Integrated energy system planning method and system based on hybrid artificial fish swarm algorithm

Abstract

A method and system for planning an integrated energy system based on a hybrid artificial fish swarm algorithm. The method and system calculate the output forecast curve of photovoltaic power generation units per square meter based on the historical meteorological data curve of typical days of local temperature and irradiance every month; the forecast data of typical daily cooling, heating and electricity loads of the integrated energy system every month based on the planning scenario are used as the load curve parameters of cooling, heating and electricity in the planning scenario; the economic planning goal of the planning scenario is established, and the objective function of the optimization algorithm is constructed; the feasible domain for solving the optimization algorithm that satisfies the equilibrium constraints and inequality constraints is constructed; and the hybrid artificial fish swarm algorithm is used to solve the objective function. The present invention achieves the planning purpose of achieving the best economy while meeting the cooling, heating and electricity load requirements of the integrated energy system. In addition, the comprehensive energy utilization efficiency of the system is improved, the support capacity of low-grade energy for high-grade electric energy is realized, and the consumption of photovoltaic and other renewable energy power generation is promoted.

Description

Technical Field

[0001] The present invention belongs to the field of integrated energy technology, relates to the field of integrated energy system planning and optimization technology, and specifically relates to an integrated energy system planning method and system based on a hybrid artificial fish swarm algorithm. Background Art

[0002] The integrated energy system is a system of multiple energy sources operating together. The coupling connection between different energy networks is strong, and the complementary substitution between different energy forms can greatly improve the overall energy utilization efficiency of the system. In the integrated energy scenario planning, it is not a simple superposition of multiple energy sources, but the capacity configuration and output characteristics of various energy equipment should be planned in accordance with the complementary coupling characteristics between different energy sources to achieve the multi-energy complementary effect. Furthermore, we should fully tap the support capacity of low-grade energy for high-grade electric energy, promote the mutual conversion of various energy sources such as water, gas, and heat with electric energy, solve the bottleneck problem that the integrated energy system is difficult to balance locally, serve the construction of regional energy Internet, and promote the scientific development of regional energy system reform.

[0003] At present, the research on integrated energy planning technology, on the one hand, when constructing economic solution models, most of them only consider the equipment purchase cost, operating cost, etc., and do not take into account factors such as government subsidies, peak-shaving benefits in response to policies, and compound interest on investment costs. On the other hand, the planning objective function of the integrated energy system is a typical multi-dimensional high-order non-convex nonlinear model. When solving it with traditional intelligent algorithms, the solution speed is slow, it is very easy to fall into the local optimum, and the solution accuracy is not high enough.

[0004] The multi-energy planning of the integrated energy system can meet the most reasonable configuration and maximum absorption of distributed green energy such as photovoltaics under the planning objectives. It can also solve the reasonable configuration capacity of storage devices in various energy forms, effectively utilize the peak-shaving and valley-filling of multi-energy storage devices, and reduce the impact on peak load periods, thereby improving the reliability and safety of power supply / cooling / heating. On the one hand, it can effectively promote the development and application of renewable energy, and on the other hand, it can ease the shortage of fossil energy and reduce environmental pollution. The three aspects of integrated energy system planning target modeling, balance constraint and inequality constraint analysis and model solving algorithm are effective means to improve the comprehensive energy efficiency of the energy system, ensure the balance of supply and demand, and optimize and integrate resources and technologies, and realize scientific planning and design of the system. Summary of the invention

[0005] The present invention aims to solve the problem that photovoltaic equipment cannot be reasonably configured in the process of multiple energy planning of the integrated energy system, whether multiple energy utilization equipment should be configured, and how to reasonably select the configuration capacity, so as to achieve the optimal economic efficiency of the planning scenario while meeting the cold / heat / electric load requirements in the planning scenario. In addition, the comprehensive energy utilization efficiency of the system is improved, the support capacity of low-grade energy for high-grade electric energy is realized, and the mutual conversion of various energy sources such as water, gas, and heat with electric energy is promoted, and a comprehensive energy system planning method and system based on a hybrid artificial fish school algorithm is provided.

[0006] To achieve the above object, the present invention specifically adopts the following technical solutions:

[0007] A method for planning an integrated energy system based on a hybrid artificial fish swarm algorithm, characterized in that the method for planning an integrated energy system comprises the following steps:

[0008] Step 1: Calculate the output forecast curve of photovoltaic generators per square meter based on the monthly typical daily meteorological historical data curve of local temperature and irradiance;

[0009] Step 2: The forecast data of typical daily cooling, heating and electricity loads of the integrated energy system in the planning scenario is used as the load curve parameters of cooling, heating and electricity in the planning scenario;

[0010] Step 3: Establish the economic planning goal of the planning scenario and construct the objective function of the optimization algorithm;

[0011] Step 4: Construct an optimization feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment, and waste heat balance, as well as a feasible domain for solving the optimization algorithm under the condition of satisfying the inequality constraints;

[0012] Step 5: In the optimal feasible domain satisfying the inequality constraints and the balanced equality constraints, the objective function is solved to obtain whether each energy device in the integrated energy system of the planning scenario is configured, the configured capacity and the operating output curve of each configured device.

[0013] The present invention further includes the following preferred embodiments.

[0014] The comprehensive energy system includes a photovoltaic power generation set, an electric boiler, a heat storage device, an electric refrigerator, a cold storage device, a large power grid, a low-voltage transformer, an electric energy bus, a thermal energy bus, a cold energy bus, a user's electric load, an electric storage device, a user's thermal load, a user's cold load, a gas turbine generator set, a waste heat boiler, a waste heat absorption refrigerator, a waste heat bus and a waste heat discharge. The photovoltaic power generation set and the gas turbine generator set are connected to the electric boiler, the electric refrigerator, the user's electric load, the electric storage device and the low-voltage side of the low-voltage transformer through the electric energy bus, the electric boiler and the waste heat boiler are connected to the heat storage device and the user's thermal load through the thermal energy bus, the electric refrigerator and the waste heat absorption refrigerator are connected to the cold storage device and the user's cold load through the cold energy bus, the high-voltage side of the low-voltage transformer is connected to the large power grid, and the gas turbine generator set is connected to the waste heat boiler, the waste heat absorption refrigerator and the waste heat discharge through the waste heat bus.

[0015] In step 1, the output of the photovoltaic power generation unit of the integrated energy system is predicted using the following formula:

[0016] P PV，k (t) = R k (t)η r η pc A[1-β(T c -T cref )]

[0017] Among them, R k (t) is the light intensity in period t of month k, η r is the temperature coefficient, η pc is the MPPT efficiency of the DC conversion link, β is the power temperature coefficient of the solar cell module, T c is the actual ambient temperature, T cref is the ambient reference temperature, A is the optimized photovoltaic configuration area, P PV，k (t) is the predicted output of the photovoltaic power generation unit after optimization in period t of month k.

[0018] In step 2, the user's cooling, heating and electricity load parameters are configured for the typical daily cooling, heating and electricity load forecast data of the integrated energy system from January to December in the planning scenario, including:

[0019]

[0020] Among them, P′ E，k (t), P′ C，k (t), P′ H，k (t) are the forecast data of electricity load, cooling load and heating load of users in typical day of period t in month k; P E，k (t), P C，k (t), P H，k(t) are the user electricity load, user cooling load, and user heating load in the kth month and tth period, respectively; ΔP′ E，k (t), ΔP′ C，k (t), ΔP′ H，k (t) are the deviations of user electric load, user cooling load, user heating load and actual load in period t of month k.

[0021] In step 3, the economic planning goal of the integrated energy system of the planning scenario, i.e., the objective function, includes:

[0022] C gh =min(P pur +p bui +f run +F main -S sub )

[0023] Among them, C gh 、f run 、F main are the total cost, operation cost, and maintenance cost of the integrated energy system in the planning scenario over its entire life cycle; P pur 、p bui They are the total purchase cost and total installation and construction cost of the integrated energy system equipment; S sub To provide government subsidies for electricity generation in integrated energy systems;

[0024] P pur It is expressed as:

[0025]

[0026] Among them, r is the discount rate, n is the design life, c i 、x i , I are the purchase cost of equipment i and the total number of purchased equipment for the integrated energy system, respectively;

[0027] p bui It is expressed as:

[0028]

[0029] Among them, j i ,t i , o i They are the land use fee, installation fee and other fees of the integrated energy system equipment i;

[0030] f run It is expressed as:

[0031]

[0032] Among them, pr grid(t), pr gas (t) are the time-of-use electricity price of the power grid and the time-of-use gas price of the gas grid during period t, PP grid，k (t), PP gas，k (t) are the electricity purchased from the power grid and the gas purchased from the gas grid during the t period in the kth month; D k is the number of days in the kth month, T is the total number of operating hours in a day, and K is the number of months in a natural year; P grid，k (t), P gas，k (t) are the power purchased from the power grid and the gas flow purchased from the gas grid during the t period in the kth month, respectively. Δt is the length of time for each operating period.

[0033] F main It is expressed as:

[0034]

[0035] Among them, F G 、F H 、F C are the maintenance costs of the power grid, heating network and cooling network respectively, m i Maintenance costs of integrated energy system equipment i.

[0036] S sub It is expressed as:

[0037]

[0038] Among them, pr grid_bt (t) is the time-of-use electricity price for power generation subsidy during period t, PP grid_bt，k (t) is the electricity sold to the grid during period t in month k, P grid_bt，k (t) is the electricity sold to the grid during period t in month k.

[0039] In step 4, the construction of an optimal feasible domain that satisfies the electric, thermal and cooling balance constraint condition includes:

[0040] P PV，k (t)+P grid，k (t)+P tur，k (t)+P ESE，k (t) = P ERB，k (t)+P ERC，k (t)+P E，k (t)

[0041] P ERB，k (t)η ERB +P WHB，k (t)η WHB +P HSE，k (t) = P H，k (t)

[0042] PERC，k (t)COP ERC +P WHC，k (t)COP WHC +PC SE，k (t) = P C，k (t)

[0043] Among them, P tur，k (t) is the power generation of the gas turbine in the kth month and the tth period, P ESE，k (t) is the charging / discharging power of the storage device during period t in month k, P ESE，k (t) greater than 0 indicates discharge, P ESE，k (t) less than 0 indicates charging; P ERB，k (t) is the power consumption of the electric heating boiler in the kth month and the tth period, η ERB is the heating efficiency of the electric boiler, P WHB，k (t) is the waste heat utilization power of waste heat boiler flue gas in period t in month k, η WHB is the heating efficiency of the waste heat boiler; P HSE，k (t) is the charging / discharging power of the heat storage device during period t in month k, P HSE，k (t) greater than 0 indicates heat release, P HSE，k (t) less than 0 indicates hot charging; P ERC，k (t) is the power consumption of the refrigerator in the kth month during the tth period, COP ERc is the coefficient of performance of the electric refrigerator, P WHC，k (t) is the waste heat utilization power of the waste heat absorption refrigerator in the kth month and period t, COP WHC P is the coefficient of performance of the waste heat absorption refrigeration machine; CSE，k (t) is the charging / discharging power of the cold storage device during period t in month k, P HSE，k (t) greater than 0 means cooling, P HSE，k (t) less than 0 indicates cold charging;

[0044] It is also characterized in that the construction of an optimal feasible domain that satisfies the self-balancing constraint conditions of the power storage / heat / cooling equipment includes:

[0045] W ESE，k (t) = (1-ε ESE )W ESE，k (t-1)-P ESE，k (t)Δt

[0046]

[0047] W HSE，k (t) = (1-ε HSE )W HSE，k (t-1)-P HSE，k (t)Δt

[0048]

[0049] W CSE，k (t) = (1-ε CSE )W CSE，k (t-1)-P CSE，k (t)Δt

[0050]

[0051] Among them, W ESE，k (t) is the storage capacity of the storage device during period t in month k, ε ESE is the self-discharge rate of the storage device, W ESE，k (t-1) is the heat storage of the heat storage device during the period t-1; W ESE，k (t 0 ) is the starting time period, i.e., t 0 The amount of electricity stored in the storage device during the period, W EL The amount of energy that should be left in the storage device at the end of the operation optimization cycle. It is the starting time period of the next cycle after the end of one running optimization cycle; W HSE，k (t) is the heat storage capacity of the heat storage device in period t in month k, ε HSE is the self-heat release rate of the heat storage device, W HSE，k (t-1) is the heat storage of the heat storage device during the period t-1; W HSE，k (t 0 ) is the starting time period, i.e., t 0 Heat storage of the time period heat storage device, W HL W is the amount of heat that should be left in the heat storage device at the end of the operation optimization cycle; CSE，k (t) is the cooling capacity of the cooling device in period t in month k, ε CSE is the self-cooling rate of the cold storage device, W CSE，k (t-1) is the cold storage capacity of the cold storage device during the period t-1; W CSE，k (t 0 ) is the starting time period, i.e., t 0 Cooling capacity of the cold storage device during the period, W CL The amount of cold storage that should be left in the cold storage device at the end of the operation optimization cycle.

[0052] The construction of an optimal feasible domain satisfying the waste heat balance constraint condition includes:

[0053]

[0054] P ex，k (t) = P tur，k (t)*HPR*η r

[0055]

[0056] P WHB，k (t) = α 1 P ex，k (t)

[0057] P WHC，k (t) = α 2 P ex，k (t)

[0058] α 1 +α 2 +α 3 =1

[0059] Where HPR is the gas turbine heat-to-power ratio, For the rated heating efficiency of the gas turbine, is the rated power generation efficiency of the gas turbine; P ex，k (t) is the waste heat power recovered by the gas turbine during period t in month k, η r Indicates the waste heat recovery efficiency of the cogeneration system, LHN NG Indicates the lower calorific value of natural gas; α 1 Indicates the proportion of waste heat entering the waste heat boiler; α 2 Indicates the proportion of waste heat entering the waste heat absorption refrigerator; α 3 Indicates the proportion of waste heat that is not utilized.

[0060] In step 4, the construction of an optimization feasible region satisfying the inequality constraint condition includes:

[0061] (1) Investment cost constraints

[0062] INV max ≥(P pur +p bui )

[0063] Among them, INV max Building maximum investment capacity for planning scenario integrated energy systems;

[0064] (2) Building area constraints

[0065]

[0066] Among them, A max The maximum construction land area for building an integrated energy system is A i Land area used for installation of integrated energy system equipment i;

[0067] (3) Grid energy supply constraints

[0068]

[0069]

[0070] Among them, D max The maximum power supply capacity of the power grid. is the power consumption of device i, is the power generation of device i, The power load designed for the integrated energy system planning scenario; RS is the safety power factor;

[0071] (4) Operation constraints of energy supply equipment

[0072]

[0073]

[0074] Among them, Q is the cooling / heating power value of the equipment, are the cooling / heating power values ​​of equipment i at time t and time t-1, respectively. and are the minimum and maximum cooling / heating powers of equipment i, and are the ramp rates of decreasing and increasing output of equipment i, respectively;

[0075] (5) Natural gas network capacity constraints

[0076]

[0077]

[0078] Among them, PQ l，t，u，y is the gas network capacity, PQ min，l and PQ max，l are the lower and upper limits of the natural gas pipeline flow rate, cl l，y V is the safety fluctuation coefficient of pipeline transmission flow; min，s and V max，s They represent the lower and upper limits of the gas supply volume at the natural gas supply end respectively;

[0079] (6) Reliability constraints

[0080]

[0081] in, is the energy gap, ΔL max The power is insufficient to the upper limit;

[0082] (7) Demand response constraints

[0083]

[0084] Among them, P t，kis the load in period t in month k, and are the lower and upper limits of the demand response load in period t in month k, respectively.

[0085] In step 5, the objective function is optimized and solved in the constructed optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment and waste heat balance, and the optimal feasible domain that satisfies the inequality constraints, including:

[0086] The optimal population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSO Each particle swarm individual performs a separate particle swarm algorithm search;

[0087] After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm;

[0088] If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution;

[0089] If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution;

[0090] Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position:

[0091]

[0092] S=V*rand1

[0093]

[0094] Among them, V is the field of view of the artificial fish in the current iteration, V min and V max are the minimum and maximum values ​​of the artificial fish’s field of view, G max is the maximum number of iterations, i ter is the current iteration number, S is the maximum step length of the artificial fish, rand1∈[0.5, 1] ​​is any random number, X i is the current position of the artificial fish, X next is the updated artificial fish position state, rand2, rand3∈[0,1] any random number, X j is the position with the highest food concentration within the field of view, Gaussian (μ, σ 2 ) is the Gaussian disturbance term, μ is the mean, σ 2 is the variance;

[0095] Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

[0096] The end conditions are:

[0097] |C yx (s)-C yx (s-1)|≤0.001 or i ter ≥G max

[0098] Among them, C yx (s), C yx (s-1) are the values ​​obtained in the current and last optimization searches respectively.

[0099] The present application also discloses a comprehensive energy system planning system using the aforementioned planning method, including a renewable energy unit output prediction module, an output data acquisition module, a constraint condition module, and a planning optimization module; the characteristics of the system are:

[0100] The renewable energy unit output prediction module is used to predict the output of the photovoltaic power generation unit on a typical day of each month in the integrated energy system and transmit it to the processing data acquisition module;

[0101] The output data acquisition module is used to obtain the output of the photovoltaic power generation group on a typical day of each month, and the cold, heat and electricity load forecast data of the planning scenario, and use the cold, heat and electricity load forecast data of the planning scenario as the load curve parameters of the cold, heat and electricity in the planning scenario. The processing data acquisition module transmits the output of the photovoltaic power generation group and the load curve parameters of the cold, heat and electricity in the planning scenario to the constraint condition module;

[0102] The constraint condition module, based on the output power data of each device in the integrated energy system, constructs an optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment and waste heat balance, and an optimal feasible domain that satisfies the constraints of inequality;

[0103] The planning optimization module is used to establish the economic planning target of the integrated energy system of the planning scenario, solve the economic planning target in the optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of storage / heat / cooling equipment and waste heat balance, and the optimal feasible domain that satisfies the inequality constraints, and obtain whether each device in the integrated energy system is configured, the configuration capacity and the typical daily power data of each month.

[0104] Further preferably,

[0105] The constraint condition module includes an electric heat and cold balance constraint condition submodule, an electric storage / heat / cold equipment self-balance constraint condition submodule, a waste heat balance constraint condition submodule, a first optimal feasible domain submodule, an inequality constraint condition and a second optimal feasible domain submodule;

[0106] The first optimization feasible domain submodule is used to determine the optimization feasible domain based on the electric heat and cooling balance constraint condition submodule, the power storage / heat / cooling equipment self-balance constraint condition submodule, and the waste heat balance constraint condition;

[0107] The second optimization feasible region submodule is used to determine the optimization feasible region based on inequality constraints.

[0108] The planning optimization module includes an economic planning target submodule and a target solution submodule;

[0109] In the economic planning target submodule, the economic planning target of the planning scenario is established, and the objective function of the optimization algorithm is constructed;

[0110] The target solving submodule solves the economic planning target in the optimal feasible domain to obtain the calculation results of whether each device in the integrated energy system is configured, the configuration capacity and the typical daily output power data of each month.

[0111] In the target solution submodule, the optimization population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSO Each particle swarm individual performs a separate particle swarm algorithm search;

[0112] After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm;

[0113] If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution;

[0114] If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution;

[0115] Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position:

[0116] Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

[0117] The beneficial effects achieved by the present invention are:

[0118] The present invention adopts the hybrid artificial fish swarm algorithm to solve the optimal economic target of the planning scenario under the conditions of satisfying the electric heat and cold balance, the self-balance of the storage / heat / cold equipment and the waste heat balance constraints and satisfying the inequality constraints, so as to achieve the optimal economic planning purpose by obtaining whether each device is configured, the configuration capacity and the output of the configured energy equipment on a typical day of each month under the conditions of satisfying the cold, heat and electricity load requirements of the comprehensive energy system. In addition, the comprehensive energy utilization efficiency of the system is improved, the support capacity of low-grade energy for high-grade electric energy is realized, and the mutual conversion of various energy sources such as water, gas, and heat with electric energy is promoted. BRIEF DESCRIPTION OF THE DRAWINGS

[0119] Figure 1 A diagram of the planning scenario composition of the integrated energy system of the present invention;

[0120] Figure 2 This is a flow chart of the hybrid artificial fish swarm optimization algorithm of the present invention;

[0121] Figure 3 This is a flow chart of integrated energy system planning optimization based on the hybrid artificial fish swarm algorithm of the present invention. DETAILED DESCRIPTION

[0122] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0123] The integrated energy system planning scenario consists of Figure 1 As shown, the comprehensive energy system includes a photovoltaic power generation set, an electric boiler, a heat storage device, an electric refrigerator, a cold storage device, a large power grid, a low-voltage transformer, an electric energy bus, a thermal energy bus, a cold energy bus, a user's electric load, an electric storage device, a user's thermal load, a user's cold load, a gas turbine generator set, a waste heat boiler, a waste heat absorption refrigerator, a waste heat bus and a waste heat discharge. The photovoltaic power generation set and the gas turbine generator set are connected to the electric boiler, the electric refrigerator, the user's electric load, the electric storage device and the low-voltage side end of the low-voltage transformer through the electric energy bus, the electric boiler and the waste heat boiler are connected to the heat storage device and the user's thermal load through the thermal energy bus, the electric refrigerator and the waste heat absorption refrigerator are connected to the cold storage device and the user's cold load through the cold energy bus, the high-voltage side end of the low-voltage transformer is connected to the large power grid, and the gas turbine generator set is connected to the waste heat boiler, the waste heat absorption refrigerator and the waste heat discharge through the waste heat bus.

[0124] Based on the above integrated energy system planning scenario, the present invention provides an integrated energy system planning method using a hybrid artificial fish algorithm, see Figure 3, including the following steps:

[0125] Step 1: Based on meteorological data, the output of photovoltaic generators in the integrated energy system is predicted. The main purpose is to obtain the predicted output of photovoltaic generators on typical days of each month in the planning scenario. In order to maximize the consumption of photovoltaics, its predicted output must be known before a comprehensive energy system planning method can be formulated. When the hardware conditions remain unchanged and the light and temperature are constant, the photovoltaic output is basically determined by the configured area. Based on the meteorological data of typical days of each month in the planning scenario, the predicted output of the photovoltaic generator is expressed as:

[0126] P PV，k (t) = R k (t)η r η pc A[1-β(T c -T cref )]

[0127] Among them, R k (t) is the light intensity in period t of month k, η r is the temperature coefficient, η pc is the MPPT efficiency of the DC conversion link, β is the power temperature coefficient of the solar cell module, T c is the actual ambient temperature, T cref is the ambient reference temperature, A is the optimized photovoltaic configuration area, P PV，k (t) is the predicted output of the photovoltaic power generation unit after optimization in period t of month k.

[0128] Step 2: Based on the forecast data of typical daily cooling, heating and electricity loads of the integrated energy system from January to December in the planning scenario, the configuration of user cooling, heating and electricity load parameters is expressed as follows:

[0129]

[0130] Among them, P′ E，k (t), P′ C，k (t), P′ H，k (t) are the forecast data of electricity load, cooling load and heating load of users in typical day of period t in month k; P E，k (t), P C，k (t), P H，k (t) are the user electricity load, user cooling load, and user heating load in the kth month and tth period, respectively; ΔP′ E，k (t), ΔP′ C，k (t), ΔP′ H，k (t) are the deviations of user electric load, user cooling load, user heating load and actual load in period t of month k.

[0131] Step 3: Using the cost summation method, the economic planning target of the integrated energy system in the planning scenario is expressed as follows:

[0132] C gh =min(P pur +p bui +f run +F main -S sub )

[0133] Among them, C gh 、f run 、F main are the total cost, operation cost, and maintenance cost of the integrated energy system in the planning scenario over its entire life cycle; P pur 、p bui They are the total purchase cost and total installation and construction cost of the integrated energy system equipment; S sub It is a government subsidy for electricity generation in integrated energy systems.

[0134] P pur It is expressed as:

[0135]

[0136] Among them, r is the discount rate, n is the design life, c i , xi, and 1 are the purchase cost of equipment i and the total number of purchased equipment for the integrated energy system, respectively.

[0137] p bui It is expressed as:

[0138]

[0139] Among them, j i ,t i , o i They are the land use fee, installation fee and other fees for integrated energy system equipment i.

[0140] f run It is expressed as:

[0141]

[0142] Among them, pr grid (t), pr gas (t) are the time-of-use electricity price of the power grid and the time-of-use gas price of the gas grid during period t, PP grid，k (t), PP gas，k(t) are the electricity purchased from the power grid and the gas purchased from the gas grid during the t period in the kth month; D k is the number of days in the kth month, T is the total number of operating hours in a day (usually 24), and K is the number of months in a natural year (usually 12); P grid，k (t), P gas，k (t) are the power purchased from the power grid and the gas flow purchased from the gas grid during period t in month k, respectively; Δt is the length of time for each operating period.

[0143] F main It is expressed as:

[0144]

[0145] Among them, F G 、F H 、F C are the maintenance costs of the power grid, heating network and cooling network respectively, m i Maintenance costs of integrated energy system equipment i.

[0146] S sub It is expressed as:

[0147]

[0148] Among them, pr grid_bt (t) is the time-of-use electricity price for power generation subsidy during period t, PP grid_bt，k (t) is the electricity sold to the grid during period t in month k, P grid_bt，k (t) is the electricity sold to the grid during period t in month k.

[0149] Step 4: Construct an optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment, and waste heat balance, as well as an optimal feasible domain that satisfies the constraints of inequality;

[0150] 4.1 Constructing an optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment, and waste heat balance

[0151] Using the equation balance method, the optimal feasible domain that satisfies the electric, thermal and cooling balance constraints is constructed as follows:

[0152] P PV，k (t)+P grid，k (t)+P tur，k (t)+P ESE，k (t) = P ERB，k (t)+P ERC，k (t)+P E，k (t)

[0153] P ERB，k (t)η ERB +PWHB，k (t)η WHB +P HSE，k (t) = P H，k (t)

[0154] P ERC，k (t)COP ERC +P WHC，k (t)COP WHC +P CSE，k (t) = P C，k (t)

[0155] Among them, P tur，k (t) is the power generation of the gas turbine in the kth month and the tth period, P ESE，k (t) is the charging / discharging power of the storage device during period t in month k, P ESE，k (t) greater than 0 indicates discharge, P ESE，k (t) less than 0 indicates charging; P ERB，k (t) is the power consumption of the electric heating boiler in the kth month and the tth period, η ERB is the heating efficiency of the electric boiler, P WHB，k (t) is the waste heat utilization power of waste heat boiler flue gas in period t in month k, η WHB is the heating efficiency of the waste heat boiler; P HSE，k (t) is the charging / discharging power of the heat storage device during period t in month k, P HSE，k (t) greater than 0 indicates heat release, P HSE，k (t) less than 0 indicates hot charging; P ERC，k (t) is the power consumption of the refrigerator during the period t in the kth month, COP ERC is the coefficient of performance of the electric refrigerator, P WHC，k (t) is the waste heat utilization power of the waste heat absorption refrigerator in the kth month and period t, COP WHC P is the coefficient of performance of the waste heat absorption refrigeration machine; CSE，k (t) is the charging / discharging power of the cold storage device during period t in month k, P HSE，k (t) greater than 0 means cooling, P HSE，k (t) less than 0 indicates cold charging.

[0156] Using the equation balance method, the optimal feasible domain that satisfies the self-balancing constraints of the storage / heating / cooling equipment is expressed as:

[0157] W ESE，k (t) = (1-ε ESE )W ESE，k (t-1)-P ESE，k (t)Δt

[0158]

[0159] W HSE，k (t) = (1-ε HSE )W HSE，k (t-1)-P HSE，k (t)Δt

[0160]

[0161] W CSE，k (t) = (1-ε CSE )W CSE，k (t-1)-P CSE，k (t)Δt

[0162]

[0163] Among them, W ESE，k (t) is the storage capacity of the storage device during period t in month k, ε ESE is the self-discharge rate of the storage device, W ESE，k (t-1) is the heat storage of the heat storage device during the period t-1; W ESE，k (t 0 ) is the starting time period, i.e., t 0 The amount of electricity stored in the storage device during the period, W EL The amount of energy that should be left in the storage device at the end of the operation optimization cycle. It is the starting time period of the next cycle after the end of one running optimization cycle; W HSE，k (t) is the heat storage capacity of the heat storage device in period t in month k, ε HSE is the self-heat release rate of the heat storage device, W HSE，k (t-1) is the heat storage of the heat storage device during the period t-1; W HSE，k (t 0 ) is the starting time period, i.e., t 0 Heat storage of the time period heat storage device, W HL W is the amount of heat that should be left in the heat storage device at the end of the operation optimization cycle; CSE，k (t) is the cooling capacity of the cooling device in period t in month k, ε CSE is the self-cooling rate of the cold storage device, W CSE，k (t-1) is the cold storage capacity of the cold storage device during the period t-1; W CSE，k (t 0 ) is the starting time period, i.e., t 0 Cooling capacity of the cold storage device during the period, W CL The amount of cold storage that should be left in the cold storage device at the end of the operation optimization cycle.

[0164] Using the equation balance method, the feasible domain that satisfies the waste heat balance constraint is expressed as:

[0165]

[0166] P ex，k (t) = P tur，k (t)*HPR*η r

[0167]

[0168] P WHB，k (t) = α 1 P ex，k (t)

[0169] P WHC，k (t) = α 2 P ex，k (t)

[0170] α 1 +α 2 +α 3 =1

[0171] Where HPR is the gas turbine heat-to-power ratio, For the rated heating efficiency of the gas turbine, is the rated power generation efficiency of the gas turbine; P ex，k (t) is the waste heat power recovered by the gas turbine during period t in month k, η r Indicates the waste heat recovery efficiency of the cogeneration system, LHN NG Indicates the lower calorific value of natural gas; α 1 Indicates the proportion of waste heat entering the waste heat boiler; α 2 Indicates the proportion of waste heat entering the waste heat absorption refrigerator; α 3 Indicates the proportion of waste heat that is not utilized.

[0172] 4.2 Construct the feasible region for optimization under the condition of satisfying inequality constraints;

[0173] The upper and lower limit constraint method is adopted to set upper and lower limit planning constraints from investment cost, building area, power grid energy supply, energy supply equipment operation, natural gas network capacity, reliability, and demand response. The feasible domain of the algorithm that satisfies the inequality constraint conditions is expressed as:

[0174] (1) Investment cost constraints

[0175] INV max ≥(P pur +p bui )

[0176] Among them, INV max To build maximum investment capacity for integrated energy systems in planning scenarios.

[0177] (2) Building area constraints

[0178]

[0179] Among them, A max The maximum construction land area for building an integrated energy system is A i Land area used for installation of integrated energy system equipment i.

[0180] (3) Grid energy supply constraints

[0181]

[0182]

[0183] Among them, D max The maximum power supply capacity of the power grid. is the power consumption of device i, is the power generation of device i, The power load designed for the integrated energy system planning scenario; RS is the safety power factor.

[0184] (4) Operation constraints of energy supply equipment

[0185]

[0186]

[0187] in, and are the minimum and maximum cooling / heating powers of equipment i, and are the ramp rates of decreasing and increasing output of equipment i respectively.

[0188] (5) Natural gas network capacity constraints

[0189]

[0190]

[0191] Among them, PQ min，l and PQ max，l are the lower and upper limits of the natural gas pipeline flow rate, cl l，y V is the safety fluctuation coefficient of pipeline transmission flow; min，s and V max，s They respectively represent the lower and upper limits of the gas supply volume at the natural gas supply end.

[0192] (6) Reliability constraints

[0193]

[0194] in, is the energy gap, ΔLmax The power is insufficient.

[0195] (7) Demand response constraints

[0196]

[0197] Among them, P t，k is the load in period t in month k, and are the lower and upper limits of the demand response load in period t in month k, respectively.

[0198] Step 5: Under the established inequality constraints and balanced equality constraints, find the optimal feasible region and calculate the total cost C of the integrated energy system over the entire life cycle of the C_gh planning scenario. gh A hybrid artificial fish swarm algorithm is used to find the optimal solution to obtain whether each energy device in the planning scenario integrated energy system is configured, the configured capacity and the operating output curve of each configured device while meeting the cooling, heating and electricity load requirements of the regional integrated energy system.

[0199] See attached Figure 2 , the hybrid artificial fish swarm algorithm is used for operation optimization and solution, as follows:

[0200] The optimal population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSO Each particle swarm individual performs a separate particle swarm algorithm search;

[0201] After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm;

[0202] If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution;

[0203] If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution;

[0204] Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position:

[0205]

[0206] S=V*rand1

[0207]

[0208] Among them, V is the field of view of the artificial fish in the current iteration, V min and Vmax are the minimum and maximum values ​​of the artificial fish’s field of view, G max is the maximum number of iterations, i ter is the current iteration number, S is the maximum step length of the artificial fish, rand1∈[0.5, 1] ​​is any random number, X i is the current position of the artificial fish, any random number of rand2 and rand3∈[0,1], X j is the position with the highest food concentration within the field of view, Gaussian (μ, σ 2 ) is the Gaussian disturbance term, μ is the mean, σ 2 is the variance.

[0209] Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

[0210] It also includes a reasonable parameter initialization process, including:

[0211] The population size is m = 50, the number of artificial fish individuals is m BA =25, the number of individual particles in the swarm is m PSO =25, maximum number of iterations t max =1000, minimum value of the artificial fish’s field of view V min =1.5, the maximum value of the artificial fish’s field of view V max =3.5, crowding factor δ = 0.618, number of foraging attempts num try =50, learning factor c 1 =c 2 =2.0, minimum inertia weight ω min =0.4, maximum inertia weight ω max =0.9, mean μ=0, variance σ 2 =|P(t)|.

[0212] Finally, determine whether the iteration meets the end condition:

[0213] |C yx (s)-C yx (s-1)|≤0.001 or i ter ≥G max

[0214] Among them, C yx (s), C yx (s-1) are the values ​​obtained in the current and last optimization searches respectively.

[0215] If satisfied, then output the optimal individual; otherwise, proceed to the next iteration until the maximum number of iterations G is reached. max , output the current optimal result.

[0216] Another aspect of the embodiment of the present invention is a comprehensive energy system planning system based on a hybrid artificial fish swarm algorithm, further comprising:

[0217] Renewable energy unit output prediction module, used to predict the output of photovoltaic generators on typical days of each month in the integrated energy system;

[0218] The output data acquisition module is used to obtain the output of photovoltaic generators on typical days of each month and plan the cold / heat / electric load data of the scenario to maximize the consumption of photovoltaic power generation and meet the cold / heat / electric load requirements;

[0219] The constraint condition module, based on the output power data of the above-mentioned equipment, constructs an optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment and waste heat balance, and an optimal feasible domain that satisfies the constraints of inequality;

[0220] The constraint condition module includes an electric heat and cold balance constraint condition submodule, a storage / heat / cold equipment self-balance constraint condition submodule, a waste heat balance constraint condition submodule, a first optimal feasible domain submodule, an inequality constraint condition and a second optimal feasible domain submodule; the first optimal feasible domain submodule is used to determine the optimal feasible domain based on the electric heat and cold balance constraint condition submodule, the storage / heat / cold equipment self-balance constraint condition submodule and the waste heat balance constraint condition; the second optimal feasible domain submodule is used to determine the optimal feasible domain based on the inequality constraint condition. The planning optimization module is used to establish the economic planning target of the integrated energy system of the planning scenario, and solve the economic planning target in the optimal feasible domain that satisfies the electric heat and cold balance, storage / heat / cold equipment self-balance and waste heat balance constraints and the optimal feasible domain that satisfies the inequality constraint condition to obtain whether each energy device is configured, the configuration capacity and the typical daily output power data of each month.

[0221] The planning optimization module includes an economic planning target submodule and a target solving submodule; in the economic planning target submodule, the economic planning target of the planning scenario is established, and the target function of the optimization algorithm is constructed; the target solving submodule solves the economic planning target in the optimization feasible domain, and obtains the calculation results of whether each device in the integrated energy system is configured, the configuration capacity and the typical daily output power data of each month.

[0222] In the target solution submodule, the optimization population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSOEach particle swarm individual performs a separate particle swarm algorithm search;

[0223] After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm;

[0224] If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution;

[0225] If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution;

[0226] Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position:

[0227]

[0228] S=V*rand1

[0229]

[0230] Among them, V is the field of view of the artificial fish in the current iteration, V min and V max are the minimum and maximum values ​​of the artificial fish’s field of view, G max is the maximum number of iterations, i ter is the current iteration number, S is the maximum step length of the artificial fish, rand1∈[0.5, 1] ​​is any random number, X i is the current position of the artificial fish, any random number of rand2 and rand3∈[0,1], X j is the position with the highest food concentration within the field of view, Gaussian (μ, σ 2 ) is the Gaussian disturbance term, μ is the mean, σ 2 is the variance.

[0231] Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

[0232] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0233] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0234] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0235] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0236] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A comprehensive energy system planning method based on a hybrid artificial fish swarm algorithm, characterized in that: The integrated energy system planning approach includes the following steps: Step 1: Calculate the output forecast curve of photovoltaic generators per square meter based on the monthly typical daily meteorological historical data curve of local temperature and irradiance; Step 2: The forecast data of typical daily cooling, heating and electricity loads of the integrated energy system in the planning scenario is used as the load curve parameters of cooling, heating and electricity in the planning scenario; Step 3: Establish the economic planning goal of the planning scenario and construct the objective function of the optimization algorithm; Step 4: Construct an optimization feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment, and waste heat balance, as well as a feasible domain for solving the optimization algorithm under the condition of satisfying the inequality constraints; Step 5: In the optimal feasible domain under the conditions of satisfying the inequality constraint and the balanced equality constraint, the objective function is solved to obtain whether each energy device in the integrated energy system of the planning scenario is configured, the configured capacity and the operating output curve of each configured device; The construction of an optimal feasible domain that satisfies the electric, thermal and cooling balance constraint condition includes: P PV,k (t)+P grid,k (t)+P tur,k (t)+P ESE,k (t)=P ERB,k (t)+P ERC,k (t)+P E,k (t) P ERB,k (t)η ERB +P WHB,k (t)η WHB +P HSE,k (t)=P H,k (t) P ERC,k (t)COP ERC +P WHC,k (t)COP WHC +P CSE,k (t)=P C,k (t) Among them, P tur,k (t) is the power generation of the gas turbine in the kth month and the tth period, P ESE,k (t) is the charging / discharging power of the storage device during period t in month k, P ESE,k (t) greater than 0 indicates discharge, P ESE,k (t) less than 0 indicates charging; P ERB,k (t) is the power consumption of the electric heating boiler in the kth month and the tth period, η ERB is the heating efficiency of the electric boiler, P WHB,k (t) is the waste heat utilization power of waste heat boiler flue gas in period t in month k, η WHB is the heating efficiency of the waste heat boiler; P HSE,k (t) is the charging / discharging power of the heat storage device during period t in month k, P HSE,k (t) greater than 0 indicates heat release, P HSE,k (t) less than 0 indicates hot charging; P ERC,k (t) is the power consumption of the refrigerator in the kth month during the tth period, COP ERC is the coefficient of performance of the electric refrigerator, P WHC,k (t) is the waste heat utilization power of the waste heat absorption refrigerator in the kth month and period t, COP WHC P is the coefficient of performance of the waste heat absorption refrigeration machine; CSE,k (t) is the charging / discharging power of the cold storage device during period t in month k, P HSE,k (t) greater than 0 means cooling, P HSE,k (t) less than 0 indicates cold charging; The construction of an optimal feasible domain satisfying the waste heat balance constraint condition includes: P ex,k (t)=P tur,k (t)*HPR*η r P WHB,k (t)=α1P ex,k (t) P WHC,k (t)=α2P ex,k (t) α1+α2+α3＝1 Where HPR is the gas turbine heat-to-power ratio, For the rated thermal efficiency of the gas turbine, is the rated power generation efficiency of the gas turbine; P ex,k (t) is the waste heat power recovered by the gas turbine during period t in month k, η r Indicates the waste heat recovery efficiency of the cogeneration system, LHN NG Indicates the lower calorific value of natural gas; α1 indicates the proportion of waste heat entering the waste heat boiler; α2 indicates the proportion of waste heat entering the waste heat absorption chiller; α3 indicates the proportion of waste heat not utilized; In step 5, the objective function is optimized and solved in the constructed optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment and waste heat balance, and the optimal feasible domain that satisfies the inequality constraints, including: The optimal population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSO Each particle swarm individual performs a separate particle swarm algorithm search; After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm; If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution; If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution; Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position: S=V*rand1 Among them, V is the field of view of the artificial fish in the current iteration, V min and V max are the minimum and maximum values ​​of the artificial fish’s field of view, G max is the maximum number of iterations, i ter is the current iteration number, S is the maximum step length of the artificial fish, rand1∈[0.5,1] is any random number, X i is the current position of the artificial fish, X next is the updated artificial fish position state, any random number of rand2 and rand3∈[0,1], X j is the position with the highest food concentration within the field of view, Gaussian(μ,σ 2 ) is the Gaussian disturbance term, μ is the mean, σ 2 is the variance; Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

2. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: The comprehensive energy system includes a photovoltaic power generation set, an electric boiler, a heat storage device, an electric refrigerator, a cold storage device, a large power grid, a low-voltage transformer, an electric energy bus, a thermal energy bus, a cold energy bus, a user's electric load, an electric storage device, a user's thermal load, a user's cold load, a gas turbine generator set, a waste heat boiler, a waste heat absorption refrigerator, a waste heat bus and a waste heat discharge. The photovoltaic power generation set and the gas turbine generator set are connected to the electric boiler, the electric refrigerator, the user's electric load, the electric storage device and the low-voltage side of the low-voltage transformer through the electric energy bus, the electric boiler and the waste heat boiler are connected to the heat storage device and the user's thermal load through the thermal energy bus, the electric refrigerator and the waste heat absorption refrigerator are connected to the cold storage device and the user's cold load through the cold energy bus, the high-voltage side of the low-voltage transformer is connected to the large power grid, and the gas turbine generator set is connected to the waste heat boiler, the waste heat absorption refrigerator and the waste heat discharge through the waste heat bus.

3. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: In step 1, the output of the photovoltaic power generation unit of the integrated energy system is predicted using the following formula: P PV,k (t)=R k (t)h r or pc A[1-β(T c -T cref )] Among them, R k (t) is the light intensity in period t of month k, η r is the temperature coefficient, η pc is the MPPT efficiency of the DC conversion link, β is the power temperature coefficient of the solar cell module, T c is the actual ambient temperature, T cref is the ambient reference temperature, A is the optimized photovoltaic configuration area, P PV,k (t) is the predicted output of the photovoltaic power generation unit after optimization in period t of month k.

4. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: In step 2, the user's cooling, heating and electricity load parameters are configured for the typical daily cooling, heating and electricity load forecast data of the integrated energy system from January to December in the planning scenario, including: Among them, P′ E,k (t), P′ C,k (t), P′ H,k (t) are the forecast data of electricity load, cooling load and heating load of users in typical day of period t in month k; P E,k (t), P C,k (t), P H,k (t) are the user electricity load, user cooling load, and user heating load in period t of month k; ΔP′ E,k (t), ΔP′ C,k (t), ΔP′ H,k (t) are the deviations of user electric load, user cooling load, user heating load and actual load in period t of month k.

5. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: In step 3, the economic planning goal of the integrated energy system of the planning scenario, i.e., the objective function, includes: C gh =min(P pur +p bui +f run +F main -S sub ) Among them, C gh 、f run 、F main are the total cost, operation cost, and maintenance cost of the integrated energy system in the planning scenario over its entire life cycle; P pur 、p bui They are the total purchase cost and total installation and construction cost of the integrated energy system equipment; S sub To provide government subsidies for electricity generation in integrated energy systems; P pur It is expressed as: Among them, r is the discount rate, n is the design life, c i , I are the purchase cost of equipment i and the total number of purchased equipment for the integrated energy system, respectively; p bui It is expressed as: Among them, j i ,t i , o i They are the land use fee, installation fee and other fees of the integrated energy system equipment i; f run It is expressed as: Among them, pr grid (t), pr gas (t) are the time-of-use electricity price of the power grid and the time-of-use gas price of the gas grid during period t, PP grid,k (t), PP gas,k (t) are the electricity purchased from the power grid and the gas purchased from the gas grid in the kth month and the tth period, respectively; D k is the number of days in the kth month, T is the total number of operating hours in a day, and K is the number of months in a natural year; P grid,k (t), P gas,k (t) are the power purchased from the power grid and the gas flow purchased from the gas grid during the t period in the kth month, respectively. Δt is the length of time for each operating period. F main It is expressed as: Among them, F G 、F H 、F C are the maintenance costs of the power grid, heating network and cooling network respectively, m i Maintenance costs of integrated energy system equipment i; S sub It is expressed as: Among them, pr grid_bt (t) is the time-of-use electricity price for power generation subsidy during period t, PP grid_bt,k (t) is the electricity sold to the grid during period t in month k, P grid_bt,k (t) is the electricity sold to the grid during period t in month k.

6. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: In step 4, the construction of an optimal feasible domain that satisfies the self-balancing constraint conditions of the power storage / heating / cooling equipment includes: W ESE,k (t)=(1-ε ESE )W ESE,k (t-1)-P ESE,k (t)Δt W HSE,k (t)=(1-ε HSE )W HSE,k (t-1)-P HSE,k (t)Δt W CSE,k (t)=(1-ε CSE )W CSE,k (t-1)-P CSE,k (t)Δt Among them, W ESE,k (t) is the storage capacity of the storage device during period t in month k, ε ESE is the self-discharge rate of the storage device, W ESE,k (t-1) is the heat storage of the heat storage device during the period t-1; W ESE,k (t0) is the starting time period, i.e., the amount of electricity stored in the storage device during the t0 period, W EL The amount of energy that should be left in the storage device at the end of the operation optimization cycle. It is the starting time period of the next cycle after the end of one running optimization cycle; W HSE,k (t) is the heat storage capacity of the heat storage device in period t in month k, ε HSE is the self-heat release rate of the heat storage device, W HSE,k (t-1) is the heat storage of the heat storage device during the period t-1; W HSE,k (t0) is the starting time period, i.e., the heat storage capacity of the heat storage device during the t0 period, W HL W is the amount of heat that should be left in the heat storage device at the end of the operation optimization cycle; CSE,k (t) is the cooling capacity of the cooling device in period t in month k, ε CSE is the self-cooling rate of the cold storage device, W CSE,k (t-1) is the cold storage capacity of the cold storage device during the period t-1; W CSE,k (t0) is the starting time period, i.e., the cold storage capacity of the cold storage device during the period t0, W CL The amount of cold storage that should be left in the cold storage device at the end of the operation optimization cycle.

7. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 5, characterized in that: In step 4, constructing an optimization feasible region that satisfies the inequality constraint condition includes: (1) Investment cost constraints INV max ≥(P pur +p bui ) Among them, INV max Building maximum investment capacity for planning scenario integrated energy systems; (2) Building area constraints Among them, A max The maximum construction land area for building an integrated energy system is A i Land area used for installation of integrated energy system equipment i; (3) Grid energy supply constraints Among them, D max The maximum power supply capacity of the power grid. is the maximum power consumption of device i, is the maximum power generation capacity of device i, The maximum power load designed for the integrated energy system planning scenario; RS is the safety power factor; (4) Energy supply equipment operation constraints Where, Q is the cooling / heating power value of the equipment, are the cooling / heating power values ​​of equipment i at time t and time t-1, respectively. and are the minimum and maximum cooling / heating powers of equipment i, and are the ramp rates of decreasing and increasing output of equipment i, respectively; (5) Natural gas network capacity constraints Among them, PQ l,t,u,y is the gas network capacity, PQ min,l and PQ max,l are the lower and upper limits of the natural gas pipeline flow rate, cl l,y V is the safety fluctuation coefficient of pipeline transmission flow; min,s and V max,s They represent the lower and upper limits of the gas supply volume at the natural gas supply end respectively; (6) Reliability constraints in, is the energy gap, ΔL max The power is insufficient to the upper limit; (7) Demand response constraints Among them, P t,k is the load in period t in month k, and are the lower and upper limits of the demand response load in period t in month k, respectively.

8. The integrated energy system planning method based on hybrid artificial fish swarm algorithm according to claim 1, characterized in that: The end conditions are: |C yx (s)-C yx (s-1)|≤0.001 or i ter ≥G max Among them, C yx (s), C yx (s-1) are the values ​​obtained in the current and last optimization searches respectively.

9. An integrated energy system planning system using the integrated energy system planning method according to any one of claims 1 to 8, comprising a renewable energy unit output prediction module, an output data acquisition module, a constraint condition module, and a planning optimization module; characterized in that: The renewable energy unit output prediction module is used to predict the output of the photovoltaic power generation unit on a typical day of each month in the integrated energy system and transmit it to the processing data acquisition module; The output data acquisition module is used to obtain the output of the photovoltaic power generation group on a typical day of each month, and the cold, heat and electricity load forecast data of the planning scenario, and use the cold, heat and electricity load forecast data of the planning scenario as the load curve parameters of the cold, heat and electricity in the planning scenario. The processing data acquisition module transmits the output of the photovoltaic power generation group and the load curve parameters of the cold, heat and electricity in the planning scenario to the constraint condition module; The constraint condition module, based on the output power data of each device in the integrated energy system, constructs an optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of power storage / heat / cooling equipment and waste heat balance, and an optimal feasible domain that satisfies the constraints of inequality; The planning optimization module is used to establish the economic planning target of the integrated energy system of the planning scenario, solve the economic planning target in the optimal feasible domain that satisfies the constraints of electric heat and cooling balance, self-balance of storage / heat / cooling equipment and waste heat balance, and the optimal feasible domain that satisfies the inequality constraints, and obtain whether each device in the integrated energy system is configured, the configuration capacity and the typical daily power data of each month.

10. The integrated energy system planning system according to claim 9, characterized in that: The constraint condition module includes an electric heat and cold balance constraint condition submodule, an electric storage / heat / cold equipment self-balance constraint condition submodule, a waste heat balance constraint condition submodule, a first optimal feasible domain submodule, an inequality constraint condition and a second optimal feasible domain submodule; The first optimal feasible domain submodule is used to determine the optimal feasible domain based on the electric, thermal and cooling balance constraint condition submodule, the electric storage / heat / cooling equipment self-balance constraint condition submodule and the waste heat balance constraint condition; The second optimization feasible region submodule is used to determine the optimization feasible region based on inequality constraints.

11. The integrated energy system planning system according to claim 10, characterized in that: The planning optimization module includes an economic planning target submodule and a target solution submodule; In the economic planning target submodule, the economic planning target of the planning scenario is established, and the objective function of the optimization algorithm is constructed; The target solving submodule solves the economic planning target in the optimal feasible domain, and obtains the calculation results of whether each device in the integrated energy system is configured, the configuration capacity and the typical daily output power data of each month.

12. The integrated energy system planning system according to claim 11, characterized in that: In the target solution submodule, the optimization population individuals are divided into two, where m ACO Artificial fish individuals perform separate artificial fish swarm algorithm search, m PSO Each particle swarm individual performs a separate particle swarm algorithm search; After each search, the global optimal solution of the artificial fish swarm algorithm is compared with the global optimal solution of the particle swarm algorithm; If the global optimal solution obtained by the artificial fish swarm algorithm is better than the global optimal solution obtained by the particle swarm algorithm, the solution obtained by the artificial fish swarm algorithm will be used as the current optimal solution; If the global optimal solution obtained by the particle swarm algorithm is better than the global optimal solution obtained by the artificial fish swarm algorithm, the solution obtained by the particle swarm algorithm will be used as the current optimal solution; Add a Gaussian perturbation term to the current optimal solution and update the artificial fish’s field of view and position: Based on the updated artificial fish field of view and position, the search continues among the artificial fish swarm individuals and particle swarm individuals until the end condition or the maximum number of iterations is reached, and the optimal individual is output to obtain the integrated energy system planning scenario. Under the premise of meeting the cooling, heating and electricity load requirements of the integrated energy system, whether each device is configured, the configuration capacity, and the output of a typical day of each month under the configuration.

Images