A multi-functional park planning method, system, computer device and storage medium

Abstract

The present invention relates to the technical field of power system planning, and discloses a multi-energy park planning method, system, computer equipment and storage medium, including obtaining relevant data of the multi-energy park and performing preprocessing; establishing a multi-energy park planning model based on an energy hub model, and performing calculations to obtain a first planning result of the multi-energy park; using an equipment fault maintenance set to perform fault detection on the first planning result, and judging whether the first planning result has a load shedding exceeding a threshold value under the operation scenario of the equipment fault maintenance set, if not, taking the first planning result as the optimal planning result; if so, adding the operation scenario in which the load shedding exceeding the threshold value occurs as a constraint condition to the multi-energy park planning model, and performing iterative calculations to obtain the optimal planning result of the multi-energy park. The present invention can reduce the construction cost and operation cost of the park while ensuring the utilization efficiency of energy, and improve the safety and stability of the operation of the multi-energy park.

Description

Technical Field

[0001] The present invention relates to the technical field of power system planning, and in particular to a multi-energy park planning method, system, computer equipment and storage medium that consider equipment fault repair sets and energy efficiency levels. Background Art

[0002] Against the backdrop of fossil energy depletion and environmental deterioration, energy conservation and emission reduction have become a hot topic, and new energy sources such as solar energy and wind energy have developed rapidly. However, problems in the consumption and utilization of new energy sources have led to low utilization efficiency at this stage; in addition, other energy system accidents caused by power grid failures have occurred frequently, which exposed the shortcomings of independent planning and operation of traditional energy systems. Against this background, the concept of Energy Internet (EI) was proposed, aiming to couple different forms of energy systems and thereby maximize energy utilization efficiency and promote energy conservation and emission reduction. As the physical carrier of Energy Internet, Integrated Energy System (IES) has developed rapidly, and its planning issues have received widespread attention. Appropriate planning schemes can ensure the efficiency and economy of park operations in the long-term planning period and provide a reference for investors' decision-making behavior. In addition, due to the coupling of various forms of energy systems, IES has also put forward higher and higher requirements and challenges for energy supply reliability. The current planning methods of multi-energy parks mainly focus on the coordinated optimization of investment and operation strategies, lack consideration of system risk management, and do not take into account the issue of energy supply reliability, so they cannot guarantee the stable and reliable operation of multi-energy parks. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a multi-energy park planning method, system, computer equipment and storage medium that considers equipment fault maintenance set and energy efficiency level, which can solve the problem that traditional planning methods do not take energy efficiency and equipment failure into consideration, ensure energy utilization efficiency, and ensure the stable operation of the multi-energy park.

[0004] In a first aspect, the present invention provides a multi-energy park planning method, the method comprising:

[0005] Obtain relevant data of the multi-energy park and pre-process the relevant data, wherein the pre-processing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters;

[0006] Establishing a multi-energy park planning model based on the energy hub model, and calculating the multi-energy park planning model to obtain a first planning result of the multi-energy park;

[0007] Using the generated equipment fault maintenance set to perform fault detection on the first planning result, determining whether the first planning result has load shedding exceeding a threshold under the operation scenario of the equipment fault maintenance set, and if not, using the first planning result as the optimal planning result of the multi-energy park;

[0008] If so, the operating scenario in which the load shedding exceeds the threshold is added as a constraint condition to the multi-energy park planning model, and the multi-energy park planning model is iteratively calculated to obtain the optimal planning result of the multi-energy park.

[0009] Furthermore, the step of obtaining relevant data of the multi-energy park and preprocessing the relevant data includes:

[0010] The k-means clustering method is used to cluster the load parameters of the multi-energy park and obtain the typical daily load curve;

[0011] According to the characteristics of the multi-energy park and the parameters of the equipment to be planned, a set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance is used as an equipment failure maintenance set.

[0012] Furthermore, the step of establishing a multi-energy park planning model based on the energy hub model includes:

[0013] Constructing an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost;

[0014] Adding constraints to the objective function, wherein the constraints include energy supply and demand balance constraints, upper and lower limit constraints on equipment output, and energy efficiency constraints under normal operation scenarios of each device;

[0015] A multi-energy park planning model is established based on the objective function and the constraints.

[0016] Furthermore, the objective function is expressed by the following formula:

[0017] min(f inv (X)+f ope (X,P)

[0018] In the formula, X and P are decision variables, which respectively represent the construction plan of each equipment and the equipment output on each typical day under the given construction plan. inv is the total investment cost of the equipment, f ope The total cost of park operation;

[0019] The energy supply and demand balance constraint is expressed by the following formula:

[0020]

[0021]

[0022]

[0023]

[0024] n∈{0,1,2,...,NC+NR}

[0025] Where L represents the cooling, heating and electricity loads, P represents the output of each device, C represents the coupling matrix, subscript - represents the energy forms of input and output, e, h, c and g represent electricity, heat, cooling and natural gas respectively, subscript n represents different equipment operation scenarios, ε is the maximum load shedding threshold in the fault / maintenance scenario set based on the characteristics of the park, and P n,s,t represents the equipment output of a certain equipment at time t on a typical day s in scenario n, CCHP represents a combined cooling, heating and power unit, GB represents a gas boiler, EC represents an electric refrigeration equipment, NC and NR represent the number of equipment failure scenarios and equipment maintenance scenarios considered, respectively, subscripts i, j, k represent the indexes of CCHP units, gas boilers and electric refrigeration equipment, respectively, and SUB represents a substation;

[0026] The following formula is used to express the upper and lower limit constraints of the equipment output:

[0027]

[0028]

[0029]

[0030]

[0031] In the formula, X represents the construction variable;

[0032] The energy efficiency constraint is expressed by the following formula:

[0033]

[0034]

[0035] Where η0 is the system energy efficiency, is the electrical energy output by the system, Q th is the output heat energy, is the electrical energy input to the system, Q FUEL is the input fuel energy, Q h , Q cThey represent the terminal power demand, heat demand and cooling demand respectively. and Q g They represent the amount of electricity and gas purchased from outside, e level Represents the minimum energy efficiency level specified in the plan.

[0036] Furthermore, the following formula is used to represent the operation scenario in which the load shedding exceeding the threshold occurs:

[0037]

[0038] In the formula, Respectively represent the output column vectors of CCHP, GB, and EC, X CCHP , X GB , X EC are the construction column vectors of CCHP, GB and EC respectively, For all the troubleshooting scenarios in n except the normal operation scenario, Represents equipment fault repair set matrix and fault repair scenario The corresponding column, Scenes, is the number of typical day types.

[0039] In a second aspect, the present invention provides a multi-functional park planning system, the system comprising:

[0040] A data preprocessing module is used to obtain relevant data of the multi-energy park and preprocess the relevant data, wherein the preprocessing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters;

[0041] A planning model building module, used to build a multi-energy park planning model based on the energy hub model, and calculate the multi-energy park planning model to obtain a first planning result of the multi-energy park;

[0042] A first planning calculation module, used to perform fault detection on the first planning result using the generated equipment fault overhaul set, and determine whether the first planning result has a load shedding exceeding a threshold under the operation scenario of the equipment fault overhaul set, and if not, use the first planning result as the optimal planning result of the multi-energy park;

[0043] The second planning calculation module is used to add the operating scenario of load shedding exceeding the threshold as a constraint condition to the multi-energy park planning model, and iteratively calculate the multi-energy park planning model to obtain the optimal planning result of the multi-energy park.

[0044] Furthermore, the data preprocessing module includes:

[0045] The typical day load generation module is used to perform cluster analysis on the load parameters of the multi-energy park using k-means clustering to obtain a typical day load curve;

[0046] The equipment fault maintenance set generation module is used to take the set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance as the equipment fault maintenance set according to the multi-energy park characteristics and the parameters of the equipment to be planned.

[0047] Furthermore, the planning model building module includes:

[0048] An objective function construction module, used to construct an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost;

[0049] A constraint construction module, used to add constraint conditions to the objective function, wherein the constraint conditions include energy supply and demand balance constraints, equipment output upper and lower limit constraints, and energy efficiency constraints under normal operation scenarios of each device;

[0050] The model building module is used to establish a multi-energy park planning model according to the objective function and the constraint conditions.

[0051] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0052] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0053] The present invention provides a multi-energy park planning method, system, computer device and storage medium. Through the method, the energy efficiency concept and equipment fault repair set are introduced into the planning consideration of the multi-energy park, and the park is planned and optimized at a certain energy efficiency level, which ensures the energy utilization efficiency, and through the introduction of the equipment fault repair set, it is ensured that the multi-energy park can still operate normally in an emergency situation of equipment failure, thereby improving the safety and stability of the operation of the multi-energy park. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart of a multi-energy park planning method provided by an embodiment of the present invention;

[0055] Figure 2 yes Figure 1 Schematic diagram of the process of step S10;

[0056] Figure 3 yes Figure 1 Schematic diagram of the process of step S20;

[0057] Figure 4 It is a schematic diagram of a comprehensive energy system based on a combined cooling, heating and power unit;

[0058] Figure 5 It is a block diagram of a two-layer planning method for a multi-energy park considering equipment fault repair set and energy efficiency level provided by the present invention;

[0059] Figure 6 A schematic diagram of the structure of the multi-functional park planning system provided by the present invention;

[0060] Figure 7 It is a diagram of the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] 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.

[0062] See also Figure 1 The first embodiment of the present invention provides a multi-functional park planning method, comprising steps S10 to S40:

[0063] Step S10, obtaining relevant data of the multi-energy park and preprocessing the relevant data, wherein the preprocessing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters.

[0064] The purpose of the present invention is to provide a device selection planning scheme for a multi-energy park including multiple energy forms such as cold, heat, and electricity, wherein the preprocessing of the multi-energy park data used is as follows: Figure 2 As shown:

[0065] Step S101, using k-means clustering to perform cluster analysis on the load parameters of the multi-energy park to obtain a typical daily load curve.

[0066] Step S102: according to the multi-energy park characteristics and the parameters of the equipment to be planned, a set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance is used as an equipment failure maintenance set.

[0067] The multi-energy park data obtained by the present invention mainly include energy prices, parameters related to the equipment to be planned, and load parameters. The local energy price includes the natural gas price required by the energy supply equipment and the time-of-use electricity price of the park; the equipment to be planned includes a combined cooling, heating and power unit (CCHP unit), a gas boiler (GB) and an electric refrigeration equipment (EC), and the corresponding parameters include energy conversion efficiency, construction cost, etc.; since the multi-energy park to be planned has not yet been built and there is no corresponding load data, the load data of the same type of park is used as the basis, and the load estimate of the multi-energy park to be planned is obtained through processing.

[0068] The main data processing of the multi-energy park includes two parts. The first part is the generation of typical load days, that is, the k-means clustering method is used to cluster the existing historical data of cold, hot and electric loads, and obtain the four typical daily load curves of spring, summer, autumn and winter and their proportion in a year, with an interval of one hour, to provide a basis for planning; the second part is the generation of equipment fault maintenance sets. The equipment fault maintenance set is based on the equipment to be selected in the park and is generated according to the needs of decision makers. Each element in the set corresponds to the operation scenario of equipment failure or regular maintenance. For example, the fault set can include scenarios where equipment with a high failure rate is out of operation, and it can also include scenarios where some equipment that requires regular maintenance is out of operation.

[0069] Step S20: establishing a multi-energy park planning model based on the energy hub model, and calculating the multi-energy park planning model to obtain a first planning result of the multi-energy park.

[0070] The multi-energy park targeted by the present invention takes into account various forms of energy such as cold, heat, and electricity, with CCHP units as the main multi-energy equipment. The designed planning method is essentially a two-layer planning model, in which the first layer of optimization is the optimization of the selection and sizing of various multi-energy supply equipment in the system, and the second layer of optimization is the optimization of the operating output of the equipment after selection. In addition, the operation plan takes into account different scenarios within the planning cycle, and maintains energy efficiency above a certain level through constraints. The present invention establishes a multi-energy park planning model based on the energy hub model to meet the requirements of the above-mentioned designed planning method. The model mainly includes two parts: objective function and related constraints. The specific steps are as follows: Figure 3 As shown:

[0071] Step S201, constructing an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost.

[0072] Step S202, adding constraints to the objective function, wherein the constraints include energy supply and demand balance constraints, upper and lower limit constraints on equipment output, and energy efficiency constraints under normal operation scenarios of each device.

[0073] Step S203: establishing a multi-energy park planning model according to the objective function and the constraint conditions.

[0074] First, the objective function is constructed. The present invention takes the lowest total cost of the multi-energy park in the planning period as the core to establish the objective function. The total cost includes the investment and construction cost of the equipment and the cost generated by operation in the planning period. The objective function is as follows:

[0075] min(f inv (X)+f ope (X,P)

[0076] In the formula, X and P are decision variables, which respectively represent the construction plan of each equipment and the equipment output of each typical day under the given construction plan. As mentioned above, the essence of this planning model is a two-layer planning optimization model. The first layer optimizes the construction decision variable X, and the second layer optimizes the operation decision variable P based on X. inv is the total investment cost of the equipment, which is only related to the construction status of each equipment. The equipment to be selected in this plan mainly includes the combined cooling, heating and power unit (CCHP) that uses natural gas as fuel and can simultaneously supply three types of energy: cooling, heating and electricity; the gas boiler (GB) that uses natural gas as fuel and generates heat energy; and the electric refrigeration equipment (EC) that uses electricity as input and outputs cooling. Figure 4 The equipment shown together constitute the park's integrated energy system IES, in which gas turbines, generator sets, waste heat boilers and other equipment together constitute CCHP units. ope It is the total cost of park operation, which is related to the construction of the equipment and the output of the equipment on different typical days, including the cost of purchasing natural gas and electricity.

[0077] Therefore, the total investment cost of the equipment can be expressed by the following formula:

[0078]

[0079]

[0080] Where IC is the construction cost of the equipment, the superscript represents the specific type of equipment to be constructed, and the subscript corresponds to the different types of equipment to be constructed. NC, NG, and NE represent the number of types of CCHP units, gas boilers, and electric refrigeration equipment available for selection, respectively. Subscripts i, j, and k are the indexes of CCHP units, gas boilers, and electric refrigeration equipment, respectively. X is the construction variable of the equipment, 1 corresponds to the construction of the equipment, and 0 corresponds to no construction.

[0081] The total cost of park operation can be expressed as:

[0082]

[0083] Where P s,0,t represents the output of a device at time t in a typical day scenario s. The 0 in the subscript indicates a normal operation scenario, that is, the scenario without considering device failure. s It represents the number of days in a year when typical day s appears. Scenes is the number of typical day types. That is, if typical days are divided into spring, summer, autumn and winter, its value is 4. Of course, it can also be divided by seasons, holidays or working days, which will not be elaborated here.

[0084] m is the capital conversion factor, which converts the cost to the planning year. m is used to convert the operating cost within the planning period to the planning year. They represent the prices of gas and electricity purchased at time t, is the output of substation SUB at time t in scenario s, that is, the amount of electricity purchased from the power grid.

[0085] After obtaining the above objective function, constraints are added to the objective function according to the actual situation of the multi-energy park. The constraints mainly include energy supply and demand balance constraints, upper and lower limit constraints of equipment output, and constraints between operating variables and construction variables of the equipment under a certain equipment failure scenario. The existing planning technology for multi-energy parks mainly focuses on planning for maximum economic efficiency. The planned capacity in the planning results is close to the maximum demand, and energy supply reliability is rarely considered. On the one hand, although the equipment failure rate is low, the losses caused by short-term failures cannot be ignored; on the other hand, the multi-energy system coupling in IES has higher requirements for system reliability, and some equipment needs to be shut down for maintenance regularly. Therefore, the present invention takes equipment failure and maintenance scenarios into consideration in the constraints, so as to obtain a certain amount of energy reserve and greatly improve system reliability. In addition, the degree of reliability conservatism is controlled by decision makers. Decision makers can determine the maximum allowable load shedding in extreme scenarios according to the type of park, and verify the planning scheme in combination with the equipment failure maintenance set proposed by the present invention.

[0086] 1) Energy supply and demand balance constraint: The energy supply and demand balance constraint is to ensure that the different forms of energy demand in the multi-energy park are met, among which the electrical load must meet the equal supply and demand, and the cold and hot output can be greater than or equal to the cold and hot demand, so that a more flexible equipment operation mode can be obtained, thereby obtaining the optimal solution. It should be noted that in the basic planning model, that is, when equipment failure or maintenance is not considered, load shedding shall not occur. In other words, in the basic planning model, all loads can be met when all equipment is operating normally. This planning model uses the Energy Hub model (Energy Hub, EH) to describe the IES energy input and output. The model expresses the input and output relationship of different forms of energy with a coupling matrix to facilitate model construction. The energy supply and demand balance constraint can be specifically expressed as the following formula:

[0087]

[0088]

[0089]

[0090]

[0091] n∈{0,1,2,...,NC+NR}

[0092] Among them, the first formula mentioned above is the expression of the energy balance constraint based on Energy Hub, and the next three formulas respectively represent the supply and demand balance constraints after the three different forms of energy, electricity, heat and cold, are expanded.

[0093] In the formula, L represents the cooling, heating and electricity loads, P represents the output of each device, C is a coupling matrix, which represents the relationship between different forms of energy output and different forms of energy input, subscript - represents the energy form of input and output, and e, h, c and g represent electricity, heat, cooling and natural gas, respectively. In the traditional planning model, it is sufficient to consider the balance of supply and demand under normal operation, while the present invention considers the scenarios of failure of different equipment and equipment maintenance, so as to provide sufficient energy backup for the system. ε is the maximum load shedding threshold in the fault maintenance scenario set in advance based on the characteristics of the park. The value is 0 in the normal operation scenario of the equipment, that is, load shedding is not allowed. P n,s,tIt represents the output of a certain device at time t on a typical day s in scenario n. The subscript n represents different equipment operation scenarios, namely, the scenarios of normal operation of each device and many possible fault / maintenance scenarios. When it takes 0, it means that no device fails, that is, the normal operation scenario. When it takes different values, it means that a corresponding device fails, or a certain device needs to be repaired, so this device is out of operation in this scenario. The total number of scenarios is 1+NC+NR, that is, one normal scenario, NC fault scenarios to be considered, and NR maintenance scenarios to be considered. The specific scenario is selected by the park planning decision maker and added to the equipment fault maintenance set. Since the probability of equipment failure is low and the duration of occurrence is short, the output of each device during normal operation is used to calculate the operating cost in the objective function. The subscript is 0, which represents the normal scenario.

[0094] It should be noted that set n initially only includes 0, that is, the normal operation scenario. In the subsequent equipment fault maintenance set test, if the current planning scheme has a load shedding exceeding the threshold in a certain fault or maintenance scenario, the corresponding scenario is added to set n and the scheme is replanned. The specific steps will be explained later. The fifth formula above is all the scenarios that set n may contain.

[0095] 2) Upper and lower limits of equipment output: The output of a device is related to its maximum capacity and construction conditions. In normal operation scenarios, the output of a device is constrained by the maximum capacity and construction variables. The output constraints of each device in normal operation scenarios are as follows:

[0096]

[0097]

[0098]

[0099]

[0100] The above formula imposes upper and lower limits on the output of CCHP, GB, and EC, where X represents the construction variable, indicating whether the corresponding equipment is built, 1 for construction, and 0 for non-construction. When the equipment is built, its output in normal scenarios must be less than the product of the construction variable and its maximum output.

[0101] 3) Energy efficiency constraint: In order to maximize the advantages of the integrated energy system in energy consumption, the present invention introduces energy efficiency and uses this indicator to measure the energy conversion efficiency of the multi-energy park, and introduces energy efficiency constraints in the planning model to maintain it above a certain level. From the perspective of physics, energy efficiency refers to the ratio of the energy that plays a role in energy utilization to the energy actually consumed. From the perspective of terminal consumption, it reflects the ratio of the services provided to users to the total energy consumption. Its definition and the energy efficiency constraints in this model are as follows:

[0102]

[0103]

[0104] The first formula above is the energy efficiency definition formula, where η0 is the system energy efficiency, is the electrical energy output by the system, Q th is the output heat energy, is the electrical energy input to the system, Q FUEL is the input fuel energy.

[0105] The second formula is a specific energy efficiency constraint formula for multi-energy parks, where the output includes three energy forms: cold, heat, and electricity, and the input includes electricity and gas. Q h , Q c They represent the terminal power demand, heat demand and cooling demand respectively. and Q g They represent the amount of electricity and gas purchased from outside, e level Represents the minimum energy efficiency level specified in the plan. This function ensures that the system energy efficiency is not less than the expected level. It should be noted that the energy efficiency level constraint is also a constraint for normal operation scenarios and does not need to be considered in fault or maintenance scenarios.

[0106] According to the above objective function and constraints, a planning model for a multi-energy park can be established. This planning model is essentially a mixed integer programming model, so it can be solved by mature algorithms such as the branch and bound method. Solvers such as CPLEX and GUROBI can solve it well, and the solution process will not be described in detail here.

[0107] Step S30, use the generated equipment fault maintenance set to perform fault detection on the first planning result, and determine whether the first planning result has load shedding exceeding the threshold under the operation scenario of the equipment fault maintenance set. If not, use the first planning result as the optimal planning result of the multi-energy park.

[0108] Step S40: If yes, the operating scenario of load shedding exceeding the threshold is added as a constraint condition to the multi-energy park planning model, and the multi-energy park planning model is iteratively calculated to obtain the optimal planning result of the multi-energy park.

[0109] As described above, the present invention introduces an equipment fault maintenance set in the design planning method to ensure the reliability of the operation of the multi-energy park. Therefore, after obtaining the multi-energy park planning model, it is necessary to use the equipment fault maintenance set obtained by data preprocessing to perform reliability detection on it to ensure the reliability of the planning scheme. The specific method is: first, set the maximum acceptable load shedding level under equipment failure or maintenance as the threshold ε. Assuming that it is set to 5% of the maximum load, it is considered that the park can still guarantee 95% of the load in extreme scenarios. The specific energy supply and demand balance constraint expression can be seen. Then, based on the existing planning scheme, according to the scenarios set in the equipment fault maintenance set, the corresponding equipment is respectively shut down, and the calculation of whether the terminal has a load shedding situation, that is, whether the energy supply and demand balance constraint can still be met. If the multi-energy park can still operate normally within the given load shedding threshold in the case of a certain built equipment failure or maintenance, then the next scenario is tested. If the planning scheme can meet the supply and demand balance constraint under the set level in any scenario considered by the fault / maintenance set, then the planning scheme is the optimal scheme. At this time, the optimal planning result corresponding to the park can be directly output.

[0110] If a certain equipment is out of operation, the supply and demand balance constraints of the multi-energy park cannot be met, and the load shedding level exceeds the threshold, then the equipment failure or maintenance scenario is added to the above set n, and the relevant constraints are introduced into the original planning model, and the constraints and model solutions in the above steps are repeatedly iterated. The specific constraints are described as follows:

[0111] In any fault / maintenance scenario considered, the equipment may be in normal operation or out of operation (including fault or maintenance), so the output is constrained by the maximum capacity and the operating state variable. In order to introduce relevant constraints, the present invention proposes an equipment fault maintenance matrix to represent the operating state variables of the equipment in a special scenario, which can be expressed as follows:

[0112]

[0113] Among them, the matrix K represents the equipment fault maintenance set, each column represents an equipment fault operation scenario, each element corresponds to the operation state variable of a device in the scenario, "0" represents a fault, and "1" represents a normal situation. Preferably, a multi-functional park fault / maintenance matrix considering 5 types of candidate equipment can be expressed as follows:

[0114]

[0115] Assuming that the park considers 5 types of candidate equipment, according to the equipment failure rate or maintenance requirements, a failure / maintenance matrix as shown in the above formula can be formed. It can be seen that the matrix considers three special cases, namely: the scenario where the first candidate equipment is out of operation, the scenario where the third equipment is out of operation, and the scenario where the fourth equipment is out of operation. The outage can include equipment failure or equipment maintenance.

[0116] Based on the fault repair matrix proposed in the present invention, the output constraints of each device in a special scenario can be obtained as follows:

[0117]

[0118] In the formula, Respectively represent the output column vectors of CCHP, GB, and EC, For example, X CCHP , X GB , X EC They are the construction column vectors of CCHP, GB, and EC, respectively. CCHP For example, is the other fault and maintenance scenarios in n except the normal operation scenario, Represents the equipment fault maintenance set matrix K and fault maintenance scenario The corresponding column uses the equipment fault repair matrix to detect that the current planning scheme cannot meet the fault scenario in the fault repair set. When the above is used as a constraint, it can be added to the original planning model together with the corresponding fault troubleshooting scenario. After obtaining the new planning result, there is no need to consider the fault troubleshooting scenario that has been checked, because the optimized result must satisfy the checked scenario, thus greatly reducing the number of fault troubleshooting scenario checks.

[0119] According to all the steps of the multi-energy park planning method mentioned above, we can get the following Figure 5 The block diagram of the two-layer planning method of the multi-energy park considering the equipment fault maintenance set and energy efficiency level is shown in the figure. According to the above planning method, the optimal planning result of the multi-energy park can be obtained. This planning method allows the multi-energy park to fully meet the load demand under the condition of normal equipment operation. Even if there is an emergency in the relevant equipment, the load demand can be met within the specified load shedding threshold in all scenarios included in the equipment fault maintenance set. In addition, during the planning period, the park as a whole achieves the optimal total investment and operation cost while maintaining a high energy efficiency level.

[0120] In order to explain in detail the multi-functional park planning method considering the equipment fault maintenance set proposed in the present invention, the corresponding method is used to optimize and solve the actual park example, and the results are compared with the traditional planning method, that is, the planning method that does not consider the equipment fault maintenance situation.

[0121] Among them, the park load data is the 8760-hour cold, hot and electric load data of similar parks in the same region throughout the year. The peak values ​​of cold, hot and electric loads of the planned park are 60MW, 85MW and 75MW respectively. The 8760-hour load curve is normalized and multiplied by the peak load of the planned park. Finally, the composite data of four typical daily scenarios are obtained through the K-means clustering method, and planning is based on this. In terms of equipment, there are 7 types of CCHP units, with capacity increasing from 5MW to 35MW, and the construction cost is 10.8 million yuan / MW; there are 10 types of gas boilers and electric refrigeration equipment, respectively, with construction costs of 400,000 yuan / MW and 430,000 yuan / MW cold load, respectively. The heating and cooling efficiency increases slightly with the increase of capacity (such as the heating efficiency of 10MW gas boiler is 0.92, and the heating efficiency of 100MW gas boiler is 0.94. The efficiency of other capacity equipment is recursive). Since this industrial park has high requirements for energy supply reliability, any load shedding will have a significant impact on production. We set the load shedding threshold ε in the fault scenario to 0 and consider the fault / maintenance scenarios of all the selected equipment. This allows us to construct a fault / maintenance matrix as shown below, that is, each special scenario where a single device is out of operation is considered:

[0122]

[0123] According to the above-mentioned park-related data, the planning method of the present invention and the traditional multi-functional park planning method are used to plan the park respectively, and the equipment selection schemes shown in Tables 1 to 3 below are obtained:

[0124]

[0125] Table 1 CCHP unit selection scheme

[0126]

[0127] Table 2 Gas boiler selection scheme

[0128]

[0129] Table 3 Selection of electric refrigeration equipment

[0130] The number "1" corresponds to equipment construction, and the number "0" indicates that the corresponding equipment is not built. As shown in the table, the CCHP unit construction plan has not changed. Under the traditional planning method, only one large-capacity equipment is built for gas boilers and electric refrigeration equipment. Under the method of the present invention, multiple small-capacity equipment are built to replace a single large-capacity equipment, thereby avoiding a large amount of load shedding caused by a single equipment failure or maintenance. Taking a 10-year planning cycle, the comparison of the relevant costs of the traditional method and the method of the present invention is shown in Table 4:

[0131]

[0132] Table 4 Comparison of total costs of planning schemes

[0133] The conclusion drawn from the cost comparison is consistent with the selection scheme. Since the planning method of the present invention takes into account the equipment failure maintenance set and chooses to build equipment with a larger total capacity, the construction cost is increased by 5.6% compared with the traditional method, and the total cost is increased by 1.3%. This result shows that the multi-energy park planning method proposed in the present invention is effective. For a multi-energy park with a large load demand, reliability is one of its most important indicators. In exchange for a more reliable energy supply stability with a 1.3% cost increase, it is of great significance in actual production operation.

[0134] In order to better illustrate the reliability of the planning method of the present invention, the traditional planning method and the planning method of the present invention are evaluated using the park reliability evaluation method, and the reliability index used is the expected energy shortage value EENS (Expected Energy Not Supplied), the unit is MW / year. The reliability parameters of the two schemes are compared as shown in Table 5 below:

[0135]

[0136]

[0137] Table 5 Comparison of reliability indicators of planning schemes

[0138] ETNS and ECNS are the annual average unsupplied heat load and the annual average unsupplied cooling load, respectively, in MW. Since the park is powered by a substation with sufficient capacity, when the CCHP unit cannot provide sufficient electricity, the substation can supplement it, so there is no missing electricity load. From Table 5, the average annual missing heat load under the traditional planning method is about 84MW, and the cooling load is about 6MW; while the planning method proposed in the present invention has zero load missing, which greatly improves the reliability, thereby verifying the superiority of the planning method of the present invention in terms of reliability.

[0139] A multi-energy park planning method provided in this embodiment, compared with the traditional planning method, which mainly plans for maximum economic efficiency, the planned capacity in the planning result is close to the maximum demand, and the issue of energy supply reliability is rarely considered. The present invention takes equipment fault maintenance scenarios into consideration in the constraint conditions, thereby obtaining a certain amount of energy reserve, thereby improving the reliability of the operation of the multi-energy park, and reducing investment costs and operating costs while maintaining a high level of energy efficiency.

[0140] See also Figure 6 Based on the same inventive concept, a multi-functional park planning system proposed in the second embodiment of the present invention includes:

[0141] A data preprocessing module 10 is used to obtain relevant data of the multi-energy park and preprocess the relevant data, wherein the preprocessing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters;

[0142] A planning model building module 20 is used to build a multi-energy park planning model based on the energy hub model, and calculate the multi-energy park planning model to obtain a first planning result of the multi-energy park;

[0143] A first planning calculation module 30, configured to perform fault detection on the first planning result using the generated equipment fault overhaul set, and determine whether the first planning result has load shedding exceeding a threshold value under the operation scenario of the equipment fault overhaul set, and if not, use the first planning result as the optimal planning result of the multi-energy park;

[0144] The second planning calculation module 40 is used to add the operating scenario of load shedding exceeding the threshold as a constraint condition to the multi-energy park planning model, and iteratively calculate the multi-energy park planning model to obtain the optimal planning result of the multi-energy park.

[0145] Furthermore, the data preprocessing module 10 includes:

[0146] A typical day load generation module 101 is used to perform cluster analysis on the load parameters of the multi-energy park using k-means clustering to obtain a typical day load curve;

[0147] The equipment fault maintenance set generation module 102 is used to take a set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance as an equipment fault maintenance set according to the multi-energy park characteristics and the parameters of the equipment to be planned.

[0148] Furthermore, the planning model building module 20 includes:

[0149] An objective function construction module 201 is used to construct an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost;

[0150] A constraint condition building module 202 is used to add constraint conditions to the objective function, wherein the constraint conditions include energy supply and demand balance constraints, equipment output upper and lower limit constraints, and energy efficiency constraints under normal operation scenarios of each device;

[0151] The model building module 203 is used to establish a multi-energy park planning model according to the objective function and the constraint conditions.

[0152] The technical features and technical effects of the multi-functional park planning system proposed in the embodiment of the present invention are the same as the method proposed in the embodiment of the present invention, and will not be described in detail here. Each module in the above-mentioned multi-functional park planning system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0153] See also Figure 7 , an internal structure diagram of a computer device in one embodiment, the computer device can specifically be a terminal or a server. The computer device includes a processor, a memory, a network interface, a display and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-functional park planning method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0154] It can be understood by those skilled in the art that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the present application scheme, and does not constitute a limitation on the computer device to which the present application scheme is applied. The specific computing device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0155] In addition, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0156] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0157] In summary, an embodiment of the present invention proposes a multi-energy park planning method, system, computer device and storage medium. The method obtains relevant data of the multi-energy park and pre-processes the relevant data, wherein the pre-processing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned and park load parameters; a multi-energy park planning model is established based on an energy hub model, and the multi-energy park planning model is calculated to obtain a first planning result of the multi-energy park; the first planning result is fault detected using the generated equipment fault maintenance set to determine whether the first planning result has a load shedding exceeding a threshold under the operating scenario of the equipment fault maintenance set, and if not, the first planning result is used as the optimal planning result of the multi-energy park; if so, the operating scenario in which the load shedding exceeding the threshold occurs is added as a constraint condition to the multi-energy park planning model, and the multi-energy park planning model is iteratively calculated to obtain the optimal planning result of the multi-energy park. The present invention introduces the concept of energy efficiency and equipment fault repair set into the planning considerations of the multi-energy park, optimizes the planning of the park under a certain energy efficiency level, ensures the energy utilization efficiency, and through the introduction of the equipment fault repair set, ensures that the multi-energy park can still operate normally in the emergency situation of equipment failure, improves the safety and stability of the operation of the multi-energy park, and reduces the construction cost and operation cost.

[0158] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A multi-energy park planning method, characterized in that: include: Obtain relevant data of the multi-energy park and pre-process the relevant data, wherein the pre-processing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters; Establishing a multi-energy park planning model based on the energy hub model, and calculating the multi-energy park planning model to obtain a first planning result of the multi-energy park; Performing fault detection on the first planning result using the generated equipment fault overhaul set, determining whether the first planning result has load shedding exceeding a threshold under the operation scenario of the equipment fault overhaul set, and if not, taking the first planning result as the optimal planning result of the multi-energy park; If so, the operation scenario in which the load shedding exceeds the threshold is added as a constraint condition to the multi-energy park planning model, and the multi-energy park planning model is iteratively calculated to obtain the optimal planning result of the multi-energy park; The step of establishing a multi-energy park planning model based on the energy hub model includes: Constructing an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost; Adding constraints to the objective function, wherein the constraints include energy supply and demand balance constraints, upper and lower limit constraints on equipment output, and energy efficiency constraints under normal operation scenarios of each device; Establishing a multi-energy park planning model according to the objective function and the constraint conditions; The objective function is expressed by the following formula: min(f inv (X)+f ope (X,P)) In the formula, X and P are decision variables, which respectively represent the construction plan of each equipment and the equipment output on each typical day under the given construction plan. inv is the total investment cost of the equipment, f ope The total cost of park operation; The energy supply and demand balance constraint is expressed by the following formula: n∈{0,1,2,...,NC+NR} Where L represents the cooling, heating and electricity loads, P represents the output of each device, C represents the coupling matrix, subscript - represents the energy forms of input and output, e, h, c and g represent electricity, heat, cooling and natural gas respectively, subscript n represents different equipment operation scenarios, ε is the maximum load shedding threshold in the fault / maintenance scenario set based on the characteristics of the park, and P n,s,t represents the equipment output of a certain equipment at time t on a typical day s in scenario n, CCHP represents a combined cooling, heating and power unit, GB represents a gas boiler, EC represents an electric refrigeration equipment, NC and NR represent the number of equipment failure scenarios and equipment maintenance scenarios considered, respectively, subscripts i, j, k represent the indexes of CCHP units, gas boilers and electric refrigeration equipment, respectively, and SUB represents a substation; The following formula is used to express the upper and lower limit constraints of the equipment output: In the formula, X represents the construction variable; The energy efficiency constraint is expressed by the following formula: In the formula, η0 is the system energy efficiency, is the electrical energy output by the system, Q th is the output heat energy, is the electrical energy input to the system, Q FUEL is the input fuel energy, Q h , Q c They represent the terminal power demand, heat demand and cooling demand respectively. and Q g They represent the amount of electricity and gas purchased from outside, e level Represents the minimum energy efficiency level specified in the plan; The following formula is used to represent the operation scenario in which the load shedding exceeds the threshold: In the formula, Respectively represent the output column vectors of CCHP, GB, and EC, X CCHP , X GB , X EC are the construction column vectors of CCHP, GB and EC respectively, For all the troubleshooting scenarios in n except the normal operation scenario, Represents equipment fault repair set matrix and fault repair scenario The corresponding column, Scenes, is the number of typical day types.

2. The multi-energy park planning method according to claim 1, characterized in that: The step of obtaining relevant data of the multi-energy park and preprocessing the relevant data includes: The k-means clustering method is used to cluster the load parameters of the multi-energy park and obtain the typical daily load curve; According to the characteristics of the multi-energy park and the parameters of the equipment to be planned, a set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance is used as an equipment failure maintenance set.

3. A multi-functional park planning system, characterized in that: include: A data preprocessing module is used to obtain relevant data of the multi-energy park and preprocess the relevant data, wherein the preprocessing includes generating equipment fault maintenance sets and generating load typical days, and the relevant data includes energy prices, parameters of equipment to be planned, and park load parameters; A planning model building module, used to build a multi-energy park planning model based on the energy hub model, and calculate the multi-energy park planning model to obtain a first planning result of the multi-energy park; A first planning calculation module, used to perform fault detection on the first planning result using the generated equipment fault overhaul set, and determine whether the first planning result has a load shedding exceeding a threshold under the operation scenario of the equipment fault overhaul set, and if not, use the first planning result as the optimal planning result of the multi-energy park; A second planning calculation module is used for, if yes, adding the operation scenario of load shedding exceeding the threshold as a constraint condition to the multi-energy park planning model, and iteratively calculating the multi-energy park planning model to obtain the optimal planning result of the multi-energy park; The planning model building module includes: An objective function construction module, used to construct an objective function according to the total cost of the multi-energy park in the planning period, wherein the total cost includes equipment investment and construction cost and equipment operation cost; A constraint construction module, used to add constraint conditions to the objective function, wherein the constraint conditions include energy supply and demand balance constraints, equipment output upper and lower limit constraints, and energy efficiency constraints under normal operation scenarios of each device; A model building module, used to establish a multi-energy park planning model according to the objective function and the constraint conditions; The objective function is expressed by the following formula: min(f inv (X)+f ope (X,P)) In the formula, X and P are decision variables, which respectively represent the construction plan of each equipment and the equipment output on each typical day under the given construction plan. inv is the total investment cost of the equipment, f ope The total cost of park operation; The energy supply and demand balance constraint is expressed by the following formula: n∈{0,1,2,...,NC+NR} Where L represents the cooling, heating and electricity loads, P represents the output of each device, C represents the coupling matrix, subscript - represents the energy forms of input and output, e, h, c and g represent electricity, heat, cooling and natural gas respectively, subscript n represents different equipment operation scenarios, ε is the maximum load shedding threshold in the fault / maintenance scenario set based on the characteristics of the park, and P n,s,t represents the equipment output of a certain equipment at time t on a typical day s in scenario n, CCHP represents a combined cooling, heating and power unit, GB represents a gas boiler, EC represents an electric refrigeration equipment, NC and NR represent the number of equipment failure scenarios and equipment maintenance scenarios considered, respectively, subscripts i, j, k represent the indexes of CCHP units, gas boilers and electric refrigeration equipment, respectively, and SUB represents a substation; The following formula is used to express the upper and lower limit constraints of the equipment output: In the formula, X represents the construction variable; The energy efficiency constraint is expressed by the following formula: In the formula, η0 is the system energy efficiency, is the electrical energy output by the system, Q th is the output heat energy, is the electrical energy input to the system, Q FUEL is the input fuel energy, Q h , Q c They represent the terminal power demand, heat demand and cooling demand respectively. and Q g They represent the amount of electricity and gas purchased from outside, e level Represents the minimum energy efficiency level specified in the plan; The following formula is used to represent the operation scenario in which the load shedding exceeds the threshold: In the formula, Respectively represent the output column vectors of CCHP, GB, and EC, X CCHP , X GB , X EC are the construction column vectors of CCHP, GB and EC respectively, For all the troubleshooting scenarios in n except the normal operation scenario, Represents equipment fault repair set matrix and fault repair scenario The corresponding column, Scenes, is the number of typical day types.

4. The multi-functional park planning system according to claim 3, characterized in that: The data preprocessing module comprises: The typical day load generation module is used to perform cluster analysis on the load parameters of the multi-energy park using k-means clustering to obtain a typical day load curve; The equipment fault maintenance set generation module is used to take the set of operation scenarios in which the equipment to be planned exits operation when it fails or is under maintenance as the equipment fault maintenance set according to the multi-energy park characteristics and the parameters of the equipment to be planned.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images