CN107844869B - Online intelligent learning decision optimization method and system for gas distributed energy system - Google Patents

Online intelligent learning decision optimization method and system for gas distributed energy system Download PDF

Info

Publication number
CN107844869B
CN107844869B CN201711232876.9A CN201711232876A CN107844869B CN 107844869 B CN107844869 B CN 107844869B CN 201711232876 A CN201711232876 A CN 201711232876A CN 107844869 B CN107844869 B CN 107844869B
Authority
CN
China
Prior art keywords
energy
model
unit
station
steam
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711232876.9A
Other languages
Chinese (zh)
Other versions
CN107844869A (en
Inventor
王恒涛
孔飞
陈耀斌
纪星星
刘洁
彭敏
纪宇飞
柳玉宾
唐军
洪博
李昭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Huadian Science And Technology Institute Co ltd
Original Assignee
China Huadian Science And Technology Institute Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Huadian Science And Technology Institute Co ltd filed Critical China Huadian Science And Technology Institute Co ltd
Priority to CN201711232876.9A priority Critical patent/CN107844869B/en
Publication of CN107844869A publication Critical patent/CN107844869A/en
Application granted granted Critical
Publication of CN107844869B publication Critical patent/CN107844869B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01K—STEAM ENGINE PLANTS; STEAM ACCUMULATORS; ENGINE PLANTS NOT OTHERWISE PROVIDED FOR; ENGINES USING SPECIAL WORKING FLUIDS OR CYCLES
    • F01K23/00—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids
    • F01K23/02—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids the engine cycles being thermally coupled
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01K—STEAM ENGINE PLANTS; STEAM ACCUMULATORS; ENGINE PLANTS NOT OTHERWISE PROVIDED FOR; ENGINES USING SPECIAL WORKING FLUIDS OR CYCLES
    • F01K23/00—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids
    • F01K23/02—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids the engine cycles being thermally coupled
    • F01K23/06—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids the engine cycles being thermally coupled combustion heat from one cycle heating the fluid in another cycle
    • F01K23/10—Plants characterised by more than one engine delivering power external to the plant, the engines being driven by different fluids the engine cycles being thermally coupled combustion heat from one cycle heating the fluid in another cycle with exhaust fluid of one cycle heating the fluid in another cycle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • 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

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Tourism & Hospitality (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Marketing (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Genetics & Genomics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Physiology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Operations Research (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)

Abstract

The invention discloses an online intelligent learning decision optimization method and system of a gas distributed energy system, wherein the method comprises the following steps: acquiring input and output parameters of single equipment of an energy central station and a substation, and establishing a single equipment dynamic model according to the input and output parameters of the single equipment; and establishing a decision optimization control model of the whole energy station, solving to obtain an optimal unit operation instruction model, and issuing an instruction to a DCS controller of the energy central station and a controller of substation single equipment. The invention obtains the corresponding set of optimal operation parameters, completes the optimal distribution of the unit load, and reaches each energy substation, thereby realizing the integral energy efficiency optimization of the energy central station and the substation, leading the integral energy utilization efficiency and economic benefit of the system to be best, leading the operation efficiency to be highest and leading the system benefit to be more stable.

Description

Online intelligent learning decision optimization method and system for gas distributed energy system
Technical Field
The invention relates to an online intelligent learning decision optimization method and system of a gas distributed energy system, and belongs to the technical field of energy system optimization.
Background
The existing operation mode of the heating and cooling machine unit sub-station combination of the central station of the co-production unit is that the energy sub-station is just equivalent to a relay station, pressurizes the heat transmitted by the central station and does not have the function of independent energy supply; in addition, the central station and each sub-station are generally operated by operators independently, however, the operation experience of the operators is different, so that the operation benefits of different operators are different, the fluctuation of the system benefits along with the load change is also larger, and the overall economy of the energy system is poor; in addition, the existing central station only sets a total flowmeter on the main pipe of the heat supply network to monitor the performance of the steam turbines, but when the types of a plurality of steam turbines installed in the energy system are inconsistent, the performance of each steam turbine cannot be monitored and obtained, so that more targeted energy system operation optimization cannot be performed. Thus, improvements are still needed.
Disclosure of Invention
The invention aims to provide an online intelligent learning decision-making optimization method and system for a gas distributed energy system, which can effectively solve the problems existing in the prior art, in particular to the problems that operators independently operate a central station and each substation, the operation benefits of different operators are large in difference due to different operation experiences of the operators, the system benefits fluctuate greatly along with load changes, and the overall economy of the energy system is poor.
In order to solve the technical problems, the invention adopts the following technical scheme: the online intelligent learning decision optimization method of the gas distributed energy system comprises the following steps: acquiring input and output parameters of single equipment of an energy central station and a substation, and establishing a single equipment dynamic model according to the input and output parameters of the single equipment; establishing a decision optimization model of the whole energy station (the solution of the decision optimization model is real-time online), solving to obtain an optimal unit operation instruction model, and transmitting the instruction to a DCS controller of an energy central station and a controller of substation single equipment;
when solving the decision optimization model of the whole energy station, firstly, carrying out local optimization by taking the substation as a unit, and optimizing the substationCorrection to->Such that:
wherein t represents time,representing the optimal output load of the master station output to the j substations, τ j Representing transmission pipeline delay of output load of main station to sub station j Representing the pipe loss ratio; then the optimization solution of each substation is further added>Substituting and optimizing the central station.
Preferably, the method specifically comprises the following steps:
s1, acquiring input and output parameters of single equipment of an energy central station and a substation, and performing online data learning and correction through a neural network to obtain a dynamic model of the single equipment; by a means ofThe dynamic model of the monomer equipment is expressed as a functional form y i ＝f i (x i ) Wherein x is i For the set of all input parameters of the device, y i A set representing all output parameters of the device;
s2, carrying out output and input association on each monomer equipment dynamic model through a process flow of a distributed energy system to form a full system model, namely Y=f (X), wherein X is a set of all input parameters of the full system, and Y is a set of all output parameters of the full system; the set of all output parameters comprises all energy output forms of the system, including a conventional cold load C, a thermal load H and an electric load E, namely Y= [ C, H, E ];
s3, establishing a decision optimization model through a whole system model; the load constraint of the decision optimization model is from energy feedback of a user and a load prediction model; the energy feedback of the user comprises a plurality of energy source forms including a conventional refrigeration load demand C r Heat load demand H r Electric load demand E r Meet the output parameters C=C of the energy station r ，H＝H r ，E＝E r ；
S4, according to different optimization targets, adopting an intelligent algorithm to solve the decision optimization model to obtain an optimal unit operation instruction model under the optimization targets, and sending the instruction to a DCS controller of an energy central station and a controller of substation single equipment; the system optimization target mainly comprises the whole plant heat efficiency, benefit, thermoelectric ratio, single unit comprehensive heat efficiency, thermoelectric ratio and optimal benefit of the whole energy station.
The objective function of the decision optimization model can be expressed into various forms, including a conventional objective form, so that the system is selected for actual operation with maximum economic benefit, maximum energy efficiency of the whole system, minimum pollutant emission and the like, namely:
economic benefit description P (Y) -P (X), wherein P (Y) represents gross profit (unit cell) of the whole system output; p (X) represents the cost (unit cells) of all inputs to the overall system;
full system energy efficiency: q (Y)/Q (X), wherein Q (Y) represents the total energy (unit J) output by the whole system; q (X) represents the total energy (in J) of all inputs of the whole system;
and (3) pollutant emission: w (X) represents the total amount of pollutants contained in the whole system consumption resource.
Preferably, a genetic algorithm is utilized to solve the decision optimization model, and an optimal unit operation instruction model is obtained.
Preferably, the central station includes: a gas turbine-waste heat boiler unit, a steam turbine unit and a hot water boiler unit; the substation includes: an electric refrigerating unit, a lithium bromide absorption refrigerating unit, a plate-exchange type heat exchanger unit and an electric heater unit; the monomer plant model (described by a function curve) was built by:
gas turbine-exhaust-heat boiler:
power generation curve:
high pressure steam curve:
low pressure steam curve:
steam turbine model:
power generation curve:
heating steam curve:
temperature and pressure reducer model:
wherein, the upper mark 3 represents a temperature and pressure reducer;
hot water boiler model:
wherein, the upper mark 4 represents a hot water boiler;
model of electric refrigerator:
lithium bromide absorption refrigerating unit model:
cooling curve:
power consumption profile:
plate-change type heat exchanger model:
electric heater model:
wherein, the upper mark 1 represents an internal combustion engine-waste heat boiler; the upper mark 2 represents a steam turbine; the upper mark 5 indicates an electric refrigerating unit; the upper mark 6 represents a lithium bromide absorption refrigerating unit; the superscript 7 indicates a plate heat exchanger; the upper mark 8 indicates an electric heater; w represents user heat, c represents user cold, g represents natural gas heat, e represents generated power or consumed power, h represents high-pressure steam heat, l represents low-pressure steam heat, s represents heat output to a heat supply network, and k represents opening of a steam extraction rotary partition plate.
Through carrying out the optimization layout to the sub-station, make it be equivalent to an energy station, both can supply cold and can supply heat, then carry out the modeling study to the performance of each unit of energy central station and sub-station to make the whole operation optimization to the energy system become possible.
Preferably, the flow parameters of each turbine are obtained by arranging the flow meter on the air exhaust pipeline of each turbine, so that the characteristics of the turbines of different types are obtained, and the turbines can be adjusted in a targeted manner (the opening degree of the air exhaust valve of each turbine is adjusted) according to the requirements of users, so that the economy of the whole energy station is improved.
In the above-mentioned online intelligent learning decision optimization method of the gas distributed energy system, the decision optimization model includes a benefit maximization model, and the benefit maximization model of the energy station is:
s.t.
wherein I is C Representing all electric refrigeration units; i x Represents all lithium bromide absorption refrigerating unit sets, I w Represents all heat exchange plate heat exchange sets, I g Representing all gas turbine-exhaust-heat boiler unit sets, I s Representing all sets of turbine units, I b Represents all hot water boiler unit sets, I h Representing all sets of electric heaters; p (P) C 、P W 、P e 、P g Respectively representing cold price, hot price, online electricity price, offline electricity price and gas price; r is (r) e Representing the power consumption of the plant; r is R c 、R w Respectively representing the cold and hot load demands of users;
the exhaust-heat boiler of the i-number gas turbine-exhaust-heat boiler combined cycle unit outputs high-pressure steam = turbine main steam + temperature and pressure reduction steam;
the exhaust-heat boiler output low-pressure steam inlet turbine of the exhaust-heat boiler combined cycle unit of No. 1 and No. 2 is constrained by the water supplementing capacity of the exhaust-heat boiler, the turbine of the No. 3 gas turbine-exhaust-heat boiler combined cycle unit is a back pressure unit, and no steam supplementing is carried out>The steam turbines of the gas turbine-waste heat boiler combined cycle units No. 1 and No. 2 are extraction condensing units; difference-> Indicating that the low-pressure steam directly enters the heat exchanger for heat exchange output; wherein (1)>Represents No. 1 waste heat boiler>Represents No. 2 waste heat boiler>Steam turbine No. 1>Steam turbine No. 2>And represents steam turbine No. 3.
The objective function and the limiting conditions of the energy station benefit maximization model can obtain a corresponding unit optimal operation parameter set, and the unit is adjusted to operate under the optimal operation parameter condition, so that the unit works at an optimal efficiency point, and the economy of the whole energy system is best.
In the above method for optimizing online intelligent learning decision of gas distributed energy system, preferably, the optimal unit operation instruction model includes parameters:and->The power generation power of the internal combustion engine-waste heat boiler, the heat supply steam quantity of the steam turbine, the low-pressure steam supplementing quantity of the steam turbine, the high-pressure steam heat quantity of the temperature and pressure reducer, the natural gas quantity of the inlet of the hot water boiler, the power consumption of the electric refrigerating unit, the (cold) load of the lithium bromide unit, the heat required to be produced by the lithium bromide unit and the power consumption of the electric heater are respectively shown.
An online intelligent learning decision optimization system of a gas distributed energy system for realizing the method comprises the following steps: the system comprises an energy central station, an energy sub-station, an iDOS device, an information center server and a DCS controller, wherein the information center server is respectively connected with the energy sub-station and the iDOS device, and the DCS controller is respectively connected with the energy central station and the iDOS device.
Preferably, the iDOS device includes a display, a processor and an iDOS cabinet, the processor is respectively connected with the display, the iDOS cabinet and the information center server, and the iDOS cabinet is respectively connected with the DCS controller and the information center server, so that rapid modeling and solving can be realized, the unit works at an optimal efficiency point, and the economy of the whole energy system is best.
The invention relates to an online intelligent learning decision optimizing system of a gas distributed energy system, wherein the energy central station comprises: the system comprises a gas turbine, a waste heat boiler, a steam turbine, a heater and a hot water boiler, wherein the hot water boiler and the heater are connected with a main pipe of a heat supply network, the gas turbine is connected with the waste heat boiler, the waste heat boiler is respectively connected with the steam turbine and the heater, and the steam turbine is connected with the heater; the gas turbine, the waste heat boiler, the steam turbine and the heater are all connected with the DCS controller, so that the load requirements of the substation can be comprehensively met.
Preferably, the air extraction pipeline of each steam turbine is provided with a flow meter, and the flow meters are connected with the DCS controller.
In the present invention, the energy substation includes: the system comprises an electric refrigerating unit, a lithium bromide absorption refrigerating unit, an electric heater and a plate-exchange heat exchanger, wherein the electric refrigerating unit, the lithium bromide absorption refrigerating unit and the electric heater are connected with an information center server, and the plate-exchange heat exchanger is respectively connected with the electric refrigerating unit, the lithium bromide absorption refrigerating unit, the electric heater and a main pipe of a heat supply network. The substation is optimally arranged to be equivalent to an energy station, so that the energy station can supply cold and heat, and then the performance of each unit of the energy central station and the substation is modeled and learned, so that the whole operation optimization of an energy system is possible
Compared with the prior art, the invention has the following advantages:
1. the method comprises the steps of collecting input and output parameters of single equipment of an energy central station and sub-stations (namely, collecting load information), then establishing a single equipment model, completing learning of a unit characteristic curve, finally establishing a decision optimization model of the whole energy station, solving to obtain an optimal unit operation instruction model, completing optimal distribution of unit load, and reaching each energy sub-station, so that the energy central station and the sub-stations are subjected to integral energy efficiency optimization, the integral energy utilization efficiency and economic benefit of the system are best, the operation efficiency is highest, and the system benefit is more stable;
2. the optimal operation mode analysis (solving in other modes) of the unit is completed by utilizing a genetic algorithm to solve the decision optimization model; then, an optimization control instruction (comprising a load optimization distribution instruction and a heating mode optimization and regulation instruction) is sent to the DCS system, the running mode of the unit is adjusted, and the network service system in the IDOS cabinet is used for issuing the optimal running optimization strategy of each energy substation, so that the overall optimization control of the central station and the substation energy systems is realized, and the running of the energy systems is ensured to achieve the running targets of high efficiency, low consumption, economic matching, reliability and safety;
3. because of more energy substations and numerous equipment, the solution space of the decision optimization model for globally solving the whole energy substation is larger, and the calculation complexity and the time complexity are also very large. According to the invention, the overall optimization problem is decomposed by utilizing the characteristics of capacity of a main station and mutual uncoupling of heat exchange of sub stations in the process flow, the sub stations are used as units for local optimization, and then the central station is optimized, so that the calculation complexity and the time complexity are reduced;
4. the invention corrects the substation optimization solution, thereby avoiding the influence of pipeline loss and transmission delay, and leading the overall energy utilization efficiency and economic benefit of the system to be better and the operation benefit to be higher;
5. the flow parameters of each turbine are obtained by arranging the flow meter on the air extraction pipeline of each turbine, so that the characteristics of the turbines of different types are obtained, the turbines can be adjusted in a targeted manner according to the requirements of users (the opening of the air extraction valve of each turbine is adjusted), and the economical efficiency of the whole energy station is improved;
6. the benefit maximization model optimizes the operation modes of the refrigerating and heating systems by comprehensively and comprehensively planning factors such as natural gas price, peak regulation mode, station electricity cost, grid valley electricity cost and the like according to the requirements of cold water load and hot water load and by combining the working characteristics of a gas turbine unit and a steam turbine, so that a corresponding unit optimal operation parameter set can be obtained, the unit is operated under the optimal operation parameter condition by adjusting the unit, the unit is operated at an optimal efficiency point, and an energy station is operated according to the optimal economic benefit mode, so that the economy of the whole energy system is best;
7. through carrying out the optimization layout to the sub-station, make it be equivalent to an energy station, both can supply cold and can supply heat, then carry out the modeling study to the performance of each unit of energy central station and sub-station to make the whole operation optimization to the energy system become possible.
Drawings
FIG. 1 is a schematic block diagram of the overall structure of an energy system of the present invention;
FIG. 2 is a schematic diagram of the energy hub of the present invention;
FIG. 3 is a diagram of a cooling system of an energy substation of the present invention;
FIG. 4 is a heating system diagram of an energy substation of the present invention;
fig. 5 is a flow chart of the method of the present invention.
Reference numerals: the system comprises a 1-energy central station, a 2-energy sub-station, a 3-iDOS device, a 4-information center server, a 5-DCS controller, a 6-display, a 7-processor, an 8-iDOS cabinet, a 9-gas turbine, a 10-waste heat boiler, an 11-steam turbine, a 12-heater, a 13-hot water boiler, a 14-flowmeter, a 15-electric refrigerating unit, a 16-lithium bromide absorption refrigerating unit, a 17-electric heater and an 18-plate-change type heat exchanger.
The invention is further described below with reference to the drawings and the detailed description.
Detailed Description
Embodiments of the invention: the online intelligent learning decision optimization method of the gas distributed energy system, as shown in fig. 5, comprises the following steps: collecting input and output parameters (including flow, pressure, temperature and the like) of single equipment of an energy central station and a substation, and establishing a single equipment dynamic model according to the input and output parameters of the single equipment; and establishing a decision optimization model of the whole energy station, solving to obtain an optimal unit operation instruction model, and issuing an instruction to a DCS controller of the energy central station and a controller of substation single equipment.
The method specifically comprises the following steps:
s1, acquiring input and output parameters of single equipment of an energy central station and a substation, and performing online data learning and correction through a neural network to obtain a dynamic model of the single equipment; the dynamic model of the monomer equipment is expressed as a functional form y i ＝f i (x i ) Wherein x is i For the set of all input parameters of the device, y i A set representing all output parameters of the device;
s2, carrying out output and input association on each monomer equipment dynamic model through a process flow of a distributed energy system to form a full system model, namely Y=f (X), wherein X is a set of all input parameters of the full system, and Y is a set of all output parameters of the full system; the set of all output parameters comprises all energy output forms of the system, including a conventional cold load C, a thermal load H and an electric load E, namely Y= [ C, H, E ];
s3, establishing a decision optimization model through a whole system model; the load constraint of the decision optimization model is from energy feedback of a user and a load prediction model; the energy feedback of the user comprises a plurality of energy source forms including a conventional refrigeration load demand C r Heat load demand H r Electric load demand E r Meet the output parameters C=C of the energy station r ，H＝H r ，E＝E r ；
S4, according to different optimization targets, adopting an intelligent algorithm to solve the decision optimization model to obtain an optimal unit operation instruction model under the optimization targets, and sending the instruction to a DCS controller of an energy central station and a controller of substation single equipment; the system optimization target mainly comprises the whole plant heat efficiency, benefit, thermoelectric ratio, single unit comprehensive heat efficiency, thermoelectric ratio and optimal benefit of the whole energy station.
The objective function of the decision optimization model can be expressed into various forms, including a conventional objective form, so that the system is selected for actual operation with maximum economic benefit, maximum energy efficiency of the whole system, minimum pollutant emission and the like, namely:
economic benefit description P (Y) -P (X), wherein P (Y) represents gross profit (unit cell) of the whole system output; p (X) represents the cost (unit cells) of all inputs to the overall system;
full system energy efficiency: q (Y)/Q (X), wherein Q (Y) represents the total energy (unit J) output by the whole system; q (X) represents the total energy (in J) of all inputs of the whole system;
and (3) pollutant emission: w (X) represents the total amount of pollutants contained in the whole system consumption resource.
Optionally, the central station may include: a gas turbine-waste heat boiler unit, a steam turbine unit and a hot water boiler unit; the substation may include: an electric refrigerating unit, a lithium bromide absorption refrigerating unit, a plate-exchange type heat exchanger unit and an electric heater unit; the monomer plant model (described in terms of a function curve) can be built by:
gas turbine-exhaust-heat boiler:
power generation curve:
high pressure steam curve:
low pressure steam curve:
steam turbine model:
power generation curve:
heating steam curve:
temperature and pressure reducer model:
wherein, the upper mark 3 represents a temperature and pressure reducer;
hot water boiler model:
wherein, the upper mark 4 represents a hot water boiler;
model of electric refrigerator:
lithium bromide absorption refrigerating unit model:
cooling curve:
power consumption profile:
plate-change type heat exchanger model:
electric heater model:
wherein, the upper mark 1 represents an internal combustion engine-waste heat boiler; the upper mark 2 represents a steam turbine; the upper mark 5 indicates an electric refrigerating unit; the upper mark 6 represents a lithium bromide absorption refrigerating unit; the superscript 7 indicates a plate heat exchanger; the upper mark 8 indicates an electric heater; w represents user heat, c represents user cold, g represents natural gas heat, e represents generated power or consumed power, h represents high-pressure steam heat, l represents low-pressure steam heat, s represents heat output to a heat supply network, and k represents opening of a steam extraction rotary partition plate.
In order to monitor and obtain the flow of each turbine, flow parameters of each turbine can be obtained by arranging a flow meter on an air extraction pipeline of each turbine, so that characteristics of turbines of various types are obtained, and the turbines can be adjusted in a targeted manner according to the requirements of users (the opening degree of an air extraction valve of each turbine is adjusted), so that the economical efficiency of the whole energy station is improved.
Optionally, the decision optimization model includes a benefit maximization model, and the benefit maximization model of the energy station is:
wherein I is C Representing all electric refrigeration units; i x Represents all lithium bromide absorption refrigerating unit sets, I w Represents all heat exchange plate heat exchange sets, I g Representing all gas turbine-exhaust-heat boiler unit sets, I s Representing all sets of turbine units, I b Represents all hot water boiler unit sets, I h Representing all sets of electric heaters; p (P) C 、P W 、P e 、P e d 、P g Respectively representing cold price, hot price, online electricity price, offline electricity price and gas price; r is (r) e Representing the power consumption of the plant; r is R c 、R w Respectively representing the cold and hot load demands of users;
the exhaust-heat boiler of the i-number gas turbine-exhaust-heat boiler combined cycle unit outputs high-pressure steam = turbine main steam + temperature and pressure reduction steam;
the exhaust-heat boiler output low-pressure steam inlet turbine of the exhaust-heat boiler combined cycle unit of No. 1 and No. 2 is constrained by the water supplementing capacity of the exhaust-heat boiler, the turbine of the No. 3 gas turbine-exhaust-heat boiler combined cycle unit is a back pressure unit, and no steam supplementing is carried out>The steam turbines of the gas turbine-waste heat boiler combined cycle units No. 1 and No. 2 are extraction condensing units; difference-> Indicating that the low-pressure steam directly enters the heat exchanger for heat exchange output; wherein (1)>Represents No. 1 waste heat boiler>Represents No. 2 waste heat boiler>Steam turbine No. 1>Steam turbine No. 2>And represents steam turbine No. 3.
The genetic algorithm can be utilized to solve the decision optimization model, so that an optimal unit operation instruction model is obtained; preferably, the optimal unit operation instruction model includes parameters:and->The power generation power of the internal combustion engine-waste heat boiler, the heat supply steam quantity of the steam turbine, the low-pressure steam supplementing quantity of the steam turbine, the high-pressure steam heat quantity of the temperature and pressure reducer, the natural gas quantity of the inlet of the hot water boiler, the power consumption of the electric refrigerating unit, the (cold) load of the lithium bromide unit, the heat required to be produced by the lithium bromide unit and the power consumption of the electric heater are respectively shown.
When solving the decision optimization model of the whole energy station, firstly, carrying out local optimization by taking the substation as a unit:
1) Substation (number j) optimization problem
P s ＝P w ；
Wherein,representing a set of j substations; p (P) w And P s Representing the thermal price.
Solving the optimization problem can obtain the maximum benefit of the j substations, and the optimal input load of the master station is required to be:
2) Master station optimization problem
After each substation meets the self-load requirement to solve the optimal input load, the global optimization problem can be transformed into the following optimization problem:
P s ＝P w .
AGC constraint, the electric quantity is a fixed value; where J represents the set of all substations.
3) Correction model
In the actual implementation process of the project, as the distance between the transmission pipeline of the master station and the substation is far, the output of the master station to the substation has certain delay and certain loss, so that the model needs to be corrected to a certain extent to optimize the substationCorrection to->I.e.
Satisfy the following requirements
Wherein t represents the time period in which,representing the optimal output load of the master station output to the j substations, τ j Representing transmission pipeline delay of output load of main station to sub station j Representing the pipe loss ratio.
The delay tau of the transmission pipeline j The parameters of the central station outlet and the substation inlet can be acquired by adopting a data convolution calculation and a characteristic matching method; transmission pipeThe track loss ratio sigma j It can be assumed that the calculation is proportional to the distance, and the calculation is obtained by calculating the energy difference between the outlet of the central station and the inlet of the substation and the distance of the equal ratio transmission pipeline.
The online intelligent learning decision optimization system of the gas distributed energy system for realizing the method comprises the following steps as shown in fig. 1: the system comprises an energy central station 1, an energy sub-station 2, an iDOS device 3, an information center server 4 and a DCS controller 5, wherein the information center server 4 is respectively connected with the energy sub-station 2 and the iDOS device 3, and the DCS controller 5 is respectively connected with the energy central station 1 and the iDOS device 3.
The iDOS device 3 may include a display 6, a processor 7, and an iDOS cabinet 8, the processor 7 is connected to the display 6, the iDOS cabinet 8, and the information center server 4, and the iDOS cabinet 8 is connected to the DCS controller 5 and the information center server 4, respectively.
As shown in fig. 1, the energy center 1 may include: the system comprises a gas turbine 9, a waste heat boiler 10, a steam turbine 11, a heater 12 and a hot water boiler 13, wherein the hot water boiler 13 and the heater 12 are connected with a main pipe of a heat supply network, the gas turbine 9 is connected with the waste heat boiler 10, the waste heat boiler 10 is respectively connected with the steam turbine 11 and the heater 12, and the steam turbine 11 is connected with the heater 12; the gas turbine 9, the waste heat boiler 10, the steam turbine 11 and the heater 12 are all connected with the DCS controller 5.
In order to obtain the flow data of each turbine, a flow meter 14 may be disposed on the air extraction pipeline of each turbine 11, and the flow meter 14 is connected to the DCS controller 5.
In order to implement unified optimal operation control for the energy substation, as shown in fig. 1, the energy substation 2 may include: the electric refrigerating unit 15, the lithium bromide absorption refrigerating unit 16, the electric heater 17 and the plate-change heat exchanger 18 are connected with the information center server 4, and the plate-change heat exchanger 18 is connected with the electric refrigerating unit 15, the lithium bromide absorption refrigerating unit 16, the electric heater 17 and a main pipe of a heat supply network respectively.
Experimental example: the technology of the invention is adopted for optimizing the operation of the energy system in the energy station project of a certain company. Specifically, the construction mode of adding the energy sub-station 2 into the energy central station 1 is adopted, the construction scale of the energy central station 1 is 214MW grade gas-steam combined cycle cogeneration unit (namely, gas turbine-waste heat boiler combined cycle cogeneration unit) and 2 116MW hot water boilers, wherein the gas-steam combined cycle unit is in a one-to-one mode and comprises 3 sets of 6F.01 gas turbine generator units, 3 double-pressure waste heat boilers, 2 steam extraction condensing steam turbine generator units and 1 back pressure steam turbine generator unit, the total power generation capacity of the 1 back pressure steam turbine generator unit is 214MW (flow meters are arranged on the air extraction pipelines of each steam extraction condensing steam turbine generator unit and the back pressure steam turbine generator unit, and flow parameters of each steam turbine are obtained), and the power supply of an administrative auxiliary center and the total heat source are supplied by each sub-station. The energy substation 2 is built with a lithium bromide absorption refrigerating unit 16, an electric refrigerating unit, a plate-exchange type heat exchanger 18, an electric heater 17 and the like, and is responsible for energy supply in a canal core area.
Compared with the traditional coal-fired power plant, the combined heat and power cogeneration unit central station and refrigeration and heating unit sub-station has the advantages of low pollution, high efficiency and the like, but the fuel cost is much higher than that of the traditional thermal power plant, and the economy of the system is improved by refined operation and optimization if the cogeneration unit generates better economy. The energy conversion efficiency and the economy of each link in the system are analyzed in detail, and the overall economy of the system is improved by adjusting the operation modes of the central station and the substation equipment. The heat supply mode and the unit output are specifically adjusted to work at the optimal efficiency point.
The energy central station 1 comprises an iDOS device 3, the iDOS device 3 further comprises a display 6, a processor 7 and an iDOS cabinet 8, and the iDOS device has the functions of information acquisition (cabinet), remote data communication (cabinet), load optimal distribution, unit characteristic curve online learning, load prediction and the like. The display 6 is used for displaying the state of the unit and the result of calculating parameters.
Specifically, the real-time calculation of the performance indexes of the plant level, the unit level and the equipment level is needed to provide guidance for load distribution and decision optimization. The iDOS device 3 collects real-time performance monitoring data of the energy central station 1 collected by the DCS controller 5 and real-time performance monitoring data of the energy sub-station 2 collected by the information central server 4, and includes performance monitoring data of main equipment such as a gas turbine 9, an exhaust heat boiler 10, a steam turbine 11 (for example, including two types of extraction and condensation and back pressure, the flow rate of each steam turbine is monitored by a flow meter 14 arranged on an extraction pipeline of each steam turbine), a hot water boiler 13, a head station heater 12, a lithium bromide absorption refrigerating unit 16, an electric refrigerating unit 15, an electric heater 17, a plate-change heat exchanger 18 and other auxiliary equipment of each energy sub-station. And obtaining output information according to the input information of each unit device, thereby obtaining the performance of efficiency, power, emission and the like of the unit under different load conditions. Then, a monomer equipment model is established through a neural network algorithm; thirdly, the network server collects load related data such as heat supply network data, user energy data and weather data, factors such as natural gas price, peak regulation mode, plant electricity cost, grid low valley electricity cost and the like are comprehensively considered, energy efficiency optimization calculation is carried out by using a benefit maximization model, and the optimal operation mode analysis of the unit is completed by using a genetic algorithm; and then, an optimization control instruction (comprising a load optimization allocation instruction and a heating mode optimization and regulation instruction) is sent to the DCS controller 5 through the iDOS cabinet 8, the running mode of the unit is adjusted, and the optimal running optimization strategy of each energy substation is issued and issued to a running operator through the network server, so that the overall optimization control of the central station and the substation energy system is realized, and the running of the energy system is ensured to achieve the running targets of high efficiency, low consumption, economic matching, reliability and safety.

Claims (10)

1. The online intelligent learning decision optimization method of the gas distributed energy system is characterized by comprising the following steps of: acquiring input and output parameters of single equipment of an energy central station and a substation, and establishing a single equipment dynamic model according to the input and output parameters of the single equipment; establishing a decision optimization model of the whole energy station, solving to obtain an optimal unit operation instruction model, and issuing an instruction to a DCS controller of the energy central station and a controller of substation single equipment;
when solving the decision optimization model of the whole energy station, firstlyLocal optimization is carried out by taking the substation as a unit, and the substation is optimized and solvedCorrection to->Such that:
wherein t represents time,representing the optimal output load of the master station output to the j substations, τ j Representing transmission pipeline delay of output load of main station to sub station j Representing the pipe loss ratio; then the optimization solution of each substation is further added>Substituting and optimizing the central station.
2. The method for optimizing online intelligent learning decisions of a gas distributed energy system according to claim 1, comprising the following steps:
s1, acquiring input and output parameters of single equipment of an energy central station and a substation, and performing online data learning and correction through a neural network to obtain a dynamic model of the single equipment; the monomer equipment dynamic model is expressed as a functional form yi=fi (xi), wherein xi is a set of all input parameters of the equipment, and yi represents a set of all output parameters of the equipment;
s2, carrying out output and input association on each monomer equipment dynamic model through a process flow of a distributed energy system to form a full system model, namely Y=f (X), wherein X is a set of all input parameters of the full system, and Y is a set of all output parameters of the full system; the set of all output parameters comprises all energy output forms of the system, including a conventional cold load C, a thermal load H and an electric load E, namely Y= [ C, H, E ];
s3, establishing a decision optimization model through a whole system model; the load constraint of the decision optimization model is from energy feedback of a user and a load prediction model; the energy consumption feedback of the user comprises various energy forms, including a conventional cold load demand Cr, a heat load demand Hr and an electric load demand Er, and meets the output parameters C=Cr, H=Hr and E=Er of an energy station;
s4, according to different optimization targets, adopting an intelligent algorithm to solve the decision optimization model to obtain an optimal unit operation instruction model under the optimization targets, and sending the instruction to a DCS controller of an energy central station and a controller of substation single equipment; the system optimization target mainly comprises the whole plant heat efficiency, benefit, thermoelectric ratio, single unit comprehensive heat efficiency, thermoelectric ratio and optimal benefit of the whole energy station.
3. The online intelligent learning decision optimization method of the gas distributed energy system according to claim 1 or 2, wherein a genetic algorithm is utilized to solve a decision optimization model to obtain an optimal unit operation instruction model.
4. The method for optimizing online intelligent learning decisions of a gas distributed energy system according to claim 1 or 2, wherein the central station comprises: a gas turbine-waste heat boiler unit, a steam turbine unit and a hot water boiler unit; the substation includes: an electric refrigerating unit, a lithium bromide absorption refrigerating unit, a plate-exchange type heat exchanger unit and an electric heater unit; the monomer equipment model is established by the following method:
gas turbine-exhaust-heat boiler:
power generation curve:
high pressure steam curve:
low pressure steam curve:
steam turbine model:
power generation curve:
heating steam curve:
temperature and pressure reducer model:
wherein, the upper mark 3 represents a temperature and pressure reducer;
hot water boiler model:
wherein, the upper mark 4 represents a hot water boiler;
model of electric refrigerator:
lithium bromide absorption refrigerating unit model:
cooling curve:
power consumption profile:
plate-change type heat exchanger model:
electric heater model:
wherein, the upper mark 1 represents an internal combustion engine-waste heat boiler; the upper mark 2 represents a steam turbine; the upper mark 5 indicates an electric refrigerating unit; the upper mark 6 represents a lithium bromide absorption refrigerating unit; the superscript 7 indicates a plate heat exchanger; the upper mark 8 indicates an electric heater; w represents user heat, c represents user cold, g represents natural gas heat, e represents generated power or consumed power, h represents high-pressure steam heat, l represents low-pressure steam heat, s represents heat output to a heat supply network, and k represents opening of a steam extraction rotary partition plate.
5. The method for optimizing online intelligent learning decisions of a gas distributed energy system according to claim 1, wherein the decision optimization model comprises a benefit maximization model, and the benefit maximization model of the energy station is:
wherein I is C Representing all electric refrigeration units; i x Represents all lithium bromide absorption refrigerating unit sets, I w Represents all heat exchange plate heat exchange sets, I g Representing all gas turbine-exhaust-heat boiler unit sets, I s Representing all sets of turbine units, I b Represents all hot water boiler unit sets, I h Representing all sets of electric heaters; p (P) C 、P W 、P e 、P g Respectively representing cold price, hot price, online electricity price, offline electricity price and gas price; r is (r) e Representing the power consumption of the plant; r is R c 、R w Respectively representing the cold and hot load demands of users;
the exhaust-heat boiler of the i-number gas turbine-exhaust-heat boiler combined cycle unit outputs high-pressure steam = turbine main steam + temperature and pressure reduction steam;
the exhaust-heat boiler output low-pressure steam inlet turbine of the exhaust-heat boiler combined cycle unit of No. 1 and No. 2 is constrained by the water supplementing capacity of the exhaust-heat boiler, the turbine of the No. 3 gas turbine-exhaust-heat boiler combined cycle unit is a back pressure unit, and no steam supplementing exists, namely l 3 2 ＝0The method comprises the steps of carrying out a first treatment on the surface of the The steam turbines of the gas turbine-waste heat boiler combined cycle units No. 1 and No. 2 are extraction condensing units; difference-> Indicating that the low-pressure steam directly enters the heat exchanger for heat exchange output; wherein (1)>Represents No. 1 waste heat boiler>Represents No. 2 waste heat boiler>Steam turbine No. 1>Steam turbine No. 2>And represents steam turbine No. 3.
6. An online intelligent learning decision optimization system for a gas distributed energy system implementing the method of any one of claims 1-5, comprising: the intelligent energy management system comprises an energy central station (1), an energy sub-station (2), an iDOS device (3), an information center server (4) and a DCS controller (5), wherein the information center server (4) is respectively connected with the energy sub-station (2) and the iDOS device (3), and the DCS controller (5) is respectively connected with the energy central station (1) and the iDOS device (3).
7. The online intelligent learning decision optimization system of a gas distributed energy system according to claim 6, wherein the iDOS device (3) comprises a display (6), a processor (7) and an iDOS cabinet (8), the processor (7) is respectively connected with the display (6), the iDOS cabinet (8) and the information center server (4), and the iDOS cabinet (8) is respectively connected with the DCS controller (5) and the information center server (4).
8. The online intelligent learning decision optimization system of a gas distributed energy system according to claim 6, wherein the energy central station (1) comprises: the system comprises a gas turbine (9), a waste heat boiler (10), a steam turbine (11), a heater (12) and a hot water boiler (13), wherein the hot water boiler (13) and the heater (12) are connected with a main pipe of a heat supply network, the gas turbine (9) is connected with the waste heat boiler (10), the waste heat boiler (10) is respectively connected with the steam turbine (11) and the heater (12), and the steam turbine (11) is connected with the heater (12); the gas turbine (9), the waste heat boiler (10), the steam turbine (11) and the heater (12) are all connected with the DCS controller (5).
9. The online intelligent learning decision optimization system of the gas distributed energy system according to claim 8, wherein a flow meter (14) is arranged on an air extraction pipeline of each steam turbine (11), and the flow meter (14) is connected with the DCS controller (5).
10. The on-line intelligent learning decision optimization system of a gas distributed energy system according to claim 6, wherein the energy substation (2) comprises: the lithium bromide absorption type heat exchanger comprises an electric refrigerating unit (15), a lithium bromide absorption type refrigerating unit (16), an electric heater (17) and a plate-exchange type heat exchanger (18), wherein the electric refrigerating unit (15), the lithium bromide absorption type refrigerating unit (16) and the electric heater (17) are connected with an information center server (4), and the plate-exchange type heat exchanger (18) is connected with the electric refrigerating unit (15), the lithium bromide absorption type refrigerating unit (16), the electric heater (17) and a main pipe of a heat supply network respectively.
CN201711232876.9A 2017-11-30 2017-11-30 Online intelligent learning decision optimization method and system for gas distributed energy system Active CN107844869B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711232876.9A CN107844869B (en) 2017-11-30 2017-11-30 Online intelligent learning decision optimization method and system for gas distributed energy system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711232876.9A CN107844869B (en) 2017-11-30 2017-11-30 Online intelligent learning decision optimization method and system for gas distributed energy system

Publications (2)

Publication Number Publication Date
CN107844869A CN107844869A (en) 2018-03-27
CN107844869B true CN107844869B (en) 2023-12-05

Family

ID=61679415

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711232876.9A Active CN107844869B (en) 2017-11-30 2017-11-30 Online intelligent learning decision optimization method and system for gas distributed energy system

Country Status (1)

Country Link
CN (1) CN107844869B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109581974B (en) * 2017-09-28 2020-10-13 北京索英电气技术有限公司 Electro-thermal dispatch communication device, system and method
CN108613247B (en) * 2018-04-02 2022-09-20 上海航天智慧能源技术有限公司 Heat load distribution method of steam-water dual-purpose gas boiler group
CN108846477B (en) * 2018-06-28 2022-06-21 上海浦东发展银行股份有限公司信用卡中心 Intelligent brain decision system and decision method based on reflection arcs
CN109657974B (en) * 2018-12-19 2023-05-02 上海发电设备成套设计研究院有限责任公司 Annual main technical index calculation method for distributed energy projects
CN109785185A (en) * 2019-01-09 2019-05-21 清华大学 The level of factory complex energy management system of more grade heat supplies is dispatched in steam power plant
CN110017184B (en) * 2019-04-01 2024-02-27 华电电力科学研究院有限公司 Distributed residual pressure power generation system based on reinforcement learning algorithm and control method thereof
CN110030050A (en) * 2019-04-11 2019-07-19 广州发展集团股份有限公司 A kind of combined cycle system and operating procedure
CN110070460A (en) * 2019-04-16 2019-07-30 东南大学 More set gas-steam combined cycle set thermoelectricity Optimal Load Dispatching Systems
CN110671206A (en) * 2019-11-05 2020-01-10 华润电力郑州航空港智慧能源有限公司 Distributed energy power station system and energy cascade utilization method
CN112859591B (en) * 2020-12-23 2022-10-21 华电电力科学研究院有限公司 Reinforced learning control system for operation optimization of energy system
CN113323734B (en) * 2021-06-18 2023-01-03 中国能源建设集团广东省电力设计研究院有限公司 Gas and steam combined cycle cogeneration heat supply system and operation method thereof
CN113655762A (en) * 2021-07-27 2021-11-16 咸阳新兴分布式能源有限公司 Operation optimization control method and system for gas energy supply system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102593860A (en) * 2012-01-18 2012-07-18 北京四方继保自动化股份有限公司 Automatic generation control and automatic voltage control integrated substation system of power plant
CN103093017A (en) * 2011-11-04 2013-05-08 新奥科技发展有限公司 Distributed energy system design method
CN103761579A (en) * 2013-12-31 2014-04-30 湖南大唐先一科技有限公司 Thermal power plant plant-level load optimal distribution system based on plant and power grid coordination
CN105869075A (en) * 2016-04-19 2016-08-17 东南大学 Economic optimization scheduling method for cold, heat and electricity combined supply type miniature energy grid

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9915965B2 (en) * 2015-03-16 2018-03-13 The Florida International University Board Of Trustees Flexible, secure energy management system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093017A (en) * 2011-11-04 2013-05-08 新奥科技发展有限公司 Distributed energy system design method
CN102593860A (en) * 2012-01-18 2012-07-18 北京四方继保自动化股份有限公司 Automatic generation control and automatic voltage control integrated substation system of power plant
CN103761579A (en) * 2013-12-31 2014-04-30 湖南大唐先一科技有限公司 Thermal power plant plant-level load optimal distribution system based on plant and power grid coordination
CN105869075A (en) * 2016-04-19 2016-08-17 东南大学 Economic optimization scheduling method for cold, heat and electricity combined supply type miniature energy grid

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
曾芳.天然气分布式能源系统设计原则及机组配置方案.《低碳世界》.2017,(第19期),全文. *

Also Published As

Publication number Publication date
CN107844869A (en) 2018-03-27

Similar Documents

Publication Publication Date Title
CN107844869B (en) Online intelligent learning decision optimization method and system for gas distributed energy system
CN107290968B (en) Coordination optimization control method of multi-energy complementary comprehensive energy system
CN108197768B (en) Energy system and pipe network layout joint optimization method
CN104571068B (en) The operating and optimization control method and system of a kind of distributed energy resource system
Yang et al. Optimal dispatching of an energy system with integrated compressed air energy storage and demand response
CN109659927B (en) Energy storage capacity configuration method of comprehensive energy microgrid considering energy storage participation degree
CN106447529A (en) Distributed energy system modeling and running optimization method considering hot water pipe network
CN110084410B (en) Operation optimization method for sewage reuse type comprehensive energy system
CN112258021B (en) Energy efficiency evaluation method and system for domestic fuel cell cogeneration building
CN112182887A (en) Comprehensive energy system planning optimization simulation method
CN109162810A (en) A kind of multipotency stream measuring point system for distributed busbar protection
CN110137953B (en) Collaborative operation optimization method based on distributed energy station multi-energy system
CN114294708B (en) Method for adjusting heat storage of long-distance heat supply pipe network
CN111008760A (en) Double-layer optimization method for combined cooling heating and power micro-grid system
Yang et al. Optimal scheduling of CCHP with distributed energy resources based on water cycle algorithm
CN113885367A (en) Building energy efficiency management control system and method
CN113128868A (en) Regional comprehensive energy system scheduling optimization method and device
CN116432817A (en) Park comprehensive energy system optimal configuration method
CN111463773A (en) Energy management optimization method and device for regional comprehensive energy system
CN116502921A (en) Park comprehensive energy system optimization management system and coordination scheduling method thereof
CN207688481U (en) Combustion gas distributed energy optimization system
CN113239550B (en) Energy storage capacity configuration method for combined cooling heating and power system and combined cooling and power system
CN208793102U (en) A kind of distributed busbar protection multipotency stream measuring point system
CN114139837A (en) Regional multi-system double-layer distributed optimization scheduling method considering double-layer carbon emission optimization distribution model
Wu et al. Distributed optimal scheduling of integrated energy system based on ADMM algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant