CN114548692A - Regional energy system multi-future scheduling optimization method and system based on metauniverse - Google Patents
Regional energy system multi-future scheduling optimization method and system based on metauniverse Download PDFInfo
- Publication number
- CN114548692A CN114548692A CN202210088263.7A CN202210088263A CN114548692A CN 114548692 A CN114548692 A CN 114548692A CN 202210088263 A CN202210088263 A CN 202210088263A CN 114548692 A CN114548692 A CN 114548692A
- Authority
- CN
- China
- Prior art keywords
- energy
- future
- scheduling
- regional
- data
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000004519 manufacturing process Methods 0.000 claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 claims description 32
- 238000013507 mapping Methods 0.000 claims description 18
- 210000004556 brain Anatomy 0.000 claims description 11
- 230000005611 electricity Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000010248 power generation Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000000644 propagated effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 206010000210 abortion Diseases 0.000 claims description 2
- 231100000176 abortion Toxicity 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06Q10/06313—Resource planning in a project environment
-
- 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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman 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
- 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a regional energy system multi-future scheduling optimization method and system based on a metauniverse. The invention constructs an energy market trading mode based on the Ethengfang in the Yuanzhou, realizes the virtual simulation of the regional energy system through the technologies such as digital twin and the like, and improves the optimization mode by means of a multi-future prediction scheduling optimization model, thereby realizing the dynamic supply and demand balance of the output of regional energy system equipment and the energy product market demand, and improving the overall efficiency and the production economy of the system.
Description
Technical Field
The invention belongs to the field of combination of a regional energy system of intelligent energy and virtual reality, and particularly relates to a method and a system for optimizing multi-future scheduling of the regional energy system based on a metauniverse.
Background
The metauniverse is a novel virtual-real fused internet application and social form generated by integrating a plurality of new technologies, and the core of the metauniverse is to provide immersive experience based on an augmented reality technology, generate a mirror image of a real world based on a digital twin technology, build an economic system based on a block chain technology, fuse the virtual world and the real world closely on the economic system, a social system and an identity system, and allow each user to perform content production and world editing by means of intelligent equipment. The method provides a new bottom logic and construction framework for the intelligent construction of the regional energy system, and the regional energy system is constructed in the Yuanzhou and overall optimization research is carried out to guide the operation of the real-world energy system.
The regional energy system is an energy scheme for comprehensively optimizing energy supply and demand of cold, heat, domestic hot water, electricity and the like in cities or regions, and aims at the overall high efficiency of the system. On the user side, the regional energy system meets the diversified energy utilization requirements of the user as much as possible, and the cascade utilization of energy is realized; on the source side, the regional energy system coordinates the energy production equipment as much as possible, and the quick load response and scheduling optimization are realized. The scheduling optimization of the current regional energy system usually focuses on the energy system, and even if the connection demand and production are modeled by the energy system, the regional energy system is usually constructed by three general modules, namely a producer, a connector and a consumer, so that the connection with a user side is realized to adapt to different systems.
In summary, the current energy system scheduling optimization method cannot realize quick response to energy demand, and even cannot realize supply and demand balance according to market real-time change in the gradually-promoted market reformation of the energy industry.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a regional energy system multi-future scheduling optimization method and system based on a metauniverse. The invention constructs an energy market trading mode based on the Ethengfang in the Yuanzhou, realizes the virtual simulation of the regional energy system through the technologies such as digital twin and the like, and improves the optimization mode by means of a multi-future prediction scheduling optimization model, thereby realizing the dynamic supply and demand balance of the output of regional energy system equipment and the energy product market demand, and improving the overall efficiency and the production economy of the system.
The invention is realized by adopting the following technical scheme:
a regional energy system multi-future scheduling optimization method based on a metauniverse comprises the following steps:
step S1, constructing an Etheng transaction result fuzzy prediction model based on the multidimensional data relation, and generating a transaction result multi-future prediction set;
step S2, selecting a possible future energy trading result from the multi-future prediction set of trading results, scheduling the regional energy system, recording an instruction tracking sequence of the optimizing process and obtaining a scheduling scheme;
step S3, forming equivalence class constraint aiming at the future energy transaction result selected in the step S2 according to the control flow and the data flow in the obtained instruction tracking sequence, and using a memorisation technology to specialize an optimization path;
step S4, repeating the steps S2 and S3 to obtain various future fast optimizing paths and form a multi-future scheduling optimization model;
step S5, the main body in the Yuanzhou generates energy product transaction according to self energy demand, the energy ether house executes transaction, and the energy market in the Yuanzhou obtains actual transaction result;
and step S6, obtaining a regional energy system real-time scheduling scheme by means of a multi-future scheduling optimization model according to an actual transaction result.
In the above technical solution, further, step S1 specifically includes:
step S11, according to various factors influencing market transaction, collecting natural environment data N (natural environment), social environment data S (social environment), and historical price data M of energy marketh(historical market), energy market historical trading result data Th(historical conversion), energy market real-time price data Mr(real-time marker). Data cost in the meta universe needs to be considered in data selection, and data types have direct relations with new energy power generation conditions, energy production and sales and energy market transactions.
The natural environment data mainly comprises meteorological factors such as wind speed, illumination and temperature, the social environment data mainly comprises soft environment factors such as energy strategy, market policy and social culture, and hard environment factors such as traffic, communication level and fossil resources. The historical price data of the energy market mainly comprises historical electricity price, historical oil gas price, historical price of energy futures and the like; the energy market historical trading result data comprises the spot trading amount of the energy product and the future trading amount of the energy product. The energy market real-time price data mainly comprises current electricity price, current oil and gas price, current energy future price and the like.
Step S12, cleaning, analyzing and integrating the acquired multidimensional data by means of big data technology, and constructing N, S, M by a machine learning methodhWith respect to the fuzzy mapping of the historical energy trading result Th, a multi-future fuzzy prediction model is obtained as follows,
f：{N，S，Mh}→Th
step S13, natural environment data N, social environment data S and energy market real-time price data MrThe possible space for obtaining the future energy market trading result including all the mappings is as follows,
X＝{X1，X2，X3...Xi...Xn}
wherein n is the number of possible mapping results; the set X is a possible space of future energy market trading results; xi represents one possible mapping result, i.e., some possible future energy trading result.
Due to the complexity of the market and the randomness of individuals, different possibilities exist in trading, and the accurate prediction of the market result is extremely difficult, so that a plurality of possible results can be caused in mapping, and when n kinds of possible results exist, the possible results are recorded as a possible space X of the future energy market trading result; xiRepresenting a possible mapping result, i.e. a possible future energy trading result.
Further, the step S2 specifically includes:
step S21, constructing a regional energy system dispatching optimization model in the meta universe; combining IoT, AR and a data transmission technology, fusing a refined physical model and operation and maintenance data, constructing an equipment digital twin model and an energy brain in the metas, wherein the digital twin model reflects the actual equipment condition in the metas, and the energy brain performs optimization scheduling according to the multi-energy flow constraint of the regional energy system in the metas to form a production scheduling instruction for the equipment, so that the regional energy system is scheduled; the device digital twin model comprises all devices in the whole process of actual energy system source network load and storage, and the energy brain considers the objective limit of the devices reflected by the digital twin model.
And step S22, converting the selected future transaction result information into multi-energy flow energy constraint on the regional energy system, and requiring the real-time output of the regional energy system energy production equipment to be equal to the sum of the spot transaction and the due futures transaction of the energy market.
Selecting a possible future energy market trading result in the possible space X of future energy market trading results
Xi，i∈(1，2，3...，n)
Note XiThe spot-transaction amount of the energy-source product is
E1＝{E1h，E1e，E1c，...}
The amount of futures due for a trade is
E2＝{E2h，E2e，E2c，E2g，...}
The subscripts h, e, c and g respectively represent various energy products such as heat, electricity, cold and gas. The multipotent abortion energy of the regional energy system is constrained to
Output＝E1+E2＝{E1h+E2h，E1e+E2e，E1c+E2c，E1g+E2g，...}
Step S23, inputting the multi-energy flow energy constraint of the regional energy system into the regional energy system scheduling optimization model, solving by taking the economic optimization as a target, executing regional energy system simulation in a virtual layer, and recording an instruction tracking sequence trace in the Yuanzhou in the solving processiAnd obtaining an energy system scheduling scheme containing the output of the equipment, wherein the solving process is realized by a computer program.
Recording the result of the device output and energy system scheduling scheme obtained in the future as RiThe instruction tracing sequence of the optimizing process in the metaseque is tracei。
Further, the step S3 specifically includes:
and step S31, evaluating the data flow and the control flow of the instruction tracking sequence, and selecting the similarity evaluation index as the evaluation index of the equivalence class.
For selecting XiLater regional energy system scheduling process, by analyzing traceiA path within the metasphere to perform this future scheduling optimization may be obtained. TraceiData stream DS ofiDescription of XiThe data circulation mode and the behavior state thereof in the scheduling optimization process of the lower-region energy system in the future; control flow CFiExpression of XiAnd controlling the logic execution sequence of the program in the scheduling optimization process of the lower-region energy system in the future.
The similarity of the actual transaction results can be evaluated according to the similarity of the data flow and the control flow. The equivalence class of trading results is all future energy market trading results that satisfy the similarity constraints of data flow and control flow. The calculation method of the similarity S adopts a Pearson product moment correlation coefficient as follows:
wherein, XjN, 1, 2, 3.. n; σ is standard deviation, cov is covariance; DS (direct sequence)i、CFiAre each XiScheduling data flow and control flow of an optimization process in the future; DS (direct sequence)jAnd CFjIs XjThe data flow and control flow of the optimization process are scheduled in the future. .
Step S32, adding a path specialization program in the optimization program by the memorization technology to the optimization program, and constructing a regional energy system dispatching optimization fast path, which specifically comprises the following steps:
when the similarity constraint is judged to be satisfied, the optimization directly enters the next stage by skipping part of the computer program by which the S23 solving process is carried out. The similarity constraint is:
|1-S(Xi，Xj)|＜Constraints
when regional energy system scheduling optimization model is in the future XjAt run-down, if the similarity constraint is satisfied at the memory point, a path specialization program is added. Setting n steps of model calculation program, the k step has memory point, the path specialization program is fastpathiIs applicable to XiThe construction method of all the equivalence classes can be expressed as follows: fastpathi：for step k，k∈(1，n)；ifS(Xi，Xj)＜Constraints；jump to step n
Further, the step S4 specifically includes:
and selecting a plurality of possible future energy trading results, and repeating the steps S2 and S3 to obtain a plurality of scheduling optimization fast paths, so that a multi-future scheduling optimization model is formed on the basis of the regional energy system scheduling optimization model in the step S21.
Selecting other possible future X in possible space of future energy market trading resultiCan obtain new fastpathiTherefore, the path library can be obtained by selecting a plurality of possible future energy transaction results, so that the future space as large as possible is covered.
For regional energy system scheduling optimization based on Ether Fang trading, the equivalence of control flow and data flow can divide the possible space of future energy market trading result into a few equivalence classes, so limited X can be selectediTo cover as much future space as possible that is large enough. The scheduling optimization model (program) combined with the path library is the final multi-future scheduling optimization model.
Further, the step S5 is specifically:
and step S51, the main body evaluates the actual energy demand and investment demand according to the external information of traffic, climate, policy and the like grasped by the individual, performs physical transaction and financial transaction, and purchases various energy products such as electricity, heat, gas, cold and the like in the form of spot goods or contracts.
A plurality of social bodies form a decentralized prediction market, and social operation information can be converted into collective real-time energy utilization load prediction. The economic system, the social system and the identity system of the main body are integrated in the meta universe, and transactions can be conducted by means of intelligent equipment such as computers and mobile phones.
Step S52, the generated transaction will be propagated and identified among the blockchain, and finally the energy market transaction result is obtained after all transactions are executed in the energy ether house, and is marked as XtrueI.e. the energy market future that actually occurs. The trading result reflects the energy supply and demand relationship, and the market price of the energy product can be influenced, so that the next trading of the main body is influenced, namely the centralized forecasting market is counteracted.
Further, the step S6 specifically includes:
the actual transaction result XtrueAnd converting the energy into multi-energy flow energy constraint for the energy production equipment according to the method of S22, and then using the multi-energy flow energy constraint as the input of the multi-future scheduling optimization model obtained in S4 to perform simulation solution to obtain the equipment output and regional energy system scheduling scheme, thereby realizing scheduling optimization.
On the basis of the solving steps, in order to improve the practicability of the invention, a regional energy system multi-future scheduling optimization system based on the metauniverse can be set up, and the regional energy system multi-future scheduling optimization system comprises a data acquisition module, an energy transaction multi-future prediction module, a regional energy system scheduling optimization module and an actual ether house transaction module.
The data acquisition module comprises a natural environment data acquisition submodule, a social environment data acquisition submodule and an energy real-time market data acquisition submodule;
the energy transaction multi-future prediction module comprises a data processing sub-module, an energy transaction fuzzy mapping model sub-module and an ether house multi-future transaction result database;
the regional energy system scheduling optimization module comprises a virtual layer actual equipment monitor, an equipment digital twin submodule, a decision layer energy brain submodule, a scheduling optimization model submodule and a production scheduling instruction controller;
the actual Ether house trading module comprises a user main body, an energy product, virtual currency and an Ether house trading platform;
the modules are respectively subjected to module packaging, a data transmission channel is established, so that the data acquisition module transmits data to the energy transaction multi-future prediction module, the energy transaction multi-future prediction module transmits the Ethenhouse multi-future transaction result database to the regional energy system scheduling optimization module, and the actual Ethenhouse transaction module transmits the actual transaction result to the regional energy system scheduling optimization module;
the system adopts the method to realize multi-future scheduling optimization of the regional energy system.
The invention has the beneficial effects that:
aiming at the defects of the current regional energy system scheduling optimization method, the invention constructs a multi-future scheduling optimization model in the meta universe and mainly has the following innovation points: firstly, key elements and logics of regional energy system scheduling optimization in the meta-universe are provided, and the prior art is integrated to achieve system optimization; secondly, providing an energy ether house based on a decentralized forecasted market formed by a main body, realizing the connection between the source side and the user side of the regional energy system in a metaspace, and reflecting the load change through a transaction result; and thirdly, a multi-future scheduling optimization model is constructed by means of the specialized optimizing path, so that the regional energy system can predict and respond to the ether house transaction result more quickly, and the dynamic balance of the energy production equipment and the energy product requirements is realized.
Drawings
FIG. 1 is a diagram illustrating the main steps of a method for optimizing multi-future scheduling of a regional energy system based on the Meta-universe;
FIG. 2 is a schematic diagram of a method for predicting the energy transaction multiple future according to the present invention;
FIG. 3 is a schematic diagram illustrating the actual transaction result of the energy in the Yuanzhou according to the present invention;
fig. 4 is a schematic diagram of the scheduling optimization of the regional energy system based on the metasma.
Detailed Description
The invention will now be described in further detail with reference to the following drawings and specific examples, which are intended to be illustrative and not limiting:
the invention discloses a regional energy system multi-future scheduling optimization method based on a metauniverse, which comprises the following steps:
step S1, constructing an Etheng transaction result fuzzy prediction model based on the multidimensional data relation, and generating a transaction result multi-future prediction set;
step S2, selecting a possible future energy trading result from the multi-future prediction set of trading results, scheduling the regional energy system, recording an instruction tracking sequence of the optimizing process and obtaining a scheduling scheme;
step S3, forming equivalence class constraint aiming at the future energy transaction result selected in the step S2 according to the control flow and the data flow in the obtained instruction tracking sequence, and using a memorisation technology to specialize an optimization path;
step S4, repeating the steps S2 and S3 to obtain various future fast optimizing paths and form a multi-future scheduling optimization model;
step S5, the main body in the Yuanzhou generates energy product transaction according to self energy demand, the energy ether house executes transaction, and the energy market in the Yuanzhou obtains actual transaction result;
and step S6, obtaining a regional energy system real-time scheduling scheme by means of a multi-future scheduling optimization model according to an actual transaction result.
In step S1:
step S11, according to various factors influencing market transaction, collecting natural environment data N (natural environment), social environment data S (social environment), and historical price data M of energy marketh(historical market), historical energy market trading result data Th (historical trading), and real-time energy market price data Mr(real-time market). Data cost in the meta universe is considered in data selection, and data types have direct relations with new energy power generation conditions, energy production and sales and energy market transactions.
In areas with more photovoltaic power generation and less fossil energy, natural environment data including illumination can be selected, and social environment data mainly including photovoltaic power generation policies and photovoltaic panel maintenance prices. The historical price data of the energy market mainly comprises historical electricity price, historical oil gas price, historical energy futures price and the like; the historical trading result data of the energy market comprises the spot trading amount of the energy product and the future trading amount of the energy product. The energy market real-time price data mainly comprises current electricity price, current oil and gas price, current energy future price and the like.
Step S12, integrating multidimensional data by means of big data technology, and constructing N, S, M by machine learning methodhWith respect to the fuzzy mapping of the historical energy trading result Th, a multi-future fuzzy prediction model is obtained as follows,
f：{N，S，Mh}→Th
step S13, natural environment data N, social environment data S and energy market real-time price data MrThe possible space for obtaining the future energy market trading result including all the mappings is as follows,
X＝{X1，X2，X3...Xi...Xn}
wherein n is the number of possible mapping results; the set X is a possible space of future energy market trading results; xiRepresenting a possible mapping result, i.e. a possible future energy trading result.
Due to the complexity of the market and the randomness of individuals, different possibilities exist in trading, and the accurate prediction of the market result is extremely difficult, so that a plurality of possible results can be caused in mapping, and when n kinds of possible results exist, the possible results are recorded as a possible space X of the future energy market trading result; xiRepresenting a possible mapping result, i.e. a possible future energy trading result.
In step S2:
and step S21, constructing a regional energy system dispatching optimization model in the meta universe. Combining IoT, AR and a data transmission technology, fusing a refined physical model and operation and maintenance data, constructing a device digital twin and an energy brain in the metas, wherein the digital twin model reflects the actual device condition in the metas, and the energy brain optimizes according to the multi-energy flow constraint scheduling of the regional energy system in the metas to form a production scheduling instruction for the device, thereby realizing the scheduling of the regional energy system. The device digital twin comprises all devices in the whole process of actual energy system source network load and storage, and the energy brain considers the objective limit of the devices reflected by the digital twin.
And step S22, converting the selected future transaction result information into the multi-energy flow energy constraint of the regional energy system. The real-time output of energy production equipment of the regional energy system is required to be equal to the sum of the spot transaction and the due futures transaction of the energy market.
Selecting a possible future energy market trading result in the possible space X of future energy market trading results
Xi，i∈(1，2，3...，n)
Note XiThe spot-transaction amount of the energy-source product is
E1＝{E1h，E1e，E1c，...}
The amount of futures due for a trade is
E2＝{E2h，E2e，E2c，...}
Wherein, subscripts h, e, c respectively represent a plurality of different energy products such as heat, electricity, cold, and the like. The energy equipment capacity constraint is
Output＝E1+E2＝{E1h+E2h，E1e+E2e，E1c+E2c，...}
And S23, inputting the multi-energy flow energy constraint of the regional energy system into a regional energy system scheduling optimization model, solving by taking economic optimization as a target, executing regional energy system simulation in a virtual layer, recording an instruction tracking sequence of a solving process in the Yuanzhou to obtain an energy system scheduling scheme containing equipment output, wherein the solving process is realized through a computer program.
Recording the result of the equipment output and energy system scheduling scheme obtained in the future as RiThe instruction tracing sequence of the optimizing process in the metaseque is tracei。
In step S3:
and step S31, evaluating the data flow and the control flow of the instruction tracking sequence, and selecting the similarity evaluation index as the evaluation index of the equivalence class.
For selecting XiLater regional energy system scheduling process, by analyzing traceiA path within the metasphere to perform this future scheduling optimization may be obtained. TraceiData stream DS ofiDescription of XiThe data circulation mode and the behavior state thereof in the scheduling optimization process of the regional energy system in the future; control flow CFiExpression of XiAnd controlling the sequence of program logic execution in the scheduling optimization process of the regional energy system in the future.
The similarity of the actual transaction results can be evaluated according to the similarity of the data flow and the control flow. The equivalence class of trading results is all future energy market trading results that satisfy the similarity constraints of data flow and control flow. The calculation method of the similarity S adopts a Pearson product moment correlation coefficient as follows:
wherein, XjN, 1, 2, 3.. n; o is the standard deviation, cov is the covariance; DS (direct sequence) systemi、CFiAre each XiScheduling data flow and control flow of an optimization process in the future; DS (direct sequence)jAnd CFjIs XjThe data and control flows of the optimization process are scheduled in the future.
Step S32, adding a path specialization program in the optimization program by the memorization technology to the optimization program, and constructing a regional energy system dispatching optimization fast path, which specifically comprises the following steps:
when the similarity constraint is judged to be satisfied, the optimization directly enters the next stage by skipping part of the computer program by which the S23 solving process is carried out. The similarity constraint is:
|1-S(Xi，Xj)|＜Constraints
when regional energy system scheduling optimization model is in the future XjAt run-down, if the similarity constraint is satisfied at the memory point, a path specialization program is added. Setting n steps of model calculation program, the k step has memory point, the path specialization program is fastpathiIs applicable to XiThe construction method of all the equivalence classes can be expressed as follows:
fastpathi：for step k，k∈(1，n)；ifS(Xi，Xj)＜Constraints；jump to step n
in step S4:
and selecting a plurality of possible future energy trading results, and repeating the steps S2 and S3 to obtain a plurality of scheduling optimization fast paths, so that a multi-future scheduling optimization model is formed on the basis of the regional energy system scheduling optimization model in the step S21.
Selecting other possible future X in possible space of future energy market trading resultiCan obtain new fastpathiTherefore, the path library can be obtained by selecting a plurality of possible future energy transaction results, so that the future space as large as possible is covered.
For regional energy system scheduling optimization based on Ether Fang trading, the equivalence of control flow and data flow can divide the possible space of future energy market trading result into a few equivalence classes, so limited X can be selectediTo cover as much future space as possible that is large enough. The scheduling optimization model (program) combined with the path library is the final multi-future scheduling optimization model.
In step S5:
and step S51, the main body evaluates the actual energy demand and investment demand according to the external information of traffic, climate, policy and the like grasped by the individual, performs physical transaction and financial transaction, and purchases various energy products such as electricity, heat, gas, cold and the like in the form of spot goods or contracts.
A plurality of social bodies form a decentralized prediction market, and social operation information can be converted into collective real-time energy utilization load prediction. The economic system, the social system and the identity system of the main body are integrated in the meta universe, and transactions can be conducted by means of intelligent equipment such as computers and mobile phones.
Step S52, the generated transaction will be propagated and identified among the blockchain, and finally the energy market transaction result is obtained after all transactions are executed in the energy ether house, and is marked as XtrueI.e. the energy market future that actually occurs. The trading result reflects the energy supply and demand relationship, and the market price of the energy product can be influenced, so that the next trading of the main body is influenced, namely the centralized forecasting market is counteracted.
In step S6:
the actual transaction result XtrueAnd converting the energy into multi-energy flow energy constraint for the energy production equipment according to the method of S22, and then using the multi-energy flow energy constraint as the input of the multi-future scheduling optimization model obtained in S4 to perform simulation solution to obtain the equipment output and regional energy system scheduling scheme, thereby realizing scheduling optimization.
On the basis of the solving steps, in order to improve the practicability of the invention, a regional energy system multi-future scheduling optimization system based on the metauniverse can be set up, and the regional energy system multi-future scheduling optimization system comprises a data acquisition module, an energy transaction multi-future prediction module, a regional energy system scheduling optimization module and an actual ether house transaction module.
The data acquisition module comprises a natural environment data acquisition submodule, a social environment data acquisition submodule and an energy real-time market data acquisition submodule;
the energy transaction multi-future prediction module comprises a data processing sub-module, an energy transaction fuzzy mapping model sub-module and an ether house multi-future transaction result database;
the regional energy system scheduling optimization module comprises a virtual layer actual equipment monitor, an equipment digital twin submodule, a decision layer energy brain submodule, a scheduling optimization model submodule and a production scheduling instruction controller;
the actual Ether house trading module comprises a user main body, an energy product, virtual currency and an Ether house trading platform;
the modules are respectively subjected to module packaging, a data transmission channel is established, so that the data acquisition module transmits data to the energy transaction multi-future prediction module, the energy transaction multi-future prediction module transmits the Ethenhouse multi-future transaction result database to the regional energy system scheduling optimization module, and the actual Ethenhouse transaction module transmits the actual transaction result to the regional energy system scheduling optimization module;
the system adopts the method to realize multi-future scheduling optimization of the regional energy system.
Claims (8)
1. A regional energy system multi-future scheduling optimization method based on a metauniverse is characterized by comprising the following steps:
step S1, constructing an Etheng transaction result fuzzy prediction model based on the multidimensional data relation, and generating a transaction result multi-future prediction set;
step S2, selecting a possible future energy trading result from the multi-future prediction set of trading results, scheduling the regional energy system, recording an instruction tracking sequence of the optimizing process and obtaining a scheduling scheme;
step S3, forming equivalence class constraint aiming at the future energy transaction result selected in the step S2 according to the control flow and the data flow in the obtained instruction tracking sequence, and using a memorisation technology to specialize an optimization path;
step S4, repeating the steps S2 and S3 to obtain various future fast optimizing paths and form a multi-future scheduling optimization model;
step S5, the main body in the Yuanzhou generates energy product transaction according to self energy demand, the energy ether house executes transaction, and the energy market in the Yuanzhou obtains actual transaction result;
and step S6, obtaining a regional energy system real-time scheduling scheme by means of a multi-future scheduling optimization model according to an actual transaction result.
2. The method for optimizing multi-future scheduling of a regional energy system based on a metauniverse according to claim 1, wherein the step S1 specifically comprises:
step S11, collecting natural environment data N, social environment data S and energy market historical price data MhEnergy market historical transaction result data ThEnergy market real-time price data Mr(ii) a Data cost in the meta universe needs to be considered in data selection, and the data types have direct relations with new energy power generation conditions, energy production and sales and energy market transactions;
step S12, cleaning, analyzing and integrating the acquired multidimensional data by means of big data technology, and constructing N, S, M by a machine learning methodhHistorical transaction results T on energyhThe fuzzy mapping of (a) to obtain a multi-future fuzzy prediction model is as follows,
f：{N，S，Mh}→Th
step S13, natural environment data N, social environment data S and energy market real-time price data MrThe possible space for obtaining the future energy market trading result including all the mappings is as follows,
X＝{X1，X2，X3...Xi...Xn}
wherein n is the number of possible mapping results; the set X is a possible space of future energy market trading results; xiRepresenting a possible mapping result, i.e. a possible future energy trading result.
3. The method for optimizing multi-future scheduling of a regional energy system based on a metauniverse according to claim 2, wherein the step S2 specifically comprises:
step S21, constructing a regional energy system dispatching optimization model in the meta universe; combining IoT, AR and a data transmission technology, fusing a refined physical model and operation and maintenance data, constructing an equipment digital twin model and an energy brain in the metas, wherein the digital twin model reflects the actual equipment condition in the metas, and the energy brain performs optimization scheduling according to the multi-energy flow constraint of the regional energy system in the metas to form a production scheduling instruction for the equipment, so that the regional energy system is scheduled; the device digital twin model comprises all devices in the whole process of actual energy system source network load storage and use, and the energy brain considers the objective limitation of the devices reflected by the digital twin model;
step S22, converting the selected future transaction result information into multi-energy flow energy constraint for the regional energy system, and requiring the real-time output of the regional energy system energy production equipment to be equal to the sum of the spot transaction and the due futures transaction of the energy market;
selecting a possible future energy market trading result in the possible space X of future energy market trading results
Xi，i∈(1，2，3...，n)
Note XiThe spot-transaction amount of the energy-source product is
E1＝{E1h，E1e，E1c，E1g}
The amount of futures due for a trade is
E2＝{E2h，E2e，E2c，E2g}
Wherein, subscripts h, e, c and g respectively represent four common energy products of heat, electricity, cold and gas; the multipotent abortion energy of the regional energy system is constrained to
Output＝E1+E2＝{E1h+E2h，E1e+E2e，E1c+E2c，E1g+E2g}
Step S23, inputting the multi-energy flow energy constraint of the regional energy system into the regional energy system scheduling optimization model, solving by taking the economic optimization as a target, executing regional energy system simulation in a virtual layer, and recording an instruction tracking sequence trace in the Yuanzhou in the solving processiObtaining an energy system scheduling scheme R containing equipment outputiThe solving process is implemented by computer programAnd (5) realizing the sequence.
4. The method for optimizing multi-future scheduling of a regional energy system based on a metauniverse according to claim 3, wherein the step S3 specifically comprises:
step S31, evaluating the data flow and the control flow of the instruction tracking sequence, and selecting the similarity evaluation index as the evaluation index of the equivalence class;
for selecting XiLater regional energy system scheduling process, by analyzing traceiObtaining a path for carrying out the future scheduling optimization in the meta-universe; traceiData stream DS ofiDescription of XiThe data circulation mode and the behavior state thereof in the scheduling optimization process of the regional energy system in the future; control flow CFiExpression of XiThe sequence of the logic execution of the control program in the scheduling optimization process of the lower-region energy system in the future;
evaluating the similarity of actual transaction results according to the similarity of the data flow and the control flow; the equivalence class of trading results is all future energy market trading results that satisfy the similarity constraints of data flow and control flow; the calculation method of the similarity S adopts a Pearson product moment correlation coefficient as follows:
wherein, XjN, 1, 2, 3.. n; σ is standard deviation, cov is covariance; DS (direct sequence)i、CFiAre each XiScheduling data flow and control flow of an optimization process in the future; DS (direct sequence)jAnd CFjIs XjData flow and control flow of a scheduling optimization process in the future;
step S32, a path specialization program is added in an optimization program in the solving process by using a memorization technology, and a regional energy system dispatching optimization fast path is constructed, which specifically comprises the following steps:
the similarity constraint is:
|1-S(Xi，Xj)|＜Constraints
when regional energy system scheduling optimization model is in the future XjIn run-down, if the similarity constraint is satisfied at the memory point, add a path specialization program: setting n steps of model calculation program, the k step has memory point, the path specialization program is fastpathiIs applicable to XiThe construction method of all the equivalence classes of (1) can be expressed as follows:
fastpathi：for step k，k∈(1，n)；ifS(Xi，Xj)＜Constraints；jump to step n
5. the method for optimizing multi-future scheduling of a regional energy system based on a metauniverse according to claim 1, wherein the step S4 specifically comprises:
selecting a plurality of possible future energy trading results, and repeating the steps S2 and S3 to obtain a plurality of scheduling optimization fast paths, thereby forming a multi-future scheduling optimization model on the basis of the regional energy system scheduling optimization model;
selecting other possible future X in possible space of future energy market trading resultiCan obtain new fastpathiTherefore, the path library can be obtained by selecting a plurality of possible future energy transaction results, so that the future space as large as possible is covered.
6. The method for optimizing multi-future scheduling of a regional energy system based on a metauniverse as claimed in claim 1, wherein the step S5 specifically comprises:
step S51, the main body evaluates the actual energy consumption requirement and the investment requirement, carries out physical transaction and financial transaction, and purchases various energy products;
the economic system, the social system and the identity system of the main body are integrated in the meta universe, and transactions can be conducted by means of intelligent equipment;
step S52, the generated transaction is propagated and identified among the blockchains, and finally the energy market transaction result is obtained after all transactions are executed in the energy ether house and recorded as XtrueNamely the real occurring energy market trading result.
7. The method for optimizing multi-future scheduling of a regional energy system based on the metauniverse according to claim 3, wherein the step S6 is:
the actual transaction result XtrueAnd converting the multi-energy flow energy into multi-energy flow energy constraint on the energy production equipment, and then using the multi-energy flow energy constraint as the input of the multi-future scheduling optimization model obtained in S4 to perform simulation solution to obtain an equipment output and regional energy system scheduling scheme so as to realize scheduling optimization.
8. A metastic-based regional energy system multi-future schedule optimization system, wherein the system implements regional energy system multi-future schedule optimization using the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210088263.7A CN114548692A (en) | 2022-01-25 | 2022-01-25 | Regional energy system multi-future scheduling optimization method and system based on metauniverse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210088263.7A CN114548692A (en) | 2022-01-25 | 2022-01-25 | Regional energy system multi-future scheduling optimization method and system based on metauniverse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114548692A true CN114548692A (en) | 2022-05-27 |
Family
ID=81671247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210088263.7A Pending CN114548692A (en) | 2022-01-25 | 2022-01-25 | Regional energy system multi-future scheduling optimization method and system based on metauniverse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114548692A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897447A (en) * | 2022-07-12 | 2022-08-12 | 北京智芯微电子科技有限公司 | Comprehensive energy cooperative control method and system |
| CN114973391A (en) * | 2022-06-30 | 2022-08-30 | 北京万里红科技有限公司 | Eyeball tracking method, device and equipment applied to metacarpal space |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510212A (en) * | 2018-04-17 | 2018-09-07 | 香港中文大学（深圳） | A kind of the distributed energy dispatching method and system of interactive mode energy resource system |
| CN112381339A (en) * | 2021-01-14 | 2021-02-19 | 南方电网数字电网研究院有限公司 | Method for optimizing operation cost of regional comprehensive energy system in electric power market environment |
| US20210304307A1 (en) * | 2020-03-26 | 2021-09-30 | Xi'an Jiaotong University | Distributed energy transaction matching method based on energy network constraints and multiple knapsack model |
-
2022
- 2022-01-25 CN CN202210088263.7A patent/CN114548692A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510212A (en) * | 2018-04-17 | 2018-09-07 | 香港中文大学（深圳） | A kind of the distributed energy dispatching method and system of interactive mode energy resource system |
| US20210304307A1 (en) * | 2020-03-26 | 2021-09-30 | Xi'an Jiaotong University | Distributed energy transaction matching method based on energy network constraints and multiple knapsack model |
| CN112381339A (en) * | 2021-01-14 | 2021-02-19 | 南方电网数字电网研究院有限公司 | Method for optimizing operation cost of regional comprehensive energy system in electric power market environment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114973391A (en) * | 2022-06-30 | 2022-08-30 | 北京万里红科技有限公司 | Eyeball tracking method, device and equipment applied to metacarpal space |
| CN114897447A (en) * | 2022-07-12 | 2022-08-12 | 北京智芯微电子科技有限公司 | Comprehensive energy cooperative control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abapour et al. | Game theory approaches for the solution of power system problems: A comprehensive review | |
| Abdi | Profit-based unit commitment problem: A review of models, methods, challenges, and future directions | |
| Ahmed et al. | Machine learning based energy management model for smart grid and renewable energy districts | |
| Pinto et al. | Adaptive portfolio optimization for multiple electricity markets participation | |
| Pinto et al. | A new approach for multi-agent coalition formation and management in the scope of electricity markets | |
| Wen et al. | Strategic bidding for electricity supply in a day-ahead energy market | |
| Vahidinasab et al. | Multiobjective environmental/techno-economic approach for strategic bidding in energy markets | |
| CN114548692A (en) | Regional energy system multi-future scheduling optimization method and system based on metauniverse | |
| Zhang et al. | Multi-agent deep reinforcement learning based distributed control architecture for interconnected multi-energy microgrid energy management and optimization | |
| Liu et al. | Dynamic supply chain integration optimization in service mass customization | |
| Kumar et al. | Dynamic economic dispatch–a review of solution methodologies | |
| Almalaq et al. | Deep learning application: Load forecasting in big data of smart grids | |
| Hua et al. | Internet thinking for layered energy infrastructure | |
| Xu et al. | Perception and decision-making for demand response based on dynamic classification of consumers | |
| Joo et al. | Adaptive load management (ALM) in electric power systems | |
| Kovalyov et al. | A platform-based approach to implementation of future smart distributed energy control systems | |
| Wang et al. | Research on the decision-making method of coal order price and coal purchase quantity based on prediction | |
| Chappin et al. | Modeling strategic and operational decision-making—an agent-based model of electricity producers | |
| Goodarzi et al. | Using axiomatic design for developing a framework of manufacturing cloud service composition in the equilibrium state | |
| Sugan | PredictOptiCloud: A hybrid framework for predictive optimization in hybrid workload cloud task scheduling | |
| Bublitz et al. | Agent-based simulation of interconnected wholesale electricity markets: an application to the German and French market area | |
| Li et al. | A system analysis and biform game modeling to emerging function and value of innovation networks | |
| Bublitz et al. | Agent-based simulation of the German and French wholesale electricity markets-Recent extensions of the powerACE model with exemplary applications | |
| Sousa | Simulation of Hydro Power Plants in Electricity Markets Using an Agent-Based Model | |
| Steber et al. | A comprehensive electricity market model using simulation and optimization techniques |
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 |