic output interval prediction method under small sample scene based on transfer learning | |
CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
CN108256693B (en) | Photovoltaic power generation power prediction method, device and system | |
CN114578087A (en) | Wind speed uncertainty measurement method based on non-dominated sorting and random simulation algorithm | |
CN116205508A (en) | Distributed photovoltaic power generation abnormality diagnosis method and system | |
CN113177675B (en) | Air conditioner cooling load prediction method based on longicorn group algorithm optimization neural network |
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 |