CN107781948A - Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter - Google Patents
Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter Download PDFInfo
- Publication number
- CN107781948A CN107781948A CN201711052379.0A CN201711052379A CN107781948A CN 107781948 A CN107781948 A CN 107781948A CN 201711052379 A CN201711052379 A CN 201711052379A CN 107781948 A CN107781948 A CN 107781948A
- Authority
- CN
- China
- Prior art keywords
- air
- conditioning
- parameter
- time
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a kind of Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter, described method comprises the following steps:Step 1: according to operation of air conditioner situation, each time granularity air conditioner load data and air-conditioning parameter are collected;Step 2: obtaining environment temperature according to air-conditioning affiliated area, environment temperature and time relation data collection are established;Step 3: according to the data parameters collected in the step 1, with reference to the environment temperature obtained in the step 2, multivariate regression models is established;Step 4:, multivariate regression models parameter is done into outlier detection, optimizes the multivariate regression models parameter, completes the Air-conditioning Load Prediction of preset time according to weather history periodically.The present invention can concisely, effectively, fast and accurately complete Air-conditioning Load Prediction, can for energy management platform electricity consumption energy forecast with assess provide valid data support.
Description
Technical field
The present invention relates to energy services technical field, suitable for energy management platform electricity consumption energy forecast and assesses, specifically
It is related to a kind of Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter.
Background technology
As China's economy is constantly fast-developing, the tremendous expansion of urbanization, the electricity needs in China constantly rises.And
In recent ten years, air-conditioning system is popularized, and air-conditioning system not only enters huge numbers of families, it is often more important that air-conditioning system is in commercial real estate
On effect it is more very important, hence in so that air-conditioning with electric energy consumption account for whole city the ratio with electric energy consumption it is rapid on
Rise, in peak times of power consumption, the air conditioning electricity energy consumption of some large- and-medium size cities has accounted for more than the 20% of total city electric energy consumption.Remove
The energy consumption pressure that air-conditioning system is brought, while it also exacerbates day peak and low valley distribution contradiction.Especially in summer city electricity consumption
Peak period, this contradiction is more acute, because other of its peak times of power consumption load day of the air-conditioning system of high energy consumption and city are big
Equipment component day peak times of power consumption high superposed, and according to investigations, the summer power load of China's air-conditioning accounts for whole electric network peak and used
More than the 30% of electric load so that for city Peak power use load with valley power consumption load difference away from significantly expanding, power network is in serious
Uneven operation in.Although the power load of air-conditioning is concentrated mainly on summer, only hundreds of hours average annual duration,
It is that its influence to China's power grid security economical operation is very big.If it is fundamentally to solve to only rely on increase supply of electric power
Energy consumption rises and powered contradiction.
Therefore, the air-conditioning system as large electricity consumer, how intelligentized regulation air-conditioning system, effectively reduce electricity consumption height
Peak, it can not only save the substantial amounts of electricity charge while also played an important role for balancing power network load.Air conditioning energy consumption is pre-
Survey and the core that assessment is whole intelligent air-conditioning system, can in time, fast and accurately predict that air conditioner load is intelligent power
Basis.
The content of the invention
Instant invention overcomes the deficiencies in the prior art, there is provided a kind of air conditioner load based on time, temperature and air-conditioning parameter
Forecasting Methodology.Not for specific brand, model, air-conditioning parameter-refrigerant type itself, volume need to only be provided by establishing forecast model
Determine power and historical load data, with reference to affiliated ambient weather temperature history and real time data, realize Air-conditioning Load Prediction.
To solve above-mentioned technical problem, the present invention uses following technical scheme:
A kind of Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter, described method comprise the following steps:
Step 1: according to operation of air conditioner situation, each time granularity air conditioner load data and air-conditioning parameter are collected;
Step 2: obtaining environment temperature according to air-conditioning affiliated area, environment temperature and time relation data collection are established;
Step 3: according to the data parameters collected in the step 1, with reference to the environment temperature obtained in the step 2,
Establish multivariate regression models;
Step 4:, multivariate regression models parameter is done into outlier detection, optimization is described polynary according to weather history periodically
Parameters in Regression Model, complete the Air-conditioning Load Prediction of preset time.
Further technical scheme is to collect air conditioner load data according to time granularity in described step one, and granularity is extremely
Less to hour level.
Further technical scheme is that described air-conditioning parameter includes:Refrigerant type, determine frequency frequency conversion and/or refrigeration
Amount.
Further technical scheme is that described refrigerant type includes:R22, R410 or R32 type.
Further technical scheme is that described step two includes:The environment temperature of air-conditioning equipment region is obtained,
And environment temperature establishes corresponding relation with the time, and granularity is at least to hour level.
Further technical scheme is in described step three, and establishing multivariate regression models is:αXRefrigerant type+βXEnvironment temperature+
γXRefrigerating capacity+δXFixed/frequency conversion=YLoad, according to the data collected in step 1 and step 2, complete model training.
Further technical scheme is that multivariate regression models parameter is done into outlier detection in described step four is logical
Cross K-means algorithms and remove outlier, further convergence, the degree of accuracy of lift scheme prediction.
Compared with prior art, one of beneficial effect of the embodiment of the present invention is:The present invention can concisely, effectively, quickly,
Air-conditioning Load Prediction is accurately completed, valid data support can be provided with assessing for energy management platform electricity consumption energy forecast.
Brief description of the drawings
Fig. 1 is the method flow diagram of one embodiment of the invention.
Embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine in any way.
Any feature disclosed in this specification (including any accessory claim, summary and accompanying drawing), except non-specifically chatting
State, can alternative features equivalent by other or with similar purpose replaced.I.e., unless specifically stated otherwise, each feature
It is an example in a series of equivalent or similar characteristics.
Below in conjunction with the accompanying drawings and the embodiment of the present invention is described in detail embodiment.
In the following detailed description, many specific descriptions are described for illustrative purposes so as to thoroughly understand institute
Disclosed embodiment, it is clear, however, that one or more embodiments can be in the case of without using these specific descriptions
Implement, in other instances, known structure and device are schematically shown, to simplify accompanying drawing.
As shown in figure 1, according to one embodiment of present invention, the present embodiment discloses one kind and is based on time, temperature and air-conditioning
The Air-conditioning Load Prediction method of parameter, not for specific brand, model, establish forecast model need to only provide air-conditioning parameter itself-
Refrigerant type, rated power and historical load data are simple with reference to affiliated ambient weather temperature history and real time data, model
It is easily achieved, predictablity rate is high.Specifically, the method for the present embodiment comprises the following steps:
Step (1), according to operation of air conditioner situation, each time granularity air conditioner load data are collected, granularity is at least to hour
Level, in other words, each air-conditioning has a load record in each hour.Collect air-conditioning parameter record, including following basic letter
Breath:Cryogen type, determine frequency frequency conversion, refrigerating capacity, wherein refrigerant (refrigerant) type includes:The polytypes such as R22/R410/R32.
Step (2), environment temperature is obtained according to affiliated area, establishes environment temperature and time relation data collection, granularity is extremely
Less to hour level.
Step (3), according to the design parameter collected in step (1), the environment temperature obtained with reference to step (2), based on more
Partial Linear Models training load forecast model, training pattern reference record is put in storage;Period dimension is introduced, during the history same period
Between in section, model parameter fluctuation has certain threshold value, and by checking outlier, screening removes outlier, training result collection is carried out
Convergence, Storage Estimation model parameter.Specifically, the multi-parameter regression model training load forecast model is:αXRefrigerant type+β
XEnvironment temperature+γXRefrigerating capacity+δXFixed/frequency conversion=YLoad, according to the history air conditioner load data collected in step (1) and step (2), train back
Return model, fitting draws parameter alpha, β, γ, δ;Complete training pattern.
Step (4), according to the training pattern completed in step (3), with reference to air-conditioning parameter to be predicted and environment temperature, it will return
Return model parameter to do outlier detection, further optimize multiple regression forecasting model, it is pre- to complete following a period of time air conditioner load
Survey.
Specifically, the multivariate regression models that the present embodiment is established according to the parameter for influenceing air conditioner load, passes through K-means
Algorithm removes outlier, further convergence, the degree of accuracy of lift scheme prediction.
Method disclosed in the present embodiment can concisely, effectively, fast and accurately complete Air-conditioning Load Prediction, can be energy
Source capsule platform electricity consumption energy forecast provides valid data support with assessing.
" one embodiment " for being spoken of in this manual, " another embodiment ", " embodiment " etc., refer to combining
Specific features, structure or the feature of embodiment description are included at least one embodiment of the application generality description.
It is not necessarily to refer to same embodiment that statement of the same race, which occur, in multiple places in the description.Furthermore, it is understood that with reference to any
When individual embodiment describes a specific features, structure or feature, what is advocated is this to realize with reference to other embodiment
Feature, structure or feature are also fallen within the scope of the present invention.
Although reference be made herein to invention has been described for the multiple explanatory embodiments invented, however, it is to be understood that this
Art personnel can be designed that a lot of other modifications and embodiment, and these modifications and embodiment will fall in the application
Within disclosed spirit and spirit.More specifically, can be to theme group in the range of disclosure claim
The building block and/or layout for closing layout carry out a variety of variations and modifications.Except the modification carried out to building block and/or layout
Outer with improving, to those skilled in the art, other purposes also will be apparent.
Claims (7)
- A kind of 1. Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter, it is characterised in that:Described method includes Following steps:Step 1: according to operation of air conditioner situation, each time granularity air conditioner load data and air-conditioning parameter are collected;Step 2: obtaining environment temperature according to air-conditioning affiliated area, environment temperature and time relation data collection are established;Step 3: according to the data parameters collected in the step 1, with reference to the environment temperature obtained in the step 2, establish Multivariate regression models;Step 4:, multivariate regression models parameter is done into outlier detection, optimizes the multiple regression according to weather history periodically Model parameter, complete the Air-conditioning Load Prediction of preset time.
- 2. the Air-conditioning Load Prediction method according to claim 1 based on time, temperature and air-conditioning parameter, it is characterised in that Air conditioner load data are collected according to time granularity in described step one, granularity is at least to hour level.
- 3. the Air-conditioning Load Prediction method according to claim 1 or 2 based on time, temperature and air-conditioning parameter, its feature It is that described air-conditioning parameter includes:Refrigerant type, determine frequency frequency conversion and/or refrigerating capacity.
- 4. the Air-conditioning Load Prediction method according to claim 3 based on time, temperature and air-conditioning parameter, it is characterised in that Described refrigerant type includes:R22, R410 or R32 type.
- 5. the Air-conditioning Load Prediction method according to claim 1 based on time, temperature and air-conditioning parameter, it is characterised in that Described step two includes:Obtain the environment temperature of air-conditioning equipment region, and environment temperature pass corresponding with time foundation System, granularity is at least to hour level.
- 6. the Air-conditioning Load Prediction method according to claim 1 based on time, temperature and air-conditioning parameter, it is characterised in that In described step three, establishing multivariate regression models is:αXRefrigerant type+βXEnvironment temperature+γXRefrigerating capacity+δXFixed/frequency conversion=YLoad, according to step One and step 2 in the data collected, complete model training.
- 7. the Air-conditioning Load Prediction method according to claim 1 based on time, temperature and air-conditioning parameter, it is characterised in that It is to remove outlier by K-means algorithms that multivariate regression models parameter is done into outlier detection in described step four, enters one Step convergence, the degree of accuracy of lift scheme prediction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711052379.0A CN107781948B (en) | 2017-10-30 | 2017-10-30 | Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711052379.0A CN107781948B (en) | 2017-10-30 | 2017-10-30 | Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107781948A true CN107781948A (en) | 2018-03-09 |
CN107781948B CN107781948B (en) | 2019-11-05 |
Family
ID=61432538
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711052379.0A Active CN107781948B (en) | 2017-10-30 | 2017-10-30 | Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107781948B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109442680A (en) * | 2018-10-17 | 2019-03-08 | 广州华凌制冷设备有限公司 | Power estimating method, device and the computer readable storage medium of outdoor fan of air conditioner |
CN109654665A (en) * | 2018-12-14 | 2019-04-19 | 广东美的暖通设备有限公司 | The control method and device and air conditioner of air conditioner |
CN109740787A (en) * | 2018-11-20 | 2019-05-10 | 第四范式(北京)技术有限公司 | Training Building air conditioning load prediction model and the method and apparatus predicted with it |
CN110285532A (en) * | 2019-07-04 | 2019-09-27 | 中国工商银行股份有限公司 | Method for controlling machine room air conditioner, apparatus and system based on artificial intelligence |
CN111023400A (en) * | 2019-12-30 | 2020-04-17 | 宁波奥克斯电气股份有限公司 | Air conditioner outdoor environment temperature prediction method and device and air conditioner |
CN112747413A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Air conditioning system load prediction method and device |
CN113108432A (en) * | 2020-09-09 | 2021-07-13 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method and system based on weather forecast |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04282703A (en) * | 1991-03-12 | 1992-10-07 | Kajima Corp | Method for forecasting load of air conditioner |
JP2005226845A (en) * | 2004-02-10 | 2005-08-25 | Fuji Electric Systems Co Ltd | Air conditioning load forecasting method, device and program, and recording medium |
CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制***有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
US20140067132A1 (en) * | 2012-08-30 | 2014-03-06 | Honeywell International Inc. | Hvac controller with regression model to help reduce energy consumption |
CN104850013A (en) * | 2015-04-28 | 2015-08-19 | 南京邮电大学 | Intelligent electricity utilization method of household appliances |
CN105387565A (en) * | 2015-11-24 | 2016-03-09 | 深圳市酷开网络科技有限公司 | Temperature adjusting method and device |
CN105719028A (en) * | 2016-03-08 | 2016-06-29 | 北京工业大学 | Method for dynamic prediction of air-conditioning loads based on multi-factor chaos support vector machine |
CN106468467A (en) * | 2015-08-17 | 2017-03-01 | 同方泰德国际科技(北京)有限公司 | A kind of air-conditioning refrigeration duty real-time estimate algorithm being applied to embedded control system |
-
2017
- 2017-10-30 CN CN201711052379.0A patent/CN107781948B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04282703A (en) * | 1991-03-12 | 1992-10-07 | Kajima Corp | Method for forecasting load of air conditioner |
JP2005226845A (en) * | 2004-02-10 | 2005-08-25 | Fuji Electric Systems Co Ltd | Air conditioning load forecasting method, device and program, and recording medium |
JP4386748B2 (en) * | 2004-02-10 | 2009-12-16 | 富士電機システムズ株式会社 | Air conditioning load prediction method, air conditioning load prediction device, air conditioning load prediction program, and recording medium |
US20140067132A1 (en) * | 2012-08-30 | 2014-03-06 | Honeywell International Inc. | Hvac controller with regression model to help reduce energy consumption |
CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制***有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
CN104850013A (en) * | 2015-04-28 | 2015-08-19 | 南京邮电大学 | Intelligent electricity utilization method of household appliances |
CN106468467A (en) * | 2015-08-17 | 2017-03-01 | 同方泰德国际科技(北京)有限公司 | A kind of air-conditioning refrigeration duty real-time estimate algorithm being applied to embedded control system |
CN105387565A (en) * | 2015-11-24 | 2016-03-09 | 深圳市酷开网络科技有限公司 | Temperature adjusting method and device |
CN105719028A (en) * | 2016-03-08 | 2016-06-29 | 北京工业大学 | Method for dynamic prediction of air-conditioning loads based on multi-factor chaos support vector machine |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109442680A (en) * | 2018-10-17 | 2019-03-08 | 广州华凌制冷设备有限公司 | Power estimating method, device and the computer readable storage medium of outdoor fan of air conditioner |
CN109740787A (en) * | 2018-11-20 | 2019-05-10 | 第四范式(北京)技术有限公司 | Training Building air conditioning load prediction model and the method and apparatus predicted with it |
CN109740787B (en) * | 2018-11-20 | 2021-07-13 | 第四范式(北京)技术有限公司 | Training building air conditioner load prediction model and prediction method and device using same |
CN109654665A (en) * | 2018-12-14 | 2019-04-19 | 广东美的暖通设备有限公司 | The control method and device and air conditioner of air conditioner |
CN110285532A (en) * | 2019-07-04 | 2019-09-27 | 中国工商银行股份有限公司 | Method for controlling machine room air conditioner, apparatus and system based on artificial intelligence |
CN110285532B (en) * | 2019-07-04 | 2021-07-30 | 中国工商银行股份有限公司 | Machine room air conditioner control method, device and system based on artificial intelligence |
CN112747413A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Air conditioning system load prediction method and device |
CN112747413B (en) * | 2019-10-31 | 2022-06-21 | 北京国双科技有限公司 | Air conditioning system load prediction method and device |
CN111023400A (en) * | 2019-12-30 | 2020-04-17 | 宁波奥克斯电气股份有限公司 | Air conditioner outdoor environment temperature prediction method and device and air conditioner |
CN113108432A (en) * | 2020-09-09 | 2021-07-13 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method and system based on weather forecast |
CN113108432B (en) * | 2020-09-09 | 2022-04-15 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method and system based on weather forecast |
Also Published As
Publication number | Publication date |
---|---|
CN107781948B (en) | 2019-11-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107781948B (en) | Air-conditioning Load Prediction method based on time, temperature and air-conditioning parameter | |
CN103559655B (en) | The Forecasting Methodology of the novel feeder line load of microgrid based on data mining | |
Powell et al. | Heating, cooling, and electrical load forecasting for a large-scale district energy system | |
Oh et al. | Forecasting long-term electricity demand for cooling of Singapore’s buildings incorporating an innovative air-conditioning technology | |
CN105973626B (en) | The assessment of central air conditioner system host operational energy efficiency and prediction technique and device | |
CN113793010B (en) | Construction method for multi-load combined control strategy and air conditioner control method | |
Zhang et al. | Field testing and performance analyses of ground source heat pump systems for residential applications in Hot Summer and Cold Winter area in China | |
CN105549516A (en) | Public building energy consumption monitoring system | |
CN104123682A (en) | Distribution network fault risk assessment method based on meteorology influence factors | |
Ghajarkhosravi et al. | Energy benchmarking analysis of multi-unit residential buildings (MURBs) in Toronto, Canada | |
Mak et al. | Power consumption modeling and energy saving practices of hotel chillers | |
CN106951630A (en) | A kind of refrigeration host computer device selection method being applied in air-conditioning system | |
CN104048390A (en) | Method for diagnosing energy efficiency of air-cooled heat-pump central air-conditioning unit | |
CN109827310B (en) | Resident air conditioner load cluster die type establishing method | |
CN107590568A (en) | A kind of load forecasting method that becomes more meticulous based on space subdivision | |
CN111486552A (en) | Method for identifying water supply temperature strategy of chilled water of air conditioner based on subentry metering data | |
Yu et al. | Energy simulation of sustainable air-cooled chiller system for commercial buildings under climate change | |
CN106557843A (en) | A kind of using can needing forecasting method | |
CN104299056A (en) | Distribution network planning basic technology supporting platform | |
CN105299846B (en) | A kind of computer room group control device optimized based on global association and its control method | |
CN105373863A (en) | Firefly algorithm based method for determining position and capacity of electric automobile charging station | |
Xie et al. | Development of a group control strategy based on multi-step load forecasting and its application in hybrid ground source heat pump | |
CN113253646A (en) | Zero-energy-consumption and zero-carbon building judgment method and energy control system | |
CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
CN107133372B (en) | Mobile communication base station energy consumption benchmarking scene evaluation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |