CN116109011B - Energy consumption management method and terminal for intelligent park - Google Patents
Energy consumption management method and terminal for intelligent park Download PDFInfo
- Publication number
- CN116109011B CN116109011B CN202310373068.3A CN202310373068A CN116109011B CN 116109011 B CN116109011 B CN 116109011B CN 202310373068 A CN202310373068 A CN 202310373068A CN 116109011 B CN116109011 B CN 116109011B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- park
- data
- prediction result
- historical
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 333
- 238000007726 management method Methods 0.000 title claims abstract description 27
- 230000015654 memory Effects 0.000 claims abstract description 61
- 238000012544 monitoring process Methods 0.000 claims abstract description 53
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 230000007787 long-term memory Effects 0.000 claims description 23
- 238000000034 method Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003064 k means clustering 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Computational Linguistics (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an energy consumption management method and a terminal for an intelligent park, wherein a first long-short-term memory network model is a long-short-term memory network model for predicting by taking a day as a unit, a second long-short-term memory network model is a long-short-term memory network model for predicting by taking a preset period as a unit, the two models are used for energy consumption prediction, a final energy consumption prediction result of the prediction day is obtained according to the obtained first energy consumption prediction result and the second energy consumption prediction result, when the final energy consumption prediction result of the prediction day exceeds a preset threshold, the energy consumption of a park area corresponding to the final energy consumption prediction result exceeding the preset threshold is monitored, when the monitoring result exceeds the preset threshold, energy consumption equipment of the park area is optimized, targeted energy consumption monitoring can be realized, the omission of the energy consumption exceeding the target area is avoided, and finally energy consumption equipment of the exceeding the target park area is optimized, so that the pertinence and the effectiveness of the energy consumption management of the park are improved, and the energy utilization rate of the park is improved.
Description
Technical Field
The invention relates to the technical field of energy consumption management, in particular to an energy consumption management method and terminal for an intelligent park.
Background
At present, the construction speed of wisdom garden is showing and is promoted, and the energy consumption management and control in the well garden is the important work of wisdom garden carbon emission reduction, and the area in present garden is big and complicated, and is not good to the monitoring effect of the energy consumption monitoring in garden, can't improve the energy utilization in garden.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the energy consumption management method and the terminal for the intelligent park can improve pertinence and effectiveness of energy consumption management of the park.
In order to solve the technical problems, the invention adopts a technical scheme that:
an energy consumption management method for an intelligent park, comprising the steps of:
respectively using a first long-short-term memory network model and a second long-term memory network model to predict the energy consumption of a prediction day based on the obtained historical energy consumption data of different park areas to obtain a first energy consumption prediction result and a second energy consumption prediction result, wherein the first long-term memory network model is a long-term memory network model for predicting in a daily unit, and the second long-term memory network model is a long-term memory network model for predicting in a preset period unit, and the preset period is longer than 24 hours;
obtaining a final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result;
judging whether the final energy consumption prediction result of the prediction day exceeds a preset threshold value, if so, performing energy consumption monitoring on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold value to obtain a monitoring result;
and judging whether the monitoring result exceeds the preset threshold value, and if so, optimizing the energy consumption equipment of the park area.
In order to solve the technical problems, the invention adopts another technical scheme that:
an energy consumption management terminal for a smart park comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
respectively using a first long-short-term memory network model and a second long-term memory network model to predict the energy consumption of a prediction day based on the obtained historical energy consumption data of different park areas to obtain a first energy consumption prediction result and a second energy consumption prediction result, wherein the first long-term memory network model is a long-term memory network model for predicting in a daily unit, and the second long-term memory network model is a long-term memory network model for predicting in a preset period unit, and the preset period is longer than 24 hours;
obtaining a final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result;
judging whether the final energy consumption prediction result of the prediction day exceeds a preset threshold value, if so, performing energy consumption monitoring on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold value to obtain a monitoring result;
and judging whether the monitoring result exceeds the preset threshold value, and if so, optimizing the energy consumption equipment of the park area.
The invention has the beneficial effects that: the first long-short-period memory network model is a long-short-period memory network model which predicts by taking a day as a unit, the second long-short-period memory network model is a long-short-period memory network model which predicts by taking a preset period as a unit, the two models are used for energy consumption prediction, a final energy consumption prediction result of a prediction day is obtained according to the obtained first energy consumption prediction result and the second energy consumption prediction result, when the final energy consumption prediction result of the prediction day exceeds a preset threshold, the energy consumption monitoring is carried out on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold, when the monitoring result exceeds the preset threshold, the energy consumption equipment of the park area is optimized, the prediction is carried out by taking the day as a unit and the preset period as a unit through prediction fusion, the prediction accuracy rate is effectively improved, the area which can be possibly subjected to energy consumption exceeding is predicted in advance, the area exceeding the preset threshold is monitored in advance, the area exceeding the preset threshold is prevented from being monitored in a large and complex area without any purpose and in a gravity center, the energy consumption monitoring is realized, and finally the energy consumption exceeding area is managed by the park area, and the energy consumption exceeding efficiency is improved.
Drawings
FIG. 1 is a flow chart of steps of a method for energy consumption management in an intelligent park according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of an energy consumption management terminal of an intelligent park according to an embodiment of the present invention.
Detailed Description
In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings.
Referring to fig. 1, an embodiment of the present invention provides an energy consumption management method for an intelligent park, including the steps of:
respectively using a first long-short-term memory network model and a second long-term memory network model to predict the energy consumption of a prediction day based on the obtained historical energy consumption data of different park areas to obtain a first energy consumption prediction result and a second energy consumption prediction result, wherein the first long-term memory network model is a long-term memory network model for predicting in a daily unit, and the second long-term memory network model is a long-term memory network model for predicting in a preset period unit, and the preset period is longer than 24 hours;
obtaining a final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result;
judging whether the final energy consumption prediction result of the prediction day exceeds a preset threshold value, if so, performing energy consumption monitoring on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold value to obtain a monitoring result;
and judging whether the monitoring result exceeds the preset threshold value, and if so, optimizing the energy consumption equipment of the park area.
From the above description, the beneficial effects of the invention are as follows: the first long-short-period memory network model is a long-short-period memory network model which predicts by taking a day as a unit, the second long-short-period memory network model is a long-short-period memory network model which predicts by taking a preset period as a unit, the two models are used for energy consumption prediction, a final energy consumption prediction result of a prediction day is obtained according to the obtained first energy consumption prediction result and the second energy consumption prediction result, when the final energy consumption prediction result of the prediction day exceeds a preset threshold, the energy consumption monitoring is carried out on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold, when the monitoring result exceeds the preset threshold, the energy consumption equipment of the park area is optimized, the prediction is carried out by taking the day as a unit and the preset period as a unit through prediction fusion, the prediction accuracy rate is effectively improved, the area which can be possibly subjected to energy consumption exceeding is predicted in advance, the area exceeding the preset threshold is monitored in advance, the area exceeding the preset threshold is prevented from being monitored in a large and complex area without any purpose and in a gravity center, the energy consumption monitoring is realized, and finally the energy consumption exceeding area is managed by the park area, and the energy consumption exceeding efficiency is improved.
Further, the predicting the energy consumption of the prediction day based on the obtained historical energy consumption data of different park areas by using the first long-short-period memory network model and the second long-period memory network model respectively, before obtaining the first energy consumption prediction result and the second energy consumption prediction result, includes:
acquiring first historical energy consumption data and second historical energy consumption data of different park areas, wherein the first historical energy consumption data is historical energy consumption data of a preset day before the prediction day, and the second historical energy consumption data is historical energy consumption data of the same day as the prediction day in a preset historical year before the prediction day;
clustering the first historical energy consumption data and the second historical energy consumption data by using a clustering algorithm respectively to obtain clustered first historical energy consumption data and clustered second historical energy consumption data;
the energy consumption prediction for the prediction day based on the obtained historical energy consumption data of different park areas by using the first long-short-period memory network model and the second long-period memory network model respectively, and the obtaining of the first energy consumption prediction result and the second energy consumption prediction result comprises the following steps:
using a first long-short-term memory network model to predict the energy consumption of the prediction day according to the clustered first historical energy consumption data, and obtaining a first energy consumption prediction result;
and carrying out energy consumption prediction on the prediction day according to the clustered second historical energy consumption data by using a second long-short-term memory network model to obtain a second energy consumption prediction result.
From the above description, the first historical energy consumption data and the second historical energy consumption data are clustered by using a clustering algorithm respectively, and then the long-term and short-term memory network model is used for prediction after clustering, so that the situations that the characteristic selection of the historical energy consumption data is inaccurate and the characteristic selection is possibly in local minimization are avoided, the effective information is prevented from disappearing due to long interval span of the data, the accuracy of energy consumption prediction is improved, and the reliability of follow-up monitoring is further ensured.
Further, the obtaining the final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result includes:
and carrying out weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result by using a linear weighting method to obtain a final energy consumption prediction result of the prediction day.
Further, the performing weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result by using a linear weighting method, and obtaining a final energy consumption prediction result of the prediction day includes:
F EC = p 1 EC ×F 1 EC +F 2 EC ×p 2 EC ；
wherein F is EC Representing the final energy consumption prediction result of the prediction day, p 1 EC Weights representing the first energy consumption prediction result, p 2 EC Weights representing the second energy consumption prediction result, F 1 EC Representing the first energy consumption prediction result, F 2 EC And representing the second energy consumption prediction result.
From the above description, it can be seen that the linear weighting method is used to perform weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result, so as to effectively fuse the two energy consumption prediction results, and improve the reliability and accuracy of the energy consumption prediction results.
Further, the energy consumption monitoring is performed on the campus area corresponding to the final energy consumption prediction result exceeding the preset threshold, and the obtaining of the monitoring result includes:
dividing areas of park areas corresponding to final energy consumption prediction results exceeding a preset threshold value to obtain a plurality of park areas;
respectively monitoring the energy consumption of the plurality of campus areas to obtain monitoring results corresponding to the campus areas;
judging whether the monitoring result exceeds the preset threshold value, if so, optimizing the energy consumption equipment of the park area comprises the following steps:
judging whether the monitoring result corresponding to the park sub-area exceeds the preset threshold value, if so, determining the park sub-area corresponding to the monitoring result exceeding the preset threshold value as an abnormal park sub-area, and optimizing energy consumption equipment of the abnormal park sub-area.
According to the above description, the region division is performed on the park region corresponding to the final energy consumption prediction result exceeding the preset threshold, the energy consumption monitoring is performed on the park regions obtained by the division, and the region division after the prediction that the energy consumption exceeds the standard is monitored, so that the finer energy consumption monitoring is realized, and the more accurate energy consumption monitoring result can be obtained.
Further, the optimizing the energy consumption equipment of the abnormal campus sub-area includes:
acquiring environment data and people stream data of the abnormal park subarea;
determining adjusting parameters corresponding to the energy consumption equipment of the abnormal park subarea according to the environment data and the people stream data and preset rules;
and optimizing the energy consumption equipment according to the adjustment parameters.
According to the description, the adjusting parameters corresponding to the energy consumption equipment in the abnormal park sub-area are determined according to the environment data and the people stream data and the preset rules, the influence of people stream and the environment on different energy consumption equipment is comprehensively considered, and effective energy consumption optimization is achieved.
Further, the people stream data includes people number and density;
the determining the adjusting parameters corresponding to the energy consumption equipment of the abnormal park sub-area according to the environment data and the people stream data and the preset rule comprises the following steps:
determining the people flow of the abnormal park subarea according to the number of people and the density;
determining a people flow gradient value according to the people flow;
determining an environment regulation parameter corresponding to the environment data and a people flow regulation parameter corresponding to the people flow gradient value according to a preset rule;
determining the type of the energy consumption equipment, and determining the weight of the environment adjusting parameter and the weight of the people flow adjusting parameter according to the type;
and determining the adjusting parameters corresponding to the energy consumption equipment of the abnormal park subarea according to the environment adjusting parameters, the weights of the environment adjusting parameters, the people flow adjusting parameters and the weights of the people flow adjusting parameters.
According to the description, the weight of the environment adjusting parameter and the weight of the people flow adjusting parameter are determined according to the type of the energy consumption equipment, different optimization adjusting methods can be used pertinently according to different energy consumption equipment, the energy consumption of a park is effectively reduced, and the energy utilization rate of the park is improved.
Further, before clustering the first historical energy consumption data and the second historical energy consumption data by using a clustering algorithm to obtain clustered first historical energy consumption data and clustered second historical energy consumption data, the method includes:
and respectively carrying out normalization processing on the first historical energy consumption data and the second historical energy consumption data to obtain normalized first historical energy consumption data and normalized second historical energy consumption data.
From the above description, the first historical energy consumption data and the second historical energy consumption data are respectively normalized, so that the subsequent data processing is more convenient and faster, the convergence speed of the algorithm is improved, and the calculation efficiency of the model fitting process is improved.
Further, the energy consumption prediction for the prediction day is performed according to the clustered first historical energy consumption data by using the first long-short-term memory network model, and before obtaining the first energy consumption prediction result, the method includes:
dividing the clustered first historical energy consumption data into first training set data and first test set data;
and inputting the first training set data into an initial first long-short-term memory network model for iteration and calculating an error, judging whether the error is smaller than a preset error and whether the iteration times exceed the preset times, if not, continuing to iterate, if so, inputting the first testing set data into the initial first long-short-term memory network model for verification, and obtaining the first long-short-term memory network model after the verification is completed.
From the above description, the clustered first historical energy consumption data is divided into the first training set data and the first test set data, so that the obtained first long-term and short-term memory network model can be quickly trained, the performance of the model obtained by training can be ensured, and the accuracy of energy consumption prediction is improved.
Referring to fig. 2, another embodiment of the present invention provides an energy consumption management terminal for a smart campus, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements each step in the energy consumption management method for the smart campus when executing the computer program.
The energy consumption management method and the terminal for the intelligent park can be applied to different intelligent parks, such as an industrial park, a logistics park and the like, and are described in the following specific embodiments:
example 1
The energy consumption management method of the intelligent park of the embodiment comprises the following steps:
s1, acquiring first historical energy consumption data and second historical energy consumption data of different park areas, wherein the first historical energy consumption data are historical energy consumption data of a preset day before a prediction day, and the second historical energy consumption data are historical energy consumption data of the same day as the prediction day in a preset historical year before the prediction day;
wherein the preset days and the preset historical year can be set according to actual conditions, and in an optional implementation manner, the preset days are 10 days, and the preset historical year is 5 years;
for example, if the predicted day is 2023, 3 and 30, then the first historical energy consumption data is 2023, 3, 20, 3, and 29, and the second historical energy consumption data is 2018, 3, 30, 2020, 3, 30, 2021, and 2022, 3, 30.
S2, respectively carrying out normalization processing on the first historical energy consumption data and the second historical energy consumption data to obtain normalized first historical energy consumption data and normalized second historical energy consumption data.
S3, clustering the first historical energy consumption data and the second historical energy consumption data by using a clustering algorithm respectively to obtain clustered first historical energy consumption data and clustered second historical energy consumption data;
in an alternative embodiment, the clustering algorithm is a K-means clustering algorithm.
S4, dividing the clustered first historical energy consumption data into first training set data and first test set data;
in an alternative embodiment, 80% of the clustered first historical energy consumption data is divided into first training set data, and 20% is divided into first test set data.
S5, inputting the first training set data into an initial first long-short-period memory network model for iteration and calculating errors, judging whether the errors are smaller than preset errors and whether the iteration times exceed preset times, if not, continuing to iterate, if so, inputting the first testing set data into the initial first long-short-period memory network model for verification, and obtaining a first long-short-period memory network model after verification is completed;
in an alternative embodiment, each sample in the first training set data includes a date and a corresponding historical energy consumption, the date is used as a target input, and a plurality of historical energy consumption are used as target outputs to train the initial first long-short-term memory network model, so that parameters in the model are updated.
S6, dividing the clustered second historical energy consumption data into second training set data and second test set data;
in an alternative embodiment, 80% of the clustered second historical energy consumption data is divided into second training set data, and 20% is divided into second test set data.
And S7, inputting the second training set data into an initial second long-short-period memory network model for iteration and calculating errors, judging whether the errors are smaller than preset errors and whether the iteration times exceed preset times, if not, continuing to iterate, if so, inputting the second testing set data into the initial second long-period memory network model for verification, and obtaining the second long-period memory network model after verification is completed.
S8, respectively using a first long-short-term memory network model and a second long-term memory network model to predict the energy consumption of a prediction day based on the obtained historical energy consumption data of different park areas, so as to obtain a first energy consumption prediction result and a second energy consumption prediction result, wherein the first long-short-term memory network model is a long-short-term memory network model for predicting in a daily unit, the second long-short-term memory network model is a long-short-term memory network model for predicting in a preset period unit, and the preset period is more than 24 hours, as shown in fig. 1, and specifically comprises:
s81, performing energy consumption prediction on the prediction day according to the clustered first historical energy consumption data by using a first long-short-term memory network model to obtain a first energy consumption prediction result;
s82, performing energy consumption prediction on the prediction day according to the clustered second historical energy consumption data by using a second long-short-term memory network model to obtain a second energy consumption prediction result.
S9, obtaining a final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result, as shown in FIG. 1;
specifically, a linear weighting method is used for carrying out weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result, and a final energy consumption prediction result of the prediction day is obtained, specifically:
F EC = p 1 EC ×F 1 EC +F 2 EC ×p 2 EC ；
wherein F is EC Representing the final energy consumption prediction result of the prediction day, p 1 EC Weights representing the first energy consumption prediction result, p 2 EC Weights representing the second energy consumption prediction result, F 1 EC Representing the first energy consumption prediction result, F 2 EC And representing the second energy consumption prediction result.
S10, judging whether a final energy consumption prediction result of the prediction day exceeds a preset threshold, if so, performing energy consumption monitoring on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold to obtain a monitoring result, wherein the monitoring result is shown in fig. 1 and specifically comprises the following steps:
in an alternative embodiment, after performing normalized inverse operation processing on the final energy consumption prediction result of the prediction day, obtaining a final energy consumption prediction value, and judging whether the final energy consumption prediction value exceeds a preset threshold value;
s101, carrying out regional division on a park area corresponding to a final energy consumption prediction result exceeding a preset threshold value to obtain a plurality of park subareas;
for example, the campus may be divided into different areas including a, B, and C, and the area a includes two buildings provided that the area a in the campus corresponding to the final energy consumption prediction result exceeding the preset threshold is: a1 and a2 can be divided according to floors to obtain a plurality of park subareas.
S102, respectively monitoring the energy consumption of the plurality of campus areas to obtain monitoring results corresponding to the campus areas;
s11, judging whether the monitoring result exceeds the preset threshold value, if so, optimizing energy consumption equipment of the campus area, as shown in fig. 1;
specifically, whether the monitoring result corresponding to the park sub-area exceeds the preset threshold value is judged, if yes, the park sub-area corresponding to the monitoring result exceeding the preset threshold value is determined to be an abnormal park sub-area, and the energy consumption equipment of the abnormal park sub-area is optimized, and the method specifically comprises the following steps:
s111, determining a park zone corresponding to the monitoring result exceeding the preset threshold as an abnormal park zone, and acquiring environment data and people stream data of the abnormal park zone;
wherein the people stream data comprises the number of people and the density; the environmental data includes temperature, humidity, brightness, air quality, etc.
Specifically, the environmental data is obtained through the sensor equipment, the video data of the abnormal park sub-area is obtained, and the video data is identified and analyzed to obtain the people stream data.
S112, determining adjusting parameters corresponding to the energy consumption equipment of the abnormal park sub-area according to the environment data and the people stream data and preset rules, wherein the adjusting parameters specifically comprise:
s1121, determining the people flow of the abnormal park subarea according to the number of people and the density;
s1122, determining a people flow gradient value according to the people flow;
in an alternative embodiment, the people flow rate is 0 person per five square meters to 2 persons per five square meters, the corresponding people flow rate gradient value is 2, the people flow rate is 3 persons per five square meters to 5 persons per five square meters, the corresponding people flow rate gradient value is 5, the people flow rate is 6 persons per five square meters to 10 persons per five square meters, the corresponding people flow rate gradient value is 7, the people flow rate is 11 persons per five square meters to 15 persons per five square meters, the corresponding people flow rate gradient value is 10, the people flow rate is 16 persons per five square meters to 25 persons per five square meters, and the corresponding people flow rate gradient value is 15.
S1123, determining an environment adjustment parameter corresponding to the environment data and a people flow adjustment parameter corresponding to the people flow gradient value according to a preset rule;
the preset rules are that corresponding environment adjusting parameters are set according to different environment data, and corresponding people flow adjusting parameters are set according to different people flow gradient values.
S1124, determining the type of the energy consumption equipment, and determining the weight of the environment adjusting parameter and the weight of the people flow adjusting parameter according to the type;
in an alternative embodiment, the energy consumption device comprises a lighting device, a heating device and a fresh air device, and the types correspondingly comprise a lighting type, a heating type and a fresh air type.
For example, the energy consumption device of the lighting type is mainly related to the brightness of the surrounding environment, and thus the weight of the brightness adjusting parameter among the environment adjusting parameters can be determined higher, while the weight of the temperature, humidity and air quality adjusting parameters is determined lower.
S1125, determining the adjusting parameters corresponding to the energy consumption equipment of the abnormal park subarea according to the environment adjusting parameters, the weight of the environment adjusting parameters, the people flow adjusting parameters and the weight of the people flow adjusting parameters.
S1126, optimizing the energy consumption equipment according to the adjustment parameters, so that the influence of the traffic and the environment on the energy consumption equipment is considered, for example, the energy consumption equipment is a lighting equipment, the brightness of the lighting equipment can be reduced under the environment with less traffic or high brightness, and even the lighting equipment in the partial area is closed, so that the effect of reducing the energy consumption is achieved.
Example two
Referring to fig. 2, an energy consumption management terminal for a smart campus of the present embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the energy consumption management method for the smart campus of the first embodiment when executing the computer program.
In summary, the method and the terminal for managing energy consumption in an intelligent park provided by the invention have the advantages that the first long-short-term memory network model is a long-short-term memory network model for predicting in a daily unit, the second long-short-term memory network model is a long-short-term memory network model for predicting in a preset period unit, the two models are used for energy consumption prediction, a final energy consumption prediction result for predicting the daily is obtained according to the obtained first energy consumption prediction result and the second energy consumption prediction result, when the final energy consumption prediction result of the predicting daily exceeds a preset threshold, the energy consumption monitoring is performed on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold, when the monitoring result exceeds the preset threshold, the energy consumption equipment of the park area is optimized, the prediction accuracy is effectively improved, the area with possible energy consumption exceeding the preset threshold can be predicted in advance, the area with the prediction result exceeding the preset threshold is monitored in a major mode, the situation that the area is monitored in a large and complex area without any purpose and in a gravity center is avoided, the targeted energy consumption monitoring is realized, and finally the energy consumption exceeding area is used for the park, and the energy consumption equipment of the park is optimized, so that the energy consumption efficiency of the park is improved; in addition, the first historical energy consumption data and the second historical energy consumption data are clustered by using a clustering algorithm respectively, and then the long-period and short-period memory network model is used for prediction after clustering, so that the situations that the characteristic selection of the historical energy consumption data is inaccurate and the characteristic selection is possibly in local minimization are avoided, the effective information is prevented from disappearing due to long interval span of the data, the accuracy of energy consumption prediction is improved, and the reliability of follow-up monitoring is further guaranteed.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent changes made by the specification and drawings of the present invention, or direct or indirect application in the relevant art, are included in the scope of the present invention.
Claims (7)
1. An energy consumption management method for an intelligent park is characterized by comprising the following steps:
respectively using a first long-short-term memory network model and a second long-term memory network model to predict the energy consumption of a prediction day based on the obtained historical energy consumption data of different park areas to obtain a first energy consumption prediction result and a second energy consumption prediction result, wherein the first long-term memory network model is a long-term memory network model for predicting in a daily unit, and the second long-term memory network model is a long-term memory network model for predicting in a preset period unit, and the preset period is longer than 24 hours;
obtaining a final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result;
judging whether the final energy consumption prediction result of the prediction day exceeds a preset threshold value, if so, performing energy consumption monitoring on a park area corresponding to the final energy consumption prediction result exceeding the preset threshold value to obtain a monitoring result;
judging whether the monitoring result exceeds the preset threshold value, if so, optimizing the energy consumption equipment of the park area;
the method for predicting the energy consumption of the park area comprises the steps of:
acquiring first historical energy consumption data and second historical energy consumption data of different park areas, wherein the first historical energy consumption data is historical energy consumption data of a preset day before the prediction day, and the second historical energy consumption data is historical energy consumption data of the same day as the prediction day in a preset historical year before the prediction day;
clustering the first historical energy consumption data and the second historical energy consumption data by using a clustering algorithm respectively to obtain clustered first historical energy consumption data and clustered second historical energy consumption data;
the energy consumption prediction for the prediction day based on the obtained historical energy consumption data of different park areas by using the first long-short-period memory network model and the second long-period memory network model respectively, and the obtaining of the first energy consumption prediction result and the second energy consumption prediction result comprises the following steps:
using a first long-short-term memory network model to predict the energy consumption of the prediction day according to the clustered first historical energy consumption data, and obtaining a first energy consumption prediction result;
using a second long-short-term memory network model to predict the energy consumption of the predicted day according to the clustered second historical energy consumption data to obtain a second energy consumption prediction result;
the obtaining the final energy consumption prediction result of the prediction day according to the first energy consumption prediction result and the second energy consumption prediction result includes:
performing weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result by using a linear weighting method to obtain a final energy consumption prediction result of the prediction day;
the step of performing weighted average processing on the first energy consumption prediction result and the second energy consumption prediction result by using a linear weighting method, and obtaining a final energy consumption prediction result of the prediction day includes:
F EC = p 1 EC ×F 1 EC +F 2 EC ×p 2 EC ；
wherein F is EC Representing the final energy consumption prediction result of the prediction day, p 1 EC Weights representing the first energy consumption prediction result, p 2 EC Weights representing the second energy consumption prediction result, F 1 EC Representing the first energy consumption prediction result, F 2 EC And representing the second energy consumption prediction result.
2. The method for energy consumption management of an intelligent campus according to claim 1, wherein the monitoring energy consumption of the campus corresponding to the final energy consumption prediction result exceeding the preset threshold value, and obtaining the monitoring result includes:
dividing areas of park areas corresponding to final energy consumption prediction results exceeding a preset threshold value to obtain a plurality of park areas;
respectively monitoring the energy consumption of the plurality of campus areas to obtain monitoring results corresponding to the campus areas;
judging whether the monitoring result exceeds the preset threshold value, if so, optimizing the energy consumption equipment of the park area comprises the following steps:
judging whether the monitoring result corresponding to the park sub-area exceeds the preset threshold value, if so, determining the park sub-area corresponding to the monitoring result exceeding the preset threshold value as an abnormal park sub-area, and optimizing energy consumption equipment of the abnormal park sub-area.
3. The energy consumption management method for a smart campus of claim 2, wherein optimizing the energy consumption device for the abnormal campus area comprises:
acquiring environment data and people stream data of the abnormal park subarea;
determining adjusting parameters corresponding to the energy consumption equipment of the abnormal park subarea according to the environment data and the people stream data and preset rules;
and optimizing the energy consumption equipment according to the adjustment parameters.
4. A method of energy consumption management for an intelligent campus according to claim 3, wherein said people stream data includes people and density;
the determining the adjusting parameters corresponding to the energy consumption equipment of the abnormal park sub-area according to the environment data and the people stream data and the preset rule comprises the following steps:
determining the people flow of the abnormal park subarea according to the number of people and the density;
determining a people flow gradient value according to the people flow;
determining an environment regulation parameter corresponding to the environment data and a people flow regulation parameter corresponding to the people flow gradient value according to a preset rule;
determining the type of the energy consumption equipment, and determining the weight of the environment adjusting parameter and the weight of the people flow adjusting parameter according to the type;
and determining the adjusting parameters corresponding to the energy consumption equipment of the abnormal park subarea according to the environment adjusting parameters, the weights of the environment adjusting parameters, the people flow adjusting parameters and the weights of the people flow adjusting parameters.
5. The method for managing energy consumption of an intelligent park according to claim 1, wherein before clustering the first historical energy consumption data and the second historical energy consumption data by using a clustering algorithm to obtain clustered first historical energy consumption data and clustered second historical energy consumption data, respectively, the method comprises:
and respectively carrying out normalization processing on the first historical energy consumption data and the second historical energy consumption data to obtain normalized first historical energy consumption data and normalized second historical energy consumption data.
6. The energy consumption management method for an intelligent park according to claim 1, wherein the energy consumption prediction for the prediction day according to the clustered first historical energy consumption data by using the first long-short-term memory network model comprises, before obtaining the first energy consumption prediction result:
dividing the clustered first historical energy consumption data into first training set data and first test set data;
and inputting the first training set data into an initial first long-short-term memory network model for iteration and calculating an error, judging whether the error is smaller than a preset error and whether the iteration times exceed the preset times, if not, continuing to iterate, if so, inputting the first testing set data into the initial first long-short-term memory network model for verification, and obtaining the first long-short-term memory network model after the verification is completed.
7. A terminal for energy consumption management of a smart park comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of a method for energy consumption management of a smart park according to any one of claims 1 to 6 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310373068.3A CN116109011B (en) | 2023-04-10 | 2023-04-10 | Energy consumption management method and terminal for intelligent park |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310373068.3A CN116109011B (en) | 2023-04-10 | 2023-04-10 | Energy consumption management method and terminal for intelligent park |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116109011A CN116109011A (en) | 2023-05-12 |
| CN116109011B true CN116109011B (en) | 2023-06-23 |
Family
ID=86260051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310373068.3A Active CN116109011B (en) | 2023-04-10 | 2023-04-10 | Energy consumption management method and terminal for intelligent park |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109011B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117077854B (en) * | 2023-08-15 | 2024-04-16 | 广州视声智能科技有限公司 | Building energy consumption monitoring method and system based on sensor network |
| CN117989676B (en) * | 2024-04-07 | 2024-06-25 | 江苏华复保利环保科技有限公司 | Air conditioner energy consumption data supervision method and system based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949947A (en) * | 2021-04-19 | 2021-06-11 | 广东电网有限责任公司计量中心 | Power failure early warning method and system based on convolution long-term and short-term memory network |
| CN114065635A (en) * | 2021-11-22 | 2022-02-18 | 中国民航大学 | Aircraft ground air conditioner energy consumption prediction method based on IALO-AM-BilSTM model and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214610B (en) * | 2018-11-16 | 2022-05-31 | 国网江苏省电力有限公司经济技术研究院 | Saturated power load prediction method based on long-term and short-term memory neural network |
| CN111145541B (en) * | 2019-12-18 | 2021-10-22 | 深圳先进技术研究院 | Traffic flow data prediction method, storage medium, and computer device |
| CN112381673B (en) * | 2021-01-07 | 2021-04-20 | 武汉中原电子信息有限公司 | Park electricity utilization information analysis method and device based on digital twin |
| CN113128793A (en) * | 2021-05-19 | 2021-07-16 | 中国南方电网有限责任公司 | Photovoltaic power combination prediction method and system based on multi-source data fusion |
| CN113341855A (en) * | 2021-06-22 | 2021-09-03 | 郑州天健湖大数据产业园发展有限公司 | Comprehensive energy consumption monitoring system applied to smart park |
| CN114492946A (en) * | 2021-12-31 | 2022-05-13 | 杭州拓深科技有限公司 | Method, device and equipment for performing fine management on energy consumption of electric appliances in park based on LSTM |
| CN115524554A (en) * | 2022-09-09 | 2022-12-27 | 杨本国 | Comprehensive operation management method and system for intelligent park |
-
2023
- 2023-04-10 CN CN202310373068.3A patent/CN116109011B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949947A (en) * | 2021-04-19 | 2021-06-11 | 广东电网有限责任公司计量中心 | Power failure early warning method and system based on convolution long-term and short-term memory network |
| CN114065635A (en) * | 2021-11-22 | 2022-02-18 | 中国民航大学 | Aircraft ground air conditioner energy consumption prediction method based on IALO-AM-BilSTM model and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116109011A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116109011B (en) | Energy consumption management method and terminal for intelligent park | |
| KR102380397B1 (en) | METHOD FOR MANAGING SMART BUILDING USING IoT SENSOR AND ARTIFICIAL INTELIGENCE | |
| CN112465243B (en) | Air quality forecasting method and system | |
| CN110648014B (en) | Regional wind power prediction method and system based on space-time quantile regression | |
| WO2015172560A1 (en) | Central air conditioner cooling load prediction method based on bp neural network | |
| US11175061B2 (en) | Methods and systems for HVAC inefficiency prediction | |
| CN106779129A (en) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor | |
| CN109116444B (en) | PCA-kNN-based air quality model PM2.5Forecasting method | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN116776745B (en) | Method and system for predicting pollutant concentration and track movement based on edge calculation | |
| CN109858700A (en) | BP neural network heating system energy consumption prediction technique based on similar screening sample | |
| CN111080039A (en) | Fan cluster fault prediction method and system | |
| CN113408659A (en) | Building energy consumption integrated analysis method based on data mining | |
| CN113033910A (en) | Photovoltaic power generation power prediction method, storage medium and terminal equipment | |
| CN113177857A (en) | Resource elastic allocation method based on typhoon disaster estimation | |
| CN117688846A (en) | Reinforced learning prediction method and system for building energy consumption and storage medium | |
| CN114358395A (en) | Attendance checking prediction method and device | |
| CN117390399A (en) | Highway pre-maintenance method and system based on deep learning, electronic equipment and medium | |
| CN116776263A (en) | Data-driven-based method and system for detecting abnormal high energy consumption of block-scale building | |
| CN116610039A (en) | Building management method, electronic device and readable storage medium | |
| CN116565850A (en) | Wind power ultra-short-term prediction method based on QR-BLSTM | |
| CN116182347A (en) | Intelligent ventilation control method and system for production process | |
| CN115879190A (en) | Model construction method and device and building load prediction method and device | |
| WO2022162798A1 (en) | Power demand prediction device, power demand prediction method, and program | |
| CN113723670A (en) | Photovoltaic power generation power short-term prediction method with variable time window |
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 |