CN117669995A - Multi-element load optimal scheduling method, system and platform of comprehensive energy system - Google Patents
Multi-element load optimal scheduling method, system and platform of comprehensive energy system Download PDFInfo
- Publication number
- CN117669995A CN117669995A CN202410137152.XA CN202410137152A CN117669995A CN 117669995 A CN117669995 A CN 117669995A CN 202410137152 A CN202410137152 A CN 202410137152A CN 117669995 A CN117669995 A CN 117669995A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- energy
- scheduling
- comprehensive energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000005457 optimization Methods 0.000 claims abstract description 66
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 25
- 239000002245 particle Substances 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000005286 illumination Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000004146 energy storage Methods 0.000 claims description 11
- 230000008439 repair process Effects 0.000 claims description 11
- 230000000295 complement effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 4
- 230000000739 chaotic effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000029087 digestion Effects 0.000 abstract description 2
- 238000005338 heat storage Methods 0.000 description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 230000008859 change Effects 0.000 description 11
- 230000005611 electricity Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 10
- 238000010438 heat treatment Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000003344 environmental pollutant Substances 0.000 description 7
- 239000007789 gas Substances 0.000 description 7
- 238000013178 mathematical model Methods 0.000 description 7
- 231100000719 pollutant Toxicity 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000004075 alteration Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000011217 control strategy Methods 0.000 description 4
- 238000005485 electric heating Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000005057 refrigeration Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011234 economic evaluation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A multi-element load optimization scheduling method, system and platform of a comprehensive energy system relate to the field of comprehensive energy system production scheduling optimization. Solves the problems of the prior art that the renewable energy sources in the comprehensive energy source system have intermittence and fluctuation, which results in the digestion of the renewable energy sources. The method comprises the following steps: acquiring data of a comprehensive energy system, and transmitting the data to an upper computer; the upper computer transmits the acquired data to a database, and preprocesses the data; establishing a comprehensive energy source multielement load prediction optimization scheduling model according to the preprocessed data; and according to the energy multi-load prediction optimization scheduling model and the PLC strategy configuration, calculating scheduling instructions on line to complete optimization scheduling control. The invention improves the energy utilization efficiency and reduces the energy consumption and emission.
Description
Technical Field
The invention relates to the field of comprehensive energy system production scheduling optimization, in particular to a multi-element load optimization scheduling method of a comprehensive energy system.
Background
The reduction in energy demand and reserves of traditional energy sources is a significant problem that current humans face in common. International energy prospect reports published by the united states energy information agency show that global energy consumption will increase by 48% by 2040 compared to 2012, at the same time the oil will drop to 30% in the energy consumption system, the natural gas will increase from 23% to 26%, and the new energy will increase from 12% to 16%. The new energy duty ratio is gradually increased from 2016 to 2019 as known from the data published by the national statistical bureau. The energy structure is changed, the previous mode of independent planning and design of each energy system is broken, and the construction of the comprehensive energy system is a necessary way for adapting to the change of the energy field.
The comprehensive energy system covers a plurality of systems such as electricity, cold, heat and the like, wherein the complementary interconnection of primary energy, secondary energy such as electricity, heat, gas and the like breaks the functional limit of the traditional energy supply system, and the integral coordination optimization is realized by integrating a plurality of energy subsystems, so that the energy utilization rate can be improved, and the carbon emission can be reduced. However, with the introduction of renewable energy sources (such as solar power generation, wind power generation and the like), due to the intermittence and fluctuation of the renewable energy sources, problems occur in the digestion of the renewable energy sources, and phenomena such as light abandon, wind abandon and the like are easy to occur, so that new energy sources cannot be fully utilized, and a large amount of energy storage space is occupied. Therefore, energy management and control of the comprehensive energy system is required at the optimal scheduling level.
Disclosure of Invention
In order to solve the problems of the prior art caused by the intermittence and fluctuation of renewable energy sources in a comprehensive energy system, the invention provides the following technical scheme:
a multi-element load optimizing and scheduling method of a comprehensive energy system, wherein the comprehensive energy system comprises a fan, photovoltaic, solar energy, an air source heat pump, energy storage equipment, an electric boiler, a power grid power supply and load, and the method comprises the following steps:
acquiring data of a comprehensive energy system, wherein the data comprise power, voltage, current, frequency and heat load, electric load, cold load, gas load data, temperature, pressure, flow, illumination intensity and environmental angle of comprehensive energy equipment in a technological process;
transmitting the data to an upper computer;
the upper computer transmits the acquired data to a database, and preprocesses the data;
establishing a comprehensive energy source multielement load prediction optimization scheduling model according to the preprocessed data;
and according to the energy multi-load prediction optimization scheduling model and the PLC strategy configuration, calculating scheduling instructions on line to complete optimization scheduling control.
Further, there is also provided a preferred mode, the upper computer transmits the data collected by the PLC to the database, and the preprocessing of the data includes:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: the electric load and the cold load are continuous and smooth in a normal state, when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the repair is carried out through the average value of the adjacent values;
the absolute value is larger than the response allowable upper limit, the upper limit is determined according to the system requirement, for example, when the load increase exceeds 2% or 5% of the real value of the last sampling period, the numerical value is judged to be abnormal.
Further, there is also provided a preferred mode, wherein the preprocessing the data further includes: filtering the electric load by adopting an empirical mode decomposition method, specifically:
decomposing the data sequence signal into a plurality of intrinsic mode functions IMF and a residual;
the eigenmode function simultaneously satisfies the following conditions:
condition 1: on the whole section of sequence signal, the difference between the number of extreme points and the number of zero crossing points is not more than 1;
condition 2: at any point, the mean of the upper and lower envelopes is 0.
Further, there is also provided a preferred mode, the method further comprising, preprocessing the data further comprising: the electrical load data, the cold load data, the heat load data and the weather data are normalized by using a min-max normalization method.
Further, a preferred mode is provided, the method for establishing the comprehensive energy multi-element load prediction optimization scheduling model according to the preprocessed data comprises the following steps: s1: setting an IPSD parameter of a particle swarm optimization algorithm, and randomly generating a first generation population according to the IPSD parameter, wherein the parameters comprise the number of particles, inertia weight, acceleration coefficient and maximum iteration times;
s2: initializing a GRU network, and constructing a GRU network model through parameters preset by an initial population and the GRU network;
s3: load prediction is carried out according to the GRU network model, and a loss function is adopted to calculate a prediction error;
s4: calculating the fitness of the GRU network model;
s4: carrying out chaotic algorithm processing on the current particles according to the fitness to obtain optimal particles;
s5: and acquiring a comprehensive energy multi-element load short-term prediction model according to fusion of the optimal particles and the GRU network model.
Based on the same inventive concept, the invention also provides a multi-element load optimization scheduling system of a comprehensive energy system, wherein the comprehensive energy system comprises a fan, photovoltaic, solar energy, an air source heat pump, energy storage equipment, an electric boiler, power supply of a power grid and load, and the device comprises:
the data acquisition module is used for acquiring data of the comprehensive energy system, wherein the data comprise power, voltage, current, frequency and thermal load, electric load, cold load, gas load data, temperature, pressure, flow, illumination intensity and environmental field angle of the comprehensive energy equipment, and the data are transmitted to the upper computer;
the data preprocessing module is used for transmitting the acquired data to the database by the upper computer and preprocessing the data;
the comprehensive energy multi-element load prediction optimization scheduling model building module is used for building a comprehensive energy multi-element load prediction optimization scheduling model according to the preprocessed data;
and the optimal scheduling control module is used for predicting an optimal scheduling model and PLC strategy configuration according to the energy multi-element load, calculating scheduling instructions on line and completing optimal scheduling control.
Further, there is also provided a preferred mode, the data preprocessing module includes:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: and the electric load and the cold load are continuously smooth in a normal state, and when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the abnormal point is repaired by the average value of the adjacent values.
Based on the same inventive concept, the invention also provides a comprehensive energy utilization system management platform, which comprises: the system comprises a multi-element load optimization scheduling system, a real-time data acquisition module and a user module;
the real-time data acquisition module is used for acquiring wind signals, optical signals, gas signals and electric signals and transmitting the acquired signals to the multi-energy complementary optimal scheduling system;
the multi-element load optimization scheduling system is used for receiving signals acquired by the real-time data acquisition module, performing optimization scheduling on the signals and inputting the signals to the user module;
and the user module is used for adjusting the multi-energy complementary optimal scheduling system at any time according to the optimal scheduling result and performing data monitoring.
Based on the same inventive concept, the invention also provides a computer readable storage medium for storing a computer program, wherein the computer program executes the multi-element load optimization scheduling method of the integrated energy system.
Based on the same inventive concept, the invention also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes a multi-element load optimization scheduling method of the integrated energy system.
The invention has the advantages that:
the invention solves the problems of the prior art that renewable energy sources in the comprehensive energy system have intermittence and fluctuation, which cause the consumption of the renewable energy sources.
According to the multi-element load optimization scheduling method of the comprehensive energy system, based on real-time data and the prediction model, the system can rapidly respond to load change and energy supply fluctuation, so that more efficient, reliable and economical energy scheduling management is realized, the energy utilization efficiency is improved, the energy consumption and emission are reduced, and the purposes of saving energy, reducing emission and reducing production cost are achieved.
According to the multi-element load optimizing and scheduling method of the comprehensive energy system, the comprehensive energy multi-element load predicting and optimizing and scheduling model is a GRU network model optimized based on an improved particle swarm algorithm, and compared with other models, the multi-element load short-term prediction of the comprehensive energy system is higher in comprehensive prediction precision. By improving the particle swarm algorithm, the defects of poor convergence and easy sinking into a local optimal solution of the existing model are overcome, and the prediction precision of the comprehensive energy multi-element load prediction optimization scheduling model is remarkably improved.
The invention is applied to the field of energy management.
Drawings
FIG. 1 is a flowchart of a method for optimizing and scheduling multiple loads of an integrated energy system according to an embodiment;
fig. 2 is a flowchart of an integrated energy multi-element load prediction optimization scheduling model establishment according to the fifth embodiment;
FIG. 3 is a schematic diagram of a platform of an integrated energy service system according to an embodiment eight;
fig. 4 is a schematic diagram of a system construction site of the source network load storage integrated heat supply test bed system according to the eighth embodiment.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments.
Embodiment one, this embodiment will be described with reference to fig. 1. The multi-element load optimization scheduling method of the comprehensive energy system, which is provided by the embodiment, comprises a fan, photovoltaic, solar energy, an air source heat pump, energy storage equipment, an electric boiler, power supply of a power grid and load, and comprises the following steps:
acquiring data of a comprehensive energy system, and transmitting the data to an upper computer, wherein the data comprises operation data and parameters, and the upper computer transmits the acquired data to a database for preprocessing the data, wherein the data comprise power, voltage, current, frequency, heat, electricity, cold, gas load data, temperature, pressure, flow, illumination intensity, environmental field angle and the like of comprehensive energy equipment (fans, photovoltaics and heat pumps);
establishing a comprehensive energy source multielement load prediction optimization scheduling model according to the preprocessed data;
and according to the energy multi-load prediction optimization scheduling model and the PLC strategy configuration, calculating scheduling instructions on line to complete optimization scheduling control.
In this embodiment, the integrated energy system includes production of multiple energy sources such as electric power, thermal power, and cold power, and real-time data and operation parameters of the energy sources need to be acquired to establish an operation model of the integrated energy system;
data acquired by real-time acquisition equipment such as a sensor and a monitoring device are transmitted to an upper computer for processing. The upper computer generally refers to a computer of a control center, and data is transmitted from the acquisition equipment to the computer through a special communication protocol and a data interface;
the upper computer transmits the acquired data to the database and preprocesses the transmitted data. The process of preprocessing typically includes removing noise, data smoothing, normalization, etc., to ensure accuracy, reliability, and integrity of the data;
and establishing a comprehensive energy multi-element load prediction optimization scheduling model based on the preprocessed data. The model can predict system load, energy production and the like, and performs optimal scheduling according to a prediction result.
On-line computing scheduling instructions: and according to the energy multi-load prediction optimization scheduling model and the PLC strategy configuration, calculating scheduling instructions on line to complete optimization scheduling control. A PLC (programmable logic controller) is a special computer controller that is programmable, customizable, and commonly used to control automated systems.
The system can rapidly respond to load change and fluctuation of energy supply based on real-time data and a prediction model, achieves more efficient, reliable and economical energy scheduling management, improves energy utilization efficiency, reduces energy consumption and emission, and achieves the purposes of energy conservation, emission reduction and production cost reduction.
The comprehensive energy source multi-element load prediction optimization scheduling model is a GRU network model optimized based on an improved particle swarm algorithm, and compared with other models, the comprehensive energy source multi-element load prediction optimization scheduling model has higher comprehensive prediction precision in the short-term prediction of the comprehensive energy source system multi-element load. By improving the particle swarm algorithm, the defects of poor convergence and easy sinking into a local optimal solution of the existing model are overcome, and the prediction precision of the comprehensive energy multi-element load prediction optimization scheduling model is remarkably improved.
In a second embodiment, the present embodiment is further defined by the multi-element load optimizing and scheduling method of the integrated energy system according to the first embodiment, where the host computer transmits data collected by the PLC to the database, and preprocesses the data, including:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: and the electric load and the cold load are continuously smooth in a normal state, and when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the abnormal point is repaired by the average value of the adjacent values.
The absolute value is larger than the response allowable upper limit, the upper limit is determined according to the system requirement, for example, when the load increase exceeds 2% or 5% of the real value of the last sampling period, the numerical value is judged to be abnormal.
By combining the vertical judgment method and the horizontal judgment method, global abnormal points and outliers can be found, so that the problem that the respective insufficient vertical judgment methods can only find the abnormal points and outliers on specific attributes and cannot be considered globally is avoided, and the problem that the horizontal judgment method may ignore certain specific attributes is avoided.
Specifically, the method can comprehensively utilize the vertical judgment method and the horizontal judgment method to perform cross verification and classification treatment, namely, the horizontal judgment method is adopted to perform global observation and analysis on electric load and cold load, then the vertical judgment method is adopted to perform deep mining on historical similar daily data, and abnormal points are repaired, so that more accurate data are obtained.
The outlier repair described in this embodiment is a key task for data cleaning and preprocessing, and is mainly used for repairing and processing outliers or error values occurring in data, so as to ensure accuracy, reliability and integrity of the data. The presence of outliers can affect the accuracy and reliability of the data, resulting in inaccurate data analysis. Abnormal points can be removed or corrected through abnormal point repair, and the quality and reliability of data are improved; and the abnormal points can cause deviation and error of the comprehensive energy multi-element load prediction optimization scheduling model, and the abnormal point repair can avoid the occurrence of the situation, reduce the noise and interference of the model and improve the prediction effect and accuracy of the model.
An embodiment three, the present embodiment is further defined by the method for optimizing and scheduling multiple loads of an integrated energy system according to the embodiment one, wherein the preprocessing the data further includes: filtering the electric load by adopting an empirical mode decomposition method, specifically:
decomposing the data sequence signal into a plurality of intrinsic mode functions IMF and a residual;
the eigenmode function simultaneously satisfies the following conditions:
condition 1: on the whole section of sequence signal, the difference between the number of extreme points and the number of zero crossing points is not more than 1;
condition 2: at any point, the mean of the upper and lower envelopes is 0.
The embodiment selects an empirical mode decomposition (Empirical Mode Decomposition, EMD) method for filtering data for characteristics of poor stability and nonlinearity of the electrical load. The principle is to decompose a segment of the sequence signal into a number of eigenmode functions (Intrinsic Mode Function, IMF) and a residual. The eigenmode function IMF must satisfy two conditions: (1) On the whole signal, the difference between the number of extreme points and the number of zero crossing points is not more than 1; (2) at any point, the mean of the upper and lower envelopes is 0; the decomposition process is as follows: finding out all maximum and minimum value points of the original data sequence x (t), fitting by using a cubic spline interpolation function to form an upper envelope curve and a lower envelope curve of metadata, marking the average value of the upper envelope curve and the lower envelope curve as m1 (t), subtracting the average envelope curve from the original data sequence to obtain a new data sequence h1 (t):
h1(t)=x(t)-m1(t)；
if the new data obtained by subtracting the envelope average from the original data has a negative local maximum and a positive local minimum, it is indicated that the new data is not an eigenfunction, and the filtering needs to be continued until two conditions of IMF are satisfied.
An embodiment four, the present embodiment is further defined by the method for optimizing and scheduling multiple loads of an integrated energy system according to the embodiment one, where the method further includes preprocessing the data, and further includes: the electrical load data, the cold load data, the heat load data and the weather data are normalized by using a min-max normalization method.
The present embodiment normalizes electrical load data, cold load data, heat load data, and weather data using a min-max normalization method. The result is mapped between 0 and 1 by linear transformation of the original data. According to the method, the electric load, the cold load and the weather data are processed by using the min-max standardization method, so that data processing can be facilitated, data comparability and additivity are improved, and meanwhile, the prediction accuracy of the comprehensive energy multi-element load prediction optimization scheduling model is improved.
Embodiment five, this embodiment will be described with reference to fig. 2. The present embodiment is further defined by the method for optimizing and scheduling multiple loads of the integrated energy system according to the first embodiment, wherein the building the integrated energy multiple load prediction and optimization scheduling model according to the preprocessed data includes: s1: setting particle swarm optimization (IPSO) parameters of an IPSO algorithm, and randomly generating a first generation population according to the IPSO parameters, wherein the parameters comprise particle quantity, inertia weight, acceleration coefficient and maximum iteration times;
s2: initializing a GRU network, and constructing a GRU network model through parameters preset by an initial population and the GRU network;
s3: load prediction is carried out according to the GRU network model, and a loss function is adopted to calculate a prediction error;
s4: calculating the fitness of the GRU network model;
s4: carrying out chaotic algorithm processing on the current particles according to the fitness to obtain optimal particles;
s5: and acquiring a comprehensive energy multi-element load short-term prediction model according to fusion of the optimal particles and the GRU network model.
The building of the comprehensive energy multi-element load prediction optimization scheduling model in the embodiment specifically comprises the following steps:
step 1: setting IPSO parameters: some parameters need to be set before using the IPSO algorithm. The set parameters comprise particle quantity, inertia weight, acceleration coefficient and maximum iteration number.
Step 2: initializing a population: an initial IPSO parameter is used to generate an initial population containing random parameters, wherein each individual represents a possible GRU network structure and configuration solution, the size of the initial population is 30-100, and the parameters of each individual are random parameters.
Step 3: initializing a GRU network: for each individual, its parameters are defined as a GRU neural network and initialized. The GRU network is able to process an input with a time series characteristic and predict the next value of the series.
Step 4: configuring network parameters: specific parameters for the GRU network need to be set. Including setting learning rate, batch size, training cycle number, etc., the values of these parameters are set according to the structure of the network and the characteristics of the task.
Step 5: GRU unit calculation and weight update: in the training samples, the predicted values are calculated by the GRU units through the GRU network, and on the basis of the predicted values, errors are calculated by using an error function. The weights of the network are then updated using a back-propagation algorithm to minimize the error. In this process, it is repeated a number of times until a preset error is reached or a maximum number of iterations is reached.
Step 6: calculating a fitness function: the fitness function of all individuals is calculated with the training set data to evaluate their performance. The fitness function is typically quantized based on computing network errors or accuracy. In this process, it is necessary to ensure that the network has been adequately trained.
Step 7: updating the IPSO parameters: and selecting optimal individuals (particles) from the current population by using the IPSD algorithm according to the fitness function result and the IPSO algorithm, generating new-generation individuals, and modifying the value of the IPSO parameter. This allows for faster searches of solution space for better GRU network structure and configuration.
Step 8: reaching the desired error or maximum number of iterations: after several iterations, it is necessary to determine whether a preset error or maximum number of iterations is reached. And (5) ending training if the result is reached, otherwise, returning to the step (5) and carrying out the next iteration until the result meets the ending condition, and obtaining the comprehensive energy multi-element load short-term prediction model.
An embodiment six, a multi-element load optimization scheduling system of a comprehensive energy system according to this embodiment, the comprehensive energy system includes a fan, a photovoltaic, solar energy, an air source heat pump, an energy storage device, an electric boiler, a power grid power supply and a load, the device includes:
the data acquisition module is used for acquiring data of the comprehensive energy system, wherein the data comprise power, voltage, current, frequency and thermal load, electric load, cold load, gas load data, temperature, pressure, flow, illumination intensity and environmental field angle of the comprehensive energy equipment, and the data are transmitted to the upper computer;
the data preprocessing module is used for transmitting the acquired data to the database by the upper computer and preprocessing the data;
the comprehensive energy multi-element load prediction optimization scheduling model building module is used for building a comprehensive energy multi-element load prediction optimization scheduling model according to the preprocessed data;
and the optimal scheduling control module is used for predicting an optimal scheduling model and PLC strategy configuration according to the energy multi-element load, calculating scheduling instructions on line and completing optimal scheduling control.
An seventh embodiment is a further limitation of the multi-element load optimization scheduling system of an integrated energy system according to the sixth embodiment, wherein the data preprocessing module includes:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: and the electric load and the cold load are continuously smooth in a normal state, and when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the abnormal point is repaired by the average value of the adjacent values.
Embodiment eight, this embodiment will be described with reference to fig. 3 and 4. An integrated energy utilization system management platform according to this embodiment, the platform includes: the multi-element load optimization scheduling system, the real-time data acquisition module and the user module are described in the first embodiment;
the real-time data acquisition module is used for acquiring wind signals, optical signals, gas signals and electric signals and transmitting the acquired signals to the multi-energy complementary optimal scheduling system;
the multi-element load optimization scheduling system is used for receiving signals acquired by the real-time data acquisition module, performing optimization scheduling on the signals and inputting the signals to the user module;
and the user module is used for adjusting the multi-energy complementary optimal scheduling system at any time according to the optimal scheduling result and performing data monitoring.
In practical application, the comprehensive energy utilization system management platform according to the embodiment includes four levels, which are respectively: a field device layer, a control strategy layer and a monitoring management layer.
The field device layer: the system mainly comprises signals of fans, heat pumps, photovoltaics, frequency converters, power grids, electric boilers, energy storage equipment and the like, user equipment, instruments and meters and the like. And transmitting the device data to the upper layer application through the signal acquisition device and the IO acquisition card.
The control strategy layer: the multi-load optimizing and dispatching system mainly comprises a plurality of parallel-stage PLC controllers and communication cards, and is realized in the layer by integrating energy dispatching strategies, control strategy calculation, multi-load predicting and optimizing algorithms and the like.
The monitoring management layer: the part mainly comprises shared memory and communication station software (HmiRunTimeDate), system monitoring software (HmiRunTimeView), engineering project management software (ProjectManager), a database and Python algorithm functional blocks. The project manager is used for engineers and administrators to complete the functions of project establishment, project network structure establishment, communication point table establishment, data refreshing frequency, process picture configuration and the like. The HmiRunTimeDate is responsible for establishing communication with a lower controller, and establishes a shared memory to complete data sharing of each software. The HmiRunTimeView is used for an operator to monitor the running condition of the field device, realize the manual control of the local device and finish the issuing of the load dispatching instruction.
The user layer: and the operation monitoring management authority of different roles to the platform software is realized. The administrator authority creates workstation information and sets user account numbers and authorities; project engineering is established by the engineer authority, project management, project database, project system, strategy and the like are configured, and the engineering authority has the operator authority; the operator rights perform a monitoring function on the system.
The embodiment also provides a concrete example of a source network load storage integrated heat supply test bed system construction field system, as shown in fig. 4:
control strategy layer construction based on PLC:
(1) When the outdoor environment is better (the sun illumination intensity is sufficient or the wind power is better) in winter, clean energy is preferentially adopted for heating when the heating requirement can be met, and the surplus heat is stored by a heat storage water tank and a phase change heat accumulator;
(2) When the outdoor environment is poor in winter (the solar illumination intensity is insufficient or the wind power is poor), valley electricity heat accumulation is used as a supplementary heat source, a compression heat pump and an electric boiler are used as a heat source foundation guarantee and supplement, and an electric boiler body, a heat accumulation water tank and a phase change heat accumulator are used as energy storage equipment to play a role in peak clipping and valley filling of heat load;
(3) In summer, when the outdoor environment is better (the sun illumination intensity is sufficient or the wind power is better), clean energy is preferentially adopted to supply domestic hot water when the domestic hot water requirement can be fully met, the redundant hot water is stored in the heat storage water tank, and the heat pump starts a refrigeration mode to meet the cold load requirement of an office building;
(4) In summer, when the outdoor environment is poor (the solar illumination intensity is insufficient or the wind power is poor), the hot water in the heat storage water tank is preferentially utilized to supply domestic hot water, and when the outdoor environment is insufficient, the original domestic hot water source or the electric heat storage boiler is utilized as a supplementary heat source, and the heat pump starts a refrigeration mode to meet the cold load requirement of an office building.
Python-based system modeling:
by adopting a steady-state modeling method, the actual load demands of different outdoor temperatures, illumination intensity, wind speeds and time-by-time fluctuation of users are comprehensively considered, mathematical models of all the devices are built by combining theory and test based on the actual operation data of all the devices of the test platform under variable working conditions, and therefore the mathematical models of the variable working conditions of the devices can be more accurate. And then, establishing a multi-objective optimizing operation mathematical model taking the operation cost and pollutant emission as optimizing targets, comprehensively considering load change, time-of-use electricity price and equipment characteristics, solving the optimal operation strategy of the system under different boundary conditions by utilizing the comprehensive energy multi-element load prediction optimizing scheduling model, regulating the operation strategy of the test bed according to the settlement result to verify the optimizing result, and correcting the optimizing model at the same time, thereby providing effective guidance for the optimizing problem of the multi-energy complementary heating system.
(1) Trough type solar collector model:
the heat collector has the following relations among heat collection quantity, heat collection efficiency, illumination intensity and heat collection area, wherein:heat is collected by the heat collector, and kW; i is the intensity of solar radiation, W/m2; />The heat collecting efficiency of the heat collector is improved; />And (3) the heat collecting area of the heat collector, and m2.
And the heat collection efficiency curve is obtained from the national solar quality supervision and detection center. The efficiency curve is formulated as follows, where:the heat collection temperature of the flat plate heat collector is DEG C.
Based on the model, the heat collection quantity corresponding to different illumination intensities of the trough type solar heat collector is tested by a control variable method, wherein the control factors also comprise outdoor temperature and water supply and return temperature of the water side of the heat collector, and the theoretical model is corrected and constructed according to the combination of test data, so that the mathematical model of the full-working-condition operation characteristic of the heat collector is achieved.
(2) Compression heat pump model:
the modeling thought taught by the university of Qinghai Tian Changqing is adopted in the compressor model, the model does not need to reflect the internal physical structure and the working process of the compressor, but can accurately calculate the influence parameters of the compressor on the performance of the heat pump and other components, and the mathematical relationship among the flow rate, the power consumption, the evaporation temperature and the condensation temperature of the compressor is established:
heating (heat radiation) amount:wherein m (t) is compressor flow, h2 is condenser inlet temperature, and h3 is condenser outlet temperature;
compressor power consumption:wherein h1 is the evaporation temperature;
outdoor heat absorption (cooling) amount:
coefficient of performance of heat pump:
heating coefficient:refrigeration coefficient: />
(3) Phase change heat accumulator model:
the regenerator provides for the output or storage of thermal energy depending on the system requirements. The method is characterized in that a model is built from the angle of energy conservation, heat energy variables of the energy storage device before and after heat storage (heat release), heat energy storage (heat release) process variables and heat storage (heat release) efficiency are set, and then the heat energy change relation stored in the heat storage (heat release) device before and after heat storage (heat release) is as follows:
wherein:、/>the heat accumulation amounts of the heat accumulation devices before and after heat accumulation (heat release) are respectively represented by kW.h; />Self-loss heat energy coefficient for heat dissipation of the heat accumulator to the environment; />The heat storage (release) amount is shown, and kW.h; />Indicating the heat storage (release) efficiency.
(4) Modeling an electric boiler:
the heat accumulating electric boiler is used as a direct electric heating device, and the modeling process only needs to carry out an electric heating efficiency experiment, and the electric heating efficiency is obtained according to experimental data so as to establish an electric heating conversion characteristic mathematical model. The heat storage function is not mainly utilized in the system, and a heat storage type electric boiler variable-working-condition heat storage characteristic mathematical model is built according to the phase change heat storage thought.
(5) The idea of multi-objective optimization mathematical model establishment:
at present, the evaluation indexes of the distributed energy supply system are mainly concentrated on the aspects of cost, energy consumption and pollutant emission, and in order to consider comprehensively and refer to the evaluation indexes of the combined cooling, heating and power system, the comprehensive cost consisting of investment depreciation cost and electricity purchasing cost is established as an economic evaluation index, and the pollutant is most seriously influenced by CO2, so that the emission quantity is used as an environmental protection evaluation index, and the two are both used as the minimum optimization targets. The overall cost and CO2 emissions are thus employed herein together as optimization objectives.
In the method, in the process of the invention,the total running cost is the element; />The unit (yuan/kW.cndot.) h is the real-time electricity price; />Is the total CO2 discharge capacity in units of (kg); />The power generation efficiency of the power plant is achieved; />The transmission efficiency of the power grid is achieved; />The low-position heating value of coal is kJ/kg; />Is the CO2 emission coefficient of standard coal, and the unit is (kg/kg).
The load-storage integrated heat supply test bed system of the embodiment is used for constructing a field system, the borne 500m2 heat supply area is matched with the multi-load optimization scheduling system of the comprehensive energy system of the sixth embodiment, the energy consumption is reduced by 48.1% on the premise of ensuring the heat and electric loads of users, the pollutant emission reduction rate mainly comprising CO2 is 88.7%, and the energy utilization rate is improved by 21.2%. The method can reduce the heat supply cost by about 6974.5 yuan, reduce the emission of CO2 pollutants by about 2437.7kg, reduce the heat supply by 76.93GJ, comprehensively consider the fluctuation of electricity price and heat load, and comprehensively consider the best balance point of the variable working condition operation characteristics and the heat load of each device by the established model and the written algorithm, so that the overall economy and the environmental protection of the system in the scheduling scheme are best.
The optimized operation of the integrated energy complementary heating system in the embodiment relates to various influencing factors such as various energy coupling, integrated cost, pollutant emission, load change, time-of-use electricity price and the like, and is a nonlinear, multi-objective, multi-variable and multi-constraint complex optimization problem. And the comprehensive energy multi-element load prediction optimization scheduling model is adopted to perform energy allocation and optimization according to the running cost, pollutant emission, time-of-use electricity price and thermal load change, so that effective guidance is provided for the optimization problem of the multi-energy complementary heating system.
The computer readable storage medium according to the ninth embodiment is used for storing a computer program for executing the multi-load optimization scheduling method of the integrated energy system according to any one of the first to fifth embodiments.
The computer device according to the tenth embodiment includes a memory and a processor, the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the multi-load optimization scheduling method of the integrated energy system according to any one of the first to fifth embodiments.
While the preferred embodiments of the present disclosure have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the disclosure.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present disclosure without departing from the spirit or scope of the disclosure. Thus, the present disclosure is intended to include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
It will be appreciated by those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present disclosure and not for limiting the scope thereof, and although the present disclosure has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: various alterations, modifications, or equivalents may be substituted for those illustrated in the detailed description of the invention after reading this disclosure, and such alterations, modifications, or equivalents are within the scope of the disclosure as defined in the claims.
Claims (10)
1. The utility model provides a comprehensive energy system's multi-element load optimization dispatch method, comprehensive energy system includes fan, photovoltaic, solar energy, air source heat pump, energy storage equipment, electric boiler, electric wire netting power supply and load, its characterized in that, the method includes:
acquiring data of a comprehensive energy system, wherein the data comprise power, voltage, current, frequency and heat load, electric load, cold load, gas load data, temperature, pressure, flow, illumination intensity and environmental angle of comprehensive energy equipment in a technological process;
transmitting the data to an upper computer;
the upper computer transmits the acquired data to a database, and preprocesses the data;
establishing a comprehensive energy source multielement load prediction optimization scheduling model according to the preprocessed data;
and according to the energy multi-load prediction optimization scheduling model and the PLC strategy configuration, calculating scheduling instructions on line to complete optimization scheduling control.
2. The multi-element load optimization scheduling method of the comprehensive energy system according to claim 1, wherein the upper computer transmits data acquired by the PLC to a database, and the preprocessing of the data comprises the following steps:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: the electric load and the cold load are continuous and smooth in a normal state, when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the repair is carried out through the average value of the adjacent values;
the absolute value excessive finger is greater than the response allowable upper limit.
3. The method for optimized multi-load scheduling of integrated energy system according to claim 2, wherein said preprocessing said data further comprises: filtering the electric load by adopting an empirical mode decomposition method, specifically:
decomposing the data sequence signal into a plurality of intrinsic mode functions IMF and a residual;
the eigenmode function simultaneously satisfies the following conditions:
condition 1: on the whole section of sequence signal, the difference between the number of extreme points and the number of zero crossing points is not more than 1;
condition 2: at any point, the mean of the upper and lower envelopes is 0.
4. The method for optimized multi-load scheduling of integrated energy systems according to claim 2, wherein said method further comprises preprocessing said data further comprising: the electrical load data, the cold load data, the heat load data and the weather data are normalized by using a min-max normalization method.
5. The multi-element load optimizing and scheduling method of the comprehensive energy system according to claim 1, wherein the building of the comprehensive energy multi-element load predicting and optimizing and scheduling model according to the preprocessed data comprises the following steps: s1: setting particle swarm optimization (IPSO) parameters of an IPSO algorithm, and randomly generating a first generation population according to the IPSO parameters, wherein the parameters comprise particle quantity, inertia weight, acceleration coefficient and maximum iteration times;
s2: initializing a GRU network, and constructing a GRU network model through parameters preset by an initial population and the GRU network;
s3: load prediction is carried out according to the GRU network model, and a loss function is adopted to calculate a prediction error;
s4: calculating the fitness of the GRU network model;
s4: carrying out chaotic algorithm processing on the current particles according to the fitness to obtain optimal particles;
s5: and acquiring a comprehensive energy multi-element load short-term prediction model according to fusion of the optimal particles and the GRU network model.
6. A multi-element load optimizing and dispatching system of an integrated energy system, wherein the integrated energy system comprises a fan, photovoltaic, solar energy, an air source heat pump, energy storage equipment, an electric boiler, a power grid power supply and load, and the dispatching system is characterized by comprising:
the data acquisition module is used for acquiring data of the comprehensive energy system, wherein the data comprise power, voltage, current, frequency and thermal load, electric load, cold load, gas load data, temperature, pressure, flow, illumination intensity and environmental field angle of the comprehensive energy equipment, and the data are transmitted to the upper computer;
the data preprocessing module is used for transmitting the acquired data to the database by the upper computer and preprocessing the data;
the comprehensive energy multi-element load prediction optimization scheduling model building module is used for building a comprehensive energy multi-element load prediction optimization scheduling model according to the preprocessed data;
and the optimal scheduling control module is used for predicting an optimal scheduling model and PLC strategy configuration according to the energy multi-element load, calculating scheduling instructions on line and completing optimal scheduling control.
7. The multiple load optimizing and scheduling system of an integrated energy system according to claim 6, wherein said data preprocessing module comprises:
carrying out data judgment and abnormal point repair according to a method combining vertical judgment and horizontal judgment:
the vertical judging method comprises the following steps: according to the historical similar day data, abnormal points are judged to be repaired through a threshold value;
the level judging method comprises the following steps: and the electric load and the cold load are continuously smooth in a normal state, and when the absolute value of the load difference value at the front and rear adjacent moments is overlarge, the abnormal point is judged, and the abnormal point is repaired by the average value of the adjacent values.
8. An integrated energy utilization system management platform, the platform comprising: the multiple load optimizing scheduling system, the real-time data acquisition module and the user module of claim 6;
the real-time data acquisition module is used for acquiring wind signals, optical signals, gas signals and electric signals and transmitting the acquired signals to the multi-energy complementary optimal scheduling system;
the multi-element load optimization scheduling system is used for receiving signals acquired by the real-time data acquisition module, performing optimization scheduling on the signals and inputting the signals to the user module;
and the user module is used for adjusting the multi-energy complementary optimal scheduling system at any time according to the optimal scheduling result and performing data monitoring.
9. A computer readable storage medium for storing a computer program for executing a multiple load optimizing scheduling method of an integrated energy system according to any one of claims 1-5.
10. A computer device, characterized by: comprising a memory and a processor, said memory having stored therein a computer program, which when executed by said processor performs a method of multiple load optimized scheduling of an integrated energy system according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410137152.XA CN117669995A (en) | 2024-02-01 | 2024-02-01 | Multi-element load optimal scheduling method, system and platform of comprehensive energy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410137152.XA CN117669995A (en) | 2024-02-01 | 2024-02-01 | Multi-element load optimal scheduling method, system and platform of comprehensive energy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117669995A true CN117669995A (en) | 2024-03-08 |
Family
ID=90077281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410137152.XA Pending CN117669995A (en) | 2024-02-01 | 2024-02-01 | Multi-element load optimal scheduling method, system and platform of comprehensive energy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669995A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886498A (en) * | 2019-03-01 | 2019-06-14 | 北京邮电大学 | A kind of EMD-GRU Short-Term Load Forecasting Method based on feature selecting |
| CN110970998A (en) * | 2019-11-07 | 2020-04-07 | 上海航天智慧能源技术有限公司 | Energy management system of multi-energy complementary smart energy based on source network charge storage |
| CN111950793A (en) * | 2020-08-17 | 2020-11-17 | 浙江工业大学 | Comprehensive energy system load prediction method considering multivariate load coupling characteristics |
| CN112348271A (en) * | 2020-11-12 | 2021-02-09 | 华北电力大学 | Short-term photovoltaic power prediction method based on VMD-IPSO-GRU |
| CN113393339A (en) * | 2021-05-21 | 2021-09-14 | 南京理工大学 | Power distribution network short-term load prediction method based on deep neural network combination model |
| CN114580250A (en) * | 2022-01-26 | 2022-06-03 | 江苏康缘药业股份有限公司 | Energy consumption prediction method and device of GRU network based on quantum particle swarm optimization |
| CN114707289A (en) * | 2021-12-28 | 2022-07-05 | 国网江苏省电力有限公司经济技术研究院 | Opportunity constraint-based multi-objective optimization method for electrothermal coupling comprehensive energy system |
| CN115062878A (en) * | 2022-08-19 | 2022-09-16 | 东方电子股份有限公司 | Optimized dispatching system for comprehensive energy system |
| CN115374527A (en) * | 2022-10-24 | 2022-11-22 | 天津大学 | Construction method of regional electricity-heat-cold comprehensive energy dynamic simulation system |
| CN117239722A (en) * | 2023-08-31 | 2023-12-15 | 国网上海市电力公司 | System wind load short-term prediction method considering multi-element load influence |
-
2024
- 2024-02-01 CN CN202410137152.XA patent/CN117669995A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886498A (en) * | 2019-03-01 | 2019-06-14 | 北京邮电大学 | A kind of EMD-GRU Short-Term Load Forecasting Method based on feature selecting |
| CN110970998A (en) * | 2019-11-07 | 2020-04-07 | 上海航天智慧能源技术有限公司 | Energy management system of multi-energy complementary smart energy based on source network charge storage |
| CN111950793A (en) * | 2020-08-17 | 2020-11-17 | 浙江工业大学 | Comprehensive energy system load prediction method considering multivariate load coupling characteristics |
| CN112348271A (en) * | 2020-11-12 | 2021-02-09 | 华北电力大学 | Short-term photovoltaic power prediction method based on VMD-IPSO-GRU |
| CN113393339A (en) * | 2021-05-21 | 2021-09-14 | 南京理工大学 | Power distribution network short-term load prediction method based on deep neural network combination model |
| CN114707289A (en) * | 2021-12-28 | 2022-07-05 | 国网江苏省电力有限公司经济技术研究院 | Opportunity constraint-based multi-objective optimization method for electrothermal coupling comprehensive energy system |
| CN114580250A (en) * | 2022-01-26 | 2022-06-03 | 江苏康缘药业股份有限公司 | Energy consumption prediction method and device of GRU network based on quantum particle swarm optimization |
| CN115062878A (en) * | 2022-08-19 | 2022-09-16 | 东方电子股份有限公司 | Optimized dispatching system for comprehensive energy system |
| CN115374527A (en) * | 2022-10-24 | 2022-11-22 | 天津大学 | Construction method of regional electricity-heat-cold comprehensive energy dynamic simulation system |
| CN117239722A (en) * | 2023-08-31 | 2023-12-15 | 国网上海市电力公司 | System wind load short-term prediction method considering multi-element load influence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Data-driven configuration optimization of an off-grid wind/PV/hydrogen system based on modified NSGA-II and CRITIC-TOPSIS | |
| Wang et al. | Combined multi-objective optimization and robustness analysis framework for building integrated energy system under uncertainty | |
| WO2021062748A1 (en) | Optimization method and apparatus for integrated energy system and computer readable storage medium | |
| CN113822496B (en) | Multi-unit thermal power plant heat supply mode and parameter online optimizing method | |
| CN106099993B (en) | A kind of power source planning method for adapting to new energy and accessing on a large scale | |
| CN111355230B (en) | Optimized scheduling method and system for comprehensive energy system | |
| CN111681130B (en) | Comprehensive energy system optimal scheduling method considering conditional risk value | |
| WO2021062753A1 (en) | Integrated energy system simulation method, apparatus and computer-readable storage medium | |
| CN112149980A (en) | Energy efficiency analysis method and system for regional comprehensive energy system | |
| CN111754037B (en) | Long-term load hybrid prediction method for regional terminal integrated energy supply system | |
| CN111737884B (en) | Multi-target random planning method for micro-energy network containing multiple clean energy sources | |
| CN114742294A (en) | Neural network algorithm for carbon emission prediction | |
| CN110661254A (en) | Method for quantifying cooling, heating and power complementary benefits of regional comprehensive energy system | |
| CN111695742A (en) | Day-ahead scheduling interval optimization method, system and equipment for comprehensive energy system | |
| CN102930343A (en) | Energy optimization method for distributed power generation and energy supply system | |
| CN111668878A (en) | Optimal configuration method and system for renewable micro-energy network | |
| WO2021062749A1 (en) | Method and apparatus for controlling integrated energy system, and computer-readable storage medium | |
| CN112348276A (en) | Comprehensive energy system planning optimization method based on multiple elements and three levels | |
| Liu et al. | Optimization of intelligent heating ventilation air conditioning system in urban building based on BIM and artificial intelligence technology | |
| Gao et al. | The spatial and temporal mismatch phenomenon in solar space heating applications: status and solutions | |
| CN111367171A (en) | Multi-objective optimization method and system for solar energy and natural gas coupled cooling, heating and power combined supply system | |
| Liu et al. | Two-layer multiple scenario optimization framework for integrated energy system based on optimal energy contribution ratio strategy | |
| CN116187173A (en) | Double-layer optimization method and system for regional comprehensive energy system | |
| CN115187018A (en) | Double-layer optimized scheduling method and device for park comprehensive energy system | |
| CN115115193A (en) | Low-carbon analysis and optimization planning method for industrial park |
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 |