CN116817415B - Air conditioner load management and adjustment method, computing equipment and storage medium - Google Patents
Air conditioner load management and adjustment method, computing equipment and storage medium Download PDFInfo
- Publication number
- CN116817415B CN116817415B CN202311084802.0A CN202311084802A CN116817415B CN 116817415 B CN116817415 B CN 116817415B CN 202311084802 A CN202311084802 A CN 202311084802A CN 116817415 B CN116817415 B CN 116817415B
- Authority
- CN
- China
- Prior art keywords
- data
- load
- sub
- historical
- time period
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004378 air conditioning Methods 0.000 claims abstract description 98
- 238000003062 neural network model Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 37
- 230000008859 change Effects 0.000 description 13
- 230000000694 effects Effects 0.000 description 8
- 230000005611 electricity Effects 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
-
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
- F24F11/64—Electronic processing using pre-stored data
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
-
- 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
- F24F11/88—Electrical aspects, e.g. circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an air conditioner load management and adjustment method, computing equipment and a storage medium, and relates to the technical field of power supply management, wherein the method comprises the following steps: acquiring historical air conditioner load data and historical load influence data of a public building in a preset time period; dividing the historical load influence data according to the characteristics of the historical load influence data to obtain historical load influence sub-data of a plurality of sub-time periods; in the historical air conditioner load data in a preset time period, determining historical air conditioner load sub-data of each sub-time period; according to the historical load influence sub-data of each sub-period, the historical air conditioning load sub-data of the corresponding sub-period is adjusted to obtain the historical air conditioning load basic data of each sub-period; and performing air conditioning load management on the public building according to the historical air conditioning load basic data of each sub-time period. The invention has the beneficial effects that: the precision of the public building air conditioner load management can be improved.
Description
Technical Field
The invention relates to the technical field of power supply management, in particular to an air conditioner load management and adjustment method, computing equipment and storage medium.
Background
At present, for urban public buildings, such as commercial complexes, hotels, office buildings, public institutions and the like, through full data access, the air conditioning load of the public buildings can be monitored, and further data support is provided for the subsequent enterprises, government departments and power supply companies to cooperatively regulate the air conditioning load so as to realize better power supply distribution.
In the management and adjustment of the air conditioning load, related influencing factors can be considered to estimate the future, for example, the influence of weather temperature, the operation plan of related enterprises in public buildings, the density change of super-business personnel and the like are considered, and the corresponding mathematical model is combined, so that the air conditioning loads of different public buildings in the future time period are estimated, and distribution management is realized. However, in actual situations, factors influencing the air conditioning load in a public building of a whole building or a district are various, the above-mentioned relations between the weather temperature, the operation plan, the personnel density and the like and the air conditioning load are very direct, the weather temperature can be obtained through relatively accurate prediction statistics, the operation plan, the personnel density and the like of related enterprises can be studied or estimated in advance, and other factors such as seasonal increase and decrease changes of the enterprises and the personnel, the gradually increased failure rate of equipment, the air conditioning load change caused by the old condition and the like exist on the air conditioning load, and the factors have a direct or indirect relation with the air conditioning load, have certain rules and trends, but are inconvenient to count.
Disclosure of Invention
The invention solves the problem of how to improve the accuracy of the air conditioner load management of the public building.
In order to solve the above problems, the present invention provides a method for managing and adjusting load of an air conditioner, comprising the steps of:
acquiring historical air conditioner load data and historical load influence data of a public building in a preset time period, wherein the historical load influence data comprises historical weather data in the preset time period;
dividing the historical load influence data according to the characteristics of the historical load influence data to obtain historical load influence sub-data of a plurality of sub-time periods;
determining historical air conditioner load sub-data of each sub-time period in the historical air conditioner load data in the preset time period;
according to the historical load influence sub-data of each sub-time period, the historical air conditioner load sub-data of the corresponding sub-time period is adjusted to obtain the historical air conditioner load basic data of each sub-time period;
and performing air conditioning load management on the public building according to the historical air conditioning load basic data of each sub-time period.
According to the air conditioner load management and adjustment method, after the historical load influence data are acquired, the historical load influence sub-data of a plurality of sub-time periods are obtained through division based on the characteristics of the historical load influence sub-data, the influence of the load influence factors on the air conditioner load is similar in the time periods, further, the generated load influence is eliminated from the actually acquired historical load influence sub-data of the sub-time periods, finally, the historical air conditioner load basic data of each sub-time period are obtained, the change condition of the historical air conditioner load basic data of the sub-time periods can be analyzed in the follow-up air conditioner load management of public buildings, the air conditioner load influence caused by influence factors which are difficult to count is analyzed, and on the basis, other influence factors which can be counted and collected at future time are considered, so that the future air conditioner load accurate management is realized. Therefore, compared with the existing mode of estimating the future air conditioner load by taking the historical load data as a basis and directly considering influence factors such as future weather conditions and the like by adopting a regression algorithm and the like, the method reduces the estimated error, can enable the estimation of the air conditioner load to be more accurate, and further enables the air conditioner load management to be more accurate and effective.
Further, the air conditioning load management of the public building according to the historical air conditioning load basic data of each sub-period includes the steps of:
determining first air conditioning load prediction data of a future time period according to the historical air conditioning load basic data of each sub time period;
acquiring load influence statistical data of the future time period, wherein the load influence statistical data comprises weather forecast data;
correcting the first air conditioner load prediction data according to the load influence statistical data to obtain second air conditioner load prediction data;
and carrying out air conditioning load management on the public building according to the second air conditioning load prediction data.
Further, the load influence statistical data further comprises people flow estimated data and people density estimated data; the air conditioning load management of the public building according to the historical air conditioning load basic data of each sub-time period further comprises the following steps:
determining the flow average value of all the people flow estimated data of the public building and the density average value of the people density estimated data;
determining the power supply priority of each public building according to the comparison condition of the estimated pedestrian flow data and the average flow value of each public building and the comparison condition of the estimated personnel density data and the average density value of each public building;
and carrying out air conditioning load management on the public building according to the power supply priority and the second air conditioning load prediction data.
Further, determining first air conditioning load prediction data of a future time period from the historical air conditioning load base data of each of the sub time periods includes the steps of:
establishing a trend model and/or a regression model according to each sub-time period and historical air conditioner load basic data of each sub-time period;
and determining the first air conditioner load prediction data of the future time period according to the trend model and/or the regression model.
Further, the step of adjusting the historical air conditioning load sub-data of the corresponding sub-time period according to the historical load influence sub-data of each sub-time period to obtain the historical air conditioning load basic data of each sub-time period includes the steps of:
determining a load adjustment estimated value of each sub-time period according to the historical load influence sub-data of each sub-time period and a preset neural network model;
and adjusting the historical air conditioner load sub-data according to the load adjustment pre-estimation value to obtain the historical air conditioner load basic data.
Further, the training process of the preset neural network model includes the steps of:
acquiring load influence sub-data of at least two continuous preset sub-time periods and air conditioner load actual data;
determining a difference value of the load influencing sub-data of the adjacent preset sub-time period as first difference value data, and determining a difference value of the air conditioner load actual data of the adjacent preset sub-time period as second difference value data;
and constructing a training data set according to the first difference data and the second difference data, so as to train an initial neural network model according to the training data set, and obtain the preset neural network model.
Further, the determining the load adjustment estimated value of each sub-period according to the historical load influence sub-data of each sub-period and a preset neural network model includes the steps of:
determining the difference value of the historical load influence sub-data and the calibration load influence data of each sub-time period as third difference value data;
and inputting the third difference value data of each sub-time period into the preset neural network model to obtain the load adjustment estimated value of each sub-time period.
Further, the step of acquiring the historical air conditioner load data and the historical load influence data of the public building in the preset time period comprises the following steps:
determining a main operation time period of the public building in the preset time period according to the type of the public building and/or the historical air conditioning load data;
the historical air conditioning load data and the historical load impact data of the public building during the primary operation period are determined.
The invention also provides a computing device comprising a computer readable storage medium storing a computer program and a processor, wherein the computer program is read and run by the processor to realize the air conditioner load management adjustment method.
The computing device of the present invention has similar technical effects to the above-mentioned air conditioner load management adjustment method, and will not be described in detail herein.
The invention also provides a computer readable storage medium storing a computer program which, when read and run by a processor, implements the air conditioner load management adjustment method as described above.
The computer readable storage medium of the present invention has similar technical effects to the above-mentioned air conditioner load management adjustment method, and will not be described in detail herein.
Drawings
FIG. 1 is a flowchart of a method for managing and adjusting an air conditioner load according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a method for adjusting the air conditioning load management according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for managing and adjusting an air conditioner load according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. While certain embodiments of the invention have been illustrated in the accompanying drawings, it is to be understood that the invention may be practiced in a variety of ways and should not be interpreted as limited to the embodiments set forth herein, which are instead provided to provide a more thorough and complete understanding of the invention. It should be understood that the drawings and embodiments of the invention are for illustration purposes only and are not intended to limit the scope of the present invention.
It should be understood that the various steps recited in the method embodiments of the present invention may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the invention is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "alternative embodiments". Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.
Referring to fig. 1, an embodiment of the present invention provides a method for managing and adjusting an air conditioner load, including the steps of:
and acquiring historical air conditioning load data and historical load influence data of the public building in a preset time period, wherein the historical load influence data comprises historical weather data in the preset time period.
The public building may include a commercial complex, a hotel, an office building, a public institution and the like, the preset time period may be set according to practical situations, for example, historical air conditioning load data and historical load influence data of the public building in one quarter are obtained, wherein the historical load influence data is data which is convenient for statistics or prediction, the embodiment of the invention includes historical weather data, for example, historical weather data of one quarter corresponding to the historical air conditioning load data in one quarter, and in other embodiments, the historical load influence data may further include a power failure plan, a personnel activity arrangement or a regional use arrangement which can influence the air conditioning load change and the like.
For the historical load impact data within these preset time periods, a preliminary screening may be performed based on the historical air conditioning load data and/or the type of public building. Specifically, determining a main operation time period of the public building in the preset time period according to the type of the public building and/or the historical air conditioning load data; the historical air conditioning load data and the historical load impact data of the public building during the primary operation period are determined.
For example, some public buildings have outstanding electricity utilization properties, such as office buildings, etc., usually concentrate on about 8 a.m. to about 10 a.m. for electricity utilization, and on about monday to about friday, concentrate on 5 a.m. to the market result for the market, and on weekends or on holidays, and on other time electricity utilization conditions, the air conditioning load is relatively low, so that the overall power supply effect is slightly less, and management and scheduling of the air conditioning load do not need to be considered too much. Thus, for these historical load influence data, it is possible to first screen out data of which the removed portion does not particularly influence the air conditioning load of the public building, for example, historical load influence data and historical air conditioning load data of a main period of time in the day are retained in units of days for different public buildings.
And dividing the historical load influence data according to the characteristics of the historical load influence data to obtain historical load influence sub-data of a plurality of sub-time periods.
Taking historical load influence data as historical weather data as an example, in a preset time period, various weather conditions exist, for example, in a quarter, a certain week is the day with the average temperature of 35 ℃ in the highest day, then rain water exists for about 2 days to cause a rainy day or a overcast and rainy day with the average temperature of 25 ℃ and the like, the weather conditions directly influence the air conditioner load, but similar weather characteristics have similar influence on the air conditioner load, therefore, finally, by combining the characteristics of the historical load influence data, the time period is divided to obtain a plurality of continuous sub-time periods, the load influence data in the same time period are similar, similar influence is caused on the overall load of the air conditioner, relatively obvious change of the load influence data appears in the adjacent sub-time periods, and finally, the historical air conditioner load data corresponding to the two sub-time periods may be different.
And determining the historical air conditioning load sub-data of each sub-time period in the historical air conditioning load data in the preset time period.
Based on the determined sub-time periods, which correspond to the historical air conditioning load sub-data in the sub-time periods, table lookup determination can be performed in the historical air conditioning load data in a preset time period.
According to the historical load influence sub-data of each sub-time period, the historical air conditioner load sub-data of the corresponding sub-time period is adjusted to obtain the historical air conditioner load basic data of each sub-time period;
and performing air conditioning load management on the public building according to the historical air conditioning load basic data of each sub-time period.
The historical load influence sub-data of each sub-period directly influences the air conditioning load of the corresponding sub-period, for example, the weather mutation of the sub-period causes the air conditioning load in the sub-period to be obviously increased, therefore, for the determined historical load influence sub-data, the influence value of the historical load influence sub-data on the air conditioning load can be further determined, for example, for the weather data, a model of the influence of relevant weather on the air conditioning load can be adopted to determine the increasing and decreasing influence quantity of the load under different weather conditions, and further, the actually detected historical air conditioning load sub-data is adjusted, so that the load data excluding the weather influence can be obtained. The method is characterized in that the influence of all the historical load influence data which can be accurately collected or estimated on the load is eliminated, the historical air conditioner load basic data of each sub-time period is finally obtained, the change condition of the historical air conditioner load basic data of the sub-time periods can be analyzed in the follow-up air conditioner load management of public buildings, the air conditioner load influence caused by influence factors which are difficult to count is analyzed, and on the basis, the influence data which can be counted and collected at the future time are considered, so that the accurate management of the future air conditioner load is realized. Therefore, compared with the existing mode of estimating the future air conditioner load by taking the historical load data as a basis and directly considering influence factors such as future weather conditions and the like by adopting a regression algorithm and the like, the method reduces the estimated error, can enable the estimation of the air conditioner load to be more accurate, and further enables the air conditioner load management to be more accurate and effective.
Referring to fig. 2, in an alternative embodiment of the present invention, the air conditioning load management of the public building according to the historical air conditioning load base data of each of the sub-time periods includes:
and determining first air conditioning load prediction data of a future time period according to the historical air conditioning load basic data of each sub time period.
Trend analysis or prediction may be performed based on the historical air conditioning load base data for each sub-period, for example, a trend model and/or a regression model may be established based on each of the sub-periods and the historical air conditioning load base data for each of the sub-periods.
And determining the first air conditioner load prediction data of the future time period according to the trend model and/or the regression model.
For example, using a trend model of the moving average method, a moving window of different length (e.g., 7 days, 30 days) is selected to predict the load (first air conditioning load prediction data) for a certain period of time in the future by calculating the average value of the historical air conditioning load base data for each sub-period and assuming that the future load will continue to vary along a similar trend. Alternatively, a trend model based on autoregressive integral moving average may be employed, and autoregressive, differential and moving average portions of the data are considered, so as to analyze the pattern of the historical load and make predictions of future loads. Alternatively, a regression model based on linear regression may be used, and the relationship with the load may be established by using the linear regression model in consideration of the date and time in each sub-period, and the first air conditioner load prediction data may be determined by fitting a linear function. Meanwhile, nonlinear relations among features can be considered by introducing polynomial regression and other methods. In an alternative embodiment, the trend model and the regression model may be verified and adjusted in combination with the actual situation, or the prediction of the first air conditioning load prediction data may be performed in combination with the trend model and the regression model.
Acquiring load influence statistical data of the future time period, wherein the load influence statistical data comprises weather forecast data;
correcting the first air conditioner load prediction data according to the load influence statistical data to obtain second air conditioner load prediction data;
and carrying out air conditioning load management on the public building according to the second air conditioning load prediction data.
The obtained first air conditioner load prediction data only considers the influence of the influence factors which are difficult to directly count or estimate on the load, and in future prediction, the further influence of the load influence statistical data such as weather, operation plan and the like on the actual air conditioner load is also existed, so that the first air conditioner load prediction data is further corrected in combination with the determination of the load influence statistical data of the future time period for air conditioner load management, and finally the second air conditioner load prediction data which is more fit with the actual requirement is obtained, and therefore, the air conditioner load management is carried out based on the second air conditioner load prediction data, so as to achieve the accurate and effective management requirement.
In an optional embodiment of the present invention, the load influence statistics further includes estimated traffic volume data and estimated density data; the air conditioning load management of the public building according to the historical air conditioning load basic data of each sub-time period further comprises the following steps:
determining the flow average value of all the people flow estimated data of the public building and the density average value of the people density estimated data;
determining the power supply priority of each public building according to the comparison condition of the estimated pedestrian flow data and the average flow value of each public building and the comparison condition of the estimated personnel density data and the average density value of each public building;
and carrying out air conditioning load management on the public building according to the power supply priority and the second air conditioning load prediction data.
In addition to the weather prediction data, the statistics data of the load influence and the historical load influence data which can be counted or estimated are also a direct influence factor, for example, the number of people in a public building in a time period, the personnel density and the flow rate of public buildings such as a market and the like, and besides the influence on the air conditioning load, the priority of power supply is required to be ensured for areas with more people.
Referring to fig. 3, in an alternative embodiment of the present invention, the step of adjusting the historical air conditioning load sub-data of the corresponding sub-time period according to the historical load influencing sub-data of each sub-time period to obtain the historical air conditioning load basic data of each sub-time period includes the steps of:
determining a load adjustment estimated value of each sub-time period according to the historical load influence sub-data of each sub-time period and a preset neural network model;
and adjusting the historical air conditioner load sub-data according to the load adjustment pre-estimation value to obtain the historical air conditioner load basic data.
In the embodiment of the invention, the prediction of the load data can be performed by constructing and training a preset neural network model, specifically, different historical load influence sub-data can cause similar influence on the air conditioner load, for example, the historical weather data with the average temperature of 30 degrees on a sunny day with the average temperature of 25 ℃ as a standard has a specific range increment on the air conditioner load, so when the historical load influence sub-data of each sub-time period is determined, the prediction of the load adjustment pre-estimated value of each sub-time period can be performed by combining the preset neural network model, so that the prediction is more accurate, and the difference value between the subsequent load adjustment pre-estimated value and the historical air conditioner load sub-data is the historical air conditioner load basic data of each sub-time period, thereby being used for the subsequent air conditioner load management.
In an alternative embodiment of the present invention, the training process of the preset neural network model includes the steps of:
acquiring load influence sub-data of at least two continuous preset sub-time periods and air conditioner load actual data;
determining a difference value of the load influencing sub-data of the adjacent preset sub-time period as first difference value data, and determining a difference value of the air conditioner load actual data of the adjacent preset sub-time period as second difference value data;
and constructing a training data set according to the first difference data and the second difference data, so as to train an initial neural network model according to the training data set, and obtain the preset neural network model.
The training data is built, the model output is obtained in an initial neural network model of a preset neural network model, the loss function value of the neural network model is further determined, parameters of the initial neural network model are adjusted until convergence conditions are met, training of the neural network model is completed, and then the prediction is achieved by inputting corresponding data values.
The training data of the neural network model is based on historical air conditioning load data and corresponding historical load influence data, and for a longer time span, other influence factors which are difficult to count are present to influence the air conditioning load, so that the training of the model by directly adopting the air conditioning load data and the corresponding load influence data cannot ensure higher accuracy, and therefore, in the embodiment of the invention, training is carried out by taking the load influence sub-data of two continuous preset sub-time periods and the corresponding air conditioner load actual data as the basis, for example, the data of the day of the weather change and the day immediately preceding the day of the change before the day, on which the significant weather change occurs, or the data of the day and the day immediately preceding the day on which the personal activity arrangement is generated. In this case, the collected air-conditioning load actual data is less affected by other influencing factors, that is, the load influencing sub-data of the preset sub-period directly influences the air-conditioning load actual data.
Based on the obtained load influencing sub-data of the preset sub-time period and the air conditioner load actual data, determining the difference value of the load influencing sub-data of the adjacent preset sub-time period as first difference data and determining the difference value of the air conditioner load actual data of the adjacent preset sub-time period as second difference data, so as to construct a training set of the model, and training the neural network model at the moment, so that the model can learn load changes which can be finally generated when different load influencing factors change, and finally, the model can be used for predicting load changes which can be possibly generated when the change of the load influencing factors of the future time period is determined.
The difference value of the load influencing sub-data in the adjacent preset sub-time period can be calculated according to the type of the load influencing sub-data, and the vector difference or the value difference can be a temperature difference, a flow change difference generated by the flow of people in a market and the like, and the like for the weather temperature influencing the air conditioner load. The second difference data is the difference of the air conditioner load values of two preset sub-time periods.
The specific architecture of the initial neural network model can be specifically set according to actual conditions, for example, the neural network model of the air conditioner load is set by considering weather factors, and the neural network model set by factors such as personnel activities, planning power consumption scheduling and the like can be considered.
Based on this, for the above-mentioned training-obtained preset neural network model, the determining the load adjustment estimated value of each sub-period according to the historical load influencing sub-data of each sub-period and the preset neural network model includes the steps of:
determining the difference value of the historical load influence sub-data and the calibration load influence data of each sub-time period as third difference value data;
and inputting the third difference value data of each sub-time period into the preset neural network model to obtain the load adjustment estimated value of each sub-time period.
The difference value of the calibration load influence data can be set according to actual conditions, so that the difference value can be used as a reference value, the scheme is not limited, the difference value of the historical load influence sub-data and the calibration load influence data of each sub-time period is determined, and the difference value is used as third difference value data, namely, the influence of the historical load influence sub-data on the historical air conditioner load basic data of the current sub-time period is represented. And aiming at the generated influence, inputting the trained preset neural network model, and finally outputting the preset neural network model to correspond to the air conditioner load change caused by the influence, namely, as a load adjustment predicted value of each sub-time period, so as to adjust the historical air conditioner load sub-data later to obtain the historical air conditioner load basic data of each sub-time period.
The invention also provides a computing device comprising a computer readable storage medium storing a computer program and a processor, wherein the computer program is read and run by the processor to realize the air conditioner load management adjustment method.
The computing device of the present invention has similar technical effects to the above-mentioned air conditioner load management adjustment method, and will not be described in detail herein.
A computer-readable storage medium of another embodiment of the present invention stores a computer program that, when read and executed by a processor, implements the air conditioning load management adjustment method as described above.
The computer readable storage medium of the present invention has similar technical effects to the above-mentioned air conditioner load management adjustment method, and will not be described in detail herein.
In general, the computer instructions for carrying out the methods of the present invention may be carried in any combination of one or more computer-readable storage media. The non-transitory computer-readable storage medium may include any computer-readable medium, except the signal itself in temporary propagation.
The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, c#, and conventional procedural programming languages, such as the "C" language or similar programming languages, particularly the Python language suitable for neural network computing and TensorFlow, pyTorch-based platform frameworks may be used. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Although the invention is disclosed above, the scope of the invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and such changes and modifications would be within the scope of the invention.
Claims (7)
1. An air conditioner load management adjustment method, characterized by comprising:
acquiring historical air conditioner load data and historical load influence data of a public building in a preset time period, wherein the historical load influence data comprises historical weather data in the preset time period;
dividing the historical load influence data according to the characteristics of the historical load influence data to obtain historical load influence sub-data of a plurality of sub-time periods;
determining historical air conditioner load sub-data of each sub-time period in the historical air conditioner load data in the preset time period;
according to the historical load influence sub-data of each sub-period, the historical air conditioner load sub-data of the corresponding sub-period is adjusted to obtain the historical air conditioner load basic data of each sub-period, which comprises the following steps: determining a load adjustment estimated value of each sub-time period according to the historical load influence sub-data of each sub-time period and a preset neural network model; adjusting the historical air conditioner load sub-data according to the load adjustment pre-estimated value to obtain the historical air conditioner load basic data;
performing air conditioning load management on the public building according to the historical air conditioning load basic data of each sub-time period;
the determining the load adjustment estimated value of each sub-time period according to the historical load influence sub-data of each sub-time period and a preset neural network model comprises:
determining the difference value of the historical load influence sub-data and the calibration load influence data of each sub-time period as third difference value data;
inputting the third difference value data of each sub-time period into the preset neural network model to obtain the load adjustment estimated value of each sub-time period;
the training process of the preset neural network model comprises the following steps:
acquiring load influence sub-data of at least two continuous preset sub-time periods and air conditioner load actual data;
determining a difference value of the load influencing sub-data of the adjacent preset sub-time period as first difference value data, and determining a difference value of the air conditioner load actual data of the adjacent preset sub-time period as second difference value data;
and constructing a training data set according to the first difference data and the second difference data, so as to train an initial neural network model according to the training data set, and obtain the preset neural network model.
2. The air conditioning load management adjustment method according to claim 1, wherein said air conditioning load management of the public building according to the historic air conditioning load base data of each of the sub-time periods comprises:
determining first air conditioning load prediction data of a future time period according to the historical air conditioning load basic data of each sub time period;
acquiring load influence statistical data of the future time period, wherein the load influence statistical data comprises weather forecast data;
correcting the first air conditioner load prediction data according to the load influence statistical data to obtain second air conditioner load prediction data;
and carrying out air conditioning load management on the public building according to the second air conditioning load prediction data.
3. The air conditioner load management adjustment method according to claim 2, wherein the load influence statistical data further includes people flow rate estimation data and people density estimation data; the air conditioning load management of the public building according to the historical air conditioning load basic data of each sub-period further comprises:
determining the flow average value of all the people flow estimated data of the public building and the density average value of the people density estimated data;
determining the power supply priority of each public building according to the comparison condition of the estimated pedestrian flow data and the average flow value of each public building and the comparison condition of the estimated personnel density data and the average density value of each public building;
and carrying out air conditioning load management on the public building according to the power supply priority and the second air conditioning load prediction data.
4. The air conditioning load management adjustment method according to claim 2, wherein the determining the first air conditioning load prediction data of the future time period from the historical air conditioning load base data of each of the sub-time periods includes:
establishing a trend model and/or a regression model according to each sub-time period and historical air conditioner load basic data of each sub-time period;
and determining the first air conditioner load prediction data of the future time period according to the trend model and/or the regression model.
5. The air conditioner load management adjustment method according to any one of claims 1 to 4, wherein the acquiring the historical air conditioner load data and the historical load influence data of the public building for a preset period of time includes:
determining a main operation time period of the public building in the preset time period according to the type of the public building and/or the historical air conditioning load data;
the historical air conditioning load data and the historical load impact data of the public building during the primary operation period are determined.
6. A computing device comprising a computer readable storage medium storing a computer program and a processor, the computer program implementing the air conditioning load management adjustment method of any of claims 1-5 when read and executed by the processor.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when read and run by a processor, implements the air-conditioning load management adjustment method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311084802.0A CN116817415B (en) | 2023-08-28 | 2023-08-28 | Air conditioner load management and adjustment method, computing equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311084802.0A CN116817415B (en) | 2023-08-28 | 2023-08-28 | Air conditioner load management and adjustment method, computing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116817415A CN116817415A (en) | 2023-09-29 |
CN116817415B true CN116817415B (en) | 2024-01-12 |
Family
ID=88141357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311084802.0A Active CN116817415B (en) | 2023-08-28 | 2023-08-28 | Air conditioner load management and adjustment method, computing equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116817415B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111181151A (en) * | 2019-10-18 | 2020-05-19 | 浙江海洋大学 | Smart power grid control method for estimating and controlling power load |
CN112865093A (en) * | 2021-03-01 | 2021-05-28 | 同济大学 | Short-time power load combined prediction method |
CN113657936A (en) * | 2021-08-17 | 2021-11-16 | 国网河北省电力有限公司邢台供电分公司 | Power load prediction method and terminal |
CN113850432A (en) * | 2021-09-24 | 2021-12-28 | 广东电网有限责任公司 | Prediction method, system, equipment and medium of power load data |
EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
CN115392690A (en) * | 2022-08-23 | 2022-11-25 | 中如信息科技有限公司 | Wisdom garden fortune dimension management system |
CN116186548A (en) * | 2023-05-04 | 2023-05-30 | 广州三晶电气股份有限公司 | Power load prediction model training method and power load prediction method |
CN116307215A (en) * | 2023-03-24 | 2023-06-23 | 广东电网有限责任公司广州供电局 | Load prediction method, device, equipment and storage medium of power system |
CN116468138A (en) * | 2022-12-06 | 2023-07-21 | 国网(北京)综合能源规划设计研究院有限公司 | Air conditioner load prediction method, system, electronic equipment and computer storage medium |
-
2023
- 2023-08-28 CN CN202311084802.0A patent/CN116817415B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
CN111181151A (en) * | 2019-10-18 | 2020-05-19 | 浙江海洋大学 | Smart power grid control method for estimating and controlling power load |
CN112865093A (en) * | 2021-03-01 | 2021-05-28 | 同济大学 | Short-time power load combined prediction method |
CN113657936A (en) * | 2021-08-17 | 2021-11-16 | 国网河北省电力有限公司邢台供电分公司 | Power load prediction method and terminal |
CN113850432A (en) * | 2021-09-24 | 2021-12-28 | 广东电网有限责任公司 | Prediction method, system, equipment and medium of power load data |
CN115392690A (en) * | 2022-08-23 | 2022-11-25 | 中如信息科技有限公司 | Wisdom garden fortune dimension management system |
CN116468138A (en) * | 2022-12-06 | 2023-07-21 | 国网(北京)综合能源规划设计研究院有限公司 | Air conditioner load prediction method, system, electronic equipment and computer storage medium |
CN116307215A (en) * | 2023-03-24 | 2023-06-23 | 广东电网有限责任公司广州供电局 | Load prediction method, device, equipment and storage medium of power system |
CN116186548A (en) * | 2023-05-04 | 2023-05-30 | 广州三晶电气股份有限公司 | Power load prediction model training method and power load prediction method |
Also Published As
Publication number | Publication date |
---|---|
CN116817415A (en) | 2023-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cancelo et al. | Forecasting the electricity load from one day to one week ahead for the Spanish system operator | |
US9727068B2 (en) | Energy search engine with autonomous control | |
US20060167591A1 (en) | Energy and cost savings calculation system | |
JP5743881B2 (en) | Power management system, power management method, customer terminal, and power management apparatus | |
CN109428344B (en) | Multi-power-supply investment planning method and device comprising wind power plant | |
US11720134B2 (en) | Method and system for predicting potential future energy consumption of built environment | |
Inderfurth | How to protect against demand and yield risks in MRP systems | |
US9658263B2 (en) | Methods and systems for measurement and verification weighting with temperature distribution | |
US20190086878A1 (en) | Systems and methods for determining baseline consumption | |
KR20190103661A (en) | Method of predicting fine dustreflecting both indoor and outdoordata | |
Li et al. | System identification and data fusion for on-line adaptive energy forecasting in virtual and real commercial buildings | |
JP6705716B2 (en) | Power demand forecasting method and power demand forecasting program | |
KR101865924B1 (en) | Appratus and method for estimation of weekly power load to improve processing time using neural network and revision factor | |
CN113743667A (en) | Method, device, equipment and storage medium for predicting power consumption of transformer area | |
CN116817415B (en) | Air conditioner load management and adjustment method, computing equipment and storage medium | |
TWI503780B (en) | Optimizing system for contract demand and optimizing method using for the same | |
US20230367033A1 (en) | Automated system and method for managing weather related energy use | |
Janjic et al. | Designing an electricity distribution reward-penalty scheme based on spatial reliability statistics | |
CN115964843A (en) | Evaluation method and system for improving new energy bearing capacity of regional power grid by considering energy storage | |
CN116485445A (en) | New energy power spot transaction auxiliary system based on data automatic acquisition and processing | |
WO2022162798A1 (en) | Power demand prediction device, power demand prediction method, and program | |
Bozorgi et al. | Improving energy retrofit decisions by including uncertainty in the energy modelling process | |
JP2019140831A (en) | Power demand prediction system, power demand prediction method, and program | |
JP2017120599A (en) | Partal supply control device, partial supply method and partial supply program | |
Rousseau et al. | Uncertainty-Aware Energy Flexibility Quantification of a Residential Building |
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 |