CN114154677A - Air conditioner operation load model construction and prediction method, device, equipment and medium - Google Patents
Air conditioner operation load model construction and prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN114154677A CN114154677A CN202111229166.7A CN202111229166A CN114154677A CN 114154677 A CN114154677 A CN 114154677A CN 202111229166 A CN202111229166 A CN 202111229166A CN 114154677 A CN114154677 A CN 114154677A
- Authority
- CN
- China
- Prior art keywords
- day
- operation load
- prediction
- subset
- predicted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010276 construction Methods 0.000 title claims description 11
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 22
- 239000012634 fragment Substances 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 10
- 238000004378 air conditioning Methods 0.000 description 9
- 238000005265 energy consumption Methods 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 5
- 238000005057 refrigeration Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001816 cooling Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000008400 supply water Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the field of automatic control of air conditioners, and discloses a method, a device, equipment and a medium for constructing and predicting an air conditioner operation load model. The method for constructing the air conditioner operation load model comprises the following steps: collecting or reading the operation loads of n prediction days to form a prediction day subset; reading m historical data sets; comparing the segment subsets of the m historical data sets with the prediction day subsets respectively, selecting the segment subsets with the operation load distribution closest to the prediction day subsets, and taking the historical data sets to which the segment subsets belong as similar day data sets; and establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the overall deviation of the segment subset and the prediction day subset of the similar day data set. The invention takes the acquisition time as the change factor of the operation load, reduces the data processing amount while ensuring the prediction precision and improves the prediction efficiency.
Description
Technical Field
The invention relates to the field of automatic control of air conditioners, in particular to a method, a device, equipment and a medium for constructing and predicting an air conditioner operation load model.
Background
In recent years, the energy consumption of public buildings is increased year by year, the energy consumption of air conditioners is a main component of the public buildings, and accounts for about 65% of the total energy consumption of the buildings according to data statistics, so that the method for improving the performance of a central air conditioner control system, reducing the energy consumption of an air conditioner system and promoting the intelligent development of the buildings has significance and is worthy of key research.
The central air-conditioning system is a set of complex mechanical system, and because the loop of the air-conditioning chilled water pipeline is long, the cycle period is long, the water heat capacity is large, the inertia is large, the temperature reaction is slow, when the load is suddenly changed, corresponding adjusting action can be generated only after the temperature is slowly reflected, the larger control time lag exists, and the timeliness of the control is influenced. When the thermal load of the system changes suddenly, the traditional closed-loop control mode and the open-loop control mode cannot solve the existing problems well due to the influence of hysteresis; such as: the large hysteresis system has the problems of inaccurate refrigeration output, untimely refrigeration output and incapability of realizing refrigeration according to requirements, and brings unnecessary loss of energy consumption.
The energy consumption of a ventilation air-conditioning system in a public area of a subway station is changed along with the peak passenger flow, the train operation interval and the season change in the morning and evening, the obvious peak-valley difference is shown, whether the loading capacity is required or not is judged according to the chilled water supply temperature by a traditional water-cooling cold water host, the load requirement at the tail end is met through variable flow control of a variable frequency water pump, the adjustment of the feedback adjustment on the water quantity and the capacity has the problems of temperature transfer lag and cooling capacity lag, the load change and the refrigerating capacity response speed are unmatched, the subway temperature is easily increased and reduced along with the passenger flow suddenly, the temperature is suddenly lowered, the system operation fluctuation is large, the loading and unloading of unit equipment during starting and stopping are frequent, and the system operation is not energy-saving.
The problem caused by hysteresis is that the larger the thermal load change is, the more the problem is prominent, in a subway scene, the adverse effect of system hysteresis can be better overcome by manual advanced control, and operators often load the load of a water chilling unit in advance; when meeting holidays and special periods, the passenger flow control system can flexibly adjust according to historical passenger flow conditions. Aiming at the problems, the cold and heat quantity required by the operation of the air conditioning system at the future moment can be predicted in a short term through a computer technology and a modern control technology, the air conditioning control service can be accurately optimized through accurate prediction of the short-term load quantity, the optimal operation working condition or set value is adjusted and set in advance, the comfort of the air conditioner is ensured, meanwhile, the refrigeration as required is realized, the operation is carried out in the most efficient mode, the system fluctuation is reduced, and the energy-saving effect is realized. However, the load prediction method in the prior art is not mature, and the problems of reducing the data processing amount, improving the prediction speed and accuracy and the like need to be solved urgently.
Disclosure of Invention
The present invention is directed to overcoming at least one of the above-mentioned drawbacks (disadvantages) of the prior art, and providing a method, an apparatus, a device, and a medium for constructing and predicting an air conditioner operation load model, which are used to reduce the data processing amount of air conditioner load prediction, increase the prediction speed, and ensure the prediction accuracy.
The technical scheme adopted by the invention comprises a method for constructing an air conditioner operation load model, which comprises the following steps: collecting or reading n preset collecting moments t of predicted day1～tnForming a predicted daily subset; reading m historical data sets; the m historical data sets are divided according to dates, each historical data set comprises the operation load of one historical date before the prediction date, and the acquisition time of each historical data set is t1～tnThe operating load of (a) is a subset of segments corresponding to each of the historical data sets; respectively comparing the m fragment subsets with the prediction day subsets, selecting the fragment subset with the operation load distribution closest to the prediction day subsets, and taking the historical data set to which the fragment subset belongs as a similar day data set; according to the similar day dataEstablishing an operation load model Q (t) taking the acquisition time as a characteristic factor by using the set and the overall deviation of the segment subset and the prediction day subset of the similar day data set; wherein n and m are preset values.
For air conditioner application scenes such as subways and shopping malls, due to the fact that the change of the flow of people in each time interval is large, the operation load and the collection time have obvious correlation, the distribution situation of the operation load in each day is very similar, the operation load of a part of time (namely a subset of a prediction day) is collected on the prediction day, the operation load of the part of time (namely a subset of the prediction day) in the history day is compared, the day with the most similar operation load distribution is found out to be used as a similar day, the operation load distribution comprises the numerical value and the change trend, the operation load of the individual time of the similar day is corrected by using the whole operation load difference between the prediction day and the similar day, and the operation load is converted into the operation load of the prediction day. Therefore, the collection time is used as a characteristic factor, the actual operation load of the historical day is referred, specific analysis on various factors influencing the operation load, such as air temperature, people flow, fresh air volume and the like, is omitted, the data analysis amount is reduced, and the prediction accuracy is guaranteed.
Further, the preset collection time t of the day of the n prediction days is collected or read1～tnThe operation load of (2) specifically includes: determining a span T of acquisition moments of the operating loads of a prediction subset of daysw(ii) a Determining the time interval T between two preset acquisition instants adjacent to a subset of predicted daysk(ii) a Collecting or reading n preset collecting moments t of predicted day1～tnN is Tw/Tk。
t1～tnThe time intervals of every two adjacent acquisition time points in the data acquisition system are the same, n is the number of elements contained in each segment subset, and is also the number of elements contained in the forecast day subset, and the size of the data analysis amount can be controlled by changing the size of n.
Further, the reading of the m historical data sets specifically includes: reading the operation data m days before the forecast day, or reading the operation data m years before the forecast day and the operation data in the same period with the forecast day, or reading the operation data m years before the same period with the forecast daym1Day's operating data and m2Day's operating data, m1+m2M. Therefore, the operation load data which cover the same climatic conditions, the same holidays, the same pedestrian volume and the like as the predicted days as much as possible is selected.
Further, the establishing of the operation load model q (t) using the acquisition time as a characteristic factor according to the similar day data set and the overall deviation between the segment subset and the prediction day subset of the similar day data set specifically includes: calculating an overall standard deviation value X of the segment subset and the prediction day subset of the similar day dataseta(ii) a Establishing an operation load model Q (t) according to the similar day data set and the overall standard deviation value:
Q(t)＝ga(t)-Xa (1)
wherein, gaAnd (t) represents the operation load of the similar day data set with the acquisition time t.
t is the acquisition time, is used as a variable in the operation load model, and has an overall standard deviation value XaRepresenting the total deviation of the forecast day subset and the segment subset, wherein the total deviation of the forecast day and the similar day is mainly caused by the difference of the air temperature of two days, and introducing a total standard deviation value X (t) into an operation load model Q (t)aAnd correcting the difference of the air temperature level between the similar day and the predicted day.
Based on the construction method of the air conditioner operation load model, the technical scheme of the invention also comprises an air conditioner operation load prediction method, which comprises the following steps: the operation load model Q (t) is constructed according to the construction method of the air conditioner operation load model, and the time t to be predicted is calculated according to the operation load model Q (t)predPredicted value Q of operating loadpred。
Further, the time t to be predicted is selectedpredThe method specifically comprises the following steps: reading the cyclic period value T of the water systemc(ii) a According to a preset acquisition time t1～tnAnd water system cycle period value TcDetermining a time t to be predictedpred: the time t to be predictedpredIs greater than or equal to tb+kTc(ii) a Wherein, tbFor a predetermined time t1～tnK is an optional value when the item is the latest item at the middle acquisition time, and k is more than or equal to 7 and more than or equal to 3.
The operation load needs the water system to complete the periodic cycle preparation, so that the hysteresis is realized, in order to ensure the reference value of the operation load predicted value, the cycle period of the water system needs to be considered, the situation that the reserved time interval is too short is avoided, and the originally set time t to be predicted is missed after the water system is cooled according to the predicted value in the cycle periodpredThe condition of (2).
Further, calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpredThe method specifically comprises the following steps: inputting the time t to be predictedpredTo the operation load model Q (t), obtaining a preliminary predicted value Q1(ii) a According to the root mean square error value RMSE of the similar day data set and the prediction day subsetaCorrecting the preliminary predicted value Q1Obtaining the predicted value Q of the running loadpred。
Output preliminary predicted value Q of operation load model Q (t)1Measuring the integral difference between the similar day and the predicted day, considering the factors of different influence degrees of the pedestrian flow and the like on the operation load in different time periods, and calculating the root mean square error value RMSE of the similar day data set and the predicted day subset to further improve the prediction precisionaCorrecting the output initial predicted value Q of the operation load model Q (t)1。
Based on the air conditioner operation load prediction method, the invention also comprises an air conditioner operation load prediction device, computer equipment and a computer readable medium:
the air conditioner operation load prediction apparatus includes: a reading module for collecting or reading n preset collection times t of the predicted day1～tnForming a predicted daily subset; and also for reading the m sets of historical data; the m historical data sets are divided according to dates, each historical data set comprises the operation load of one historical date before the prediction date, and the acquisition time of each historical data set is t1～tnThe operating load of (a) is a subset of segments corresponding to each of the historical data sets; wherein n and m are preset values;
the processing module is used for respectively comparing the m fragment subsets with the prediction day subsets, selecting the fragment subset with the operation load distribution closest to the prediction day subsets, and taking the historical data set to which the fragment subset belongs as a similar day data set; the system is also used for establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the overall deviation of the segment subset and the prediction day subset of the similar day data set; and is also used for calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpred。
The computer device comprises a memory and a processor, wherein the memory stores a computer program; wherein the processor implements the method for predicting the air conditioner operating load as described above when executing the computer program.
The computer readable medium, on which a computer program is stored, which, when executed by a processor, implements the air conditioner operation load prediction method as described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) the acquisition time is used as a change factor of the operation load, so that the detailed analysis of various factors influencing the operation load is avoided, and the data processing amount is greatly reduced.
(2) The analysis of the prediction day and the similar day reduces the data comparison in a preset time span; short-term predictions can be made with high accuracy in the short-term prediction.
(3) The selection range of the historical data set covers the scene data of the same weather condition and the same holiday to the maximum extent, and the prediction precision is guaranteed.
Drawings
Fig. 1 is a first flowchart illustrating steps of embodiment 1 of the present invention.
FIG. 2 is a flowchart illustrating a second step of embodiment 1 of the present invention.
Fig. 3 is a first schematic view of an operation load model according to embodiment 1 of the present invention.
Fig. 4 is a second schematic view of the operation load model of embodiment 1 of the present invention.
Fig. 5 is a third schematic view of an operation load model in embodiment 1 of the present invention.
Detailed Description
Example 1
As shown in fig. 1 and 2, the present embodiment provides an air conditioner operation load prediction method, including the steps of:
s1: collecting or reading n preset collecting moments t of predicted day1～tnThe operating load of (a) forms a prediction daily subset f (t), t ═ t1～tn；
Wherein, step S1 specifically includes:
s11: determining a span T of acquisition moments of the operating loads of a prediction subset of daysw；
S12: determining the time interval T between two preset acquisition instants adjacent to a subset of predicted daysk；
S13: collecting or reading n preset collecting moments t of predicted day1～tnN is Tw/Tk；
To ensure prediction accuracy, n should generally not be less than 10.
S2: reading m historical data sets; the m historical data sets are divided according to dates and respectively comprise operating loads of m historical days, and the acquisition time of each historical data set is t1～tnThe operating load of (a) is a subset of segments of the historical data set; the expression of the historical data set is gm(t) representing the operating load at time t on the mth day, the expression of the subset of the segments being the same is gm(t)，t＝t1～tn；
Wherein the m historical data sets are operation data m days before the forecast day, or operation data m years before the forecast day and the same period as the forecast day, or operation data m years before the last year and the same period as the forecast day1Day's operating data and m2Day's operating data, m1+m2＝m
It should be noted that the execution sequence of steps S1 and S2 may be changed according to actual situations, and the history data set is not limited to include the entire day of the history dayThe line load set is set, if the historical data set does not contain the preset acquisition time t1～tnThe running load of the system can be fitted through the running loads at other moments, so that the running load at the preset acquisition moment is calculated.
S3: respectively comparing the m fragment subsets with the prediction day subsets, selecting the fragment subset with the operation load distribution closest to the prediction day subsets, and taking the historical data set to which the fragment subset belongs as a similar day data set ga(t), day a of m is a similar day;
wherein, step S3 specifically includes:
calculating the root mean square error value of each segment subset and the prediction day subset according to the formula (2):
Xmfor the total standard deviation values of the segment subset and the prediction day subset of the mth historical data set, the calculation method is as the formula (3):
comparing the root mean square error value (RMSE) of each subset of segments to the predicted daily subsetmComparing to find out the minimum root mean square error value RMSEminSubset of segments g with the smallest root mean square error valuea(t)，t＝t1～tnThe historical data set g to which the subset of segments belongsa(t) is a similar daily data set, RMSEmin＝RMSEa. In other embodiments, the approximation/approximation degrees of the prediction day subset and the segment subset may be estimated by selecting a variance, a mean square error, and the like according to actual conditions.
S4: establishing an operation load model Q (t) taking the acquisition time as a characteristic factor by taking the similar day data set as a basis and combining the overall deviation of the segment subset and the prediction day subset;
wherein, step S4 specifically includes:
s41: calculating a similar day data set ga(t) total standard deviation value X for the subset of segments and the subset of prediction days f (t)a； XaRoot mean square error value RMSE may be calculated at step S3mOr may be recalculated after a similar date is established.
S42: and (3) establishing an operation load model Q (t) by combining the similar day data set and the overall standard deviation value:
Q(t)＝ga(t)-Xa (1)
s5: selecting a time t to be predictedpred(ii) a Calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpred；
Wherein, step S5 specifically includes:
s51: inputting a time t to be predictedpredTo the operation load model Q (t), outputting a preliminary predicted value Q1；
S52: root mean square error value RMSE from the similar day data set to the predicted day subsetaCorrecting the preliminary predicted value Q1Obtaining the predicted value Q of the running loadpred：
Considering the hysteresis of water circulation system, to ensure QpredReference value of, tpredDetermined by equation (5):
tpred≥tb+kTc (5)
wherein, TcTime required for one cycle for the current water system cycle, tbFor a predetermined time t1～tnAnd k is an optional value when the medium acquisition time is the latest item, and k is more than or equal to 3 and more than or equal to 7.
FIGS. 3 to 5 are schematic diagrams illustrating a process of forming the operation load model Q (t). The load in a day may be different according to the environmental temperature and the load size, and is not consistent with the number of passengersMeanwhile, the load size is different at different time; as shown in fig. 5, 2 load curves are drawn according to the actual operating load of the application scenario, the load is different under different environmental temperatures and other factors, and the environmental temperature on the predicted day is higher than the environmental temperature on the similar day; in order to eliminate the influence caused by factors such as environmental temperature, the total standard deviation X of the 2 curves is calculatedaThen, the total mean value of the deviation values of the historical data set is shifted to obtain a new data set g 'shown in FIG. 4'a(t) graph, g'a(t)＝ga(t)-Xa(ii) a After the overall mean difference is eliminated, the difference between the 2 displayed load curves is mainly caused by the factors of people flow fluctuation, holidays, working days and the like, and as shown in FIG. 5, the difference is obtained by a root mean square error value RMSEaCorrected so that Q (t) is ga(t)-Xa+RMSEa。
Due to the invariance of load change, in order to ensure the accuracy of prediction, the method of the embodiment restarts calculation at regular intervals, dynamically searches and calculates the most accurate load predicted value, and adjusts the load predicted value at any time;
in addition, in this embodiment, an evaluation model is added, error calculation is performed on the predicted value and the realized value, an average error value in one day is obtained, the accuracy of the current algorithm model can be evaluated according to the average error value, and algorithm parameters are adjusted in time to gradually iterate to reach an optimal state. Similarly, in other embodiments, other correction terms may be introduced into the operation load model q (t) to further improve the prediction accuracy.
Based on the air conditioner operation load model construction method and the air conditioner operation load prediction method, the embodiment also provides computer equipment and a computer readable medium. The computer equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the air conditioner operation load prediction method when executing the computer program. The computer readable medium stores a computer program which, when executed by a processor, implements the above-described method of predicting an operating load of an air conditioner.
Example 2
The present embodiment provides an apparatus and a system for implementing the method for predicting an air conditioner operating load of embodiment 1.
The air conditioner operation load prediction apparatus includes: a reading module for collecting or reading n preset collection times t of the predicted day1～tnForming a predicted subset of days; and also for reading the m sets of historical data; the m historical data sets are divided according to dates and respectively comprise operating loads of m historical days, and the acquisition time of each historical data set is t1～tnThe operating load of (a) is a subset of segments of the historical data set; wherein n and m are preset values; the processing module is used for comparing the variation trends of the m segment subsets with the prediction day subset, and selecting the historical data set corresponding to the segment subset with the closest variation trend as a similar day data set; the system is also used for establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the prediction day subset; and is also used for calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpred。
The air conditioner operation load prediction system includes: the air conditioner operation load prediction device as described above; a database for recording the operation load of each collection time of the historical days and/or establishing a change function g of the operation load according to part of the collection timem(t); the air conditioner operation load prediction means reads the historical data set from a database. The partitioning of the historical data set may be performed by the database, or may be performed by the reading module after reading the operating data from the database. Wherein g can be obtained by fitting existing operational loads when the historical data set does not contain operational loads for a complete daym(t) to calculate the operating load, g, at other timesm(t) represents the operating load at time t on the m-th day. The operation load of the predicted day can be read by the reading module connected with the measuring device or transmitted to the reading module by taking the database as an intermediary.
The computer-readable medium stores thereon a computer program that, when executed by a processor, implements the method of predicting an air conditioner operation load according to embodiment 1.
Based on the air conditioner operation load prediction system, the embodiment also provides a refrigeration system applying the air conditioner operation load prediction system, which comprises a monitoring server module, a control acquisition unit, an air conditioner system module and a signal sensor group module;
the monitoring server module is composed of an air conditioner running load prediction device, a database and a monitoring configuration interface, and is responsible for communication reading and controlling the running data of the acquisition unit, storing the running data in the local database, displaying the running data on a built-in monitoring configuration software interface, and simultaneously calculating the future time t by inquiring the running data in the database by a timing running load prediction algorithm programpredThe magnitude of the air conditioner operation load at any moment;
the control acquisition unit is controlled by a controller, a communication module and a signal acquisition module, the controller firstly acquires sensor signals of the air conditioning system, controls the operation of cold source equipment, transmission equipment and a tail end system of the air conditioning system through a built-in control logic strategy, and simultaneously receives instructions of a monitoring server, including a load prediction result and an output optimization control instruction of an optimization parameter, and timely adjusts the state of the air conditioning system to ensure the operation under an optimal energy-saving working condition;
the air conditioning system consists of a cold source system, a conveying system and a tail end system, wherein the cold source system consists of a cold water host, a cooling tower and a cooling pump, the conveying system consists of a freezing pump and a pipeline, the tail end system mainly consists of an air cabinet, a combined air conditioner and a fan coil device, and a water supply temperature set value can be adjusted in advance through predicted load, so that the working input of the host and the operating frequency of the water pump are changed, and the change of the load is matched in advance;
the signal sensor group mainly comprises various water temperature sensors, pressure sensors, flow sensors, outdoor temperature and humidity sensors and the like in the refrigerating system, and the control core unit can supply water temperature T according to chilled waterFor supplying toTemperature T of return waterGo back toThe difference value of (2) and the flow rate L, calculating the operation load of the air conditioner, and calculating the air conditioner according to the detected sensor valueAnd the operation load and the energy consumption value are uniformly uploaded to a monitoring server for storage and calculation.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific embodiments of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention claims should be included in the protection scope of the present invention claims.
Claims (10)
1. An air conditioner operation load model construction method is characterized by comprising the following steps:
collecting or reading n preset collecting moments t of predicted day1～tnForming a predicted daily subset;
reading m historical data sets; the m historical data sets are divided according to dates, each historical data set comprises the operation load of one historical date before the prediction date, and the acquisition time of each historical data set is t1～tnThe operating load of (a) is a subset of segments corresponding to each of the historical data sets;
respectively comparing the m fragment subsets with the prediction day subsets, selecting the fragment subset with the operation load distribution closest to the prediction day subsets, and taking the historical data set to which the fragment subset belongs as a similar day data set;
establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the overall deviation of the segment subset and the prediction day subset of the similar day data set;
wherein n and m are preset values.
2. The air conditioner operation load model construction method according to claim 1,
the preset collection time t of the current day of the collection or reading n prediction days1～tnThe operation load of (2) specifically includes:
determining a span T of acquisition moments of the operating loads of a prediction subset of daysw；
Determining the time interval T between two preset acquisition instants adjacent to a subset of predicted daysk；
Collecting or reading n preset collecting moments t of predicted day1～tnN is Tw/Tk。
3. The air conditioner operation load model construction method according to claim 1,
the reading of the m historical data sets specifically includes:
reading the operation data m days before the forecast day, or reading the operation data m years before the forecast day and the operation data m days before the forecast day, or reading the operation data m years before the same date as the forecast day1Day's operating data and m2Day's operating data, m1+m2＝m。
4. The air conditioner operation load model construction method according to claim 1,
establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the overall deviation of the segment subset and the prediction day subset of the similar day data set, and specifically comprising the following steps:
calculating an overall standard deviation value X of the segment subset and the prediction day subset of the similar day dataseta；
Establishing an operation load model Q (t) according to the similar day data set and the overall standard deviation value:
Q(t)＝ga(t)-Xa
wherein, gaAnd (t) represents the operation load of the similar day data set with the acquisition time t.
5. An air conditioner operation load prediction method is characterized by comprising the following steps:
selecting a time t to be predictedpred；
Construction of an operation load model according to the air conditioner operation load model construction method of any one of claims 1 to 4Q (t), calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpred。
6. The air conditioner operation load prediction method according to claim 5,
selecting the time t to be predictedpredThe method specifically comprises the following steps:
reading the cyclic period value T of the water systemc；
According to a preset acquisition time t1～tnAnd water system cycle period value TcDetermining a time t to be predictedpred：
The time t to be predictedpredIs greater than or equal to tb+kTc；
Wherein, tbFor a predetermined time t1～tnK is an optional value when the item is the latest item at the middle acquisition time, and k is more than or equal to 7 and more than or equal to 3.
7. The air conditioner operation load prediction method according to claim 5,
calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpredThe method specifically comprises the following steps:
inputting the time t to be predictedpredTo the operation load model Q (t), obtaining a preliminary predicted value Q1；
According to the root mean square error value RMSE of the similar day data set and the prediction day subsetaCorrecting the preliminary predicted value Q1Obtaining the predicted value Q of the running loadpred。
8. An air conditioner operation load prediction apparatus, comprising:
a reading module for collecting or reading n preset collection times t of the predicted day1～tnForming a predicted daily subset; and also for reading the m sets of historical data; the m historical data sets are divided by date, and each historical data set comprises data before the prediction dateThe running load of a historical day, and the collection time of each historical data set is t1～tnThe operating load of (a) is a subset of segments corresponding to each of the historical data sets; wherein n and m are preset values;
the processing module is used for respectively comparing the m fragment subsets with the prediction day subsets, selecting the fragment subset with the operation load distribution closest to the prediction day subsets, and taking the historical data set to which the fragment subset belongs as a similar day data set; the system is also used for establishing an operation load model Q (t) taking the acquisition time as a characteristic factor according to the similar day data set and the overall deviation of the segment subset and the prediction day subset of the similar day data set; and is also used for calculating the time t to be predicted according to the operation load model Q (t)predPredicted value Q of operating loadpred。
9. A computer device comprising a memory and a processor, the memory storing a computer program; it is characterized in that the preparation method is characterized in that,
the processor, when executing the computer program, implements the air conditioner operation load prediction method according to any one of claims 5 to 7.
10. A computer-readable medium, having stored thereon a computer program,
the computer program is executed by a processor to realize the method for predicting the air conditioner operation load according to any one of claims 5 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111229166.7A CN114154677A (en) | 2021-10-21 | 2021-10-21 | Air conditioner operation load model construction and prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111229166.7A CN114154677A (en) | 2021-10-21 | 2021-10-21 | Air conditioner operation load model construction and prediction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114154677A true CN114154677A (en) | 2022-03-08 |
Family
ID=80458402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111229166.7A Pending CN114154677A (en) | 2021-10-21 | 2021-10-21 | Air conditioner operation load model construction and prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114154677A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115682572A (en) * | 2022-11-07 | 2023-02-03 | 珠海格力电器股份有限公司 | Chilled water unit load determining and loading and unloading control method, device and equipment |
| CN115861011A (en) * | 2023-02-15 | 2023-03-28 | 山东优嘉环境科技有限公司 | Smart city optimization management method and system based on multi-source data fusion |
| CN116795655A (en) * | 2023-08-25 | 2023-09-22 | 深圳市银闪科技有限公司 | Storage device performance monitoring system and method based on artificial intelligence |
-
2021
- 2021-10-21 CN CN202111229166.7A patent/CN114154677A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115682572A (en) * | 2022-11-07 | 2023-02-03 | 珠海格力电器股份有限公司 | Chilled water unit load determining and loading and unloading control method, device and equipment |
| CN115861011A (en) * | 2023-02-15 | 2023-03-28 | 山东优嘉环境科技有限公司 | Smart city optimization management method and system based on multi-source data fusion |
| CN115861011B (en) * | 2023-02-15 | 2023-05-05 | 山东优嘉环境科技有限公司 | Smart city optimization management method and system based on multi-source data fusion |
| CN116795655A (en) * | 2023-08-25 | 2023-09-22 | 深圳市银闪科技有限公司 | Storage device performance monitoring system and method based on artificial intelligence |
| CN116795655B (en) * | 2023-08-25 | 2023-11-24 | 深圳市银闪科技有限公司 | Storage device performance monitoring system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3483517B1 (en) | System and method for predicting load of and controlling subway heating, ventilation, and air conditioning system | |
| CN114154677A (en) | Air conditioner operation load model construction and prediction method, device, equipment and medium | |
| CN110410942B (en) | Energy-saving optimization control method and system for cold and heat source machine room | |
| CN111237989A (en) | Building ventilation air conditioner control method and device based on load prediction | |
| CN101782258B (en) | Energy-saving method for air conditioner | |
| CN108489013A (en) | Central air-conditioner control method based on genetic algorithm and load on-line amending and device | |
| CN105091209B (en) | A kind of control system and method based on Air-conditioning Load Prediction | |
| CN115325682B (en) | Optimal control method and device for monitoring performance of efficient intelligent refrigeration machine room | |
| CN113739365A (en) | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium | |
| CN109341010B (en) | Energy supply integrated control method and device for air conditioning system of electric refrigerator | |
| CN111047117B (en) | Differential pressure bypass valve energy-saving optimization method based on terminal load prediction | |
| CN112283890A (en) | Cold and heat quantity control method and device suitable for building heating and ventilation equipment monitoring system | |
| CN109960874A (en) | A kind of cold accumulation system operation method based on performance driving economy | |
| CN114282729A (en) | Load prediction-based ice storage air conditioner optimal scheduling method | |
| CN110895029A (en) | Building load prediction method based on temperature of chilled water | |
| CN115081220A (en) | Adjusting method and system for high-energy-efficiency central air-conditioning system | |
| CN115049141A (en) | Control method and control device for refrigeration system and refrigeration system | |
| CN113446713A (en) | Digital twin-based intelligent data optimal control and energy saving method and system | |
| CN111664560B (en) | Intelligent energy-saving control method for central air-conditioning host | |
| CN116045560A (en) | Remote management method and system for refrigerating system and computer readable storage medium | |
| CN111043720B (en) | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty | |
| CN107883525A (en) | A kind of central air-conditioning intelligence energy-saving operation control system and method | |
| CN113654198A (en) | Energy efficiency management and control system of central air conditioner | |
| CN107631420B (en) | IBeacon technology-based energy-saving method and device for hospital air conditioner tail end variable air volume system | |
| CN115978736B (en) | Self-adaptive prediction wind-water linkage control method for subway station air conditioning 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 |