WO2024016504A1 - 一种基于安全经济的电热综合能源控制方法 - Google Patents
一种基于安全经济的电热综合能源控制方法 Download PDFInfo
- Publication number
- WO2024016504A1 WO2024016504A1 PCT/CN2022/126957 CN2022126957W WO2024016504A1 WO 2024016504 A1 WO2024016504 A1 WO 2024016504A1 CN 2022126957 W CN2022126957 W CN 2022126957W WO 2024016504 A1 WO2024016504 A1 WO 2024016504A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- power
- integrated energy
- energy system
- electrical node
- neural network
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000013528 artificial neural network Methods 0.000 claims abstract description 48
- 239000002245 particle Substances 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 26
- 238000003860 storage Methods 0.000 claims description 23
- 238000010248 power generation Methods 0.000 claims description 21
- 230000005611 electricity Effects 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005338 heat storage Methods 0.000 claims description 13
- 238000002922 simulated annealing Methods 0.000 claims description 12
- 238000005485 electric heating Methods 0.000 claims description 10
- 239000000243 solution Substances 0.000 claims description 10
- 238000010438 heat treatment Methods 0.000 claims description 8
- 238000002940 Newton-Raphson method Methods 0.000 claims description 6
- 238000000137 annealing Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000002347 injection Methods 0.000 claims description 3
- 239000007924 injection Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 239000007789 gas Substances 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000007599 discharging Methods 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 230000010354 integration Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
Definitions
- the invention belongs to the field of energy system control, and specifically relates to a safe and economical electric and thermal comprehensive energy control method.
- the purpose of the present invention is to provide a safe and economical electric and thermal comprehensive energy control method to ensure safe operation of the system while performing economic optimization dispatch.
- the first aspect of the present invention provides a safe and economical electric and thermal comprehensive energy control method, including:
- the particle swarm SA-PSO algorithm of simulated annealing optimization is used to optimize and solve the objective function, and the integrated energy system is controlled based on the optimized solution of the objective function;
- the training process of the SA-PSO-BP neural network includes:
- the BP neural network is trained through the feature training set.
- the particle swarm SA-PSO algorithm optimized by simulated annealing is used to iteratively update the weights and thresholds of the BP neural network to obtain the SA-PSO-BP neural network.
- the method for preprocessing relevant features includes:
- the 3 ⁇ principle is used to eliminate abnormal data in the relevant characteristics of wind power, photovoltaic and electric heating loads.
- the expression formulas are:
- p i represents the i-th sample value of the same feature attribute, represents the sample mean, ⁇ represents the reference standard value, n is the number of samples, and p e is the residual error; when the residual error p e of the relevant feature value is greater than 3 ⁇ , the relevant feature value is eliminated;
- x i represents the time of the i+1th value point
- y i represents the eigenvalue of the i+1th value point
- x j represents the eigenvalue of the jth value point
- L(x ) represents the feature interpolation corresponding to a given time x.
- the method of screening relevant features to obtain preferred features includes:
- the Pearson correlation coefficient is used to estimate the correlation between relevant features, and the expression formula is:
- X represents the eigenvalue vector
- Y represents the actual value vector of wind power generation or photovoltaic power generation or electrical load or heat load demand
- ⁇ The covariance of ⁇ X and ⁇ Y represents the standard deviation of X and Y respectively;
- the method of constructing the objective function of the integrated energy system includes
- the electricity purchase and sale cost C E , the gas purchase cost C GAS , the equipment operation cost C OP and the wind and light abandonment penalty cost C GWP are combined into the economic cost f 2 and normalized to F 2 ;
- ⁇ 1 and ⁇ 2 are the weights of F 1 and F 2 respectively; f 1 max is the maximum sum of absolute differences in voltage deviations of each node in the integrated energy system; f 2 max is the maximum output of each device in the integrated energy system Cost value; T is the total working period of the integrated energy system; N V is the number of electrical nodes; is the difference between the i-th electrical node voltage and the safety boundary during the t period.
- the difference between the electrical node voltage and the safety margin includes:
- V max represents the upper limit of the voltage per unit value
- V min represents the lower limit of the voltage per unit value
- the Newton-Raphson method is used to correct the voltage per unit value of the electrical node under the influence of the thermal network.
- Calculation methods include:
- the relative injection power of the electrical node is expressed as:
- P i and Q i respectively represent the active power and reactive power injected into the i-th electrical node
- P chp,i and Q chp,i respectively represent the active power and reactive power of the CHP unit in the i-th electrical node
- P es,i and Q es,i respectively represent the active power and reactive power of the battery in the i-th electrical node
- P wd,i and Q wd,i respectively represent the active power and reactive power of the wind turbine in the i-th electrical node.
- P pv,i and Q pv,i respectively represent the active power and reactive power of the photovoltaic in the i-th electrical node
- P eb,i and Q eb,i respectively represent the active power of the electric boiler in the i-th electrical node and reactive power
- P load,i and Q load,i respectively represent the active power and reactive power of the electrical load in the i-th electrical node
- P is and Q is are the active power and reactive power set at the electrical node i;
- V i and V j are the voltages injected into the electrical node i and the electrical node j respectively;
- G ij , B ij and ⁇ ij are respectively The conductance, susceptance and phase angle difference between electrical node i and electrical node j;
- phase angle correction amount ⁇ and phase angle correction amount ⁇ V of the electrical node Calculate the phase angle correction amount ⁇ and phase angle correction amount ⁇ V of the electrical node according to the correction equation. Repeat the correction of the phase angle and voltage of the electrical node. When both ⁇ P i and ⁇ Q i are less than ⁇ , stop the correction to obtain the final phase of the electrical node. Angle and the final voltage; ⁇ represents the allowable error of the node power imbalance.
- the expression formula of the electricity purchase and sale cost C E is:
- the calculation formula of gas purchase cost C GAS is:
- N chp represents the number of CHP units
- w gas represents the price of unit electric power generated by the CHP unit
- the calculation formula of equipment operating cost C OP is:
- N wd , N pv , N es , N hs and N eb represent the number of wind turbine generators, photovoltaic generator units, power storage equipment, heat storage equipment and electric boilers respectively
- O wd , O pv , O es , O chp , O hs and O eb represent the operating cost coefficients of wind power generation, photovoltaic power generation, power storage equipment, CHP units, heat storage equipment and electric boilers respectively, and Represents the electrical power generated by wind power generation, photovoltaic power generation, power storage equipment and CHP units respectively, and Represents the thermal power emitted by thermal storage equipment and electric boiler respectively.
- the calculation formula of penalty cost C GWP for abandoning wind and light is:
- ⁇ wd and ⁇ pv represent the penalty coefficients of wind and light abandonment respectively, and represent the predicted values of wind power and photovoltaic respectively.
- the power network constraints added for optimal dispatch include: active power balance constraints, electrical node voltage constraints, branch transmission power constraints and power network branch power loss constraints of the power network; the thermal network constraints added for optimal scheduling include thermal network power. Balance constraints and thermal network pipe heat loss constraints.
- the particle swarm SA-PSO algorithm optimized by simulated annealing is used to iteratively update the weights and thresholds of the BP neural network.
- the method of obtaining the SA-PSO-BP neural network includes:
- Initialize the weights and thresholds of the BP neural network use the length of the weights and thresholds in the BP neural network as the dimensions of the particle swarm, use the weights and thresholds as the positions of the particles, and initialize the weight w, learning rate c 1 and c 2 , position x and speed v as well as simulated annealing temperature T and annealing coefficient K;
- the prediction error during the neural network training process is used as the fitness F of the particle population, and a random perturbation is given to the particles to obtain new particles x new . If the new fitness Less than or equal to existing F x , accept As the optimal value of fitness;
- exp(-(FF)/TK) ⁇ rand() holds, then accept As the optimal value of fitness, if And exp(-(FF)/TK) ⁇ rand() is established, retaining the existing F x as the optimal fitness value; exp() is expressed as an exponential operation with the natural logarithm base e as the base; rand() is is a random function that generates random numbers;
- This invention collects the relevant features of wind power, photovoltaic and electric heating loads in the integrated energy system, preprocesses and screens the relevant features to obtain optimal features and constructs a feature training set, and trains the BP neural network through the feature training set.
- SA -PSO-BP neural network predicts renewable energy and multiple loads in the integrated energy system, and controls the integrated energy system based on the prediction results of renewable energy and multiple loads, thereby improving the safety and stability of system operation.
- This invention constructs the objective function of the comprehensive energy system, adds power network constraints and thermal network constraints for optimal dispatching; based on the prediction results of renewable energy and multi-load, and uses the simulated annealing optimized particle swarm SA-PSO algorithm to optimize the objective function Solve and control the integrated energy system based on the optimal solution of the objective function, so that the control of the integrated energy system takes into account both safety and economy.
- Figure 1 is a flow chart of a safe and economical electric and thermal comprehensive energy control method provided by an embodiment of the present invention
- Figure 2 is a flow chart for forecasting renewable energy and multiple loads based on the SA-PSO-BP neural network
- Figure 3 is a topology diagram of a safe and economical integrated design method for an electric-thermal integrated energy system
- Figure 4 is a flow chart for solving the objective optimization function based on simulated annealing-particle swarm algorithm
- Figure 5 is a graph of renewable energy and multi-variable load forecasting based on SA-PSO-BP neural network
- Figure 6 is a power grid dispatching diagram based on the security and economic integration method
- Figure 7 is a heating network dispatching diagram based on the safety and economic integration method
- Figure 8 is a system electrical node voltage diagram based on the safety and economic integration method.
- a safe and economical electric and thermal comprehensive energy control method includes:
- the process includes:
- Methods for preprocessing relevant features include:
- the 3 ⁇ principle is used to eliminate abnormal data in the relevant characteristics of wind power, photovoltaic and electric heating loads.
- the expression formulas are:
- p i represents the i-th sample value of the same feature attribute, represents the sample mean, ⁇ represents the reference standard value, n is the number of samples, and p e is the residual error; when the residual error p e of the relevant feature value is greater than 3 ⁇ , the relevant feature value is eliminated;
- x i represents the time of the i+1th value point
- y i represents the eigenvalue of the i+1th value point
- x j represents the eigenvalue of the jth value point
- L(x ) represents the feature interpolation corresponding to a given time x.
- Methods for screening relevant features to obtain preferred features include:
- the Pearson correlation coefficient is used to estimate the correlation between relevant features, and the expression formula is:
- X represents the eigenvalue vector
- Y represents the actual value vector of wind power generation or photovoltaic power generation or electrical load or heat load demand
- ⁇ The covariance of ⁇ X and ⁇ Y represents the standard deviation of X and Y respectively; according to the degree of correlation ⁇
- the BP neural network is trained through the feature training set.
- the particle swarm SA-PSO algorithm optimized by simulated annealing is used to iteratively update the weights and thresholds of the BP neural network to obtain the SA-PSO-BP neural network.
- the specific methods include :
- Initialize the weights and thresholds of the BP neural network use the length of the weights and thresholds in the BP neural network as the dimensions of the particle swarm, use the weights and thresholds as the positions of the particles, and initialize the weight w, learning rate c 1 and c 2 , position x and speed v as well as simulated annealing temperature T and annealing coefficient K;
- the prediction error during the neural network training process is used as the fitness F of the particle population, and a random perturbation is given to the particles to obtain new particles x new . If the new fitness Less than or equal to existing F x , accept As the optimal value of fitness;
- exp(-(FF)/TK) ⁇ rand() holds, then accept As the optimal value of fitness, if And exp(-(FF)/TK) ⁇ rand() is established, retaining the existing F x as the optimal fitness value; exp() is expressed as an exponential operation with the natural logarithm base e as the base; rand() is is a random function that generates random numbers;
- the electricity purchase and sale cost C E , the gas purchase cost C GAS , the equipment operation cost C OP and the wind and light abandonment penalty cost C GWP are combined into the economic cost f 2 and normalized to F 2 ;
- ⁇ 1 and ⁇ 2 are the weights of F 1 and F 2 respectively;
- f 1 max is the maximum sum of absolute differences in voltage deviations of each node in the integrated energy system; is the maximum cost value of each equipment in the integrated energy system;
- T is the total working period of the integrated energy system;
- N V is the number of electrical nodes; is the difference between the i-th electrical node voltage and the safety boundary during the t period.
- the difference between the electrical node voltage and the safety margin includes:
- V max represents the upper limit of the voltage per unit value
- V min represents the lower limit of the voltage per unit value
- the relative injection power of the electrical node is expressed as:
- P i and Q i respectively represent the active power and reactive power injected into the i-th electrical node
- P chp,i and Q chp,i respectively represent the active power and reactive power of the CHP unit in the i-th electrical node
- P es,i and Q es,i respectively represent the active power and reactive power of the battery in the i-th electrical node
- P wd,i and Q wd,i respectively represent the active power and reactive power of the wind turbine in the i-th electrical node.
- P pv,i and Q pv,i respectively represent the active power and reactive power of the photovoltaic in the i-th electrical node
- P eb,i and Q eb,i respectively represent the active power of the electric boiler in the i-th electrical node and reactive power
- P load,i and Q load,i respectively represent the active power and reactive power of the electrical load in the i-th electrical node
- P is and Q is are the active power and reactive power set at the electrical node i;
- V i and V j are the voltages injected into the electrical node i and the electrical node j respectively;
- G ij , B ij and ⁇ ij are respectively The conductance, susceptance and phase angle difference between electrical node i and electrical node j;
- phase angle correction amount ⁇ and phase angle correction amount ⁇ V of the electrical node Calculate the phase angle correction amount ⁇ and phase angle correction amount ⁇ V of the electrical node according to the correction equation. Repeat the correction of the phase angle and voltage of the electrical node. When both ⁇ P i and ⁇ Q i are less than ⁇ , stop the correction to obtain the final phase of the electrical node. Angle and the final voltage; ⁇ represents the allowable error of the node power imbalance.
- N chp represents the number of CHP units
- w gas represents the price of unit electric power generated by the CHP unit
- N wd , N pv , N es , N hs and N eb represent the number of wind turbine generators, photovoltaic generator units, power storage equipment, heat storage equipment and electric boilers respectively
- O wd , O pv , O es , O chp , O hs and O eb represent the operating cost coefficients of wind power generation, photovoltaic power generation, power storage equipment, CHP units, heat storage equipment and electric boilers respectively, and Represents the electrical power generated by wind power generation, photovoltaic power generation, power storage equipment and CHP units respectively, and Represents the thermal power emitted by thermal storage equipment and electric boiler respectively.
- ⁇ wd and ⁇ pv represent the penalty coefficients of wind and light abandonment respectively, and represent the predicted values of wind power and photovoltaic respectively.
- N eb and N el represent the number of electric boilers and electric loads respectively. and represent the charging and discharging power of the power storage device respectively, eta c and eta d represent the charging and discharging efficiency respectively, Indicates the electric power consumed by the electric boiler, The electrical power consumed by the electrical load, is the power lost by the i-th branch of the power grid during period t.
- the value of the safety weight ⁇ 1 is set to be much greater than the value of the cost weight ⁇ 2 , which is equivalent to ensuring that the voltage is economical within the safety zone [V min , V max ] Scheduling.
- Thermal network constraints added for optimal scheduling include thermal network power balance constraints, thermal network pipeline heat loss constraints, and other thermal network constraints;
- N hl represents the number of heating loads
- N pip is the number of heating network branches
- the thermal power generated by the CHP unit and the electric boiler respectively and represent the states of heat storage and heat release respectively, and represent the heat storage and heat release power respectively
- the heat loss power of the i-th heating network pipe is the heat loss power of the i-th heating network pipe; l i is the length of the i-th heating network pipe; T i,t is the temperature of the hot water in the pipe; T 0 is the ambient temperature outside the pipe; R 1 is the heating network Thermal resistance of the pipe; R2 is the thermal resistance of the pipe insulation layer.
- ⁇ chp represents the thermoelectric ratio coefficient
- ⁇ chp represents the price of natural gas
- L ng represents the low calorific value of natural gas
- eta chp represents the power generation efficiency of the CHP unit
- ⁇ t represents the unit dispatching time
- ⁇ eb represents the heat-to-power ratio coefficient of the electric boiler
- ⁇ eb represents the heat loss rate of the electric boiler
- ⁇ hs represents heat loss rate
- represent the efficiency of heat storage and heat release respectively and represent the heat storage and heat release power respectively, and represent the upper and lower limits of heat storage capacity respectively, and represent the upper and lower limits of heat storage power respectively, and represent the upper and lower limits of heat release power respectively, and are the initial storage capacity of the battery and the storage capacity after one cycle, respectively, indicating that the scheduling of the battery should be such that the capacity after one cycle returns to the initial state.
- the particle swarm SA-PSO algorithm of simulated annealing optimization is used to optimize and solve the objective function.
- Methods include:
- the particle population size is 40
- the maximum iteration number D max is 800
- the particle swarm weights w max and w min are 1 and 0.5 respectively
- the learning factors c max and c min are 2.5 and 0.5 respectively
- the initial temperature T is 100
- the annealing coefficient k is 0.96.
- d is the current number of iterations
- D max is the maximum number of iterations
- w max and w min are the parameter adjustment factors of the weight
- c max and c min are the parameter adjustment factors of the learning factor
- V i k and represent the velocity and position of the i-th particle at the k-th iteration respectively
- gb k respectively represent the historical optimal position of individual i at the k-th iteration and the historical optimal experience of the group
- w is the weight of the particle swarm
- rd 1 and rd 2 are random numbers between 0 and 1.
- embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
- computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
- These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions
- the device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
- These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device.
- Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
Abstract
一种基于安全经济的电热综合能源控制方法，包括：通过预先训练后的SA-PSO-BP神经网络对综合能源系统中的可再生能源和多元负荷进行预测，构建综合能源系统的目标函数，添加优化调度的电力网络约束和热力网络约束；基于可再生能源和多元负荷的预测结果，并利用模拟退火优化的粒子群SA-PSO算法对目标函数进行优化求解，根据目标函数的优化解对综合能源系统进行控制；其中训练过程包括：通过特征训练集对BP神经网络进行训练，利用模拟退火优化的粒子群SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络。
Description
本发明属于能源系统控制领域，具体涉及一种基于安全经济的电热综合能源控制方法。
随着技术和经济的不断发展，社会生产和生活的各个领域均对能源提出了更大的需求，在化石能源不断消耗下，能源和环境问题日益突出。为了满足能源和环保需求，将低碳、清洁、绿色的可再生能源加入现有能源系统中成为了各国的战略首选。然而风电，光伏这类可再生能源的随机性和间歇性极大的阻碍了综合能源系统对风电和光伏的消纳，因此对可再生能源发电的预测显得十分重要。
将电、热和气等异质能源互联的综合能源系统被提出后，得到广泛应用，这打破了不同能源之间的壁垒，增强了能源间的相互支撑，有效的提高了各个能源供应的稳定性。
但是目前对于电-热综合能源系统的研究多数处于经济优化和提高可再生能源渗透率，对其安全性研究不够充分。由于电-热互联综合能源系统中存在一些不确定因素例如风电、光伏的出力以及多元负荷的需求，使得系统可能会出现电压越限等安全事故。
发明内容
本发明的目的在于提供一种基于安全经济的电热综合能源控制方法，保证系统安全运行的同时进行经济优化调度。
为达到上述目的，本发明所采用的技术方案是：
本发明第一方面提供了一种基于安全经济的电热综合能源控制方法，包括：
通过预先训练后的SA-PSO-BP神经网络对综合能源系统中的可再生能源和多元负荷进行预测，
构建综合能源系统的目标函数，添加优化调度的电力网络约束和热力网络约束；
基于可再生能源和多元负荷的预测结果，并利用模拟退火优化的粒子群SA-PSO算法对目标函数进行优化求解，根据目标函数的优化解对综合能源系统进行控制；
所述SA-PSO-BP神经网络的训练过程包括：
根据优选特征和综合能源系统的输出功率确定BP神经的网络拓扑结构；采集综合能源系统中风电光伏和电热负荷的相关特征，对相关特征进行预处理和筛选获得优选特征并构建特征训练集；
通过特征训练集对BP神经网络进行训练，训练过程中利用模拟退火优化的粒子群 SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络。
优选的，对相关特征进行预处理的方法包括：
通过3δ原则剔除风电光伏和电热负荷的相关特征中的异常数据，表达公式分别为：
公式中，p
i表示同一特征属性第i个样本值，
表示样本均值，δ表示参考标准值，n为采样个数，p
e为剩余误差；当相关特征值的剩余误差p
e大于3δ，将该相关特征值进行剔除；
通过拉格朗日插值法填充风电光伏和电热负荷的相关特征中的缺失数据，表达公式为：
公式中，x
i表示为第i+1个取值点的时间，y
i表示第i+1个取值点的特征值；x
j表示为第j个取值点的特征值；L(x)表示给定时间x对应的特征插值。
优选的，对相关特征进行筛选获得优选特征的方法包括：
采用皮尔逊相关系数估算相关特征之间的相关性，表达公式为：
公式中，X表示特征值向量，Y表示风力发电或者光伏发电或者电负荷或者热负荷需求的实际值向量，ρ
XY表示X与Y之间的关联程度；Cov(X,Y)表示X与Y的协方差，σ
X和σ
Y分别表示X和Y的标准差；
根据关联程度ρ
XY由风电光伏和电热负荷的相关特征中筛选出优选特征。
优选的，构建综合能源系统的目标函数的方法包括
将综合能源系统各时段各节点的电压绝对偏差和f
1归一化为F
1；
将购售电成本C
E、购气成本C
GAS、设备运行成本C
OP和弃风弃光惩罚成本C
GWP综合为经济成本f
2且归一化为F
2；
构建目标函数表达公式为：
公式中，λ
1和λ
2分别为F
1和F
2权值；f
1
max为综合能源系统中各节点电压偏离绝对差值之和最大值；f
2
max为综合能源系统中各设备出力最大成本值；T为综合能源系统的工作总时段；N
V为电节点的数量；
为t时段第i电节点电压与安全边界的差。
优选的，电节点电压与安全边界的差
的计算过程包括：
公式中，
表示第i个电节点t时段电压标幺值，V
max表示电压标幺值的上限，V
min表示电压标幺值的下限。
优选的，在热网的影响下利用牛顿-拉普逊方法修正电节点的电压标幺值
计算方法包括：
电节点相对注入功率，表达公式为：
公式中，P
i和Q
i分别表示第i个电节点注入的有功功率和无功功率，P
chp,i和Q
chp,i分别表示第i个电节点中CHP机组有功功率和无功功率，P
es,i和Q
es,i分别表示第i个电节点中蓄电池有功功率和无功功率，P
wd,i和Q
wd,i分别表示第i个电节点中风机的有功功率和无功功率，P
pv,i和Q
pv,i分别为示第i个电节点中光伏的有功功率和无功功率，P
eb,i和Q
eb,i分别表示第i个电节点中电锅炉的有功功率和无功功率，P
load,i和Q
load,i分别表示第i个电节点中电负荷的有功功率 和无功功率；
计算电节点功率误差方程，表达公式为：
公式中，P
is，Q
is为电节点i设定的有功功率及无功功率；V
i和V
j分别为注入电节点i和电节点j的电压；G
ij、B
ij和θ
ij分别为电节点i和电节点j之间的电导、电纳和相角差；
基于牛顿-拉普逊方法简化的修正方程为：
根据修正方程计算电节点的相角修正量Δθ和相角修正量ΔV，重复对电节点的相角和电压进行修正，当满足ΔP
i和ΔQ
i均小于ε后停止修正获得电节点的最终相角和最终电压；ε表示为节点功率不平衡量的允许误差。
优选的，购售电成本C
E的表达公式为：
公式中，
和
分别表示t时段购电、售电的电价，
表示购电和售电的电功率，购电时为正值，售电时为负值。
优选的，购气成本C
GAS的计算公式为：
公式中，N
chp表示CHP机组的数量，w
gas表示CHP机组产生单位电功率的价格，
表示第i台CHP机组产生的电功率。
优选的，设备运行成本C
OP的计算公式为：
公式中，N
wd、N
pv、N
es、N
hs和N
eb分别表示风力发电机组、光伏发电机组、储电设备、储热设备和电锅炉的数量，O
wd、O
pv、O
es、O
chp、O
hs和O
eb分别表示风力发电、光伏发电、储电设备、CHP机组、储热设备和的电锅炉的运行成本系数，
和
分别表示风力发电、光伏发电、储电设备和CHP机组产生的电功率，
和
分别表示储热设备和电锅炉发出的热功率。
优选的，弃风弃光惩罚成本C
GWP的计算公式为：
公式中，α
wd和α
pv分别表示弃风和弃光的惩罚系数，
和
分别表示风电和光伏的预测值。
优选的，添加优化调度的电力网络约束包括：电力网络的有功功率平衡约束、电节点电压约束、支路传输功率约束和电力网络支路功率损耗约束；添加优化调度的热力网络约束包括热力网络功率平衡约束和热力网络管道热损耗约束。
优选的，利用模拟退火优化的粒子群SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络的方法包括：
初始化对BP神经网络的权值和阈值；将BP神经网络中权值和阈值的长度作为粒子群的维度，将权值和阈值作为粒子的位置，初始化粒子群的权重w、学习率c
1和c
2、位置x和速度v以及模拟退火的温度T和退火系数K；
将神经网络训练过程中的预测误差作为粒子种群的适应度F，给粒子一个随机扰动得到新的粒子x
new，若新适应度
小于或等于现有F
x，接受
作为适应度最优值；
若
且exp(-(F-F)/TK)≤rand()成立，则接受
作为适应度最优值，若
且exp(-(F-F)/TK)≤rand()成立，保留现有的F
x作为适应度最优值；exp()表示为以自然对数底数e为底数的指数运算；rand()表示为产生随机数的随机函数；
迭代更新粒子群的权重w、学习率c
1和c
2、位置x和速度v以及粒子种群的适应度F；当迭代次数达到预定值输出全局最优解F
g和对应BP神经网络，将训练后的BP神经网络作为SA-PSO-BP神经网络。
与现有技术相比，本发明的有益效果：
本发明采集综合能源系统中风电光伏和电热负荷的相关特征，对相关特征进行预处理和筛选获得优选特征并构建特征训练集，通过特征训练集对BP神经网络进行训练，通过预先训练后的SA-PSO-BP神经网络对综合能源系统中的可再生能源和多元负荷进行预测，根据可再生能源和多元负荷的预测结果对综合能源系统进行控制，使系统运行安全稳定性得到提高。
本发明构建综合能源系统的目标函数，添加优化调度的电力网络约束和热力网络约束；基于可再生能源和多元负荷的预测结果，并利用模拟退火优化的粒子群SA-PSO算法对目标函数进行优化求解，根据目标函数的优化解对综合能源系统进行控制，使得对综合能源系统的控制兼顾安全性和经济性。
图1是本发明实施例提供的一种基于安全经济的电热综合能源控制方法的流程图；
图2是基于SA-PSO-BP神经网络对可再生能源和多元负荷进行预测的流程图；
图3是一种电-热综合能源系统的安全经济一体化设计方法的拓扑图；
图4是基于模拟退火-粒子群算法求解目标优化函数的流程图；
图5是基于SA-PSO-BP神经网络的可再生能源和多元负荷预测图；
图6是基于安全经济一体化方法的电网调度图；
图7是基于安全经济一体化方法的热网调度图；
图8是基于安全经济一体化方法的系统电节点电压图。
下面结合附图对本发明作进一步描述。以下实施例仅用于更加清楚地说明本发明的技术方案，而不能以此来限制本发明的保护范围。
如图1至图8所示，一种基于安全经济的电热综合能源控制方法，包括：
对SA-PSO-BP神经网络进行训练，过程包括：
根据优选特征和综合能源系统的输出功率确定BP神经的网络拓扑结构；
采集综合能源系统中风电光伏和电热负荷的相关特征，对相关特征进行预处理和筛选获得优选特征并构建特征训练集；
对相关特征进行预处理的方法包括：
通过3δ原则剔除风电光伏和电热负荷的相关特征中的异常数据，表达公式分别为：
公式中，p
i表示同一特征属性第i个样本值，
表示样本均值，δ表示参考标准值，n为采样个数，p
e为剩余误差；当相关特征值的剩余误差p
e大于3δ，将该相关特征值进行剔除；
通过拉格朗日插值法填充风电光伏和电热负荷的相关特征中的缺失数据，表达公式为：
公式中，x
i表示为第i+1个取值点的时间，y
i表示第i+1个取值点的特征值；x
j表示为第j个取值点的特征值；L(x)表示给定时间x对应的特征插值。
对相关特征进行筛选获得优选特征的方法包括：
采用皮尔逊相关系数估算相关特征之间的相关性，表达公式为：
公式中，X表示特征值向量，Y表示风力发电或者光伏发电或者电负荷或者热负荷需求的实际值向量，ρ
XY表示X与Y之间的关联程度；Cov(X,Y)表示X与Y的协方差，σ
X和σ
Y分别表示X和Y的标准差；根据关联程度ρ
XY由风电光伏和电热负荷的相关特征中筛选出优选特征。
通过特征训练集对BP神经网络进行训练，训练过程中利用模拟退火优化的粒子群SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络，具体方法包括：
初始化对BP神经网络的权值和阈值；将BP神经网络中权值和阈值的长度作为粒子群的维度，将权值和阈值作为粒子的位置，初始化粒子群的权重w、学习率c
1和c
2、位置x和速度v以及模拟退火的温度T和退火系数K；
将神经网络训练过程中的预测误差作为粒子种群的适应度F，给粒子一个随机扰动得到新的粒子x
new，若新适应度
小于或等于现有F
x，接受
作为适应度最优值；
若
且exp(-(F-F)/TK)≤rand()成立，则接受
作为适应度最优值，若
且exp(-(F-F)/TK)≤rand()成立，保留现有的F
x作为适应度最优值；exp()表示为以自然对数底数e为底数的指数运算；rand()表示为产生随机数的随机函数；
迭代更新粒子群的权重w、学习率c
1和c
2、位置x和速度v以及粒子种群的适应度F；当迭代次数达到预定值输出全局最优解F
g和对应BP神经网络，将训练后的BP神经网络作为SA-PSO-BP神经网络。
通过预先训练后的SA-PSO-BP神经网络对综合能源系统中的可再生能源和多元负荷进行预测，
将综合能源系统各时段各节点的电压绝对偏差和f
1归一化为F
1；
将购售电成本C
E、购气成本C
GAS、设备运行成本C
OP和弃风弃光惩罚成本C
GWP综合为经济成本f
2且归一化为F
2；
构建综合能源系统的目标函数，添加优化调度的电力网络约束和热力网络约束；
综合能源系统的目标函数的表达公式为：
公式中，λ
1和λ
2分别为F
1和F
2权值；f
1
max为综合能源系统中各节点电压偏离绝对差值之和最大值；
为综合能源系统中各设备出力最大成本值；T为综合能源系统的工作总时段；N
V为电节点的数量；
为t时段第i电节点电压与安全边界的差。
电节点电压与安全边界的差
的计算过程包括：
公式中，
表示第i个电节点t时段电压标幺值，V
max表示电压标幺值的上限，V
min表示电压标幺值的下限。
在热网的影响下利用牛顿-拉普逊方法修正电节点的电压标幺值
计算方法包括：
电节点相对注入功率，表达公式为：
公式中，P
i和Q
i分别表示第i个电节点注入的有功功率和无功功率，P
chp,i和Q
chp,i分别表示第i个电节点中CHP机组有功功率和无功功率，P
es,i和Q
es,i分别表示第i个电节点中蓄电池有功功率和无功功率，P
wd,i和Q
wd,i分别表示第i个电节点中风机的有功功率和无功功率，P
pv,i和Q
pv,i分别为示第i个电节点中光伏的有功功率和无功功率，P
eb,i和Q
eb,i分别表示第i个电节点中电锅炉的有功功率和无功功率，P
load,i和Q
load,i分别表示第i个电节点中电负荷的有功功率和无功功率；
计算电节点功率误差方程，表达公式为：
公式中，P
is，Q
is为电节点i设定的有功功率及无功功率；V
i和V
j分别为注入电节点i和电节点j的电压；G
ij、B
ij和θ
ij分别为电节点i和电节点j之间的电导、电纳和相角差；
基于牛顿-拉普逊方法简化的修正方程为：
根据修正方程计算电节点的相角修正量Δθ和相角修正量ΔV，重复对电节点的相角和电压进行修正，当满足ΔP
i和ΔQ
i均小于ε后停止修正获得电节点的最终相角和最终电压；ε表 示为节点功率不平衡量的允许误差。
购售电成本C
E的表达公式为：
公式中，
和
分别表示t时段购电、售电的电价，
表示购电和售电的电功率，购电时为正值，售电时为负值；
购气成本C
GAS的计算公式为：
公式中，N
chp表示CHP机组的数量，w
gas表示CHP机组产生单位电功率的价格，
表示第i台CHP机组产生的电功率。
设备运行成本C
OP的计算公式为：
公式中，N
wd、N
pv、N
es、N
hs和N
eb分别表示风力发电机组、光伏发电机组、储电设备、储热设备和电锅炉的数量，O
wd、O
pv、O
es、O
chp、O
hs和O
eb分别表示风力发电、光伏发电、储电设备、CHP机组、储热设备和的电锅炉的运行成本系数，
和
分别表示风力发电、光伏发电、储电设备和CHP机组产生的电功率，
和
分别表示储热设备和电锅炉发出的热功率。
弃风弃光惩罚成本C
GWP的计算公式为：
公式中，α
wd和α
pv分别表示弃风和弃光的惩罚系数，
和
分别表示风电和光伏的 预测值。
针对目标函数添加优化调度的电力网络约束和热力网络约束；添加优化调度的电力网络约束包括：电力网络的有功平衡约束、电节点电压约束、支路传输功率约束、电力网络支路功率损耗约束以及其他电力网络约束；
(1)电力网络的有功平衡约束表达公式为：
公式中，N
eb、N
el分别表示电锅炉和电负荷的数量，
和
分别表示储电设备充电和放电的功率，η
c和η
d分别表示充电和放电的效率，
表示电锅炉消耗的电功率，
为电负荷消耗的电功率，
为t时段电网第i条支路损耗的功率。
(2)支路传输功率约束
为了确保系统电节点电压不逾越安全界限，本实施例中设定安全权重λ
1的值远大于成本权重λ
2的值，即相当于确保电压在安全域[V
min,V
max]内进行经济调度。
(3)电力网络支路功率损耗约束
公式中，
和
分别表示支路l的有功潮流最小值和最大值。
表示支路l的有功潮流，
表示节点i和j之间线路的功率。G
ij和B
ij分别表示节点导纳矩阵第i行第j列元素的实部与虚部。θ
i表示节点i的电压相角，θ
ij表示θ
i与θ
j的电压相角差值。
(4)电力网络支路功率损耗约束
公式中，
和
分别为注入到第i个电节点的有功和无功功率；U
0和R
i分别表示系统的参考电压和节点i相连支路的电阻。
(5)电力网络其他约束
公式中，
和
分别表示风力发电机组出力的上限和下限，
和
分别表示光伏发电机组出力的上下限，
和
分别表示CHP机组发电出力的上限和下限，
和
分别表示CHP机组爬坡的上限和下限，
表示储电容量，α
hs为储热罐热量损失率，
和
分别表示充电和放电的功率，η
c和η
d分别表示充电和放电的效率，
和
分别表示储电容量的上下限，
和
分别表示充电功率的上下限，
和
分别表示放电功率的上下限，
和
分别为蓄电池初始的蓄电量和一个周期结束后的蓄电量，表明蓄电池的调度应满足一个周期后的容量回到初始状态，
和
分别表示电锅炉消耗电能的上限和下限，β
eb表示电锅炉热电比系数，P
e
max和P
e
min分别表示购售电的上下限。
添加优化调度的热力网络约束包括热力网络功率平衡约束、热力网络管道热损耗约束以及热力网络其他约束；
(1)热力网络功率平衡约束
式中，N
hl表示热负荷的数量，N
pip为热网支路的数量，
和
分别表示CHP机组和电锅炉产生的热功率，
和
分别表示储热和放热的状态，
和
分别表示储热和放 热的功率，
表示t时段第i条热网支路的散热量。
(2)热力网络管道热损耗约束
式中
为第i条热网管道的热损失功率；l
i为第i条热网管道的长度；T
i,t为管道内热水的温度；T
0为管道外的环境温度；R
1为热网管道的热阻；R
2为管道保温层的热阻。
(3)热力网络其他约束
式中，β
chp表示热电比系数，
表示天然气的价格，
表示CHP发出的电功率，L
ng表示天然气的低热值，η
chp表示CHP机组的发电效率，Δt表示单位调度时长，β
eb表示电锅炉热电比系数，α
eb表示电锅炉散热损失率，
表示储热容量，α
hs表示热量损失率，
和
分别表示储热和放热的效率，
和
分别表示储热和放热的功率，
和
分别表示储热容量的上下限，
和
分别表示储热功率的上下限，
和
分别表示放热功率的上下限，
和
分别为蓄电池初始的蓄电量和一个周期结束后的蓄电量，表明蓄电池的调度应满足一个周期后的容量回到初始状态。
基于可再生能源和多元负荷的预测结果，并利用模拟退火优化的粒子群SA-PSO算法对目标函数进行优化求解，方法包括：
初始化参数：粒子的种群规模为40，最大迭代次数D
max为800，粒子群权重w
max和w
min分别为1和0.5，学习因子c
max和c
min分别为2.5和0.5，初始温度T为100，退火系数k为0.96。
更新粒子的权重w、学习因子c
1和c
2、速度v和位置x，计算粒子的适应度F，表达公式如下：
式中d为当前迭代次数，D
max为最大迭代次数，w
max和w
min为权重的调参因子，其中c
max和c
min为学习因子的调参因子，V
i
k和
分别表示第i个粒子第k次迭代时的速度和位置，
和gb
k分别表示个体i第k次迭代时历史最优位置和群体的历史最优经验；w为粒子群的权重，rd
1和rd
2是介于0到1之间的随机数。
将目标函数F作为粒子的适应度，计算粒子种群适应度，对比得到全局初始最优解F
g。
给粒子一个随机扰动得到新的粒子x
new，若
接受
作为个体最优值，若
则判断
是否成立，成立则接受
作为个体最优值，反之则不接受。
根据T＝Tk进行退火；更新粒子个体历史最优F
p和群体历史最优F
g；根据目标函数的优化解对综合能源系统进行控制。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指 令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明技术原理的前提下，还可以做出若干改进和变形，这些改进和变形也应视为本发明的保护范围。
Claims (10)
- 一种电热综合能源系统的控制方法，其特征在于，包括：通过预先训练后的SA-PSO-BP神经网络对综合能源系统中的可再生能源和多元负荷进行预测，构建综合能源系统的目标函数，添加优化调度的电力网络约束和热力网络约束；基于可再生能源和多元负荷的预测结果，并利用模拟退火优化的粒子群SA-PSO算法对目标函数进行优化求解，根据目标函数的优化解对综合能源系统进行控制；所述SA-PSO-BP神经网络的训练过程包括：根据优选特征和综合能源系统的输出功率确定BP神经的网络拓扑结构；采集综合能源系统中风电光伏和电热负荷的相关特征，对相关特征进行预处理和筛选获得优选特征并构建特征训练集；通过特征训练集对BP神经网络进行训练，训练过程中利用模拟退火优化的粒子群SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络。
- 根据权利要求1所述的一种电热综合能源系统的控制方法，其特征在于，对相关特征进行预处理的方法包括：通过3δ原则剔除风电光伏和电热负荷的相关特征中的异常数据，表达公式分别为：
公式中，p i表示同一特征属性第i个样本值，表示样本均值，δ表示参考标准值，n为采样个数，p e为剩余误差；当相关特征值的剩余误差p e大于3δ，将该相关特征值进行剔除；
通过拉格朗日插值法填充风电光伏和电热负荷的相关特征中的缺失数据，表达公式为：
公式中，x i表示为第i+1个取值点的时间，y i表示第i+1个取值点的特征值；x j表示为第 j个取值点的特征值；L(x)表示给定时间x对应的特征插值。 - 根据权利要求2所述的一种电热综合能源系统的控制方法，其特征在于，对相关特征进行筛选获得优选特征的方法包括：采用皮尔逊相关系数估算相关特征之间的相关性，表达公式为：
公式中，X表示特征值向量，Y表示风力发电或者光伏发电或者电负荷或者热负荷需求的实际值向量，ρ XY表示X与Y之间的关联程度；Cov(X,Y)表示X与Y的协方差，σ X和σ Y分别表示X和Y的标准差；根据关联程度ρ XY由风电光伏和电热负荷的相关特征中筛选出优选特征。 - 根据权利要求1或权利要求3所述的一种电热综合能源系统的控制方法，其特征在于，构建综合能源系统的目标函数的方法包括：将综合能源系统各时段各节点的电压绝对偏差和f 1归一化为F 1；将购售电成本C E、购气成本C GAS、设备运行成本C OP和弃风弃光惩罚成本C GWP综合为经济成本f 2且归一化为F 2；构建目标函数表达公式为：
公式中，λ 1和λ 2分别为F 1和F 2权值；f 1 max为综合能源系统中各节点电压偏离绝对差值之和最大值；为综合能源系统中各设备出力最大成本值；T为综合能源系统的工作总时段；N V为电节点的数量；
为t时段第i电节点电压与安全边界的差。
- 根据权利要求4所述的一种电热综合能源系统的控制方法，其特征在于，电节点电压 与安全边界的差的计算过程包括：
公式中，表示第i个电节点t时段电压标幺值，V max表示电压标幺值的上限，V min表示电压标幺值的下限。
- 根据权利要求5所述的一种电热综合能源系统的控制方法，其特征在于，在热网的影响下利用牛顿-拉普逊方法修正电节点的电压标幺值计算方法包括：
电节点相对注入功率，表达公式为：
公式中，P i和Q i分别表示第i个电节点注入的有功功率和无功功率，P chp,i和Q chp,i分别表示第i个电节点中CHP机组有功功率和无功功率，P es,i和Q es,i分别表示第i个电节点中蓄电池有功功率和无功功率，P wd,i和Q wd,i分别表示第i个电节点中风机的有功功率和无功功率，P pv,i和Q pv,i分别为示第i个电节点中光伏的有功功率和无功功率，P eb,i和Q eb,i分别表示第i个电节点中电锅炉的有功功率和无功功率，P load,i和Q load,i分别表示第i个电节点中电负荷的有功功率和无功功率；计算电节点功率误差方程，表达公式为：
公式中，P is，Q is为电节点i设定的有功功率及无功功率；V i和V j分别为注入电节点i和电节点j的电压；G ij、B ij和θ ij分别为电节点i和电节点j之间的电导、电纳和相角差；基于牛顿-拉普逊方法简化的修正方程为：
根据修正方程计算电节点的相角修正量Δθ和相角修正量ΔV，重复对电节点的相角和电压进行修正，当满足ΔP i和ΔQ i均小于ε后停止修正获得电节点的最终相角和最终电压；ε表示为节点功率不平衡量的允许误差。 - 根据权利要求4所述的一种电热综合能源系统的控制方法，其特征在于，设备运行成本C OP的计算公式为：
公式中，N wd、N pv、N es、N hs和N eb分别表示风力发电机组、光伏发电机组、储电设备、储热设备和电锅炉的数量，O wd、O pv、O es、O chp、O hs和O eb分别表示风力发电、光伏发电、储电设备、CHP机组、储热设备和的电锅炉的运行成本系数，和
分别表示风力发电、光伏发电、储电设备和CHP机组产生的电功率，
和
分别表示储热设备和电锅炉发出的热功率。
- 根据权利要求7所述的一种电热综合能源系统的控制方法，其特征在于，弃风弃光惩罚成本C GWP的计算公式为：
公式中，α wd和α pv分别表示弃风和弃光的惩罚系数，和
分别表示风电和光伏的预测值。
- 根据权利要求1所述的一种电热综合能源系统的控制方法，其特征在于，添加优化调度的电力网络约束包括：电力网络的有功功率平衡约束、电节点电压约束、支路传输功率约束和电力网络支路功率损耗约束；添加优化调度的热力网络约束包括热力网络功率平衡约束和热力网络管道热损耗约束。
- 根据权利要求1或权利要求9所述的一种电热综合能源系统的控制方法，其特征在于，利用模拟退火优化的粒子群SA-PSO算法对BP神经网络的权值和阈值进行迭代更新，获得SA-PSO-BP神经网络的方法包括：初始化对BP神经网络的权值和阈值；将BP神经网络中权值和阈值的长度作为粒子群的维度，将权值和阈值作为粒子的位置，初始化粒子群的权重w、学习率c 1和c 2、位置x和速度v以及模拟退火的温度T和退火系数K；将神经网络训练过程中的预测误差作为粒子种群的适应度F，给粒子一个随机扰动得到新的粒子x new，若新适应度小于或等于现有F x，接受
作为适应度最优值；
若且exp(-(F-F)/TK)≤rand()成立，则接受
作为适应度最优值，若
且exp(-(F-F)/TK)≤rand()成立，保留现有的F x作为适应度最优值；exp()表示为以自然对数底数e为底数的指数运算；rand()表示为产生随机数的随机函数；
迭代更新粒子群的权重w、学习率c 1和c 2、位置x和速度v以及粒子种群的适应度F；当迭代次数达到预定值输出全局最优解F g和对应BP神经网络，将训练后的BP神经网络作为SA-PSO-BP神经网络。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210838509.8 | 2022-07-18 | ||
| CN202210838509.8A CN115169916A (zh) | 2022-07-18 | 2022-07-18 | 一种基于安全经济的电热综合能源控制方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024016504A1 true WO2024016504A1 (zh) | 2024-01-25 |
Family
ID=83495848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/126957 WO2024016504A1 (zh) | 2022-07-18 | 2022-10-24 | 一种基于安全经济的电热综合能源控制方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115169916A (zh) |
| WO (1) | WO2024016504A1 (zh) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115169916A (zh) * | 2022-07-18 | 2022-10-11 | 南京邮电大学 | 一种基于安全经济的电热综合能源控制方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011130584A (ja) * | 2009-12-17 | 2011-06-30 | Fuji Electric Systems Co Ltd | 発電計画作成方法および発電計画作成システム |
| CN111191820A (zh) * | 2019-12-17 | 2020-05-22 | 国网浙江省电力有限公司 | 一种综合能源系统中储能装置的选址定容优化规划方法 |
| CN111709182A (zh) * | 2020-05-25 | 2020-09-25 | 温州大学 | 基于sa-pso优化的bp神经网络的电磁铁故障预测方法 |
| CN113239607A (zh) * | 2021-06-16 | 2021-08-10 | 国网浙江省电力有限公司杭州供电公司 | 综合能源系统经济调度优化方法、系统、设备及存储介质 |
| CN115169916A (zh) * | 2022-07-18 | 2022-10-11 | 南京邮电大学 | 一种基于安全经济的电热综合能源控制方法 |
-
2022
- 2022-07-18 CN CN202210838509.8A patent/CN115169916A/zh active Pending
- 2022-10-24 WO PCT/CN2022/126957 patent/WO2024016504A1/zh unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011130584A (ja) * | 2009-12-17 | 2011-06-30 | Fuji Electric Systems Co Ltd | 発電計画作成方法および発電計画作成システム |
| CN111191820A (zh) * | 2019-12-17 | 2020-05-22 | 国网浙江省电力有限公司 | 一种综合能源系统中储能装置的选址定容优化规划方法 |
| CN111709182A (zh) * | 2020-05-25 | 2020-09-25 | 温州大学 | 基于sa-pso优化的bp神经网络的电磁铁故障预测方法 |
| CN113239607A (zh) * | 2021-06-16 | 2021-08-10 | 国网浙江省电力有限公司杭州供电公司 | 综合能源系统经济调度优化方法、系统、设备及存储介质 |
| CN115169916A (zh) * | 2022-07-18 | 2022-10-11 | 南京邮电大学 | 一种基于安全经济的电热综合能源控制方法 |
Non-Patent Citations (1)
| Title |
|---|
| HONGWEI KANG, LI QIANG; YU SHUO; YAO SHUN: "Ultra Short-Term Forecasting for Wind Power Output Based on SA-PSO-BP Algorithmr", INNER MONGOLIA ELECTRIC POWER, vol. 38, no. 6, 28 December 2020 (2020-12-28), pages 64 - 68, XP093130607, ISSN: 1008-6218, DOI: 10.3969/j.issn.1008-6218.2020.00.103 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115169916A (zh) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Data-driven configuration optimization of an off-grid wind/PV/hydrogen system based on modified NSGA-II and CRITIC-TOPSIS | |
| CN106936147B (zh) | 一种基于双层优化的微电网面向电蓄热锅炉的优化运行管理方法 | |
| US11610214B2 (en) | Deep reinforcement learning based real-time scheduling of Energy Storage System (ESS) in commercial campus | |
| Bidgoli et al. | Multi-stage optimal scheduling of multi-microgrids using deep-learning artificial neural network and cooperative game approach | |
| CN108206543A (zh) | 一种基于能源梯级利用的能源路由器及其运行优化方法 | |
| Tutkun | Minimization of operational cost for an off-grid renewable hybrid system to generate electricity in residential buildings through the SVM and the BCGA methods | |
| CN111598289A (zh) | 计及lstm光伏出力预测的综合能源系统分散式优化方法 | |
| He et al. | The many-objective optimal design of renewable energy cogeneration system | |
| CN112418488B (zh) | 一种基于两阶段能量优化的综合能源系统调度方法及装置 | |
| CN116187601B (zh) | 一种基于负荷预测的综合能源系统运行优化方法 | |
| WO2024016504A1 (zh) | 一种基于安全经济的电热综合能源控制方法 | |
| CN113592133A (zh) | 一种能量枢纽优化配置方法及系统 | |
| CN116108360A (zh) | 一种区域综合能源系统优化运行控制方法及装置 | |
| CN112836849A (zh) | 一种考虑风电不确定性的虚拟电厂调度方法 | |
| Georgiou et al. | Implementing artificial neural networks in energy building applications—A review | |
| Ganesan et al. | Hopfield neural networks approach for design optimization of hybrid power systems with multiple renewable energy sources in a fuzzy environment | |
| Toosi et al. | Machine learning for performance prediction in smart buildings: Photovoltaic self-consumption and life cycle cost optimization | |
| Si et al. | Cost-effective operation of the urban energy system with variable supply and demand via coordination of multi-energy flows | |
| Wang et al. | Unified operation optimization model of integrated coal mine energy systems and its solutions based on autonomous intelligence | |
| Ju et al. | Three‐level energy flexible management strategy for micro energy grids considering multiple uncertainties at different time scales | |
| Liu et al. | Coordinated energy management for integrated energy system incorporating multiple flexibility measures of supply and demand sides: A deep reinforcement learning approach | |
| CN104112168B (zh) | 一种基于多代理系统的智能家居优化方法 | |
| Zhang et al. | Research on economic optimal dispatching of microgrid cluster based on improved butterfly optimization algorithm | |
| CN117077960A (zh) | 一种区域综合能源系统日前调度优化方法 | |
| CN113864854B (zh) | 一种蓄热式电采暖参与风电消纳的多目标优化方法及系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22951767 Country of ref document: EP Kind code of ref document: A1 |