Energy supply and demand optimization evaluation method and system

Abstract

The embodiment of the invention provides an energy supply and demand optimization evaluation method and system, and the method comprises the steps: taking energy supply and demand balance limitation and energy equipment power limitation as constraints based on energy supply and demand data under a preset working condition, and calculating a target function with the minimum operation and maintenance cost of energy equipment as a target; probability operation is performed on the target function through a genetic algorithm, and a target supply deviation set is determined; calculating the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using an entropy weight method, and determining the weight coefficient with the minimum value as the target weight coefficient; evaluating the operation and maintenance cost and the supply deviation based on the target weight coefficient, and outputting an optimal evaluation operation strategy; the optimal evaluation operation strategy is determined according to the minimum comprehensive weighted index of the operation and maintenance cost and the supply deviation, the established operation strategy and the actual operation of the equipment are associated and interacted, and the diversified utilization and flexible allocation of energy are realized while the consumption resource cost is minimized.

Description

Technical Field

[0001] The present invention relates to the field of energy supply and demand, and in particular to an energy supply and demand optimization evaluation method and system. Background Art

[0002] In recent years, the Integrated Energy System (IES) has become an inevitable choice for my country's energy structure adjustment and green and low-carbon transformation and upgrading process due to its distinctive features such as high energy utilization efficiency, strong energy supply reliability, and low pollutant emissions. Compared with the traditional energy system, the biggest advantage of the integrated energy system is that it can effectively reduce dependence on traditional fossil energy, realize diversified utilization and flexible allocation of energy, significantly reduce energy losses in the energy conversion process, and reduce greenhouse gas emissions, ultimately achieving the goal of energy conservation and emission reduction.

[0003] However, with the diversification of equipment composition of integrated energy systems, the complexity of energy supply types and scheduling mechanisms, and the increasing attention paid to user energy experience, traditional system scheduling strategy formulation has failed to interact with the actual operation of the equipment. There are common defects such as over-simplification of equipment output calculations, low reliability and rationality of strategy formulation, and frequent imbalances in energy supply and demand. This makes it impossible to achieve diversified utilization and flexible allocation of energy while minimizing resource consumption costs. Summary of the invention

[0004] In view of this, in order to solve the problem that the traditional system scheduling strategy formulation of the integrated energy system fails to achieve correlation and interaction with the actual operation of the equipment, there are common defects such as over-simplification of equipment output calculation, low reliability and rationality of strategy formulation, frequent imbalance of energy supply and demand, etc., thereby failing to minimize the cost of resource consumption while achieving diversified utilization and flexible allocation of energy, an embodiment of the present invention provides an energy supply and demand optimization evaluation method and system.

[0005] An energy supply and demand optimization evaluation method, comprising:

[0006] Obtaining energy supply and demand data under preset working conditions, and based on the energy supply and demand data, calculating an objective function with the goal of minimizing the energy equipment operation and maintenance cost with energy supply and demand balance constraints and energy equipment power constraints as constraints;

[0007] Performing probability calculation on the objective function through a genetic algorithm, thereby determining a target supply deviation set;

[0008] Calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using the entropy weight method, and determine the smallest value as the target weight coefficient;

[0009] The operation and maintenance cost and supply deviation are evaluated based on the target weight coefficient, and an optimal evaluation operation strategy is output; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of the operation and maintenance cost and the supply deviation.

[0010] In a possible embodiment, the method further includes:

[0011] Calculate the historical operating data of the energy equipment under the preset working conditions, and input the historical operating data into the mechanism simulation model for simulation operation to determine the energy supply and demand data, which includes: energy demand and energy supply produced by the corresponding equipment.

[0012] In a possible embodiment, the energy equipment includes: a gas turbine, a gas boiler, a waste heat boiler, a lithium bromide refrigerator and an electric refrigerator;

[0013] The historical operation data of the energy equipment under the preset working conditions is calculated, including:

[0014] Based on the operation and maintenance cost of the energy equipment, the compressor operation data, combustion chamber operation data, turbine operation data contained in the operation of the gas turbine, and the heat production data of the gas boiler, waste heat boiler, lithium bromide refrigerator, and electric refrigerator are calculated to obtain historical operation data.

[0015] In a possible embodiment, the supply deviation is the difference between the energy demand and the energy supply in the energy supply and demand data;

[0016] The method of performing probability calculation on the objective function by using a genetic algorithm to determine a target supply deviation set includes:

[0017] Constructing a fitness function for the objective function using the inverse method;

[0018] Calculate the selection probability of the supply deviation corresponding to the objective function under each working condition based on the fitness function by using the roulette method;

[0019] Perform crossover calculation based on the selection probability of the supply deviation under at least two working conditions to obtain a new supply deviation under the corresponding working condition, and combine the new supply deviation with the supply deviation corresponding to the objective function to form an initial supply deviation set;

[0020] The initial supply deviation set is mutated by mutation probability, so that any supply deviation in the initial supply deviation set generates multiple optional supply and demand modes, thereby generating a target supply deviation set.

[0021] In a possible embodiment, the entropy weight method is used to calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation, and the smallest value is determined as the target weight coefficient, which includes:

[0022] m evaluation indicators are set for the supply deviation and the corresponding operation and maintenance cost, and the importance level of any evaluation indicator is determined among n importance levels;

[0023] Generating an importance table according to the m evaluation indicators and the n importance levels;

[0024] A sampling matrix is ​​generated according to the importance table.

[0025] In a possible embodiment, the using of the entropy weight method to calculate the weight coefficients of the supply deviations in the target supply deviation set and the operation and maintenance costs corresponding to the supply deviations, and determining the smallest value as the target weight coefficient, includes:

[0026] The sampling matrix is ​​calculated using the entropy weight method to determine the weight coefficient of each supply deviation in the supply deviation set, as well as the weight coefficient of the operation and maintenance cost corresponding to the supply deviation. The calculation formula is as follows:

[0027]

[0028] Where P ij is the standardized value of the jth importance level of the ith evaluation indicator; r ij is the initial value of the jth importance level of the ith evaluation indicator in the sampling matrix, i = 1, 2, ..., m, m = 4, representing the type of evaluation indicator; j = 1, 2, ..., n, n = 5, representing the importance level in descending order from high to low; H i is the entropy value of the i-th evaluation index; k is the importance level coefficient; V i is the difference coefficient of the i-th evaluation index; W i is the weight coefficient of the i-th evaluation index;

[0029] The supply deviation W with the smallest value i As the target weight coefficient of the supply deviation, and the operation and maintenance cost W that minimizes the value i As the target weight coefficient of operation and maintenance cost;

[0030] The evaluation indicators include: operation and maintenance cost, the gap between power supply and user demand, the gap between cooling capacity and user cooling demand, and the gap between heating capacity and user heating demand.

[0031] In a possible embodiment, the operation and maintenance cost and supply deviation are evaluated based on the target weight coefficient, and the optimal evaluation operation strategy is output, which includes:

[0032] The m evaluation indicators of the operation and maintenance cost and the supply deviation are normalized, and the calculation formula is as follows:

[0033]

[0034] Among them, q i is the standardized value of the i-th indicator to be normalized; s i is the absolute value of the ith evaluation index.

[0035] In a possible embodiment, the operation and maintenance cost and supply deviation are evaluated based on the target weight coefficient, and an optimal evaluation operation strategy is output; the optimal evaluation operation strategy is determined with the minimum comprehensive weighted index of the operation and maintenance cost and supply deviation as the goal, and includes:

[0036] Based on the target weight coefficients of the supply deviation and operation and maintenance cost, a comprehensive weighted index is calculated for the energy supply and demand data corresponding to the supply deviation and operation and maintenance cost under each operating condition;

[0037] A comprehensive weighted index with the smallest value is selected, an operation strategy is obtained from energy supply and demand data corresponding to the comprehensive weighted index with the smallest value, and the operation strategy is output as an optimal evaluation operation strategy.

[0038] In a possible embodiment, based on the target weight coefficient of the supply deviation and the operation and maintenance cost, a comprehensive weighted index is calculated for the energy supply and demand data corresponding to the supply deviation and the operation and maintenance cost under each working condition, and the calculation formula is as follows:

[0039]

[0040] w i is the target weight coefficient of the i-th evaluation index; q i is the standardized value of the i-th indicator to be normalized, i = 1, 2, …, m.

[0041] Based on the same concept, an embodiment of the present invention provides an energy supply and demand optimization evaluation system, including:

[0042] An optimization module is run to obtain energy supply and demand data under preset working conditions, and based on the energy supply and demand data, an objective function with the energy supply and demand balance limit and the energy equipment power limit as constraints is calculated to minimize the energy equipment operation and maintenance cost;

[0043] An intelligent optimization algorithm module, used for performing probability calculation on the objective function through a genetic algorithm, thereby determining a target supply deviation set;

[0044] A target coefficient generation module calculates the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using an entropy weight method, and determines the smallest value as the target weight coefficient;

[0045] The global optimal strategy module evaluates the operation and maintenance cost and supply deviation based on the target weight coefficient and outputs the optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of operation and maintenance cost and supply deviation.

[0046] The embodiment of the present invention provides an energy supply and demand optimization evaluation method and system, which obtains energy supply and demand data under preset working conditions, and based on the energy supply and demand data, takes energy supply and demand balance restrictions and energy equipment power restrictions as constraints, calculates an objective function with the goal of minimizing the operation and maintenance cost of energy equipment, and calculates the equipment output in more detail and accuracy; performs probability calculation on the objective function through a genetic algorithm, and then determines a target supply deviation set; uses an entropy weight method to calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation, and determines the smallest value as the target weight coefficient, thereby avoiding the phenomenon of energy supply and demand imbalance; evaluates the operation and maintenance cost and supply deviation based on the target weight coefficient, and outputs an optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of the operation and maintenance cost and the supply deviation, so that the operation strategy formulated is associated and interactive with the actual operation of the equipment, which is more reasonable and reliable, and realizes diversified utilization and flexible allocation of energy while taking into account the minimization of resource consumption costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 A flow chart of an embodiment of an energy supply and demand optimization evaluation method provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram for comparing the prediction results and actual output of a gas turbine mechanism simulation model provided by an embodiment of the present invention;

[0050] Figure 3 A genetic algorithm iterative process diagram provided by an embodiment of the present invention;

[0051] Figure 4 A graph showing the index calculation and ranking results of summer energy supply and demand data provided by an embodiment of the present invention;

[0052] Figure 5A diagram of the index calculation and sorting results of winter energy supply and demand data provided by an embodiment of the present invention

[0053] Figure 6 An optimal energy supply strategy diagram for a typical summer day provided by an embodiment of the present invention;

[0054] Figure 7 An optimal energy supply strategy diagram for a typical winter day provided by an embodiment of the present invention;

[0055] Figure 8 A schematic diagram of the architecture of an energy supply and demand optimization evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0057] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0058] In practice, there are huge differences in energy demand for different factors or environments, including but not limited to temperature, climate, season, etc. The following uses the season factor as an example to compare energy demand and prices in different seasons. The following table uses energy prices and energy demand on typical summer days and typical winter days as examples, as shown in Table 1 and Table 2.

[0059] Table 1 Energy prices and energy demand on a typical day in summer

[0060]

[0061] Table 2 Energy prices and energy demand on a typical day in winter

[0062]

[0063]

[0064] See also Figure 1 , is a flow chart of an embodiment of an energy supply and demand optimization evaluation method provided by an embodiment of the present invention, such as Figure 1 As shown, the process may include the following steps:

[0065] Step 101: Obtain energy supply and demand data under preset working conditions, and based on the energy supply and demand data, calculate an objective function with the goal of minimizing the energy equipment operation and maintenance cost, with energy supply and demand balance restrictions and energy equipment power restrictions as constraints.

[0066] In one embodiment, the energy supply and demand data under the preset working conditions can be obtained by obtaining the historical operation data of the energy equipment. The working conditions here may include but are not limited to: power supply working conditions, heat supply working conditions, cold energy supply working conditions, etc. The energy equipment may include but is not limited to: gas turbines, gas boilers, waste heat boilers, lithium bromide refrigerators, and electric refrigerators.

[0067] Here, historical operation data refers to the operation data related to energy equipment, which can represent the actual operation of energy equipment. Therefore, the operation of energy equipment can be simulated by using a mechanism simulation model, so as to realize the interaction between energy supply and demand mode and energy equipment operation. Figure 2 A schematic diagram showing the comparison between the prediction results of the mechanism simulation model and the actual output of a gas turbine provided by an embodiment of the present invention. Figure 2 As shown, the error between the prediction results of the mechanism simulation model and the actual output is not large, which shows that the interaction between the energy supply and demand mode and the operation of energy equipment is feasible.

[0068] Specifically, it can be achieved through the following methods, including:

[0069] Calculate the historical operating data of the energy equipment under the preset working conditions, and input the historical operating data into the mechanism simulation model for simulation operation to determine the energy supply and demand data. The energy supply and demand data includes: energy demand and the energy supply produced by the corresponding equipment.

[0070] The acquisition of historical operation data can determine the energy generation method according to the type of energy equipment. This embodiment takes gas turbines, gas boilers, waste heat boilers, lithium bromide refrigerators, and electric refrigerators as examples for explanation. Based on the operation and maintenance cost of energy equipment, the compressor operation data, combustion chamber operation data, and turbine operation data contained in the operation of the gas turbine, as well as the heat production data of the gas boilers, waste heat boilers, lithium bromide refrigerators, and electric refrigerators are calculated and obtained.

[0071] Specifically, the compressor operation data can be calculated using the following formula:

[0072] P out =π c *P in (Formula 1)

[0073]

[0074] σ c =w in / wout (Formula 6)

[0075]

[0076]

[0077] Where P in is the compressor inlet pressure, pa; P out is the outlet pressure of the compressor, pa; π C is the pressure ratio of the compressor; T in is the compressor inlet temperature, K; T out is the compressor outlet temperature, K; k gas is the air specific heat ratio; γ c is the pressure ratio of the compressor; σ c is the efficiency of the compressor; C a , C b , C c is the reduced pressure ratio coefficient of the compressor; γ0 is the initial speed of the compressor, r / min; γ z is the reduced speed of the compressor, r / min; F c is the compressor inlet air flow rate, kg / s; F zc is the equivalent inlet air flow rate of the compressor, kg / s; w in is the effective work obtained by the air, kW; w out is the effective work delivered to the air by the compressor impeller, kW; R g is the air constant, J / (kg*K); T g is the ambient temperature, K; λ0 is the slip coefficient; v is the compressed air velocity of the compressor, m / s; T0 is the air temperature under standard conditions, K; C pa is the specific heat capacity of air at constant pressure; N c is the work done by the compressor, kW; F a,m is the air flow rate in the compressor; η c Volumetric efficiency of the compressor.

[0078] The combustion chamber operation data can be calculated using the following formula:

[0079]

[0080] P out =aP2 (Formula 11)

[0081] In the formula, q r is the lower calorific value of natural gas, J / kg; h r is the enthalpy of natural gas, J / kg; η B is the combustion efficiency; F outis the outlet gas flow rate of the combustion chamber, kg / s; F a,out is the outlet air flow of the compressor; C pg is the constant pressure specific heat capacity of natural gas, J / (kg*K); C pa is the specific heat capacity of air at constant pressure, J / (kg*K); P out is the outlet pressure of the combustion chamber, Pa; a is the total combustion pressure recovery coefficient; T2 is the inlet temperature of the combustion chamber; T3 is the outlet temperature of the combustion chamber; P2 is the inlet pressure of the combustion chamber.

[0082] The turbine operation data can be calculated using the following formula:

[0083]

[0084] E gt =(N t -N c )×σ (Equation 14)

[0085] Q eg =(N t -N c )×(1-σ-σ loss ) (Formula 15)

[0086] Where N t is the turbine power, N c is the work done by the compressor; kW; π t is the turbine expansion ratio; k g is the average specific heat ratio of the gas; σ t is the turbine efficiency; G out is the gas flow rate entering the turbine, kg / s; E gt is the power generation of the gas turbine, kW; Q eg is the waste heat flue gas volume of the gas turbine, kW; σ is the efficiency of the gas turbine; σ loss is the heat loss coefficient of the gas turbine. T4 is the gas outlet temperature of the turbine.

[0087] Specifically, how to calculate the objective function with the minimum energy equipment operation and maintenance cost as the goal based on energy supply and demand data and energy supply and demand balance constraints and energy equipment power constraints can be calculated in the following way:

[0088] minC=C e +C g +C m (Formula 16)

[0089]

[0090] Where minC is the minimum total cost of energy equipment operation and maintenance; C e , Cg and C m are electricity purchase cost, gas cost and equipment maintenance cost, RMB; Z(t) is the electricity purchase amount at time t, kWh; C ep (t) is the electricity price at time t, RMB / kWh; V gt (t) is the gas consumption of the gas turbine at time t, m 3 ; V gah (t) is the gas consumption of the gas boiler at time t, m 3 ; C ng (t) is the natural gas price, RMB / m 3 ; C mgt is the operation and maintenance cost of the gas turbine per unit power generation, RMB / kWh; C mgh is the operation and maintenance cost of the waste heat boiler per unit heat output, RMB / kW; C mgah is the operation and maintenance cost of the gas boiler per unit heat output, RMB / kW; C mref is the operation and maintenance cost of lithium bromide refrigerator per unit cooling capacity, RMB / kW; C meref E is the operation and maintenance cost of the electric refrigerator per unit cooling capacity, RMB / kW; gt (t) is the power generation of the gas turbine at time t; Q gh (t) is the heat output of the waste heat boiler at time t, kW; Q gah (t) is the heat output of the gas boiler at time t, kW; Q ref (t) is the cooling capacity of the lithium bromide refrigerator at time t, kW; Q eref (t) is the cooling capacity of the electric refrigerator at time t, kW.

[0091] Here, the constraints of energy supply and demand balance and energy equipment power limit can be calculated as follows:

[0092] Z(t)+E gt (t)-E eref (t)≥E equip (t) (Equation 20)

[0093] Q gh (t)+Q gah (t)≥Q heat (t) (Equation 21)

[0094] Q ref (t)+Q eref (t)≥Q cool (t) (Equation 22)

[0095]

[0096] Q eref (t) = E eref(t)×COP eref (Formula 24)

[0097] Q gh (t) = Q eg (t)×(1-x(t))×η gh (Formula 25)

[0098] V gah (t) = Q gah (t) / (η gah ×H u ) (Formula 26)

[0099]

[0100] In the formula, E equip (t) is the electricity demand at time t, kWh; Q heat (t) is the heat demand at time t, kW; Q cool (t) is the cooling demand at time t; x(t) is the amount of waste heat flue gas extracted by the gas turbine and allocated to lithium bromide refrigeration, x(t)∈[0,1]; η ref is the heat recovery rate of lithium bromide refrigerator, %; COP a is the refrigeration coefficient of lithium bromide refrigerator; E eref (t) is the power consumption of the refrigerator at time t, kWh; COP eref is the energy efficiency ratio of the electric refrigerator; η gh is the heat recovery efficiency of the gas boiler, %; η gah is the heat recovery efficiency of the gas boiler, %; H u is the calorific value of natural gas. Among them, the upper and lower limits of the inequalities (Equation 27) to (Equation 31) are the power limits of various energy equipment at time t, that is, the maximum and minimum outputs.

[0101] Step 102: Perform probability calculation on the target function through a genetic algorithm to determine a target supply deviation set.

[0102] The supply deviation here is the difference between energy demand and energy supply in the energy supply and demand data.

[0103] In this embodiment, the genetic algorithm can be set with parameters according to Table 3, as shown in Table 3:

[0104] Table 3 Genetic algorithm parameter settings

[0105]

[0106] In one embodiment, there are multiple ways of energy supply and demand, for example, only providing electrical energy, thermal energy or cold energy, or multiple energy sources can be supplied at the same time, which is not limited here. Of course, if the energy supply and demand data corresponding to the provided objective function represents one of the supply and demand methods, the supply and demand methods that can be selected are limited to a certain extent, and only the objective function that meets the conditions can be locally identified, and the goal of minimizing the operation and maintenance cost cannot be determined globally.

[0107] On this basis, the same crossover parts can be removed under various working conditions, and the supply deviation under the working conditions can be changed to avoid local convergence. Probability calculation can also be performed based on the objective function under the current working conditions to change some genes (factors) and present a variety of supply and demand methods. Of course, the two can also be combined to achieve diversified utilization and flexible allocation of energy, which is not limited here.

[0108] As for how to perform probability calculation on the objective function through the genetic algorithm and then determine the target supply deviation set, it can be determined according to the following steps 201 to 204, which will not be described in detail here.

[0109] Step 201: Use the inverse method to construct a fitness function for the objective function.

[0110] In one embodiment, the fitness function can be constructed by the following formula, and the calculation formula is as follows:

[0111]

[0112] In the formula, F itness (x) is the fitness function value; f(x) is the objective function.

[0113] Step 202: Calculate the selection probability of the supply deviation corresponding to the objective function under each working condition based on the fitness function by using the roulette method.

[0114] In one embodiment, each operating condition corresponds to an objective function representing the minimum operation and maintenance cost, and each objective function corresponds to a supply deviation. In practice, different energy supply and demand data will be generated under various operating conditions, and the probability of encountering different conditions will vary greatly depending on the type of operating condition. Therefore, the selection probability under the current operating condition can be determined.

[0115] Specifically, the roulette method can be used to determine the selection probability of the supply deviation corresponding to the objective function under the current working conditions. The calculation formula is as follows:

[0116]

[0117] Where P i is the probability of supply deviation being selected under the i-th working condition; Fitness iis the fitness of the supply deviation under the i-th working condition.

[0118] Step 203 , performing crossover operation calculation based on the selection probability of the supply deviation under at least two working conditions to obtain a new supply deviation under the corresponding working condition, and combining the new supply deviation with the supply deviation corresponding to the objective function to form an initial supply deviation set.

[0119] In one embodiment, based on the probability of supply deviation being selected under each working condition determined in step 202, a crossover operation of supply deviation between working conditions can be performed. The crossover operation simulates gene exchange in the biological world, exchanges chromosomes of two parent individuals, and generates new individuals. In the application of this embodiment, the parent individuals represent supply deviations under different working conditions.

[0120] Specifically, a new supply deviation can be obtained by genetically exchanging supply deviations under at least two working conditions. At this time, the new supply deviation will also correspond to new energy supply and demand data.

[0121] Specifically, the crossover operation can be implemented by the following calculation formula:

[0122] offspring1=P1[:cross_point]+P2[cross_point:] (Equation 34)

[0123] offspring2=P2[:cross_point]+P1[cross_point:] (Equation 35)

[0124] Among them, offspring1 is the new supply deviation 1; offspring2 is the new supply deviation 2; P1[:cross_point] is the part before the cross point of the parent supply deviation p1; P2[:cross_point] is the part before the cross point of the parent supply deviation p2; P1 is the probability of supply deviation p1 being selected under the first working condition; P2 is the probability of supply deviation p2 being selected under the second working condition.

[0125] Step 204: Perform a mutation operation on the supply deviation set through the mutation probability, so that any supply deviation in the initial supply deviation set generates multiple optional supply and demand modes, thereby generating a target supply deviation set.

[0126] In one embodiment, after the cross operation of step 203 is performed on the supply deviations under multiple working conditions, it is also performed under the original data of the existing working conditions, which is not comprehensive. Therefore, the diversification of energy can be increased by changing the supply deviations under the working conditions themselves, and the energy supply method can be made more comprehensive, which is convenient for subsequent deployment and utilization. Specifically, the supply deviations that meet the variation restriction conditions can be mutated. During the specific operation, the probability of becoming a supply deviation can also be considered to further determine whether to mutate the supply deviation.

[0127] The above operation can be achieved by the following calculation formula, as shown below:

[0128] P i_new =P i +α×(g max -g min )×β (Equation 36)

[0129] Among them, α is the mutation probability; g max and g min Represent the maximum and minimum values ​​of the gene respectively; β is a random number between (-1,1). i_new The supply deviation p under the i-th working condition i Mutation to p i_new probability.

[0130] Here, the mutation operation of supply deviation is controlled within the limit range by setting the maximum and minimum values ​​of the gene, thus ensuring the balance of energy supply and demand.

[0131] The process of determining the target supply deviation set by genetic algorithm from step 201 to step 204 can be performed once or iteratively for multiple times, which is not limited here. Figure 3 A genetic algorithm iteration process diagram provided by an embodiment of the present invention. Figure 3 As shown in the figure, if the iteration is performed iteratively, the required running cost decreases as the number of iterations increases, showing a low parabola shape, which drops sharply before about 240 times and tends to be flat after more than 240 times.

[0132] Step 103: Calculate the supply deviations in the target supply deviation set and the weight coefficients of the operation and maintenance costs corresponding to the supply deviations using the entropy weight method, and determine the smallest value as the target weight coefficient.

[0133] In one embodiment, the above step 102 allows the user to have a comprehensive selection when determining the operation strategy corresponding to the energy supply and demand data based on the supply deviation, but this only provides the user with a choice in one aspect. In addition, on the operation strategy represented by the selected supply deviation, the user has more requirements for the operation strategy to be implemented, such as: whether the energy used by the operation strategy conflicts with the current operation strategy, whether the operation and maintenance cost meets the user's requirements, or whether the supply deviation of the operation strategy is acceptable to the user.

[0134] In this case, the weight coefficient can be determined to indicate the importance by the supply deviation in the target supply deviation set and the operation and maintenance cost corresponding to the supply deviation determined in step 102. As for how to use the entropy weight method to calculate the weight coefficients of the supply deviation in the target supply deviation set and the operation and maintenance cost corresponding to the supply deviation, and determine the minimum value as the target weight coefficient, it is explained in the following steps 401 to 402, and will not be described in detail here.

[0135] In practice, in order to ensure the reliability and rationality of the operation strategy, before determining the weight coefficient, evaluation indicators can be set for the supply deviation and operation and maintenance cost of the operation strategy, and the importance level can be set according to the importance of the evaluation indicators. Specifically, the following operations can be performed according to step 301 to step 303, including:

[0136] Step 301: m evaluation indicators are set for supply deviation and corresponding operation and maintenance cost, and the importance level of any evaluation indicator is determined among n importance levels.

[0137] Step 302: Generate an importance table based on the m evaluation indicators and the n importance levels.

[0138] Step 303: Generate a sampling matrix according to the importance table.

[0139] The following is a unified description of steps 301 to 303:

[0140] The evaluation indicators here may include but are not limited to: operation and maintenance costs, the gap between power supply and user demand, the gap between cooling capacity and user cooling demand, and the gap between heating capacity and user heating demand.

[0141] In one embodiment, the importance of the evaluation index can be determined by experts through an expert survey form. For example, referring to Table 4, assuming that 10 experts participate in the importance survey of the evaluation index, the number of indicators is set to 4, and the importance level is divided into 5 levels. Taking the cost index as an example, 4 experts think it is very important. Therefore, fill in 4 in the first box in the upper left corner, and so on, the scores of the remaining indicators can be determined.

[0142] Table 4. Results of the importance of indicators

[0143]

[0144] According to the above table, generate the sampling matrix R:

[0145]

[0146] Among them, r ij is the initial value of the jth importance level scale of the ith indicator, i = 1, 2, ..., m, representing the type of evaluation indicator; j = 1, 2, ..., n, representing the importance level in descending order from high to low.

[0147] The following describes how to use the entropy weight method to calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation, and determine the smallest value as the target weight coefficient. The specific steps include:

[0148] Step 401: Use the entropy weight method to calculate the sampling matrix to determine the weight coefficient of each supply deviation in the supply deviation set, as well as the weight coefficient of the operation and maintenance cost corresponding to the supply deviation.

[0149] Step 402: The supply deviation W with the smallest value i As the target weight coefficient of the supply deviation, and the operation and maintenance cost W that minimizes the value i As the target weight coefficient of operation and maintenance cost.

[0150] The following is a unified description of step 401 and step 402:

[0151] In one embodiment, the weight coefficient is calculated based on the sampling matrix, which can be implemented by the following calculation formula:

[0152]

[0153] In the formula, R ij is the standardized value of the jth importance level of the ith evaluation indicator; r ij is the initial value of the jth importance level of the ith evaluation indicator in the sampling matrix, i = 1, 2, ..., m, m = 4, representing the type of evaluation indicator; j = 1, 2, ..., n, n = 5, representing the importance level in descending order from high to low; H i is the entropy value of the i-th evaluation index; k is the importance level coefficient; V i is the difference coefficient of the i-th evaluation index; W i is the weight coefficient of the ith evaluation index.

[0154] Furthermore, according to the principle of minimizing resource consumption cost, the supply deviation W with the smallest value isi As the target weight coefficient of the supply deviation, and the operation and maintenance cost W that minimizes the value i As the target weight coefficient of the operation and maintenance cost. It is understandable that when the target weight coefficient is currently selected, the corresponding minimum supply deviation and / or minimum operation and maintenance cost is also selected, and thus the energy supply and demand data under the working conditions of the minimum supply deviation and / or minimum operation and maintenance cost will also be selected.

[0155] For example, continue to take the evaluation indicators in Table 4 as an example, set the target weight coefficient for the evaluation indicators in Table 4, as shown in Table 5:

[0156] Table 5 Summary of the weight calculation results of evaluation indicators

[0157]

[0158]

[0159] It can be seen from Table 5 that the operation and maintenance cost has the largest weight, and the target weight coefficient is 0.3548. The gap between the cooling capacity and the user's cooling demand has the smallest weight, and the target weight coefficient is 0.1621.

[0160] Step 104: Evaluate the operation and maintenance cost and supply deviation based on the target weight coefficient, and output the optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of the operation and maintenance cost and supply deviation.

[0161] In one embodiment, it can be seen from Table 5 that the target weight coefficients of operation and maintenance cost and supply deviation can determine their importance while indicating the evaluation index of energy supply and demand data. Furthermore, the importance of the evaluation index becomes a determining condition for determining the optimal evaluation operation strategy.

[0162] Before this, the operation and maintenance cost and supply deviation were data from different parties and difficult to evaluate together. Therefore, the operation and maintenance cost and supply deviation can be normalized. The calculation formula is as follows:

[0163]

[0164] Among them, q i is the standardized value of the i-th indicator to be normalized; s i is the absolute value of the ith evaluation index.

[0165] Specifically, the optimal evaluation operation strategy can be determined by the following steps:

[0166] Step 501: Based on the target weight coefficients of supply deviation and operation and maintenance cost, a comprehensive weighted index is calculated for energy supply and demand data corresponding to supply deviation and operation and maintenance cost under each operating condition.

[0167] Step 502: Select the comprehensive weighted index with the smallest value, obtain the operation strategy from the energy supply and demand data corresponding to the comprehensive weighted index with the smallest value, and output the operation strategy as the optimal evaluation operation strategy.

[0168] The following is a unified description of step 501 and step 502:

[0169] Based on the target weight coefficients of supply deviation and operation and maintenance cost, the comprehensive weighted index of energy supply and demand data corresponding to supply deviation and operation and maintenance cost under each working condition is calculated. The calculation formula is as follows:

[0170]

[0171] w i is the target weight coefficient of the i-th evaluation index; q i is the standardized value of the i-th indicator to be normalized, i = 1, 2, …, m.

[0172] From the above formula, we can see that the smaller the supply deviation and operation and maintenance cost, the smaller the calculated comprehensive weighted index of the two, which is positively correlated. Therefore, the comprehensive weighted index with the smallest value is selected, and then the energy supply and demand data corresponding to the comprehensive weighted index with the smallest value is determined; thus, the operation strategy can be obtained from it, and the operation strategy can be output as the optimal evaluation operation strategy.

[0173] In another embodiment, step 104 can also determine the optimal evaluation operation strategy in another way. Specifically, the comprehensive weighted index of operation and maintenance cost and supply deviation is minimized, and the same way of expressing the meaning is: the weighted value of operation and maintenance cost and supply deviation is minimized, which can specifically include the following steps:

[0174] Step 601: sum the target weight coefficient of the operation and maintenance cost and the target weight coefficient of the supply deviation under any working condition to obtain a weighted sum, and then obtain the weighted sum under multiple working conditions.

[0175] Step 602: According to the size of the weighted sum, the operation and maintenance cost and the supply deviation under the corresponding working condition are determined in a descending order.

[0176] Step 603: Taking the weighted sum of the maximum operation and maintenance cost and the supply deviation as the target condition, search in the energy supply and demand data, and output the operation strategy corresponding to the target condition in the energy supply and demand data as the optimal evaluation operation strategy.

[0177] The following is a unified description of steps 601 to 603:

[0178] For example, combined with the weight coefficients provided in Table 5, the weighted sum method is used to comprehensively rank the weighted sums under all operating conditions to determine the optimal operation plan of the system. The calculation results of the total operation and maintenance cost, three types of supply deviation values ​​and comprehensive weighted values ​​under typical daily conditions in summer and winter are expressed in tabular form, as shown in Tables 6 and 7.

[0179] Table 6 Index calculation and sorting results of typical daily energy supply and demand data in summer (taking the first 20 chromosomes)

[0180]

[0181] Table 7 Index calculation and sorting results of typical daily energy supply and demand data in winter (taking the first 20 chromosomes)

[0182]

[0183]

[0184] See also Figure 4 The present invention provides an index calculation and ranking result diagram of summer energy supply and demand data. Figure 4 As shown in Table 6, when the supply deviation of energy supply and demand is not considered, the operation and maintenance cost of condition 94 is the lowest, which is 31483.85 yuan; however, the power supply deviation corresponding to this condition is large, which is 1329.71kW, and there is a risk of imbalance in power supply and demand. On the contrary, when the actual energy supply and the level of differentiation of user energy demand are comprehensively considered, the comprehensive score of condition 53 is the highest. The system operation cost corresponding to this chromosome is 31655.29 yuan, and the supply and demand deviations of electricity, heat and cold are 1090.25kW, 1081.06kW and 460.19kW respectively. Compared with the optimal chromosome 94 without considering the level of differentiation of energy supply and demand, although the operating cost of chromosome 53 is 171.44 yuan higher, its power supply deviation is reduced by 239.46kW, indicating that chromosome 53 is the global optimal energy supply strategy for the system that takes into account both the minimum energy supply cost and the minimum energy supply and demand difference.

[0185] Optional, see Figure 5 A diagram of index calculation and ranking results of winter energy supply and demand data provided by an embodiment of the present invention. Figure 5 and Table 7 show the calculation results of the comprehensive weighted values ​​of the optimal energy supply and demand data in winter, such as Figure 5 The results show that under the two scenario conditions of considering and not considering the level of differentiation of energy supply and demand, the optimal energy supply plan of the system is operating condition 2, the system operating cost is 25,176.04 yuan, and the corresponding supply and demand deviations of electricity, heat and cooling are 1,176.20 kW, 411.58 kW and 928.13 kW respectively.

[0186] Optional, see Figure 6 The optimal energy supply strategy diagram for a typical summer day provided by the embodiment of the present invention shows the equipment output corresponding to the optimal energy supply strategy for a typical summer day. Figure 6 (a) shows the power load of the power grid and gas turbine power generation on a typical day in summer. Figure 6 (b) shows the cooling load of the electric chiller and the lithium bromide chiller on a typical summer day. Figure 7 The optimal energy supply strategy diagram for a typical winter day provided by the embodiment of the present invention. Figure 7 As shown in Figure 1, the equipment output corresponding to the optimal energy supply strategy on a typical winter day is shown. Figure 7 (a) shows the power load of the power grid and gas turbine power generation on a typical winter day. Figure 7 (b) shows the heat load of the supplementary-fired boiler and the waste heat boiler on a typical day in winter.

[0187] like Figure 6 and Figure 7 As shown, firstly, the electricity demand of two types of typical days is mainly met by gas turbines. This is because when the gas turbine generates electricity, the high-temperature waste heat flue gas generated is utilized by the lithium bromide refrigerator and the waste heat boiler, thereby reducing the energy input cost. Therefore, the system prefers to be powered by gas turbines.

[0188] Secondly, the cooling load on a typical day in summer is mainly met by lithium bromide refrigerators. As for the high proportion of cooling capacity of electric refrigerators from 21:00 to 1:00, the main reason is that this period is a period of low electricity prices, and the economic cost of purchasing electricity from the power grid is lower. Similarly, the heat demand on a typical day in winter is mainly met by waste heat boilers. The main reason is that waste heat boilers use the waste heat generated during the power generation process of gas turbines as an energy source, realizing the cascade utilization of energy, thereby reducing the operating cost of the system, which fully reflects the flexible energy supply form of the integrated energy system and the main advantage of realizing the cascade utilization of energy.

[0189] The embodiment of the present invention provides an energy supply and demand optimization evaluation method and system, which obtains energy supply and demand data under preset working conditions, and based on the energy supply and demand data, takes energy supply and demand balance restrictions and energy equipment power restrictions as constraints, calculates an objective function with the goal of minimizing the operation and maintenance cost of energy equipment, and calculates the equipment output in more detail and accuracy; performs probability calculation on the objective function through a genetic algorithm, and then determines a target supply deviation set; uses an entropy weight method to calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation, and determines the smallest value as the target weight coefficient, thereby avoiding the phenomenon of energy supply and demand imbalance; evaluates the operation and maintenance cost and supply deviation based on the target weight coefficient, and outputs an optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of the operation and maintenance cost and the supply deviation, so that the operation strategy formulated is associated and interactive with the actual operation of the equipment, which is more reasonable and reliable, and realizes diversified utilization and flexible allocation of energy while taking into account the minimization of resource consumption costs.

[0190] See also Figure 8 , is a schematic diagram of the architecture of an energy supply and demand optimization evaluation system provided by an embodiment of the present invention. Figure 8 As shown, the system includes:

[0191] An optimization module is run to obtain energy supply and demand data under preset working conditions, and based on the energy supply and demand data, an objective function with the energy supply and demand balance limit and the energy equipment power limit as constraints is calculated to minimize the energy equipment operation and maintenance cost;

[0192] An intelligent optimization algorithm module, used for performing probability calculation on the objective function through a genetic algorithm, thereby determining a target supply deviation set;

[0193] A target coefficient generation module calculates the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using an entropy weight method, and determines the smallest value as the target weight coefficient;

[0194] The global optimal strategy module evaluates the operation and maintenance cost and supply deviation based on the target weight coefficient and outputs the optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of operation and maintenance cost and supply deviation.

[0195] In a possible embodiment, the system further includes:

[0196] The equipment simulation module is used to calculate the historical operating data of the energy equipment under the preset working conditions, and input the historical operating data into the mechanism simulation model for simulation operation to determine the energy supply and demand data, which includes: energy demand and the energy supply produced by the corresponding equipment.

[0197] In a possible embodiment, the device simulation module includes (not shown in the figure):

[0198] A data calculation unit, which calculates and obtains historical operation data based on the operation and maintenance cost of the energy equipment, the compressor operation data, the combustion chamber operation data, the turbine operation data contained in the operation of the gas turbine, and the heat generation data of the gas boiler, the waste heat boiler, the lithium bromide refrigerator, and the electric refrigerator;

[0199] The energy equipment includes: a gas turbine, a gas boiler, a waste heat boiler, a lithium bromide refrigerator and an electric refrigerator.

[0200] In a possible embodiment, the intelligent optimization algorithm module includes (not shown in the figure):

[0201] A fitness unit, used for constructing a fitness function for the objective function using a reciprocal method;

[0202] A probability calculation unit, used for calculating the selection probability of the supply deviation corresponding to the objective function under each working condition based on the fitness function by using a roulette method;

[0203] An initial set unit, configured to perform crossover operation calculation based on the selection probability of the supply deviation under at least two working conditions, obtain a new supply deviation under the corresponding working condition, and combine the new supply deviation with the supply deviation corresponding to the objective function to form an initial supply deviation set;

[0204] A mutation unit is used to perform a mutation operation on the initial supply deviation set through a mutation probability so that any supply deviation in the initial supply deviation set produces multiple optional supply and demand modes, thereby generating a target supply deviation set; the supply deviation is the difference between the energy demand and the energy supply in the energy supply and demand data.

[0205] In a possible embodiment, the system further includes (not shown in the figure):

[0206] An indicator level module, used to set m evaluation indicators for the supply deviation and the corresponding operation and maintenance cost, and to determine the importance level of any evaluation indicator among n importance levels;

[0207] A table generation module, used for generating an importance table according to the m evaluation indicators and the n importance levels;

[0208] A matrix generation module is used to generate a sampling matrix according to the importance table.

[0209] In a possible embodiment, the target coefficient generation module includes (not shown in the figure):

[0210] The coefficient calculation unit is used to calculate the sampling matrix using the entropy weight method to determine the weight coefficient of each supply deviation in the supply deviation set, as well as the weight coefficient of the operation and maintenance cost corresponding to the supply deviation. The calculation formula is as follows:

[0211]

[0212] Where P ij is the standardized value of the jth importance level of the ith evaluation indicator; r ij is the initial value of the jth importance level of the ith evaluation indicator in the sampling matrix, i = 1, 2, ..., m, m = 4, representing the type of evaluation indicator; j = 1, 2, ..., n, n = 5, representing the importance level in descending order from high to low; H i is the entropy value of the i-th evaluation index; k is the importance level coefficient; V i is the difference coefficient of the i-th evaluation index; W i is the weight coefficient of the i-th evaluation index;

[0213] The target coefficient selection unit is used to minimize the supply deviation W i As the target weight coefficient of the supply deviation, and the operation and maintenance cost W that minimizes the value i As the target weight coefficient of operation and maintenance cost; the evaluation indicators include: operation and maintenance cost, the gap between power supply and user demand, the gap between cooling capacity and user cooling demand, and the gap between heating capacity and user heating demand.

[0214] In a possible embodiment, the system further includes (not shown in the figure):

[0215] The normalization processing module is used to normalize the m evaluation indicators of the operation and maintenance cost and the supply deviation. The calculation formula is as follows:

[0216]

[0217] Among them, q i is the standardized value of the i-th indicator to be normalized; s i is the absolute value of the ith evaluation index.

[0218] In a possible embodiment, the global optimal strategy module includes (not shown in the figure):

[0219] A comprehensive weighted index unit calculates a comprehensive weighted index for energy supply and demand data corresponding to the supply deviation and the operation and maintenance cost under each operating condition based on the target weight coefficients of the supply deviation and the operation and maintenance cost;

[0220] The strategy output unit is used to select the comprehensive weighted index with the smallest value, obtain the operation strategy from the energy supply and demand data corresponding to the comprehensive weighted index with the smallest value, and output the operation strategy as the optimal evaluation operation strategy.

[0221] In a possible embodiment, the policy output unit includes (not shown in the figure):

[0222] The calculation formula is as follows:

[0223]

[0224] w i is the target weight coefficient of the i-th evaluation index; q i is the standardized value of the i-th indicator to be normalized, i = 1, 2, …, m.

[0225] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

Claims

1. A method for optimizing energy supply and demand, characterized in that: include: Obtaining energy supply and demand data under preset working conditions, and based on the energy supply and demand data, calculating an objective function with the goal of minimizing the energy equipment operation and maintenance cost with energy supply and demand balance constraints and energy equipment power constraints as constraints; Performing probability calculation on the objective function through a genetic algorithm, thereby determining a target supply deviation set; Calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using the entropy weight method, and determine the smallest value as the target weight coefficient; The operation and maintenance cost and supply deviation are evaluated based on the target weight coefficient, and an optimal evaluation operation strategy is output; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of the operation and maintenance cost and the supply deviation.

2. The method according to claim 1, characterized in that The method further comprises: Calculate the historical operating data of the energy equipment under the preset working conditions, and input the historical operating data into the mechanism simulation model for simulation operation to determine the energy supply and demand data, which includes: energy demand and energy supply produced by the corresponding equipment.

3. The method according to claim 2, characterized in that The energy equipment includes: gas turbines, gas boilers, waste heat boilers, lithium bromide refrigerators and electric refrigerators; The historical operation data of the energy equipment under the preset working conditions is calculated, including: Based on the operation and maintenance cost of the energy equipment, the compressor operation data, combustion chamber operation data, turbine operation data contained in the operation of the gas turbine, and the heat production data of the gas boiler, waste heat boiler, lithium bromide refrigerator, and electric refrigerator are calculated to obtain historical operation data.

4. The method according to claim 1, characterized in that: The supply deviation is the difference between the energy demand and the energy supply in the energy supply and demand data; The method of performing probability calculation on the objective function by using a genetic algorithm to determine a target supply deviation set includes: Constructing a fitness function for the objective function using the inverse method; Calculate the selection probability of the supply deviation corresponding to the objective function under each working condition based on the fitness function by using the roulette method; Perform crossover calculation based on the selection probability of the supply deviation under at least two working conditions to obtain a new supply deviation under the corresponding working condition, and combine the new supply deviation with the supply deviation corresponding to the objective function to form an initial supply deviation set; The initial supply deviation set is mutated by mutation probability, so that any supply deviation in the initial supply deviation set generates multiple optional supply and demand modes, thereby generating a target supply deviation set.

5. The method according to claim 1, characterized in that The method of using the entropy weight method to calculate the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation, and determining the smallest value as the target weight coefficient, includes: m evaluation indicators are set for the supply deviation and the corresponding operation and maintenance cost, and the importance level of any evaluation indicator is determined among n importance levels; Generating an importance table according to the m evaluation indicators and the n importance levels; A sampling matrix is ​​generated according to the importance table.

6. The method according to claim 5, characterized in that The method of calculating the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using the entropy weight method, and determining the smallest value as the target weight coefficient, includes: The sampling matrix is ​​calculated using the entropy weight method to determine the weight coefficient of each supply deviation in the supply deviation set, as well as the weight coefficient of the operation and maintenance cost corresponding to the supply deviation. The calculation formula is as follows: Where P ij is the standardized value of the jth importance level of the ith evaluation indicator; r ij is the initial value of the jth importance level of the ith evaluation indicator in the sampling matrix, i = 1, 2, ..., m, m = 4, representing the type of evaluation indicator; j = 1, 2, ..., n, n = 5, representing the importance level in descending order from high to low; H i is the entropy value of the i-th evaluation index; k is the importance level coefficient; V i is the difference coefficient of the i-th evaluation index; W i is the weight coefficient of the i-th evaluation index; The supply deviation W with the smallest value i As the target weight coefficient of the supply deviation, and the operation and maintenance cost W that minimizes the value i As the target weight coefficient of operation and maintenance cost; The evaluation indicators include: operation and maintenance cost, the gap between power supply and user demand, the gap between cooling capacity and user cooling demand, and the gap between heating capacity and user heating demand.

7. The method according to claim 6, characterized in that The step of evaluating the operation and maintenance cost and supply deviation based on the target weight coefficient and outputting the optimal evaluation operation strategy includes: The m evaluation indicators of the operation and maintenance cost and the supply deviation are normalized, and the calculation formula is as follows: Among them, q i is the standardized value of the i-th indicator to be normalized; s i is the absolute value of the ith evaluation index.

8. The method according to any one of claims 1 to 7, characterized in that: The operation and maintenance cost and supply deviation are evaluated based on the target weight coefficient, and an optimal evaluation operation strategy is output; The optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of operation and maintenance cost and supply deviation, and includes: Based on the target weight coefficients of the supply deviation and operation and maintenance cost, a comprehensive weighted index is calculated for the energy supply and demand data corresponding to the supply deviation and operation and maintenance cost under each operating condition; A comprehensive weighted index with the smallest value is selected, an operation strategy is obtained from energy supply and demand data corresponding to the comprehensive weighted index with the smallest value, and the operation strategy is output as an optimal evaluation operation strategy.

9. The method according to claim 8, characterized in that The target weight coefficient based on the supply deviation and operation and maintenance cost is used to calculate the comprehensive weighted index of the energy supply and demand data corresponding to the supply deviation and operation and maintenance cost under each working condition. The calculation formula is as follows: w i is the target weight coefficient of the i-th evaluation index; q i is the standardized value of the i-th indicator to be normalized, i = 1, 2, …, m.

10. An energy supply and demand optimization evaluation system, characterized in that: include: An optimization module is run to obtain energy supply and demand data under preset working conditions, and based on the energy supply and demand data, an objective function with the energy supply and demand balance limit and the energy equipment power limit as constraints is calculated to minimize the energy equipment operation and maintenance cost; An intelligent optimization algorithm module, used for performing probability calculation on the objective function through a genetic algorithm, and then determining a target supply deviation set; A target coefficient generation module calculates the supply deviation in the target supply deviation set and the weight coefficient of the operation and maintenance cost corresponding to the supply deviation by using an entropy weight method, and determines the smallest value as the target weight coefficient; The global optimal strategy module evaluates the operation and maintenance cost and supply deviation based on the target weight coefficient and outputs the optimal evaluation operation strategy; the optimal evaluation operation strategy is determined with the goal of minimizing the comprehensive weighted index of operation and maintenance cost and supply deviation.

Images