Comprehensive energy system collaborative planning method and device considering uncertain factors

Abstract

The invention relates to the technical field of energy management, and provides an integrated energy system collaborative planning method and device suitable for a park and considering uncertain factors. Mathematical models are constructed for the wind turbine generator, the cold load, the thermal load and the electric load respectively, and an operation scene set is constructed; clustering each kind of scene feature data in the operation scene set to obtain a plurality of data class groups of each kind of scene feature data; classifying the scenes according to the corresponding relationship between the scene feature data and the scenes in the data class groups to obtain a plurality of scene class groups corresponding to each scene feature data; determining a plurality of scene class groups to which the current park planning belongs; determining an intersection of a plurality of scene class groups to which the current park planning belongs; and according to the cost data of each scene in the intersection, planning integrated energy system distributed energy supply equipment and energy supply equipment construction site selection. According to the method, finer multi-energy planning design can be realized, and the multi-energy planning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a method and device for collaborative planning of an integrated energy system taking into account uncertain factors applicable to a park. Background Art

[0002] Traditional multi-energy system planning methods only plan based on deterministic prediction scenarios, and rarely consider the impact of uncertain factors. With the widespread access of renewable energy power generation to the energy system, the uncertainty and complexity of the operation of the integrated energy system have been exacerbated by the need to consider the impact of uncertain factors such as renewable energy power generation on the planning results in multi-energy planning. Therefore, new multi-energy system planning methods suitable for uncertain factors such as renewable energy power generation are needed. Summary of the invention

[0003] In view of the above problems, the present invention provides a method and device for collaborative planning of an integrated energy system taking into account uncertain factors, and in particular, a method and device for collaborative planning of an integrated energy system taking into account uncertain factors suitable for a park.

[0004] In a first aspect, the present invention provides a method for collaborative planning of an integrated energy system taking into account uncertain factors, the method comprising:

[0005] Mathematical models are constructed for wind turbines, cooling loads, heating loads and electric loads respectively, and an operation scenario set is constructed based on the mathematical models; when constructing the operation scenario set, the uncertainties of wind turbines, cooling loads, heating loads and electric loads are taken into account to generate data for the operation scenario set that is closer to the actual environment; the operation scenario set is constructed based on the mathematical model, including: randomly sampling the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and clustering the acquired data to generate scenarios reflecting wind power and loads; each scenario includes wind power scenario feature data, various load scenario feature data, and corresponding cost data;

[0006] Clustering the characteristic data of each scenario in the running scenario set respectively to obtain multiple data clusters of the characteristic data of each scenario;

[0007] Classify the scenes according to the correspondence between the scene feature data and the scenes in the data group, and obtain multiple scene groups corresponding to each scene feature data;

[0008] According to the objective function of the park planning, the upper-level planning model and the lower-level planning model are constructed respectively, and the power balance constraint conditions are established; the objective function of the upper-level planning model is to minimize the annual comprehensive cost; the objective function of the lower-level planning model is to minimize the operating cost and maximize the utilization efficiency of primary energy throughout the entire period;

[0009] Based on the data of the operation scenario set, the upper-level planning model and the lower-level planning model are solved, and according to the solution results, the wind turbines, cooling load, heating load and electric load data of the current park planning are determined;

[0010] Compare the wind turbines, cooling load, heating load and electric load data of the current park planning with each scene group of the same scene feature data in the operation scene set to determine the multiple scene groups to which the current park planning belongs;

[0011] Determine the intersection of multiple scenario groups to which the current park planning belongs;

[0012] Based on the cost data of each scenario in the intersection, the distributed energy supply equipment of the integrated energy system and the construction site selection of the energy supply equipment are planned.

[0013] In a second aspect, the present invention provides a comprehensive energy system collaborative planning device taking uncertainty factors into account, comprising: a modeling unit, a target unit and a solution unit connected in sequence;

[0014] A modeling unit is used to construct mathematical models for wind turbines, cooling loads, heating loads and electric loads respectively, and to construct an operation scenario set based on the mathematical models; constructing the operation scenario set based on the mathematical models includes: randomly sampling the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and clustering the acquired data to generate scenarios reflecting wind power and loads; each scenario includes wind power scenario feature data, various load scenario feature data, and corresponding cost data; clustering the feature data of each scenario in the operation scenario set respectively to obtain multiple data groups for each scenario feature data; classifying the scenarios according to the corresponding relationship between the scene feature data and the scenarios in the data group to obtain multiple scenario groups corresponding to each scene feature data;

[0015] The target unit is used to construct the upper-level planning model and the lower-level planning model according to the objective function of the park planning, and to establish power balance constraints; the objective function of the upper-level planning model is to minimize the annual comprehensive cost; the objective function of the lower-level planning model is to minimize the operating cost and maximize the utilization efficiency of primary energy throughout the entire period;

[0016] The planning unit is used to solve the upper-level planning model and the lower-level planning model based on the data of the operating scenario set, and determine the wind turbine group, cooling load, heating load and electric load data of the current park plan according to the solution results; compare the wind turbine group, cooling load, heating load and electric load data of the current park plan with each scenario group of the same scenario feature data in the operating scenario set to determine the multiple scenario groups to which the current park plan belongs; determine the intersection of the multiple scenario groups to which the current park plan belongs; and plan the distributed energy supply equipment and construction site selection of the energy supply equipment of the comprehensive energy system according to the cost data of each scenario in the intersection.

[0017] In a third aspect, the present invention provides an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0018] Memory, used to store computer programs;

[0019] The processor is used to implement the above-mentioned comprehensive energy system collaborative planning method taking uncertainty factors into account when executing the program stored in the memory.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for collaborative planning of an integrated energy system taking into account uncertain factors.

[0021] The present invention has at least the following beneficial effects:

[0022] The present invention adopts a simplification algorithm to obtain a suitable number of typical scenarios, and based on the scenario feature data, determines the scenarios that are closer to the current park planning, thereby realizing further screening of the model solution data, helping to achieve more refined planning and design, and helping to plan the construction site selection of distributed energy supply equipment and energy supply equipment in the integrated energy system, thereby improving the efficiency of multi-energy planning. By considering the operating scenarios of source-load uncertainty, it helps to improve the penetration rate of wind power in the integrated energy system, and helps to ensure the economy and power supply reliability of wind power in the long-term planning process.

[0023] The present invention proposes a collaborative planning model for an integrated energy system taking uncertainty factors into account, which can not only achieve the goal of higher economic benefits for the integrated energy system, but also effectively improve the economy and flexibility of the integrated energy system.

[0024] Other features and advantages of the present invention will be described in the following description, and partly become obvious from the description, or be understood by implementing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 This is a flow chart of the collaborative planning method of the present invention;

[0027] Figure 2 This is a schematic diagram of the structure of the collaborative planning device of the present invention;

[0028] Figure 3 Solve the flow chart for the collaborative planning model;

[0029] Figure 4 Schematic diagram of collaborative planning of integrated energy systems considering uncertainties;

[0030] Figure 5 This is a schematic diagram of time-of-use electricity prices;

[0031] Figure 6 is the wind power curve;

[0032] Figure 7 This is a typical daily load curve in spring and autumn;

[0033] Figure 8 This is a typical daily load curve in summer;

[0034] Fig. 9 This is a typical daily load curve in winter;

[0035] Fig.10 The target change curve diagram when only the operation and maintenance cost is considered for the lower-level target;

[0036] Fig.11 The target change curve diagram when only energy utilization efficiency is considered for the lower-level target;

[0037] Fig.12 Iterate the scatter plot for the target. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] First, as Figure 1 As shown, the present invention provides a method for collaborative planning of an integrated energy system taking uncertain factors into account, the method comprising:

[0040] Mathematical models are constructed for wind turbines, cooling loads, heating loads and electrical loads respectively, and operation scenario sets are constructed based on the mathematical models;

[0041] According to the objective function of the park planning, the upper-level planning model and the lower-level planning model are constructed respectively, and the power balance constraint conditions are established;

[0042] Based on the data of the operation scenario set, the upper-level planning model and the lower-level planning model are solved, and the distributed energy supply equipment and the construction site of the energy supply equipment of the integrated energy system are planned according to the solution results.

[0043] In specific implementation, due to the non-sustainability and volatility of wind power, there are uncertain factors that affect the stability of wind power generation; there are also uncertain factors that affect the stability of cooling load and heating load.

[0044] In the upper model, a genetic algorithm is used to solve the multi-objective planning model, which includes indicators such as annual cost of construction investment and operating cost, which are themselves affected by uncertain factors. In the lower model, a multi-scenario verification model is used, with the goal of maximizing the utilization efficiency of primary energy throughout the entire period, to verify the ability of the Pareto optimal planning solution set to withstand wind power and load uncertainties, which also fully considers the impact of uncertain factors.

[0045] In addition, in the lower model, the constraints of the upper model are modified according to the expected value of the primary energy utilization efficiency of the lower model throughout the entire period, so as to pass the influence of wind power and load uncertainty to the upper model. Finally, the quantum evolutionary algorithm is used to solve the model, and a collaborative planning scheme with higher economic benefits is obtained based on the consideration of uncertainty factors.

[0046] According to the solution results, the distributed energy supply equipment of the integrated energy system and the construction site selection of the energy supply equipment are planned. First, the heat load, cold load and electricity load data of the park are obtained, and a model is proposed; then, according to the proposed model, the distributed energy supply equipment of the integrated energy system is planned, including the selection and configuration capacity of cogeneration units, electric refrigeration machines, and gas boilers. Finally, the construction site of the energy supply equipment is selected according to the collaborative planning results.

[0047] In this embodiment, the mathematical models for the wind turbine, cooling load, heating load and electrical load are constructed respectively, including:

[0048] The historical wind speed and load data are used to construct the probability distribution model of wind turbines, cooling load, heating load and electrical load through parameter estimation.

[0049] In this embodiment, the method of using historical wind speed and load data to construct a probability distribution model of wind turbines, cooling load, heating load and electric load through parameter estimation includes:

[0050] For wind turbines, the wind speed in a certain period of time is a two-parameter Weibull distribution, and its probability density function is:

[0051]

[0052] The output power of the fan and the fan satisfy the following relationship:

[0053]

[0054] in,

[0055]

[0056] Where v represents the actual wind speed; c and k represent the scale parameter and shape parameter respectively; r is the fan radius; ρ is the air density; P w (v) is the output power of the fan; P r is the rated power of the fan; g(x) is the calculation expression; v r Indicates rated wind speed; v in Indicates the cut-in wind speed; v out Indicates the cut-out wind speed;

[0057] The parameters of the wind turbine model are estimated using historical wind speed data.

[0058] In this embodiment, the method of using historical wind speed and load data to construct a probability distribution model of wind turbines, cooling load, heating load and electric load through parameter estimation includes:

[0059] The cold, hot and electric loads obey the normal distribution, and the probability distribution of the loads is expressed as:

[0060]

[0061] in, is the probability density function; is the load power, i = e / h / c, which is represented by the power of electric load, heat load and cooling load respectively; μ is the mean of the random variable; σ is the variance of the random variable,

[0062] The probability distribution model of cooling load, heating load and electrical load is estimated based on historical load data to obtain the parameter values.

[0063] In this embodiment, the operation scenario set is constructed based on the mathematical model, including:

[0064] Monte Carlo sampling is performed on the mathematical models of wind turbines, cooling loads, heating loads, and electrical loads to generate random scenarios that reflect the uncertainties of wind power and loads.

[0065] In this embodiment, the operation scenario set is constructed based on the mathematical model, including:

[0066] Monte Carlo sampling is performed on the mathematical models of wind turbines, cooling loads, heating loads, and electrical loads, and the obtained data is clustered using the k-means clustering algorithm to generate random scenarios that reflect the uncertainty of wind power and loads. Each scenario includes wind power scenario feature data, scenario feature data of various loads (cooling load, heating load, and electrical load), and corresponding cost data.

[0067] In this embodiment, Monte Carlo sampling is performed on the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and the acquired data is clustered using a k-means clustering algorithm to obtain a plurality of wind power scenario characteristic data and various types of load scenario characteristic data; based on the plurality of wind power scenario characteristic data and various types of load scenario characteristic data, a random scenario reflecting the uncertainty of wind power and load is generated, including:

[0068] The wind power scenario characteristic data is obtained in the following way: the probability density and probability distribution function of wind power output are obtained according to the historical wind farm output, an N-dimensional Copula function is constructed and the correlation coefficient of the Copula function is solved, Monte Carlo sampling is performed to generate random values ​​with correlation, and the random values ​​are inverted to obtain the wind power simulation scenario data; the wind power simulation scenario data is clustered and analyzed using the k-means clustering algorithm to obtain multiple wind power scenario characteristic data.

[0069] The scene characteristic data of various loads (cooling load, heating load and electric load) are obtained in the following ways: according to the historical data of various loads, the probability density and probability distribution function of various loads are obtained, and Monte Carlo sampling is performed to generate random values ​​with correlation, and the random values ​​are inverted to obtain the simulated scene data of the loads; the simulated scene data of the loads are clustered using the k-means clustering algorithm to obtain multiple scene characteristic data of various loads.

[0070] Based on the above-mentioned multiple wind power scene characteristic data and various load scene characteristic data, a scene reflecting wind power and load is generated.

[0071] Cluster the characteristic data of each scenario in the operation scenario set to obtain multiple data groups of each scenario characteristic data. For example, cluster the characteristic data of wind power scenarios in the operation scenario set to obtain multiple data groups of wind power scenario characteristic data. Therefore, multiple scenarios in the same data group of wind power scenario characteristic data have strong data commonality in wind power scenario characteristic data; cluster the cold load scenario characteristic data in the operation scenario set to obtain multiple data groups of cold load scenario characteristic data; cluster the heat load scenario characteristic data in the operation scenario set to obtain multiple data groups of heat load scenario characteristic data; cluster the electric load scenario characteristic data in the operation scenario set to obtain multiple data groups of electric load scenario characteristic data.

[0072] The data groups of the above-mentioned different scene feature data are equivalent to classifying the multiple scenes in the running scene set from the perspective of different scene feature data, so as to facilitate the selection of scenes that are closer to the current park planning in the subsequent steps. Specifically, according to the corresponding relationship between the scene feature data and the scenes in the data group, the scenes are classified to obtain multiple scene groups corresponding to each scene feature data.

[0073] In this embodiment, the upper-level planning model and the lower-level planning model are constructed respectively according to the objective function of the park planning, including:

[0074] The objective function of the upper-level planning model is to minimize the annual comprehensive cost. inv and operating cost C op , the upper objective function value is as follows:

[0075] minC=C inv +C op (5)

[0076] Among them, C inv is the equivalent annual investment cost of all equipment; C op is the operating cost of the system on a typical day;

[0077]

[0078] Among them, C ω is the unit investment cost of the equipment; R ω is the construction capacity of the equipment ω, and the specific equipment includes the combined cooling, heating and power device CCHP, the electric refrigerator EC, and the gas boiler GB.

[0079] In this embodiment, the upper-level planning model and the lower-level planning model are constructed according to the objective function of the park planning, and further include:

[0080] The lower-level planning model is based on the running cost C op Minimization and maximization of the primary energy utilization efficiency F in all periods of operation are taken as the objective function;

[0081] The lower-level operating cost indicators include operating and maintenance costs C OM 、Electricity transaction cost C Trade , natural gas fuel cost C Gas and carbon tax

[0082]

[0083] in:

[0084]

[0085]

[0086] in, is the unit maintenance cost of type i energy conversion equipment; P ik , t is the input power of the kth type i energy conversion device in period t; is the unit maintenance cost of type k renewable energy equipment; P lk,t is the output power of the kth renewable energy device of type l in period t; C t is the electricity price in time period t; C g is the natural gas price; C c is the carbon tax price; δ e is the carbon emission factor of electricity; δ g is the carbon emission factor of natural gas; P tg Input electric power to the regional power grid; P g The gas purchasing power of the park; v LHV It is the lower calorific value of natural gas combustion.

[0087] In this embodiment, the upper-level planning model and the lower-level planning model are constructed according to the objective function of the park planning, and further include:

[0088] The lower efficiency index takes the full-time operation efficiency of primary energy as the objective function. Based on the electric load, cooling load, heating load and input transformer power in the t period, the objective function of calculating the efficiency index is as follows:

[0089]

[0090] S t =P tg / η e η g +P w +P g +P gas (14)

[0091] Among them, F is the energy utilization rate; T is the simulation period; L t is the total load in time period t; is the electrical load; is the heat load; is the cooling load; S t is the total power input into the integrated energy system; P w P is the power of RIES input to the wind turbine; Gas is the calorific value of the input natural gas; η e is the average power generation efficiency of the power plant; η g is the average transmission efficiency of the power plant.

[0092] In this embodiment, the establishing of the power balance constraint condition includes:

[0093] Establish the electric load power balance constraint:

[0094]

[0095] Among them, P j,t is the total electrical load; P g,t The power output from the power grid to the park; are the output powers of the cth CCHP and the wth wind turbine at time t respectively; and are the power consumption of the e-th electric refrigerator, the g-th gas boiler and the b-th electric boiler respectively; J is the set of all nodes in the power system; Cj, Wj, Ej, Gj and Bj are the sets of CCHP, fans, electric refrigerators, gas boilers and electric boilers connected to the grid node j respectively.

[0096] In this embodiment, the establishing of the power balance constraint condition includes:

[0097] Establish heat load power balance constraints:

[0098] Total heat load It is expressed as:

[0099]

[0100] Among them, T c,t Provides heat for CCHP c; T b,t Provide heat for electric boiler b; T g,t g is the heat supply of gas boiler; C means the number of CCHP heating equipment; B means the number of electric boilers; H means the number of gas boilers.

[0101] In this embodiment, the establishing of the power balance constraint condition includes:

[0102] Establish cooling load power balance constraints:

[0103] Total cooling load demand It is expressed as:

[0104]

[0105] Among them, F c,t Cooling capacity of CCHP c; F e,t e is the cooling capacity of the electric refrigeration machine; H means the number of CCHP cooling equipment; I means the number of electric refrigeration machines.

[0106] In this embodiment, the establishing of the power balance constraint condition includes:

[0107] Establish upper and lower limit constraints for each device operation:

[0108]

[0109] in, is the running state variable of device w; is the total power of the integrated energy system input to the device w; Enter the total power of the integrated energy system for minimum and maximum.

[0110] In this embodiment, solving the upper-level planning model and the lower-level planning model includes:

[0111] The upper model is solved by genetic algorithm and the Pareto optimal planning scheme set is passed to the lower model. The lower model is used to verify the tolerance of the Pareto optimal planning scheme set to wind power and load uncertainties. The constraints of the upper model are modified according to the expected value of the primary energy utilization efficiency of the lower model throughout the entire period, thereby passing the impact of wind power and load uncertainties to the upper model and solving it by quantum evolution algorithm.

[0112] In this embodiment, the distributed energy supply equipment of the integrated energy system and the construction site selection of the energy supply equipment are planned according to the solution results, including:

[0113] According to the solution results, plan the distributed energy supply equipment of the integrated energy system, including the selection and configuration capacity of the combined heat and power units, electric refrigerators, and gas boilers;

[0114] The construction site of the energy supply equipment is selected based on the solution results.

[0115] Specifically, according to the solution results, determine the wind turbine, cooling load, heating load and electric load data of the current park plan; compare the wind turbine, cooling load, heating load and electric load data of the current park plan with each scenario group of the same scenario feature data in the operating scenario set to determine the multiple scenario groups to which the current park plan belongs; determine the intersection of the multiple scenario groups to which the current park plan belongs; and plan the distributed energy supply equipment and construction site of the energy supply equipment of the integrated energy system based on the cost data of each scene in the intersection.

[0116] Specifically, the wind turbine, cooling load, heating load and electric load data of the current park planning are compared with each scene group of the same scene feature data in the operating scenario set to determine the multiple scene groups to which the current park planning belongs, including: determining the central data of each scene group of each scene feature data in the operating scenario set; based on the same scene feature data, comparing the scene feature data of the current park planning with the central data of each scene group of the same scene feature data in the operating scenario set, and determining the scene group to which the central data with the highest similarity belongs as the scene group to which the current park planning belongs; and determining the multiple scene groups to which the current park planning belongs based on each scene feature data.

[0117] For example, the wind power scenario characteristic data of the current park plan is compared with each scenario group of the wind power scenario characteristic data in the operating scenario set to determine the scenario group that is closest to the wind power scenario characteristic data of the current park plan; the cold load scenario characteristic data of the current park plan is compared with each scenario group of the cold load scenario characteristic data in the operating scenario set to determine the scenario group that is closest to the cold load scenario characteristic data of the current park plan; the heat load scenario characteristic data of the current park plan is compared with each scenario group of the heat load scenario characteristic data in the operating scenario set to determine the scenario group that is closest to the heat load scenario characteristic data of the current park plan; and so on, each scenario characteristic data of the current park plan is compared with each scenario group of the same scenario characteristic data in the operating scenario set to determine the multiple scenario groups to which the current park plan belongs. Among them, to determine the scene group that is closest to the same scene feature data of the current park planning, a distance calculation method can be used. Under the same scene feature data, the distance between the data of the current park planning and the corresponding data of each scene is calculated, and the distance between the corresponding data of all scenes in each scene group and the current park planning data is summed up. The scene group with the smallest distance sum is determined as the scene group that is closest to the same scene feature data of the current park planning. Among them, when calculating the distance of two-dimensional or multi-dimensional scene feature data, the Euclidean distance calculation method can be used. According to the above method, multiple scene groups to which the current park planning belongs are determined.

[0118] Determine the central data of each scene cluster for each scene feature data in the running scene set, and the process is described as follows. Under the first scene feature data, the running scene set is divided into M1 scene clusters, each scene cluster includes at least one scene, and select a data representing the scene cluster from the first scene feature data of each scene in the same scene cluster as the central data of the scene cluster, or select the average or median of the first scene feature data of each scene in the scene cluster as the central data of the scene cluster. According to the above method, determine the central data of each scene cluster for each scene feature data. When judging data similarity, methods such as Minkowski distance or Euclidean distance can be used.

[0119] The present invention uses a reduction algorithm to obtain a suitable number of typical scenarios, and based on the scenario feature data, determines the scenarios that are closer to the current park planning, realizes further screening of the model solution data, helps to achieve more sophisticated planning and design, helps to plan the construction site selection of distributed energy supply equipment and energy supply equipment in the integrated energy system, improves the efficiency of multi-energy planning, and considers typical operation scenarios of source-load uncertainty. It can not only improve the penetration rate of wind power in the integrated energy system, but also ensure the economy and power supply reliability of wind power in the long-term planning process. The present invention can not only achieve the purpose of higher economic benefits of the integrated energy system, but also effectively improve the economy and flexibility of the integrated energy system. The energy-related coupling and interconnection of the park integrated energy system, the planning, selection and configuration results of the system can meet the requirements of safety and economy in each complex scenario involved in its operation, and the overall planning result of the system is more economical.

[0120] Second, as Figure 2 As shown, the present invention provides a comprehensive energy system collaborative planning device taking uncertainty factors into account, comprising: a modeling unit, a target unit and a solution unit connected in sequence;

[0121] A modeling unit is used to construct mathematical models for wind turbines, cooling loads, heating loads and electric loads respectively, and to construct an operation scenario set based on the mathematical models; constructing the operation scenario set based on the mathematical models includes: randomly sampling the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and clustering the acquired data to generate scenarios reflecting wind power and loads; each scenario includes wind power scenario feature data, various load scenario feature data, and corresponding cost data; clustering the feature data of each scenario in the operation scenario set respectively to obtain multiple data groups for each scenario feature data; classifying the scenarios according to the corresponding relationship between the scene feature data and the scenarios in the data group to obtain multiple scenario groups corresponding to each scene feature data;

[0122] The target unit is used to construct the upper-level planning model and the lower-level planning model according to the objective function of the park planning, and to establish power balance constraints; the objective function of the upper-level planning model is to minimize the annual comprehensive cost; the objective function of the lower-level planning model is to minimize the operating cost and maximize the utilization efficiency of primary energy throughout the entire period;

[0123] The planning unit is used to solve the upper-level planning model and the lower-level planning model based on the data of the operating scenario set, and determine the wind turbine group, cooling load, heating load and electric load data of the current park plan according to the solution results; compare the wind turbine group, cooling load, heating load and electric load data of the current park plan with each scenario group of the same scenario feature data in the operating scenario set to determine the multiple scenario groups to which the current park plan belongs; determine the intersection of the multiple scenario groups to which the current park plan belongs; and plan the distributed energy supply equipment and construction site selection of the energy supply equipment of the comprehensive energy system according to the cost data of each scenario in the intersection.

[0124] In specific implementation, the implementation process of the integrated energy system collaborative planning device taking into account uncertain factors and the integrated energy system collaborative planning method taking into account uncertain factors of the present invention correspond to each other, and the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, which will not be repeated here.

[0125] In a third aspect, the present invention provides an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0126] Memory, used to store computer programs;

[0127] The processor is used to implement the above-mentioned comprehensive energy system collaborative planning method taking uncertainty factors into account when executing the program stored in the memory.

[0128] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for collaborative planning of an integrated energy system taking into account uncertain factors.

[0129] In order to enable those skilled in the art to better understand the present invention, the present invention is described as follows in conjunction with the accompanying drawings:

[0130] In order to improve the energy allocation efficiency of the integrated energy system with a high proportion of renewable energy access, the present invention proposes a collaborative two-level planning model for the integrated energy system that takes into account the uncertainty of wind power and load. The upper model is a multi-objective planning model with the annual cost of construction investment and operating cost as the target, which is solved by genetic algorithm and the Pareto optimal planning scheme set is passed to the lower layer; the lower model is a multi-scenario verification model with the maximum efficiency of primary energy in all periods as the target, which is used to verify the tolerance of the Pareto optimal planning scheme set for wind power and load uncertainty, and modify the constraints of the upper model according to the expected value of the primary energy efficiency in all periods of the lower model, so as to pass the influence of wind power and load uncertainty to the upper model, and solve it by quantum evolution algorithm. The simulation example results show that the method can obtain a more economically efficient collaborative planning scheme on the basis of considering uncertainty factors, effectively improving the economy and flexibility of the integrated energy system.

[0131] The present invention proposes a collaborative two-level planning model for an integrated energy system that takes into account the uncertainty of wind power and load. The upper model is a multi-objective planning model with the goal of minimizing the annual cost of construction investment and operating costs. It is solved by a genetic algorithm and the optimal planning scheme set is passed to the lower layer; the lower model is a multi-scenario verification model with the goal of maximizing the full-time operation efficiency of primary energy. It is used to verify the tolerance of the optimal planning scheme set to wind power and load uncertainties, and modify the constraints of the upper model according to the expected value of the full-time operation efficiency of primary energy of the lower model, so as to pass the influence of wind power and load uncertainties to the upper model, and solve it by a quantum evolutionary algorithm. The effectiveness of this method is verified by taking an actual microgrid in a certain park as an example.

[0132] The uncertainty of wind power and load studied in this invention is mainly reflected in the influence of wind speed on wind farm output and the random fluctuation of load demand. The probability distribution model of wind power output and load can be constructed by parameter estimation using historical wind speed and load data, and then Monte Carlo sampling is performed on the probability distribution model of wind power and load to generate random scenarios reflecting the uncertainty of wind power and load. Too many random scenarios will make it difficult to solve the model, so the random scenarios are clustered based on the k-means clustering algorithm to obtain typical scenarios that can reflect the uncertainty of wind power and load, which are used to verify the uncertainty of the planning scheme.

[0133] The wind turbine model is as follows:

[0134] The wind turbine of the present invention has a wind speed of two-parameter Weibull distribution within a certain period of time, and its probability density function is:

[0135]

[0136] For wind turbines, the output power of the wind turbine and the wind turbine satisfy the following relationship:

[0137]

[0138] Where v represents the actual wind speed; c and k represent the scale parameter and shape parameter respectively; r is the fan radius; ρ is the air density; P w (v) is the output power of the fan; P r is the rated power of the fan; g(x) is the calculation expression; v r Indicates rated wind speed; v in Indicates the cut-in wind speed; v out Indicates the cut-out wind speed.

[0139] The probability distribution model of cold, hot and electric loads is as follows:

[0140] The cold, hot and electric loads obey the normal distribution, so the probability distribution of the load can be expressed as:

[0141]

[0142] in, is the probability density function; is the load power, i=e / h / c, which is represented by the electric load, thermal load and cooling load power respectively; μ is the mean of the random variable; σ is the variance of the random variable, and its value can be obtained by parameter estimation based on historical load data.

[0143] A typical set of operating scenarios is calculated as follows:

[0144] System state sampling is a common method for quantitatively representing system uncertainty factors. Monte Carlo simulation has been widely used in system state sampling due to its good flexibility and reliability. The method for wind power uncertainty simulation is as follows:

[0145] The first step is to obtain the probability density and probability distribution function of wind power output based on the historical wind farm output.

[0146] The second step is to construct an N-dimensional Copula function and solve the Copula function correlation coefficient.

[0147] The third step is to perform Monte Carlo sampling to generate a large number of correlated random values, and then invert the random values ​​to obtain the simulated scenario data of wind power.

[0148] In the fourth step, the load scenario simulation method is similar, except that joint probability distribution modeling is not required.

[0149] The Monte Carlo sampling method is used to sample the system states, which generates a large number of random scenarios. This makes the planning model difficult to solve and the amount of calculation is too large. Therefore, the k-means clustering algorithm is used to perform cluster analysis on the acquired data to obtain typical scenarios that reflect the uncertainty of wind power and load. This can fully reflect the uncertainty of wind power and load and significantly improve the solution efficiency.

[0150] The objective function is as follows:

[0151] Upper level planning model

[0152] The objective function of the upper-level planning model is to minimize the annual comprehensive cost. The decision variables are the installation type and quantity of energy equipment, considering the investment cost C inv and operating cost C op The upper objective function value is as follows:

[0153] minC=C inv +C op (5)

[0154] Among them, C inv is the equivalent annual investment cost of all equipment; C op is the operating cost of the system on a typical day.

[0155]

[0156] Among them, C ω is the unit investment cost of the equipment; R ω is the construction capacity of the equipment ω, and the specific equipment includes the combined cooling, heating and power device CCHP, the electric refrigerator EC, and the gas boiler GB.

[0157] Lower level planning model

[0158] The lower-level planning model aims to optimize the coordinated operation of energy devices within the energy internet in a typical daytime park, with an operating cost of C op The goal is to minimize and maximize the primary energy utilization efficiency F throughout the entire period of operation.

[0159] The lower-level operating cost indicator is composed of the operating and maintenance cost C OM 、Electricity transaction cost C Trade , natural gas fuel cost C Gas , Carbon tax composition.

[0160]

[0161] in, is the unit maintenance cost of type i energy conversion equipment; P ik,t is the input power of the k-th type i energy conversion device in period t; is the unit maintenance cost of type k renewable energy equipment; P lk,t is the output power of the kth renewable energy device of type l in period t; C t is the electricity price in time period t; C g is the natural gas price; C c is the carbon tax price; δ e is the carbon emission factor of electricity; δ g is the carbon emission factor of natural gas; P tg Input electric power to the regional power grid; P g The gas purchasing power of the park; v LHV It is the lower calorific value of natural gas combustion.

[0162] The lower efficiency index takes the full-time operation efficiency of primary energy as the objective function, taking into account the electrical load, cooling load, heating load and input transformer power in period t. The objective function for calculating the efficiency index is as follows:

[0163]

[0164] Among them, F is the energy utilization rate; T is the simulation period; L t is the total load in time period t; is the electrical load; is the heat load; is the cooling load; S t is the total power input into the integrated energy system; P w P is the power of RIES input to the wind turbine; Gas is the calorific value of the input natural gas; η e is the average power generation efficiency of the power plant; η g is the average transmission efficiency of the power plant.

[0165] The constraints are as follows:

[0166] Power balance constraints

[0167] 1. Electrical load

[0168]

[0169] Among them, P j,t is the total electrical load; P g,t The power output from the power grid to the park; are the output powers of the cth CCHP and the wth wind turbine at time t respectively; and are the power consumption of the e-th electric refrigerator, the g-th gas boiler and the b-th electric boiler respectively; J is the set of all nodes in the power system; Cj, Wj, Ej, Gj and Bj are the sets of CCHP, fans, electric refrigerators, gas boilers and electric boilers connected to the grid node j respectively.

[0170] 2. Total heat load It can be expressed as:

[0171]

[0172] Among them, T c,t Provides heat for CCHP c; T b,t Provide heat for electric boiler b; T g,t g is the heat supply of gas boiler; C means the number of CCHP heating equipment; B means the number of electric boilers; H means the number of gas boilers.

[0173] 3. Total cooling load demand It can be expressed as:

[0174]

[0175] Among them, F c,t Cooling capacity of CCHP c; F e,t e is the cooling capacity of the electric refrigeration machine; H means the number of CCHP cooling equipment; I means the number of electric refrigeration machines.

[0176] The upper and lower limits of each device are as follows:

[0177]

[0178] in, is the running state variable of device w; is the total power of the integrated energy system input to the device w; Enter the total power of the integrated energy system for minimum and maximum.

[0179] The solution of the multi-objective programming model is as follows:

[0180] The construction part of the multi-objective planning model proposed in the present invention includes the selection and configuration capacity of distributed energy supply equipment, the operation part includes the typical electric heating and cooling load balance in three seasons, and the system power supply reliability will be reflected by converting it into energy utilization rate. Therefore, the solution idea of ​​the present invention is that the upper model is solved by genetic algorithm, and the Pareto optimal planning scheme set is passed to the lower layer; the lower model is used to verify the ability of the Pareto optimal planning scheme set to withstand wind power and load uncertainties, and the constraints of the upper model are modified according to the expected value of the primary energy utilization efficiency of the lower model during the entire period of operation, so as to pass the influence of wind power and load uncertainty to the upper model, and use the quantum evolutionary algorithm (qunantum-inspired evolutionary algorithm) to solve it. The solution process is as follows: Figure 3 shown.

[0181] The multi-objective collaborative planning of the integrated energy system is as follows:

[0182] The present invention proposes a distributed energy supply collaborative planning method for an integrated energy system taking into account the uncertainty factor of wind power output, such as Figure 4 First, the data of the park's heat load, cold load and electricity load are obtained, and a model is proposed; then, based on the proposed model, the distributed energy supply equipment of the integrated energy system is planned, including the selection and configuration capacity of the combined heat and power units, electric refrigeration units, and gas boilers; finally, the construction site of the energy supply equipment is selected based on the collaborative planning results.

[0183] This invention takes a real project in a certain park as an example. Figure 5 As shown, the natural gas price is 3.3 yuan / m 3 , v LHV The low calorific value of natural gas combustion is 9.73 (kW·h) / m 3 , δ e 0.7921kgCO 2 / kWh, natural gas 2.162kgCO 2 / m 3 , the carbon tax price is 60 yuan / ton, the average power generation efficiency of the power plant is 0.65, the average transmission efficiency of the power plant is 0.94, the probability of a typical day in spring and autumn is 0.5, and the probability of a typical day in summer and winter is 0.25. The relevant parameters of the energy conversion equipment are shown in Table 1, the relevant parameters of the renewable energy equipment are shown in Table 2, and the wind power curve is shown in Figure 6 The typical daily load curve in spring and autumn is shown in Figure 7 The typical daily load curve in summer is shown as Figure 8 The typical daily load curve in winter is shown as Fig. 9 shown.

[0184] Tab.1 Related parameters of the energy conversion equipment

[0185]

[0186]

[0187] Tab.2Related parameters of the renewable energy equipment

[0188] Renewable energy equipment Capacity(kW) Investment cost (yuan / kW) Operation and maintenance cost (yuan / kW) Lifespan (years) Failure probability Fan 1500 7000 0.02 20 0.01

[0189] Simulation results:

[0190] Integrated energy system planning for uncertain load scenarios

[0191] QEA is a kind of random optimization algorithm, and the results of each operation of the algorithm are not necessarily consistent. Therefore, in order to avoid the occurrence of accidental factors, the present invention runs the algorithm 10 times. The experimental results are as follows:

[0192] When the lower-level goal only considers the operation and maintenance costs, the operation results are shown in Table 3:

[0193] Tab.3 Consider only operational maintenance costs

[0194]

[0195] At this time, the change curves of each target are as follows Fig.10 shown.

[0196] When the lower-level goal only considers energy efficiency, the operating results are shown in Table 4:

[0197] Tab.4When considering energy efficiency only

[0198]

[0199] At this time, the change curves of each target are as follows Fig.11 As shown:

[0200] When the lower-level goal considers both operating cost and energy efficiency, the operating result is a solution set, so it cannot be quantitatively analyzed using a table. The target iteration scatter plot is as follows: Fig.12 shown.

[0201] At this time, the upper-level objectives in the solution set are shown in Table 5:

[0202] Tab.5 When considering both operating costs and energy efficiency

[0203] Operation and maintenance costs 84173684 Electricity trading costs 307537463 Natural gas fuel costs 226765776 Carbon tax 307537463 Total investment cost 1166507888

[0204] 4.2.2 Parameter Comparison Analysis

[0205] The quantum rotation angle in QEA has a great influence on the convergence speed and convergence accuracy of the algorithm. Therefore, in order to analyze the influence of the rotation angle on the algorithm, four rotation angles of 0.02*pi, 0.06*pi, 0.1*pi, and 0.2*pi are set. The comparative experimental results are shown in Table 6:

[0206] Tab.6 Contrast the results

[0207]

[0208] It can be seen from Table 6 that as the quantum rotation angle in QEA increases, the optimal values ​​of investment cost, operating cost and energy utilization become larger, the algorithm converges faster and the convergence accuracy becomes more accurate.

[0209] 4.2.3 Comparative Analysis of Collaborative Planning

[0210] Solution 1: Integrated energy system collaborative planning scheme for deterministic load scenarios.

[0211] Scheme 2: A coordinated planning scheme for an integrated energy system that takes into account source-load uncertainty factors.

[0212] The collaborative planning results are shown in Table 7.

[0213] Tab.7 Collaborative planning and comparison results

[0214] Comparison Items Solution 1 Solution 2 Investment cost 8945406256 5083003883 Running costs 4378677795 1795505556 Energy efficiency 0.2788 0.39925

[0215] The following conclusions were drawn from the collaborative planning results: As shown in Table 7, the total planning, construction and operation costs of Scheme 1 are relatively high, and the planning results are relatively conservative. Scheme 2 is more economical because it takes into account the uncertainty of wind power output. Each complex scenario involved in the operation of the system meets the requirements of economy and safety. The power supply reliability of the system can be reflected by the energy utilization rate. Compared with Scheme 1, the energy utilization rate of the collaborative planning results of Scheme 2 has improved, indicating that the power supply reliability of Scheme 2 is stronger.

[0216] Aiming at the problem of low energy allocation efficiency of high-proportion wind power access integrated energy system, this paper proposes a coordinated two-level planning model for integrated energy system considering wind power and load uncertainty. The following conclusions are drawn through example simulation:

[0217] The timing characteristics of distributed power sources are highly random, which will make it difficult to solve the problem in the coordinated planning of integrated energy systems due to the huge amount of calculations. The k-means clustering algorithm is used to obtain a suitable number of typical scenarios, which can improve the efficiency of solving planning problems. By establishing typical operating scenarios that take into account the uncertainty of wind power and load, it can not only increase the penetration rate of wind power in the integrated energy system, but also ensure the economy and power supply reliability of wind power in the long-term planning process.

[0218] The present invention proposes a coordinated two-level planning model for an integrated energy system that takes into account wind power and load uncertainty, which can not only achieve a higher economic benefit for the integrated energy system, but also effectively improve the economy and flexibility of the integrated energy system.

[0219] The timing characteristics of distributed power sources are highly random, and in the collaborative planning of integrated energy systems, the huge amount of calculations will lead to difficulties in solving. The present invention adopts a simplification algorithm to obtain an appropriate number of typical scenarios, which can improve the efficiency of solving planning problems. By considering typical operating scenarios with source-load uncertainty, not only can the penetration rate of wind power in the integrated energy system be improved, but also the economy and power supply reliability of wind power in the long-term planning process are guaranteed. The present invention can not only achieve the goal of higher economic benefits for the integrated energy system, but also effectively improve the economy and flexibility of the integrated energy system. The energy-related coupling and interconnection of the park integrated energy system, the planning, selection and configuration results of the system can meet the requirements of safety and economy in each complex scenario involved in its operation, and the overall planning results of the system are more economical.

[0220] In order to improve the energy allocation efficiency of the integrated energy system with a high proportion of renewable energy access, the present invention proposes a collaborative two-level planning model for the integrated energy system that takes into account the uncertainty of wind power and load. The upper model is a multi-objective planning model with the annual cost of construction investment and operating cost as the target, which is solved by genetic algorithm and the Pareto optimal planning scheme set is passed to the lower layer; the lower model is a multi-scenario verification model with the maximum efficiency of primary energy in all periods as the target, which is used to verify the tolerance of the Pareto optimal planning scheme set for wind power and load uncertainty, and modify the constraints of the upper model according to the expected value of the primary energy efficiency in all periods of the lower model, so as to pass the influence of wind power and load uncertainty to the upper model, and solve it by quantum evolution algorithm. The simulation example results show that the method can obtain a more economically efficient collaborative planning scheme on the basis of considering uncertainty factors, effectively improving the economy and flexibility of the integrated energy system.

[0221] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A collaborative planning method for an integrated energy system taking uncertainty factors into account, characterized in that: The method comprises: Mathematical models are constructed for wind turbines, cooling loads, heating loads and electric loads respectively, and an operation scenario set is constructed based on the mathematical models; the operation scenario set is constructed based on the mathematical models, including: randomly sampling the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and clustering the acquired data to generate scenarios reflecting wind power and loads; each scenario includes wind power scenario characteristic data, various load scenario characteristic data, and corresponding cost data; Clustering the characteristic data of each scenario in the running scenario set respectively to obtain multiple data clusters of the characteristic data of each scenario; Classify the scenes according to the correspondence between the scene feature data and the scenes in the data group, and obtain multiple scene groups corresponding to each scene feature data; According to the objective function of the park planning, the upper-level planning model and the lower-level planning model are constructed respectively, and the power balance constraint conditions are established; the objective function of the upper-level planning model is to minimize the annual comprehensive cost; the objective function of the lower-level planning model is to minimize the operating cost and maximize the utilization efficiency of primary energy throughout the entire period; Based on the data of the operation scenario set, the upper-level planning model and the lower-level planning model are solved, and according to the solution results, the wind turbines, cooling load, heating load and electric load data of the current park planning are determined; Compare the wind turbines, cooling load, heating load and electric load data of the current park planning with each scene group of the same scene feature data in the operation scene set to determine the multiple scene groups to which the current park planning belongs; Determine the intersection of multiple scenario groups to which the current park planning belongs; Based on the cost data of each scenario in the intersection, the distributed energy supply equipment of the integrated energy system and the construction site selection of the energy supply equipment are planned.

2. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The mathematical models for the wind turbine, cooling load, heating load and electrical load are constructed respectively, including: The historical wind speed and load data are used to construct the probability distribution model of wind turbines, cooling load, heating load and electrical load through parameter estimation.

3. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 2, characterized in that: The method of constructing a probability distribution model of a wind turbine generator set by parameter estimation using historical wind speed and load data includes: The wind speed adopts a two-parameter Weibull distribution, and its probability density function is: The probability distribution model of the wind turbine is constructed by parameter estimation based on historical wind speed and load data. The output power of the wind turbine and the wind turbine satisfy the following relationship: in, Where v represents the actual wind speed; c and k represent the scale parameter and shape parameter respectively; r is the fan radius; ρ is the air density; P w (v) is the output power of the fan; P r is the rated power of the fan; v r Indicates rated wind speed; v in Indicates the cut-in wind speed; v out Indicates the cut-out wind speed; The parameters of the wind turbine model are estimated using historical wind speed data.

4. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 2, characterized in that: The probability distribution model for estimating cooling load, heating load and electric load by parameters using historical wind speed and load data also includes: The cold, hot and electric loads obey the normal distribution, and the probability distribution of the loads is expressed as: in, is the probability density function; is the load power, i = e / h / c, which is represented by the power of electric load, heat load and cooling load respectively; μ is the mean of the random variable; σ is the variance of the random variable, The probability distribution model of cooling load, heating load and electrical load is estimated based on historical load data to obtain the parameter values.

5. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The random sampling of mathematical models of wind turbines, cooling loads, heating loads and electrical loads includes: Monte Carlo sampling is performed on the mathematical models of wind turbines, cooling loads, heating loads and electrical loads to generate scenarios reflecting wind power and loads.

6. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The mathematical models of wind turbines, cooling loads, heating loads and electrical loads are randomly sampled, and the acquired data are clustered to generate scenes reflecting wind power and loads, including: Monte Carlo sampling is performed on the mathematical models of wind turbines, cooling loads, heating loads and electrical loads, and the acquired data is clustered to obtain a plurality of wind power scenario characteristic data and various types of load scenario characteristic data; based on the plurality of wind power scenario characteristic data and various types of load scenario characteristic data, a scene reflecting wind power and load is generated.

7. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 6, characterized in that: Monte Carlo sampling is performed on the mathematical model of the wind turbine, and the acquired data is clustered to obtain multiple wind power scene feature data, including: The scenario of wind turbines is obtained by: The probability density and probability distribution function of wind power output are obtained based on the historical wind farm output. Construct an N-dimensional Copula function and solve the Copula function correlation coefficient. Perform Monte Carlo sampling to generate correlated random values; Invert the random value to obtain the simulated scenario data of wind power; The wind power simulation scene data is clustered using a k-means clustering algorithm to obtain a plurality of wind power scene feature data.

8. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 6, characterized in that: Monte Carlo sampling is performed on the mathematical models of cooling load, heating load and electrical load, and the acquired data is clustered to obtain multiple characteristic data of various load scenarios, including: The scenarios of cooling load, heating load and electrical load are obtained by: According to the historical data of various loads, the probability density and probability distribution function of various loads are obtained, and Monte Carlo sampling is performed to generate random values ​​with correlation; Invert the random value to obtain the simulated scenario data of the load; The simulated scene data of the load is clustered using a k-means clustering algorithm to obtain multiple types of load scene feature data.

9. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: According to the objective function of the park planning, the upper planning model and the lower planning model are constructed respectively, including: The objective function of the upper-level planning model is to minimize the annual comprehensive cost C. The objective function value of the upper-level planning model is shown in the following formula: minC=C inv +C op (5) Among them, C inv is the equivalent annual investment cost of all equipment; C op is the operating cost of the system on a typical day; Among them, C ω is the unit investment cost of the equipment; R ω is the construction capacity of the equipment ω, and the specific equipment includes the combined cooling, heating and power device CCHP, the electric refrigerator EC, and the gas boiler GB.

10. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 9, characterized in that: The upper-level planning model and the lower-level planning model are constructed according to the objective function of the park planning, and further include: The lower-level planning model is based on the running cost C op Minimization and maximization of the primary energy utilization efficiency F in all periods of operation are taken as the objective function; The operating cost indicators of the lower-level planning model include the operating and maintenance cost C OM 、Electricity transaction cost C Trade , natural gas fuel cost C Gas and carbon tax in: in, is the unit maintenance cost of type i energy conversion equipment; P ik,t is the input power of the k-th type i energy conversion device in period t; is the unit maintenance cost of type k renewable energy equipment; P lk,t is the output power of the kth renewable energy device of type l in period t; C t is the electricity price in time period t; C g is the natural gas price; C c is the carbon tax price; δ e is the carbon emission factor of electricity; δ g is the carbon emission factor of natural gas; P tg Input electric power to the regional power grid; P g The gas purchasing power of the park; v LHV It is the lower calorific value of natural gas combustion.

11. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 10, characterized in that: The upper-level planning model and the lower-level planning model are constructed according to the objective function of the park planning, and further include: The efficiency index of the lower-level planning model takes the full-time operation efficiency of primary energy as the objective function. Based on the electric load, cooling load, heating load and input transformer power in the t period, the objective function for calculating the efficiency index is as follows: S t JP tg / η e η g +P w +P g +P gas (14) Among them, F is the energy utilization rate; T is the simulation period; L t is the total load in time period t; is the electrical load; is the heat load; is the cooling load; S t is the total power input into the integrated energy system; P w is the power of the fan input RIES; Pgas is the calorific value of the input natural gas; η e is the average power generation efficiency of the power plant; η g is the average transmission efficiency of the power plant.

12. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The establishing of the power balance constraint condition comprises: Establish the electric load power balance constraint: Among them, P j,t is the total electrical load; P g,t The power output from the power grid to the park; are the output powers of the Cth CCHP and the Wth wind turbine at time t respectively; and are the power consumption of the e-th electric refrigerator, the g-th gas boiler and the b-th electric boiler respectively; J is the set of all nodes in the power system; Cj, Wj, Ej, Gj and Bj are the sets of CCHP, fans, electric refrigerators, gas boilers and electric boilers connected to the grid node j respectively.

13. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The establishing of the power balance constraint condition comprises: Establish heat load power balance constraints: Total heat load It is expressed as: Among them, T c,t Provides heat for CCHP c; T b,t Provide heat for electric boiler b; T g,t g is the heat supply of gas boiler; C means the number of CCHP heating equipment; B means the number of electric boilers; H means the number of gas boilers.

14. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The establishing of the power balance constraint condition comprises: Establish cooling load power balance constraints: Total cooling load demand It is expressed as: Wherein, Fc,t is the cooling capacity of CCHP c; Fe,t is the cooling capacity of electric refrigerator e; H means the number of CCHP cooling equipment; I means the number of electric refrigerators.

15. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The establishing of the power balance constraint condition comprises: Establish upper and lower limit constraints for each device operation: in, is the running state variable of device w; is the total power of the integrated energy system input to the device w; Enter the total power of the integrated energy system for minimum and maximum.

16. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to claim 1, characterized in that: The solving of the upper-level planning model and the lower-level planning model includes: The upper model is solved using a genetic algorithm and the set of Pareto optimal planning solutions is passed to the lower layer; The lower model is solved by quantum evolutionary algorithm. The lower model is used to verify the ability of the Pareto optimal planning scheme set to withstand wind power and load. The constraints of the upper model are modified according to the expected value of the primary energy utilization efficiency of the lower model throughout the entire period of operation, and the impact of wind power and load is passed to the upper model.

17. The method for collaborative planning of an integrated energy system taking uncertainty factors into account according to any one of claims 1 to 16, characterized in that: Compare the wind turbines, cooling load, heating load and electric load data of the current park planning with each scene group of the same scene feature data in the operation scene set to determine the multiple scene groups to which the current park planning belongs, including: Determine the central data of each scene cluster of each scene characteristic data in the running scene set; Based on the same scene feature data, the scene feature data of the current park planning is compared with the central data of each scene group of the same scene feature data in the running scene set, and the scene group to which the central data with the highest similarity belongs is determined as the scene group to which the current park planning belongs; Based on the characteristic data of each scenario, multiple scenario groups to which the current park planning belongs are determined.

18. A device for collaborative planning of an integrated energy system taking into account uncertain factors, characterized in that: include: Modeling units, target units and solution units connected in sequence; A modeling unit, used to construct mathematical models for wind turbines, cooling loads, heating loads and electrical loads respectively, and to construct an operation scenario set based on the mathematical models; Constructing an operation scenario set based on a mathematical model, including: randomly sampling the mathematical models of wind turbines, cooling loads, heating loads and electric loads, and clustering the acquired data to generate scenarios reflecting wind power and loads; each scenario includes wind power scenario characteristic data, various load scenario characteristic data, and corresponding cost data; clustering the characteristic data of each scenario in the operation scenario set to obtain multiple data groups of each scenario characteristic data; classifying the scenarios according to the corresponding relationship between the scenario characteristic data and the scenarios in the data group to obtain multiple scenario groups corresponding to each scenario characteristic data; The target unit is used to construct the upper-level planning model and the lower-level planning model according to the objective function of the park planning, and to establish power balance constraints; the objective function of the upper-level planning model is to minimize the annual comprehensive cost; the objective function of the lower-level planning model is to minimize the operating cost and maximize the utilization efficiency of primary energy throughout the entire period; The planning unit is used to solve the upper-level planning model and the lower-level planning model based on the data of the operating scenario set, and determine the wind turbine group, cooling load, heating load and electric load data of the current park plan according to the solution results; compare the wind turbine group, cooling load, heating load and electric load data of the current park plan with each scenario group of the same scenario feature data in the operating scenario set to determine the multiple scenario groups to which the current park plan belongs; determine the intersection of the multiple scenario groups to which the current park plan belongs; and plan the distributed energy supply equipment and construction site selection of the energy supply equipment of the comprehensive energy system according to the cost data of each scenario in the intersection.

19. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor is used to implement the integrated energy system collaborative planning method taking into account uncertain factors as described in any one of claims 1-17 when executing a program stored in a memory.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for collaborative planning of an integrated energy system taking uncertainty factors into account as described in any one of claims 1-17 is implemented.

Images