CN109959122A - A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network - Google Patents
A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network Download PDFInfo
- Publication number
- CN109959122A CN109959122A CN201910178740.7A CN201910178740A CN109959122A CN 109959122 A CN109959122 A CN 109959122A CN 201910178740 A CN201910178740 A CN 201910178740A CN 109959122 A CN109959122 A CN 109959122A
- Authority
- CN
- China
- Prior art keywords
- data
- shot
- long term
- input
- neural network
- 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
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network, comprising the following steps: step 1, acquire data, the water cooled central air conditioner data for the water cooled central air conditioner project normal operation that acquisition favourable opposition energy company provides, corresponding environmental data；Step 2, to operated normally water cooled central air conditioner data, corresponding environmental data carry out data prediction；Step 3 is trained data set, realize Energy consumption forecast for air conditioning, Recognition with Recurrent Neural Network is remembered using LSTM-RNN shot and long term, using pretreated data set and corresponding power consumption as the input of LSTM-RNN shot and long term memory Recognition with Recurrent Neural Network, after carrying out network training, final prediction model is obtained；Step 4, by test data input prediction model, obtain the power consumption values under air-conditioning current working.This invention simplifies model training processes, improve predictablity rate.
Description
Technical field
The present invention relates to a kind of Energy consumption forecast for air conditioning methods based on shot and long term memory Recognition with Recurrent Neural Network.
Background technique
In China, the energy consumption of building increases year by year, has accounted for 40% of global energy requirements or so.Meanwhile air-conditioning and
Heating system accounts for about the half of building total energy consumption, and proportion is continuously increased in recent years.According to statistics, China's public building
Energy saving compliance rate is less than 10%.So doing certain adjustment for air-conditioning system, it can accomplish that the maximum of energy-saving potential excavates.It is existing
Generation building is usually combined with various technologies, accomplishes a degree of building energy saving.
Building automation system (BAS) is to be integrated with technology of Internet of things, the system of the technologies such as control technology, network technology.
It by the monitoring of various equipment Comprehensive Automations to building (group) and management, for owner and user provide safety, comfortably,
The work and living environment of convenient and efficient, and whole system and one of the various equipment is made to be in optimal working condition, thus
The economy of guarantee system operation and modernization, informationization and the intelligence of management.At the same time, in BAS system, largely
Air-conditioning data such as temperature, humidity, flow, power etc. are all recorded in the database.But these data seldom effectively by with
In air-conditioning analysis, modeling.Air-conditioning system is analyzed by mass data, is modeled, air conditioning energy consumption can be better anticipated,
Reflect air conditioning condition in building and carry out automatic management in real time, realizes automatic management and energy conservation, while improving personnel in building
Comfort.
Summary of the invention
In order to overcome the shortcomings of that air-conditioned energy consumption modeling accuracy is lower, modeling procedure is many and diverse, the present invention provides one
The higher Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network of kind accuracy.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network, comprising the following steps:
Step 1, data are acquired, are acquired in the water cooling that the water cooled central air conditioner project that favourable opposition energy company provides operates normally
Entreat air-conditioning data, corresponding environmental data；
Step 2, the pretreatment for carrying out data set, to operated normally water cooled central air conditioner data, corresponding environment
Data carry out data prediction；
Step 3 is trained data set, realizes Energy consumption forecast for air conditioning, remembers circulation mind using LSTM-RNN shot and long term
Through network, using pretreated data set and corresponding power consumption as the defeated of LSTM-RNN shot and long term memory Recognition with Recurrent Neural Network
Enter, after carrying out network training, obtains final prediction model；
Step 4, by test data input prediction model, obtain the power consumption values under air-conditioning current working.
Further, in the step 2, the realization process of the data prediction are as follows:
(2.1) for missing data, abnormal processing: if this air-conditioning data have attribute missing or abnormal, but closing on number
According to not lacking, using upper and lower mean value method, average value is calculated using upper and lower data and is filled, if this air-conditioning data have attribute to lack
It loses or abnormal, and close on data also to have more missing or exception, directly batch deletes missing data；
(2.2) for the increase of data characteristics: since flow of the people has an impact to air conditioning energy consumption, and festivals or holidays, working time
Deng having an impact to flow of the people, labeling is carried out to month, working time, the addition as characteristic.Cooling supply water temperature
Cooling tower heat-sinking capability, freezing backwater temperature difference and freezing can be intuitively embodied for the difference of water temperature difference with the difference of cooling backwater temperature
Air conditioner refrigerating ability can be intuitively embodied, therefore cooling supply backwater temperature difference, cooling two characteristic items of supply backwater temperature difference is added；
(2.3) feature selecting is carried out to the tables of data after integration: is the feelings of continuous variable for feature corresponding eigenvalue
Condition calculates pearson product away from related coefficient, filters out the feature that related coefficient is greater than 10%；For ordinal data or it is unsatisfactory for
The data at equal intervals that normal distribution is assumed calculate Spearman rank correlation coefficient, filter out the feature that related coefficient is greater than 10%；
The Pearson correlation coefficient of described two variables calculates as follows:
The Spearman related coefficient is defined as the Pearson correlation coefficient between grade variables, initial data
The descending position average in conceptual data according to it, is assigned a corresponding grade；
(2.4) all features screened are merged, and normalized, obtained eventually for trained data.
Further, in the step 2, obtain eventually for trained data are as follows:
(1) input variable: wherein the input quantity includes at least outdoor temperature, outside humidity, cooling supply water temperature, cooling
Supply water temperature, freezing supply water temperature, freezing return water temperature, general pipeline flow, month label and time tag；
(2) predictive variable: predictive variable is the air conditioning energy consumption under current working；
(3) data normalization: the sample data of input variable is normalized by following formula
Wherein x' is the data after normalization, and x is input data, and μ is the mean value of data, and σ is the standard deviation of data.
Further, in the step 3, LSTM-RNN shot and long term remembers Recognition with Recurrent Neural Network prediction model network structure such as
Under:
(1) Timesteps:Timesteps, that is, time step indicates the parameter of memory historical information length, value in RNN
The length of time series that RNN can be utilized is represented, due to needing the model with more versatility, directly adopt Timesteps is
1；
(2) activation primitive: selecting tanh as activation primitive in RNN, it can the continuous real value of input " compressed " to-
Between 1 and 1, if it is very big negative, then output is exactly -1；If it is very big positive number, output is exactly 1；
(3) neuron selects: shot and long term memory (long-short term memory, LSTM) network is one in RNN
The specific neuron of kind, controls retaining for information in hidden layer by the structure of 3 doors, can filter out weight in information flow
To keep result more accurate with unessential information；
(4) loss function: being modified mean square error (mean squared error, MSE), when calculating predicted value
predictedtWith actual value observertDifference square after, then divided by actual value observert, obtain square-error for reality
The ratio of actual value, then be averaged；
(5) other parameters: the hidden layer that model uses 10 layers of LSTM node to constitute, every layer has 50 nodes；Adaptive ladder
Descent method is spent, exercise wheel number is 5000 wheels.Batch_size is 30, learning rate 0.00005.
Technical concept of the invention are as follows: in the part air-conditioning project data that favourable opposition energy science and technology company provides, and the external world
On the basis of environmental data, certain data prediction is carried out, Feature Selection obtains more higher with the air conditioning energy consumption degree of association
Characteristic is trained characteristic and energy consumption data by specific algorithm, generates energy consumption prediction model, further according to
Air-conditioning data and environmental data data, and predicted using the model, obtain the air conditioning energy consumption under current working.
Beneficial effects of the present invention are mainly manifested in: when handling air-conditioning data, in statistics
The methods of related coefficient excludes some extraneous features, and increases some correlated characteristics according to information such as times；On this basis, make
With LSTM-RNN come training pattern, model training process is simplified to a certain extent, improves predictablity rate.
Detailed description of the invention
Fig. 1 is the flow chart of the Energy consumption forecast for air conditioning method of the present invention that Recognition with Recurrent Neural Network is remembered based on shot and long term；
Fig. 2 is LSTM-RNN basic block diagram belonging to the present invention；
Fig. 3 is LSTM unit basic block diagram.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
Referring to Fig.1, Fig. 2, Fig. 3, a kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network are described
Method the following steps are included:
Step 1, data are acquired, are acquired in the water cooling that the water cooled central air conditioner project that favourable opposition energy company provides operates normally
Entreat air-conditioning data, corresponding environmental data；
Table 1 is the description to data set, and table 2 is description of the project 7 to air-conditioning data and environmental data:
Table 1
Table 2
Step 2, the pretreatment for carrying out data set, to operated normally water cooled central air conditioner data, corresponding environment
Data carry out data prediction；
The realization process of the data prediction are as follows:
(2.1) for missing data, abnormal processing: table 3 is 7 part air-conditioning of project and external environment data sample.
It can be seen that the second data, in addition to the date, remaining is null value.60% or more information of this shortage of data, can by it
It deletes, since item is complete above and below its data, and gap is little, and mean value method up and down also can be used, be filled to data；
Table 3
(2.2) for the increase of data characteristics: since flow of the people has an impact to air conditioning energy consumption, and festivals or holidays, working time
Deng having an impact to flow of the people, labeling is carried out to month, working time, the addition as characteristic.Cooling supply water temperature
Cooling tower heat-sinking capability, freezing backwater temperature difference and freezing can be intuitively embodied for the difference of water temperature difference with the difference of cooling backwater temperature
Air conditioner refrigerating ability can be intuitively embodied, therefore cooling supply backwater temperature difference, cooling two characteristic items of supply backwater temperature difference is added；Table 4 is
Project 7 increases attribute description.
Table 4
(2.3) feature selecting is carried out to the tables of data after integration: is the feelings of continuous variable for feature corresponding eigenvalue
Condition calculates pearson product away from related coefficient, filters out the feature that related coefficient is greater than 10%；For ordinal data or it is unsatisfactory for
The data at equal intervals that normal distribution is assumed calculate Spearman rank correlation coefficient, filter out the feature that related coefficient is greater than 10%；
The Pearson correlation coefficient of described two variables calculates as follows:
The Spearman related coefficient is defined as the Pearson correlation coefficient between grade variables.Initial data
The descending position average in conceptual data according to it, is assigned a corresponding grade.Table 5 is each feature and air-conditioning function
The Pearson correlation coefficient of consumption.
| Outdoor temperature | 0.789 |
| Outside humidity | -0.523 |
| General pipeline flow | 0.551 |
| Freeze supply water temperature | -0.204 |
| Freeze return water temperature | 0.158 |
| Freeze supply backwater temperature difference | 0.652 |
| Cooling supply water temperature | 0.702 |
| Cooling backwater temperature | 0.234 |
| Cooling supply backwater temperature difference | 0.292 |
| Month label | 0.737 |
| Time tag | 0.294 |
Table 5
(2.4) all features screened are merged, and normalized, obtained eventually for trained data.
Due to freezing supply water temperature, freezing return water temperature, freezing supply backwater temperature difference, and it is cooling supply water temperature, cooling backwater temperature, cold
But three features of supply backwater temperature difference can select Pearson correlation coefficient maximum two two-by-two in conjunction with obtaining third feature
Feature.
(1) input variable: wherein the input quantity includes at least outdoor temperature, outside humidity, cooling supply water temperature, cooling
Return water temperature, freezing supply water temperature, freezing return water temperature, general pipeline flow, month label and time tag；
(2) predictive variable: predictive variable is the air conditioning energy consumption under current working；
(3) data normalization: the sample data of input variable is normalized by following formula
Wherein x' is the data after normalization, and x is input data, and μ is the mean value of data, and σ is the standard deviation of data.
Step 3 is trained data set, realizes Energy consumption forecast for air conditioning, remembers circulation mind using LSTM-RNN shot and long term
Through network, using pretreated data set and corresponding power consumption as the defeated of LSTM-RNN shot and long term memory Recognition with Recurrent Neural Network
Enter, after carrying out network training, obtains final prediction model；LSTM-RNN shot and long term remembers Recognition with Recurrent Neural Network prediction model net
Network parameter is as follows:
(1) Timesteps:Timesteps, that is, time step indicates the parameter of memory historical information length, value in RNN
The length of time series that RNN can be utilized is represented, due to needing the model with more versatility, directlying adopt Timesteps is
1；
(2) activation primitive: selecting tanh as activation primitive in RNN, it can the continuous real value of input " compressed " to-
Between 1 and 1, particularly, if it is very big negative, then output is exactly -1；If it is very big positive number, output is exactly
1；
(3) neuron selects: shot and long term memory (long-short term memory, LSTM) network is one in RNN
The specific neuron of kind, controls retaining for information in hidden layer by the structure of 3 doors, can filter out weight in information flow
To keep result more accurate with unessential information.As shown in figure 3, LSTM cellular construction is as follows:
It in time t, inputs as Xt, the preceding input of hidden layer is ht-1 generation, may be not too important in table last data
Information, the preceding input of unit are that Ct-1 represents possible important information in last data.These three inputs pass through input gate
It, the processing for forgeing door ft and out gate ot, form unit output state Ct, and hidden layer exports ht and final output Yt.
Input gate:
Forget door:
Out gate:
Unit input:
Unit output:
Hidden layer output:
ht=ot*tanh(Ct)
WhereinBy xtIt is connected to the weight matrix of three doors and unit input,It is by ht-1It is connected to the weight matrix of three doors and the input of unit unit, bi, bf, bi, bCIt is three
The shift term of door and unit input, σ represent sigmoid functionTanh is exactly hyperbolic tangent function
(4) loss function: mean square error (mean squared error, MSE) is modified.When calculating predicted value
predictedtWith actual value observertDifference square after, then divided by actual value observert, obtain square-error for reality
The ratio of actual value, then be averaged so that model suitably focuses on the adjustment of big error rate data, and can be very good to exclude from
The interference of group's point, some particular values can also be looked after, and obtained result is average, can more preferably accomplish universality.
(5) other parameters: the hidden layer that model uses 10 layers of LSTM node to constitute, every layer has 50 nodes, adaptive ladder
Descent method is spent, exercise wheel number is 5000 wheels, batch_size 30, learning rate 0.00005.
Step 4, by test data input prediction model, obtain the power consumption values under air-conditioning current working.Table 6 is of the invention
Trained and test result:
| Data set | Training set error rate | Test set error rate |
| Project 7 | 0.00852 | 0.01103 |
| Project 8 | 0.00892 | 0.01633 |
| Project 9 | 0.00824 | 0.01386 |
Table 6
For the final evaluation criterion that the present invention uses for mean error ME (Mean Error), formula is as follows:
Mean error refers in equal precision measurement, the arithmetic mean of instantaneous value of the random error of measured all measured values.
Claims (5)
1. a kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network, which is characterized in that the method packet
Include following steps:
Step 1, data, the water cooling central hollow that the water cooled central air conditioner project that acquisition favourable opposition energy company provides operates normally are acquired
Adjusting data, corresponding environmental data；
Step 2, the pretreatment for carrying out data set, to operated normally water cooled central air conditioner data, corresponding environmental data
Carry out data prediction；
Step 3 is trained data set, realizes Energy consumption forecast for air conditioning, remembers circulation nerve net using LSTM-RNN shot and long term
Network remembers the input of Recognition with Recurrent Neural Network using pretreated data set and corresponding power consumption as LSTM-RNN shot and long term, into
After row network training, final prediction model is obtained；
Step 4, by test data input prediction model, obtain the power consumption values under air-conditioning current working.
2. a kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network according to claim 1,
It is characterized in that: in the step 2, the realization process of the data prediction are as follows:
(2.1) for missing data, abnormal processing: if this air-conditioning data have attribute missing or abnormal, but closing on data not
Missing is calculated average value using upper and lower data and is filled using upper and lower mean value method, if this air-conditioning data have attribute lack or
It is abnormal, and close on data also and have more missing or exception, directly batch deletes missing data；
(2.2) for the increase of data characteristics: since flow of the people has an impact to air conditioning energy consumption, and festivals or holidays, working time etc. pair
Flow of the people has an impact, and carries out labeling to month, working time, as the addition of characteristic, cooling supply water temperature and cold
But it is straight for the difference energy of water temperature difference intuitively to embody cooling tower heat-sinking capability, freezing backwater temperature difference and freezing for the difference of return water temperature
Sight embodies air conditioner refrigerating ability, therefore cooling supply backwater temperature difference, cooling two characteristic items of supply backwater temperature difference is added；
(2.3) to after integration tables of data carry out feature selecting: for feature corresponding eigenvalue be continuous variable the case where, meter
Pearson product is calculated away from related coefficient, filters out the feature that related coefficient is greater than 10%；For ordinal data or it is unsatisfactory for normal state point
The data at equal intervals that cloth is assumed calculate Spearman rank correlation coefficient, filter out the feature that related coefficient is greater than 10%；
(2.4) all features screened are merged, and normalized, obtained eventually for trained data.
3. a kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network according to claim 2,
It is characterized in that: obtained eventually for trained data in the step 2 are as follows:
(1) input variable: wherein the input quantity includes at least outdoor temperature, outside humidity, cooling supply water temperature, cooling backwater
Temperature, freezing supply water temperature, freezing return water temperature, general pipeline flow, month label and time tag；
(2) predictive variable: predictive variable is the air conditioning energy consumption under current working；
(3) data normalization: the sample data of input variable is normalized by following formula
Wherein x' is the data after normalization, and x is input data, and μ is the mean value of data, and σ is the standard deviation of data.
4. a kind of Energy consumption forecast for air conditioning based on shot and long term memory Recognition with Recurrent Neural Network described according to claim 1~one of 3
Method, it is characterised in that: in the step 3, LSTM-RNN shot and long term remembers Recognition with Recurrent Neural Network prediction model network structure such as
Under:
(1) input layer: first converting a two-dimensional array for the air-conditioning data of input, and abscissa is to have number of data n altogether, indulges and sits
The data attribute attribute input_size for being designated as input enters back into activation primitive tanh by a weight and bigoted conversion,
A three-dimensional array is converted by data again, as the input for entering hidden layer, x coordinate is to train batch number into this
Batch_size, y-coordinate are the number of data of a batch, that is, the primary data bulk into rnn training, z coordinate are
Cell_size hides layer unit number；
(2) hidden layer: the data that will be handled well, and the hiding layer state input lstm unit that last time rnn is obtained, if first
Secondary training, then hidden layer state initialization be 0, by input gate, forget door, out gate, obtain hidden layer output data and
Hiding layer state at this time；
(3) output layer: the output that hidden layer is obtained carries out redeformation, and passes through output layer weight and bigoted conversion, obtains
The air-conditioning power consumption finally entered；
(4) other: in the backpropagation of period, weight, adjustment that is bigoted, hiding layer state are all come by loss loss function true
It is fixed, pass through construction loss function and carry out gradient decline processing, parameters are corrected in backpropagation.
5. a kind of Energy consumption forecast for air conditioning based on shot and long term memory Recognition with Recurrent Neural Network described according to claim 1~one of 3
Method, it is characterised in that: in the step 3, it is as follows that LSTM-RNN shot and long term remembers Recognition with Recurrent Neural Network prediction model parameters:
(1) Timesteps: its value represents the length of time series that RNN can be utilized, and is typically set to a cycle or half week
Phase since data set is random ordering, and needs the model with more versatility, and directlying adopt timesteps is 1；
(2) activation primitive: selecting tanh as activation primitive in RNN, it can be the continuous real value of input " compressed " to -1 and 1
Between, if it is very big negative, then output is exactly -1；If it is very big positive number, output is exactly 1；
(3) neuron selects: shot and long term memory LSTM network is the specific neuron of one of RNN, in hidden layer, by defeated
Introduction, forget door, and the structure of out gate controls retaining for information, can filter out in information flow for result it is important with
Unessential information；
(4) loss function: being modified mean square error MSE, as calculating predicted value predictedtAnd actual value
observertDifference square after, then divided by actual value observert, show that square-error for the ratio of actual value, then carries out
It is average；
(5) other parameters: the hidden layer that model uses 10 layers of LSTM node to constitute, every layer has 50 nodes, under self-adaption gradient
Drop method, exercise wheel number are 5000 wheels, batch_size 30, learning rate 0.00005.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910178740.7A CN109959122A (en) | 2019-03-11 | 2019-03-11 | A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910178740.7A CN109959122A (en) | 2019-03-11 | 2019-03-11 | A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109959122A true CN109959122A (en) | 2019-07-02 |
Family
ID=67024196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910178740.7A Pending CN109959122A (en) | 2019-03-11 | 2019-03-11 | A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109959122A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443425A (en) * | 2019-08-09 | 2019-11-12 | 长江慧控科技(武汉)有限公司 | Intelligent railway station electric energy energy consumption prediction technique based on Prophet |
| CN110762768A (en) * | 2019-10-30 | 2020-02-07 | 南京亚派软件技术有限公司 | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system |
| CN110836525A (en) * | 2019-11-19 | 2020-02-25 | 珠海格力电器股份有限公司 | Self-adaptive adjusting method and device for air conditioner running state |
| CN111209695A (en) * | 2019-12-30 | 2020-05-29 | 浙江大学 | LSTM-based structural dynamic response prediction method |
| CN111692716A (en) * | 2020-06-24 | 2020-09-22 | 珠海格力电器股份有限公司 | Air conditioner energy consumption calculation method and system and air conditioner |
| CN111797980A (en) * | 2020-07-20 | 2020-10-20 | 房健 | Self-adaptive learning method for personalized floor heating use habits |
| CN112443943A (en) * | 2019-08-30 | 2021-03-05 | 珠海格力电器股份有限公司 | Model training method based on small amount of labeled data, control system and air conditioner |
| CN112651537A (en) * | 2019-10-10 | 2021-04-13 | 国网河北省电力有限公司 | Photovoltaic power generation ultra-short term power prediction method and system |
| CN112906915A (en) * | 2021-01-22 | 2021-06-04 | 江苏安狮智能技术有限公司 | Rail transit system fault diagnosis method based on deep learning |
| CN113419902A (en) * | 2021-06-29 | 2021-09-21 | 上海大学 | Multichannel electroencephalogram signal correlation analysis and data recovery method based on long-time and short-time memory network |
| CN113432247A (en) * | 2021-05-20 | 2021-09-24 | 中南大学 | Water chilling unit energy consumption prediction method and system based on graph neural network and storage medium |
| CN113654200A (en) * | 2021-07-29 | 2021-11-16 | 中国水利水电第六工程局有限公司 | Temperature control system for steel pipe production workshop |
| CN113970170A (en) * | 2020-07-24 | 2022-01-25 | 中国移动通信集团浙江有限公司 | Central air-conditioning system energy consumption prediction method and device and computing equipment |
| CN114322634A (en) * | 2021-12-29 | 2022-04-12 | 博锐尚格科技股份有限公司 | Data screening method and device for refrigerating system strategy model |
| CN116644867A (en) * | 2023-07-27 | 2023-08-25 | 梁山中维热力有限公司 | Data processing method for thermodynamic heat supply remote relation system |
| CN117346418A (en) * | 2023-12-05 | 2024-01-05 | 珠海科创储能科技有限公司 | Control method and device of water chilling unit, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| WO2017155660A1 (en) * | 2016-03-11 | 2017-09-14 | Qualcomm Incorporated | Action localization in sequential data with attention proposals from a recurrent network |
| CN109118014A (en) * | 2018-08-30 | 2019-01-01 | 浙江工业大学 | A kind of traffic flow speed prediction technique based on time recurrent neural network |
-
2019
- 2019-03-11 CN CN201910178740.7A patent/CN109959122A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017155660A1 (en) * | 2016-03-11 | 2017-09-14 | Qualcomm Incorporated | Action localization in sequential data with attention proposals from a recurrent network |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN109118014A (en) * | 2018-08-30 | 2019-01-01 | 浙江工业大学 | A kind of traffic flow speed prediction technique based on time recurrent neural network |
Non-Patent Citations (2)
| Title |
|---|
| 廖文强，王江宇等: "基于长短期记忆神经网络的暖通空调系统能耗预测", 《制冷技术》 * |
| 易丽蓉，王绍宇等: "基于多变量LSTM的工业传感器时序数据预测", 《智能计算机与应用》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443425A (en) * | 2019-08-09 | 2019-11-12 | 长江慧控科技(武汉)有限公司 | Intelligent railway station electric energy energy consumption prediction technique based on Prophet |
| CN112443943A (en) * | 2019-08-30 | 2021-03-05 | 珠海格力电器股份有限公司 | Model training method based on small amount of labeled data, control system and air conditioner |
| CN112651537A (en) * | 2019-10-10 | 2021-04-13 | 国网河北省电力有限公司 | Photovoltaic power generation ultra-short term power prediction method and system |
| CN110762768A (en) * | 2019-10-30 | 2020-02-07 | 南京亚派软件技术有限公司 | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system |
| CN110836525A (en) * | 2019-11-19 | 2020-02-25 | 珠海格力电器股份有限公司 | Self-adaptive adjusting method and device for air conditioner running state |
| CN111209695A (en) * | 2019-12-30 | 2020-05-29 | 浙江大学 | LSTM-based structural dynamic response prediction method |
| CN111692716A (en) * | 2020-06-24 | 2020-09-22 | 珠海格力电器股份有限公司 | Air conditioner energy consumption calculation method and system and air conditioner |
| CN111797980A (en) * | 2020-07-20 | 2020-10-20 | 房健 | Self-adaptive learning method for personalized floor heating use habits |
| CN113970170A (en) * | 2020-07-24 | 2022-01-25 | 中国移动通信集团浙江有限公司 | Central air-conditioning system energy consumption prediction method and device and computing equipment |
| CN112906915A (en) * | 2021-01-22 | 2021-06-04 | 江苏安狮智能技术有限公司 | Rail transit system fault diagnosis method based on deep learning |
| CN112906915B (en) * | 2021-01-22 | 2024-03-22 | 江苏安狮智能技术有限公司 | Rail transit system fault diagnosis method based on deep learning |
| CN113432247A (en) * | 2021-05-20 | 2021-09-24 | 中南大学 | Water chilling unit energy consumption prediction method and system based on graph neural network and storage medium |
| CN113432247B (en) * | 2021-05-20 | 2022-04-26 | 中南大学 | Water chilling unit energy consumption prediction method and system based on graph neural network and storage medium |
| CN113419902A (en) * | 2021-06-29 | 2021-09-21 | 上海大学 | Multichannel electroencephalogram signal correlation analysis and data recovery method based on long-time and short-time memory network |
| CN113654200A (en) * | 2021-07-29 | 2021-11-16 | 中国水利水电第六工程局有限公司 | Temperature control system for steel pipe production workshop |
| CN114322634A (en) * | 2021-12-29 | 2022-04-12 | 博锐尚格科技股份有限公司 | Data screening method and device for refrigerating system strategy model |
| CN116644867A (en) * | 2023-07-27 | 2023-08-25 | 梁山中维热力有限公司 | Data processing method for thermodynamic heat supply remote relation system |
| CN116644867B (en) * | 2023-07-27 | 2023-10-24 | 梁山中维热力有限公司 | Data processing method for thermodynamic heat supply remote relation system |
| CN117346418A (en) * | 2023-12-05 | 2024-01-05 | 珠海科创储能科技有限公司 | Control method and device of water chilling unit, storage medium and electronic equipment |
| CN117346418B (en) * | 2023-12-05 | 2024-03-22 | 珠海科创储能科技有限公司 | Control method and device of water chilling unit, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109959122A (en) | A kind of Energy consumption forecast for air conditioning method based on shot and long term memory Recognition with Recurrent Neural Network | |
| CN109961177A (en) | A kind of general water cooled central air conditioner energy consumption prediction technique based on shot and long term memory Recognition with Recurrent Neural Network | |
| Cai et al. | Predicting the energy consumption of residential buildings for regional electricity supply-side and demand-side management | |
| CN109959123A (en) | A kind of energy-saving method for air conditioner based on genetic algorithm and shot and long term memory Recognition with Recurrent Neural Network | |
| Zhang et al. | A deep reinforcement learning approach to using whole building energy model for hvac optimal control | |
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN110392515A (en) | A kind of Cooling and Heat Source equipment room energy-conserving control method and system based on historical data | |
| CN105069525A (en) | All-weather 96-point daily load curve prediction and optimization correction system | |
| CN104484715A (en) | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method | |
| CN105320184B (en) | Building Indoor Environment intelligent monitor system | |
| CN111639823B (en) | Building cold and heat load prediction method constructed based on feature set | |
| CN108053052B (en) | A kind of oil truck oil and gas leakage speed intelligent monitor system | |
| Song et al. | An indoor temperature prediction framework based on hierarchical attention gated recurrent unit model for energy efficient buildings | |
| CN113326651A (en) | Refrigerating station load and energy efficiency ratio dynamic modeling method based on T-S fuzzy model | |
| CN112524751B (en) | Dynamic air conditioning system energy consumption prediction model construction and prediction method and device | |
| CN114200839B (en) | Intelligent office building energy consumption control model for dynamic monitoring of coupling environment behaviors | |
| CN104636800A (en) | Freezing station system neural network optimization unit based on least square weighted and method thereof | |
| CN105160441B (en) | It is transfinited the real-time electric power load forecasting method of vector regression integrated network based on increment type | |
| CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
| CN113237135B (en) | SD-LSTMs-based apartment independent heating system heat demand prediction and energy-saving control method | |
| Lei et al. | Prediction method of energy consumption for high building based on LMBP neural network | |
| CN108376294A (en) | A kind of heat load prediction method of energy supply feedback and meteorologic factor | |
| Wang et al. | Multi-criteria comprehensive study on predictive algorithm of heating energy consumption of district heating station based on timeseries processing | |
| Huang et al. | Model predictive control for energy-efficient buildings: An airport terminal building study | |
| CN112307675A (en) | Neural network-based temperature-sensitive load separation identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190702 |