CN116702424A - Big data intelligence emission reduction system - Google Patents
Big data intelligence emission reduction system Download PDFInfo
- Publication number
- CN116702424A CN116702424A CN202310464522.6A CN202310464522A CN116702424A CN 116702424 A CN116702424 A CN 116702424A CN 202310464522 A CN202310464522 A CN 202310464522A CN 116702424 A CN116702424 A CN 116702424A
- Authority
- CN
- China
- Prior art keywords
- module
- energy consumption
- big data
- prediction
- follows
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000009467 reduction Effects 0.000 title claims abstract description 20
- 238000005265 energy consumption Methods 0.000 claims abstract description 67
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 38
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 229910052739 hydrogen Inorganic materials 0.000 claims description 37
- 239000001257 hydrogen Substances 0.000 claims description 37
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 36
- 238000003860 storage Methods 0.000 claims description 20
- 238000013178 mathematical model Methods 0.000 claims description 18
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 238000004146 energy storage Methods 0.000 claims description 15
- 238000011161 development Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 239000007789 gas Substances 0.000 claims description 9
- 230000006835 compression Effects 0.000 claims description 7
- 238000007906 compression Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 6
- 239000003795 chemical substances by application Substances 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 238000007418 data mining Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 3
- 239000001569 carbon dioxide Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 239000012528 membrane Substances 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000004134 energy conservation Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000003139 buffering effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 150000002431 hydrogen Chemical class 0.000 description 1
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Primary Health Care (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Entrepreneurship & Innovation (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a big data intelligent emission reduction system, which comprises a big data retrieval module, a monitoring module, a prediction module, an early warning module and an intelligent control module; the big data retrieval module is used for retrieving the energy consumption equipment and outputting a retrieval result to the prediction module; the monitoring module is used for monitoring the energy consumption of the energy consumption equipment and the carbon emission, and transmitting monitoring data to the prediction module; the prediction module is used for predicting according to the data transmitted by the big data retrieval module and the monitoring module, and transmitting a prediction result to the early warning module and the intelligent control module; the early warning module is used for analyzing the result of the prediction module and sending early warning to the management layer when necessary; the intelligent control module is used for adjusting the power of the energy consumption equipment according to the result of the prediction module; the prediction algorithm provided by the invention can be used for rapidly and accurately predicting the energy consumption value and the carbon emission of the energy consumption equipment, carrying out early warning and regulation, achieving the effects of energy conservation and emission reduction, and improving the utilization rate of energy sources.
Description
Technical Field
The invention relates to an intelligent emission reduction system, in particular to a big data intelligent emission reduction system.
Background
Deep learning is a new field in machine learning research, has great advantages in the aspect of processing big data, and can be used for carrying out training learning through a large amount of data, further extracting the characteristics of the bottom layer of the data to form more abstract high-level characteristics, forming a model of a certain type and predicting other data. Deep learning is well applied in the fields of computer vision, voice recognition, natural language processing and the like. The theory of the deep learning algorithm is adopted, and the deep learning algorithm which can be matched with the energy consumption data mining purpose is learned and selected based on the application fields of pattern recognition, image recognition, complex power system simulation and the like. However, in the prior art, the accuracy of a prediction result is not enough, the exploration capability of a prediction algorithm on the global optimal individual position is not high, the coverage on a search space is not strong, the influence of a random factor on the robustness of the algorithm is high, and the algorithm speed and the algorithm accuracy are not enough.
Disclosure of Invention
The invention aims to: the invention aims to provide a big data intelligent emission reduction system which can rapidly and accurately predict the energy consumption value and the carbon emission of energy consumption equipment, perform early warning and regulation and control and can improve the utilization rate of energy.
The technical scheme is as follows: the invention relates to a big data intelligent emission reduction system, which comprises a big data retrieval module, a monitoring module, a prediction module, an early warning module and an intelligent control module; the big data retrieval module is used for retrieving the energy consumption equipment, classifying and outputting the energy consumption equipment with different models and different powers, and transmitting the output result to the prediction module; the monitoring module is used for monitoring energy consumption and carbon emission of the energy consumption equipment and transmitting monitoring data to the prediction module; the prediction module is used for predicting according to the data transmitted by the big data retrieval module and the monitoring module, and transmitting a prediction result to the early warning module and the intelligent control module; the early warning module is used for analyzing the result of the prediction module and sending early warning to the management layer when necessary; the intelligent control module is used for adjusting the power of the energy consumption equipment according to the result of the prediction module.
The big data retrieval module is used for performing task decomposition processing on all data sets stored in the system by adopting a distributed parallel data mining mode, and summarizing by adopting a fuzzy C algorithm, wherein the fuzzy C algorithm is expressed as follows:
wherein u is ij Representing the clustering coefficient, D i Representing the number of tasks before decomposition, v j And (3) representing the number of decomposed tasks, wherein R and N are real numbers.
The big data retrieval module retrieval process mainly comprises the following steps:
(1) Establishing a system dictionary: constructing a basic word stock by utilizing an elastic search default word stock to finish the establishment of a dictionary;
(2) Establishing an information indexing mechanism: carrying out breadth index by adopting information such as equipment keywords, models and the like;
(3) Realizing an automatic searching scheme: and according to the requirements, the keywords are handed to an index request agent, the index memory matches the keyword information sent by the index agent, the relevance is ordered according to the search results, and finally the search results are input into the prediction module to complete the whole big data search flow.
The prediction module comprises an energy consumption prediction model, a carbon emission prediction model and an intelligent optimization algorithm for optimizing model weights, and the output result of the prediction module is an energy consumption value and a carbon emission in the future 24 hours.
The energy consumption prediction model and the carbon emission prediction model are realized as follows:
T 1 +T 2 =1
k 1 +k 2 =1
C=0.785E
in the middle ofE represents the total energy consumption value,indicating the i hour operating power of the air conditioner, < >>Indicating the i-th hour operating power of the lighting system, for example>Indicating the type of air conditioner big data retrieval power, < >>Representing the big data retrieval and acquisition power of the lighting system, T 1 And T 2 Indicating the air conditioner distribution time, k 1 And k 2 As a weighting factor, C represents carbon dioxide emissions;
the specific prediction algorithm comprises the following steps:
(1) Searching for optimal weight factor k by adopting improved eagle optimization algorithm IAO 1 And k 2 For ensuring prediction accuracy, the objective function is as follows:
wherein f represents a quantization standard for a prediction error, E i.T Representing the actual energy consumption value of the first data point, E i Representing a predicted energy consumption value of a first data point, wherein N represents the total number of groups in the energy consumption data;
(2) Randomly initializing a population position, wherein a population position matrix is as follows:
X ij =rand×(UB j -LB j )+LB j ,i=1,2,.....,N j=1,2,...,Dim
wherein: n represents population size and Dim represents the dimension of the search space;
(3) Establishing a mathematical model of an expanding search stage, wherein the mathematical model is as follows:
wherein X (t) and X (t+1) respectively represent the individual positions of the AO algorithm in the t th and t+1th iterations, X best (t) represents the current optimal individual position, X M (T) represents the average position of the population, T represents the maximum number of iterations;
(4) And (3) establishing a data model in a reduced search stage, wherein a model formula is as follows:
X 2 (t+1)=X best (t)×Levy(D)+X R (t)+(y-x)*rand
wherein Levy (D) represents a Levy flight strategy, s is a constant with a value of 0.01, and u and v are random numbers ranging between [0,1 ];
(5) The flight shape of x and y is determined, and the flight shape formula of x and y is as follows:
y=r×cos(θ)
x=r×sin(θ)
r=r 1 +U×D 1
θ=-ω×D 1 +θ 1
wherein r is the search step length, the value range is a constant between [1,20], and the value in the patent is 12; u is 0.00565; omega is 0.005;
(6) And establishing a mathematical model in an expansion development stage, wherein the mathematical model is as follows:
X 3 (t+1)=(X best (t)-X M (t))×a-rand+((UB-LB)×rand+LB)×δ
wherein a and delta represent developed adjustment parameters, and the values are 0.1;
(7) And establishing a mathematical model in a shrinking development stage, wherein the mathematical model is as follows:
X 4 (t+1)=QF×X best (t)-(G 1 ×X(t)×rand)-G 2 ×Levy(D)+rand×G 1
G 1 =2×rand-1
wherein QF (t) represents a quality function value for the balanced search strategy; g 1 Representing various movements of AO during the course of tracking a prey; g 2 The value of the flying slope which is reduced linearly is in the range of [0,2]Between them;
(8) The development stage of the algorithm is improved, the exploration capability of the algorithm on the global optimal individual position is ensured, the coverage of the search space is enhanced, and an improvement formula is shown as follows:
X 3 (t+1)=X best (t)+r 2 ×(X r (t)-X i (t))+μ×(X best (t)-X i (t))
wherein r is 2 And r 3 Between [0,1]]In between the two,X r (t) random eagle individuals in the current iterative population; mu is the screw coefficient;
(9) The algorithm is improved in the stage of shrinking and developing, the influence of the original random factor on the robustness of the algorithm is reduced, the later convergence speed and the algorithm precision are fully improved, and an improvement formula is shown as follows:
X 4 (t+1)=QF×X best (t)+r 4 ×Num×X i (t)
wherein r is 4 Between [0,1]]Between F r (t) random individuals X r Fitness value of (t), F i (t) is X i The fitness function value of (t).
The early warning module is used for comparing the standard energy consumption value and the standard carbon emission with the energy consumption value and the carbon emission in the future 24 hours transmitted by the prediction module, and sending early warning to the management layer when detecting that the energy consumption value and the carbon emission at a certain moment are higher than the standard energy consumption value and the standard carbon emission in the future 24 hours.
The range of the intelligent control module for adjusting the power of the energy consumption equipment is kept within the power range of the equipment which can normally work.
The big data intelligent emission reduction system also comprises a power supply module and a hydrogen production module.
The power supply module comprises a power grid and photovoltaic energy storage equipment, wherein the photovoltaic energy storage equipment consists of a plurality of photovoltaic plates and energy storage batteries, and the photovoltaic plates absorb solar energy to supply power to the energy consumption equipment and store redundant energy and the energy storage batteries; the photovoltaic energy storage device discharges in the power consumption peak period or the power failure period, charges in the power consumption valley period, improves the energy utilization rate, reduces the power supply pressure of a power grid, and inputs redundant power into the hydrogen production module.
The hydrogen production module is used for carrying out electrolytic hydrogen production by using redundant power of the power supply module and storing the redundant power, the hydrogen production mode is a PEM (proton exchange membrane) electrolytic tank, and the chemical reaction process is shown as the following formula:
2H 2 O→2H 2 +O 2
the storage steps are as follows:
(1) And (3) compressing hydrogen, namely compressing the hydrogen at normal temperature and normal pressure into a common required pressure standard, wherein the compression system equation is as follows:
wherein E is COM For the power consumption of the compressor,the hydrogen mass flow rate, K is the adiabatic index, the numerical value is 1.4, the air constant of the gas R is 4124J/(kg.times.K), T is the temperature of the compressed gas, and P 2 For gas compression pressure, P 1 Is the compressor inlet pressure;
(2) The hydrogen is stored through the storage tank system, the generation of the hydrogen has volatility, the requirement of the system on the hydrogen supply stability cannot be met, therefore, the hydrogen is required to be utilized through the hydrogen storage tank system to play a buffering role, the working pressure of the storage tank system is less than 20MPa, and the pressure formula of the storage tank is as follows:
wherein P is Hst Is the pressure of the storage tank and,for hydrogen mass, V Hst Is the volume of the storage tank, and the unit is m 3 。
The beneficial effects are that: compared with the prior art, the invention has the following remarkable advantages: 1. the energy consumption value and the carbon emission of the main energy consumption model can be accurately predicted, the power of energy consumption equipment can be intelligently regulated and controlled, and energy conservation and emission reduction can be effectively carried out; 2. the exploration capability of the prediction algorithm on the global optimal individual position is higher, the coverage on the search space is stronger, the influence of the original random factor on the robustness of the algorithm is reduced, and the later convergence speed and the algorithm precision are improved; 3. the utilization rate of energy sources is effectively improved.
Drawings
FIG. 1 is a structural frame diagram of the present invention;
FIG. 2 is a flowchart of an improved eagle optimization algorithm IAO adopted by the invention;
FIG. 3 is a graph comparing the amount of carbon emissions before and after intelligent emission reduction;
fig. 4 is a graph of the result of predicting the carbon emission amount.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and the embodiments.
As shown in fig. 1, the embodiment comprises a big data retrieval module, a monitoring module, a prediction module, an early warning module, an intelligent control module, a power supply module and a hydrogen production module;
the large data retrieval module retrieves main energy consumption equipment, classifies and outputs the main energy consumption equipment with different models and different powers, adopts a distributed parallel data mining mode to perform task decomposition processing on all data sets stored in the system, adopts a fuzzy C algorithm to summarize, and the fuzzy C algorithm is expressed as follows:
wherein u is ij Representing the clustering coefficient, D i Representing the number of tasks before decomposition, v j The number of decomposed tasks is represented, and R and N are real numbers;
the big data automatic search is mainly realized by the establishment of a system dictionary, the establishment of an information indexing mechanism and an automatic search scheme:
firstly, constructing a basic word stock by utilizing an elastic search default word stock to finish the establishment of a dictionary;
secondly, carrying out breadth index by adopting information such as equipment keywords, models and the like so as to improve the quality of retrieval service;
finally, according to the requirements, the keywords are handed to an index request agent, the index memory matches the keyword information sent by the index agent, the relevance is ordered according to the index result, and finally, the index result is input into the prediction module to complete the whole big data retrieval flow;
the result obtained by big data retrieval in the embodiment is that an air conditioner and a lighting system are main energy consumption devices, and the energy consumption of the air conditioner and the lighting system accounts for more than 70% of the total energy consumption devices, so the air conditioner and the lighting system are selected as objects of energy conservation and emission reduction for optimal control;
the detection module comprises energy consumption monitoring and carbon emission monitoring of main equipment, takes monitoring data and big data retrieval data as input and transmits the monitoring data and the big data retrieval data to the input end of the prediction module;
the prediction module comprises an energy consumption prediction model, a carbon emission prediction model and an intelligent optimization algorithm for optimizing model weights, predicts according to the detection module and data transmitted by big data retrieval, predicts energy consumption values and carbon emission in 24 hours in the future, and transmits prediction results to the early warning module and the intelligent control module;
the early warning module compares the energy consumption value and the carbon emission amount in the future 24 hours acquired from the prediction module with the standard energy consumption value and the standard carbon emission amount set in advance, and when the energy consumption value and the carbon emission amount at a certain moment in the future 24 hours are detected to be higher than the equipment standard, the early warning system sends early warning to the management layer;
the intelligent control module adjusts the power of the air conditioner and the lighting equipment on the premise of not influencing the work according to the energy consumption value and the carbon emission in the future 24 hours acquired from the prediction module, thereby achieving the effects of energy conservation and emission reduction.
The power supply system comprises a power grid and a photovoltaic energy storage device, wherein the photovoltaic energy storage device consists of a plurality of photovoltaic plates and lithium iron phosphate batteries, and the photovoltaic plates absorb solar energy to supply power and store redundant energy for coping with sudden power failure and other conditions; the photovoltaic energy storage equipment discharges in the electricity consumption peak period and charges in the electricity consumption valley period, so that the energy utilization rate can be effectively improved, and the power supply pressure of a power grid is reduced; meanwhile, the photovoltaic energy storage equipment can use redundant electric power for electrolytic hydrogen production, so that the electric energy utilization rate is further improved, and clean energy of hydrogen is obtained.
The hydrogen production module utilizes redundant power of the energy storage equipment to carry out electrolytic hydrogen production and store, the hydrogen production mode is a PEM (proton exchange membrane) electrolytic tank, and the chemical reaction process is shown in the following formula:
2H 2 O→2H 2 +O 2
the storage steps are as follows:
(1) Because the generated hydrogen is at normal temperature and normal pressure, the pressure requirement of the system cannot be met, and therefore the compression treatment is needed, and the compression system equation is as follows:
wherein E is COM For the power consumption of the compressor,the hydrogen mass flow rate, K is the adiabatic index, the numerical value is 1.4, the air constant of the gas R is 4124J/(kg.times.K), T is the temperature of the compressed gas, and P 2 For gas compression pressure, P 1 Is the compressor inlet pressure;
(2) The hydrogen is stored by the storage tank, the generation of the hydrogen has volatility, and the requirement of the system on the hydrogen supply stability cannot be met, so that the hydrogen is required to be utilized by the storage tank system to play a buffering role, the storage tank system with the working pressure below 20MPa is selected, and the storage tank pressure formula is shown as follows:
wherein P is Hst Is the pressure of the storage tank and,for hydrogen mass, V Hst Is the volume of the storage tank, and the unit is m 3
As shown in fig. 2, an energy consumption prediction model and a carbon emission prediction model are established according to the detection module and the data of the big data retrieval transmission, and the implementation process of the energy consumption prediction model and the carbon emission prediction model is as follows:
T 1 +T 2 =1
k 1 +k 2 =1
C=0.785E
where E represents the total energy consumption value,indicating the i hour operating power of the air conditioner, < >>Indicating the i-th hour operating power of the lighting system, for example>Indicating the type of air conditioner big data retrieval power, < >>Representing the big data retrieval and acquisition power of the lighting system, T 1 And T 2 Indicating the air conditioner distribution time, k 1 And k 2 As a weighting factor, C represents carbon dioxide emissions;
(1) Searching for optimal weight factor k by adopting improved eagle optimization algorithm IAO 1 And k 2 In this way, the prediction accuracy is ensured, and the objective function is as follows:
wherein f represents a quantization standard for a prediction error, E i.T Representing the actual energy consumption value of the first data point, E i Representing a predicted energy consumption value of a first data point, wherein N represents the total number of groups in the energy consumption data;
(2) Randomly initializing a population position, wherein a population position matrix is as follows:
X ij =rand×(UB j -LB j )+LB j ,i=1,2,.....,N j=1,2,...,Dim
wherein: n represents population size and Dim represents the dimension of the search space;
(3) Establishing a mathematical model of an expanding search stage, wherein the mathematical model is as follows:
wherein X (t) and X (t+1) respectively represent the individual positions of the AO algorithm in the t th and t+1th iterations, X best (t) represents the current optimal individual position, X M (T) represents the average position of the population, T represents the maximum number of iterations;
(4) And (3) establishing a data model in a reduced search stage, wherein a model formula is as follows:
X 2 (t+1)=X best (t)×Levy(D)+X R (t)+(y-x)*rand
wherein Levy (D) represents a Levy flight strategy, s is a constant with a value of 0.01, and u and v are random numbers ranging between [0,1 ];
(5) The flight shape of x and y is determined, and the flight shape formula of x and y is as follows:
y=r×cos(θ)
x=r×sin(θ)
r=r 1 +U×D 1
θ=-ω×D 1 +θ 1
wherein r is the search step length, the value range is a constant between [1,20], and the value in the patent is 12; u is 0.00565; omega is 0.005;
(6) And establishing a mathematical model in an expansion development stage, wherein the mathematical model is as follows:
X 3 (t+1)=(X best (t)-X M (t))×a-rand+((UB-LB)×rand+LB)×δ
wherein a and delta represent developed adjustment parameters, and the values are 0.1;
(7) And establishing a mathematical model in a shrinking development stage, wherein the mathematical model is as follows:
X 4 (t+1)=QF×X best (t)-(G 1 ×X(t)×rand)-G 2 ×Levy(D)+rand×G 1
G 1 =2×rand-1
wherein QF (t) represents a quality function value for the balanced search strategy; g 1 Representing various movements of AO during the course of tracking a prey; g 2 The value of the flying slope which is reduced linearly is in the range of [0,2]Between them;
(8) In order to ensure the exploration capability of the algorithm on the global optimal individual position and enhance the coverage of the search space, the development stage of the algorithm is improved, and the improvement formula is as follows:
X 3 (t+1)=X best (t)+r 2 ×(X r (t)-X i (t))+μ×(X best (t)-X i (t))
wherein r is 2 And r 3 Between [0,1]]Between X r (t) random eagle individuals in the current iterative population; mu is the screw coefficient;
(9) In order to reduce the influence of the original random factor on the robustness of the algorithm, the late convergence speed and the algorithm precision are fully improved, the algorithm is improved in the stage of shrinkage development, and the improvement formula is as follows:
X 4 (t+1)=QF×X best (t)+r 4 ×Num×X i (t)
wherein r is 4 Between [0,1]]Between F r (t) random individuals X r Fitness value of (t), F i (t) is X i The fitness function value of (t);
as shown in fig. 3, the carbon emission amount of the energy consumption equipment is 3130.5kg per day and the average carbon emission amount per hour is 130.43kg before intelligent emission reduction; after the intelligent emission reduction is performed by using the system, the daily carbon emission is 2485.5kg, and the average carbon emission per hour is 103.56kg, so that the energy conservation and emission reduction are performed by using the system, the emission reduction rate reaches 20.6%, and the emission reduction effect is obvious;
as shown in fig. 4, the prediction model of the embodiment is used for predicting the carbon emission, the prediction accuracy is high, the carbon emission amount per hour of actual data is about 130.43kg, the carbon emission amount per hour of the prediction result is about 130.77kg, and the average error is only 2.64%, so that the prediction result of the embodiment is used as the regulation and control basis of the intelligent control module.
Claims (10)
1. The big data intelligent emission reduction system is characterized by comprising a big data retrieval module, a monitoring module, a prediction module, an early warning module and an intelligent control module;
the big data retrieval module is used for retrieving the energy consumption equipment, classifying and outputting the energy consumption equipment with different models and different powers, and transmitting the output result to the prediction module;
the monitoring module is used for monitoring energy consumption and carbon emission of the energy consumption equipment and transmitting monitoring data to the prediction module;
the prediction module is used for predicting according to the data transmitted by the big data retrieval module and the monitoring module, and transmitting a prediction result to the early warning module and the intelligent control module;
the early warning module is used for analyzing the result of the prediction module and sending early warning to the management layer when necessary;
the intelligent control module is used for adjusting the power of the energy consumption equipment according to the result of the prediction module.
2. The big data intelligent emission abatement system of claim 1, wherein: the big data retrieval module is used for performing task decomposition processing on all data sets stored in the system by adopting a distributed parallel data mining mode, and summarizing by adopting a fuzzy C algorithm, wherein the fuzzy C algorithm is expressed as follows:
wherein u is ij Representing the clustering coefficient, D i Representing the number of tasks before decomposition, v j And (3) representing the number of decomposed tasks, wherein R and N are real numbers.
3. The big data intelligent emission abatement system of claim 2, wherein: the big data retrieval module retrieval process mainly comprises the following steps:
(1) Establishing a system dictionary: constructing a basic word stock by utilizing an elastic search default word stock to finish the establishment of a dictionary;
(2) Establishing an information indexing mechanism: carrying out breadth index by adopting information such as equipment keywords, models and the like;
(3) Realizing an automatic searching scheme: and according to the requirements, the keywords are handed to an index request agent, the index memory matches the keyword information sent by the index agent, the relevance is ordered according to the search results, and finally the search results are input into the prediction module to complete the whole big data search flow.
4. The big data intelligent emission abatement system of claim 1, wherein: the prediction module comprises an energy consumption prediction model, a carbon emission prediction model and an intelligent optimization algorithm for optimizing model weights, and the output result of the prediction module is an energy consumption value and a carbon emission in the future 24 hours.
5. The big data intelligent emission abatement system of claim 4, wherein: the energy consumption prediction model and the carbon emission prediction model are realized as follows:
T 1 +T 2 =1
k 1 +k 2 =1
C=0.785E
where E represents the total energy consumption value,indicating the i hour operating power of the air conditioner, < >>Indicating the i-th hour operating power of the lighting system, for example>Indicating the type of air conditioner big data retrieval power, < >>Representing the big data retrieval and acquisition power of the lighting system, T 1 And T 2 Indicating the air conditioner distribution time, k 1 And k 2 As a weighting factor, C represents carbon dioxide emissions;
the specific prediction algorithm comprises the following steps:
(1) Searching for optimal weight factor k by adopting improved eagle optimization algorithm IAO 1 And k 2 The objective function is as follows:
wherein f represents a quantization standard for a prediction error, E i.T Representing the actual energy consumption value of the first data point, E i Representing a predicted energy consumption value of a first data point, wherein N represents the total number of groups in the energy consumption data;
(2) Randomly initializing a population position, wherein a population position matrix is as follows:
X ij =rand×(UB j -LB j )+LB j ,i=1,2,.....,N j=1,2,...,Dim
wherein: n represents population size and Dim represents the dimension of the search space;
(3) Establishing a mathematical model of an expanding search stage, wherein the mathematical model is as follows:
wherein X (t) and X (t+1) respectively represent the individual positions of the AO algorithm in the t th and t+1th iterations, X best (t) represents the current optimal individual position, X M (T) represents the average position of the population, T represents the maximum number of iterations;
(4) And (3) establishing a data model in a reduced search stage, wherein a model formula is as follows:
X 2 (t+1)=X best (t)×Levy(D)+X R (t)+(y-x)*rand
wherein Levy (D) represents a Levy flight strategy, s is a constant with a value of 0.01, and u and v are random numbers ranging between [0,1 ];
(5) The flight shape of x and y is determined, and the flight shape formula of x and y is as follows:
y=r×cos(θ)
x=r×sin(θ)
r=r 1 +U×D 1
θ=-ω×D 1 +θ 1
wherein r is the search step length, the value range is a constant between [1,20], and the value in the patent is 12; u is 0.00565; omega is 0.005;
(6) And establishing a mathematical model in an expansion development stage, wherein the mathematical model is as follows:
X 3 (t+1)=(X best (t)-X M (t))×a-rand+((UB-LB)×rand+LB)×δ
wherein a and delta represent developed adjustment parameters, and the values are 0.1;
(7) And establishing a mathematical model in a shrinking development stage, wherein the mathematical model is as follows:
X 4 (t+1)=QF×X best (t)-(G 1 ×X(t)×rand)-G 2 ×Levy(D)+rand×G 1
G 1 =2×rand-1
wherein QF (t) represents a quality function value for the balanced search strategy; g 1 Representing various movements of AO during the course of tracking a prey; g 2 The value of the flying slope which is reduced linearly is in the range of [0,2]Between them;
(8) The development stage of the algorithm is improved, and the improvement formula is as follows:
X 3 (t+1)=X best (t)+r 2 ×(X r (t)-X i (t))+μ×(X best (t)-X i (t))
wherein r is 2 And r 3 Between [0,1]]Between X r (t) random eagle individuals in the current iterative population; mu is the screw coefficient;
(9) The algorithm is improved in the reduction development stage, and the improvement formula is as follows:
X 4 (t+1)=QF×X best (t)+r 4 ×Num×X i (t)
wherein r is 4 Between [0,1]]Between F r (t) random individuals X r Fitness value of (t), F i (t) is X i The fitness function value of (t).
6. The big data intelligent emission abatement system of claim 1, wherein: the early warning module is used for comparing the standard energy consumption value and the standard carbon emission with the energy consumption value and the carbon emission in the future 24 hours transmitted by the prediction module, and sending early warning to the management layer when detecting that the energy consumption value and the carbon emission at a certain moment are higher than the standard energy consumption value and the standard carbon emission in the future 24 hours.
7. The big data intelligent emission abatement system of claim 1, wherein: the range of the intelligent control module for adjusting the power of the energy consumption equipment is kept within the power range of the equipment which can normally work.
8. The big data intelligent emission abatement system of claim 1, wherein: the hydrogen production device also comprises a power supply module and a hydrogen production module.
9. The big data intelligent emission abatement system of claim 9, wherein: the power supply module comprises a power grid and photovoltaic energy storage equipment, wherein the photovoltaic energy storage equipment consists of a plurality of photovoltaic plates and energy storage batteries, and the photovoltaic plates absorb solar energy to supply power to the energy consumption equipment and store redundant energy and the energy storage batteries; the photovoltaic energy storage device discharges in the electricity consumption peak period or the electricity failure period, charges in the electricity consumption valley period and inputs redundant electric power into the hydrogen production module.
10. The big data intelligent emission abatement system of claim 9, wherein: the hydrogen production module is used for carrying out electrolytic hydrogen production by using redundant power of the power supply module and storing the redundant power, the hydrogen production mode is a PEM (proton exchange membrane) electrolytic tank, and the chemical reaction process is shown as the following formula:
2H 2 O→2H 2 +O 2
the storage steps are as follows:
(1) The hydrogen is compressed and the compression system equation is as follows:
wherein E is COM For compressor power consumption, M H2 The hydrogen mass flow rate, K is the adiabatic index, the numerical value is 1.4, the air constant of the gas R is 4124J/(kg.times.K), T is the temperature of the compressed gas, and P 2 For gas compression pressure, P 1 Is the compressor inlet pressure;
(2) The hydrogen is stored by the storage tank system, the working pressure of the storage tank system is less than 20MPa, and the storage tank pressure formula is as follows:
wherein P is Hst Is the pressure of the storage tank, M H2 For hydrogen mass, V Hst Is the volume of the storage tank, and the unit is m 3 。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310464522.6A CN116702424B (en) | 2023-04-26 | 2023-04-26 | Big data intelligence emission reduction system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310464522.6A CN116702424B (en) | 2023-04-26 | 2023-04-26 | Big data intelligence emission reduction system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116702424A true CN116702424A (en) | 2023-09-05 |
CN116702424B CN116702424B (en) | 2024-06-14 |
Family
ID=87822902
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310464522.6A Active CN116702424B (en) | 2023-04-26 | 2023-04-26 | Big data intelligence emission reduction system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116702424B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118245848A (en) * | 2024-05-20 | 2024-06-25 | 广东邦盛北斗农业科技有限公司 | Intelligent agricultural farm-based energy consumption control and adjustment method and system |
CN118245848B (en) * | 2024-05-20 | 2024-07-30 | 广东邦盛北斗农业科技有限公司 | Intelligent agricultural farm-based energy consumption control and adjustment method and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106920006A (en) * | 2017-02-23 | 2017-07-04 | 北京工业大学 | A kind of subway station air conditioning energy consumption Forecasting Methodology based on ISOA LSSVM |
CN111596643A (en) * | 2020-05-09 | 2020-08-28 | 中船重工信息科技有限公司 | Visual dynamic energy consumption diagnosis, analysis and pre-control system based on big data |
CN112180780A (en) * | 2020-09-09 | 2021-01-05 | 四川九门科技股份有限公司 | Intelligent energy consumption monitoring and management system and method |
CN114169570A (en) * | 2021-11-04 | 2022-03-11 | 合肥中能电力科技有限公司 | Smart energy management platform based on Internet of things and cloud computing technology |
CN114583725A (en) * | 2022-02-25 | 2022-06-03 | 山东大学 | Hydrogen-based near-zero carbon emission comprehensive energy system and operation optimization method thereof |
CN114722574A (en) * | 2022-03-16 | 2022-07-08 | 华南理工大学 | Chilled water parameter setting method of data center central air conditioner based on AI algorithm |
WO2022251700A1 (en) * | 2021-05-28 | 2022-12-01 | Johnson Controls Tyco IP Holdings LLP | Building control system with predictive control of carbon emissions using marginal operating emissions rate |
CN115423140A (en) * | 2022-05-31 | 2022-12-02 | 南京工程学院 | Short-term load prediction method for power system |
-
2023
- 2023-04-26 CN CN202310464522.6A patent/CN116702424B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106920006A (en) * | 2017-02-23 | 2017-07-04 | 北京工业大学 | A kind of subway station air conditioning energy consumption Forecasting Methodology based on ISOA LSSVM |
CN111596643A (en) * | 2020-05-09 | 2020-08-28 | 中船重工信息科技有限公司 | Visual dynamic energy consumption diagnosis, analysis and pre-control system based on big data |
CN112180780A (en) * | 2020-09-09 | 2021-01-05 | 四川九门科技股份有限公司 | Intelligent energy consumption monitoring and management system and method |
WO2022251700A1 (en) * | 2021-05-28 | 2022-12-01 | Johnson Controls Tyco IP Holdings LLP | Building control system with predictive control of carbon emissions using marginal operating emissions rate |
CN114169570A (en) * | 2021-11-04 | 2022-03-11 | 合肥中能电力科技有限公司 | Smart energy management platform based on Internet of things and cloud computing technology |
CN114583725A (en) * | 2022-02-25 | 2022-06-03 | 山东大学 | Hydrogen-based near-zero carbon emission comprehensive energy system and operation optimization method thereof |
CN114722574A (en) * | 2022-03-16 | 2022-07-08 | 华南理工大学 | Chilled water parameter setting method of data center central air conditioner based on AI algorithm |
CN115423140A (en) * | 2022-05-31 | 2022-12-02 | 南京工程学院 | Short-term load prediction method for power system |
Non-Patent Citations (4)
Title |
---|
DANA MARSETIYA UTAMA ETC.: "A novel hybrid Aquila optimizer for energy-efficient hybrid flow shop scheduling", RESULTS IN CONTROL AND OPTIMIZATION, pages 3 * |
JIE JI ETC.: "Evaluation Study on a Novel Structure CCHP System with a New Comprehensive Index Using Improved ALO Algorithm", SUSTAINABILITY, 20 November 2022 (2022-11-20) * |
SEYDALI FERAHTIA ETC.: "Optimal techno-economic energy management strategy for building’s microgrids based bald eagle search optimization algorithm", APPLIED ENERGY, 12 October 2021 (2021-10-12) * |
尚小晶: "以数据挖掘为主导的能源监管***优化", 计算机应用, 30 June 2022 (2022-06-30) * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118245848A (en) * | 2024-05-20 | 2024-06-25 | 广东邦盛北斗农业科技有限公司 | Intelligent agricultural farm-based energy consumption control and adjustment method and system |
CN118245848B (en) * | 2024-05-20 | 2024-07-30 | 广东邦盛北斗农业科技有限公司 | Intelligent agricultural farm-based energy consumption control and adjustment method and system |
Also Published As
Publication number | Publication date |
---|---|
CN116702424B (en) | 2024-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11874640B2 (en) | Wind power prediction method and system for optimizing deep transformer network | |
CN109193756B (en) | Scene decoupling dynamic economic dispatching model solving method of wind power access system | |
CN110929920A (en) | Hybrid power train energy management method based on working condition identification | |
CN111832812A (en) | Wind power short-term prediction method based on deep learning | |
CN116628972A (en) | Heat supply system control method for industrial waste heat integrated heat supply network based on predictive model | |
CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
CN115409369A (en) | Comprehensive energy system reliability evaluation method based on mechanism and data hybrid driving | |
CN117273409B (en) | Intelligent operation and maintenance method, system and storage medium for intelligent environment-friendly system of park | |
CN116702424B (en) | Big data intelligence emission reduction system | |
CN117708710A (en) | Short-term lightweight load prediction method for power distribution area | |
CN116681154A (en) | Photovoltaic power calculation method based on EMD-AO-DELM | |
Yu et al. | Dynamic grouping control of electric vehicles based on improved k-means algorithm for wind power fluctuations suppression | |
CN115528750A (en) | Data model hybrid drive unit combination method for power grid safety and stability | |
CN115481788A (en) | Load prediction method and system for phase change energy storage system | |
CN115513998A (en) | New energy consumption improving method based on group increment learning algorithm | |
CN115712976A (en) | Heat energy and electric load optimization method based on multi-element heat supply unit and related equipment | |
CN109506248B (en) | Case reasoning boiler combustion optimization method based on online optimization | |
CN115021269A (en) | Two-stage optimal power flow solving method based on data driving | |
CN114707750A (en) | Load prediction method based on PSO-CNN-LSTM model | |
CN114818455A (en) | Power system multi-agent transient state stability judging method and system for small amount of PMU sampling | |
Chen et al. | Short-term PV power forecasting based on time-phased and error correction | |
CN112134304B (en) | Micro-grid full-automatic navigation method, system and device based on deep learning | |
Ren | Construction of an Optimized Configuration Model for Wind Power System Energy Storage Based on OOB-GWO-SVR | |
Li et al. | Short-term LOAD Forecasting Method of TPA-LSTNet Model Based on Time Series Clustering | |
Zou et al. | Random Forest Algorithm Based Dynamictraining Set for Cold Load Prediction |
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 |