Coal mine integrated energy system optimization method based on time-sharing multi-task optimization

Abstract

The invention discloses a coal mine integrated energy system optimization method based on time-sharing multi-task optimization. The method comprises the following steps: S1, establishing a CMIES optimization model; s2, taking the minimum cost and the minimum waste energy cost as optimization targets of a CMIES optimization model; s3, determining constraint conditions according to an optimization target of the CMIES optimization model and operation requirements of the coal mine integrated energy system; and S4, executing operation on the optimization target by using a time-sharing multi-task optimization method. According to the method, sub-problems are set for problem decoupling, so that the optimization difficulty is reduced; through a two-stage optimization strategy, the convergence speed of the algorithm is improved; by setting a single-target auxiliary population, the algorithm diversity is improved, so that more solutions are provided; the method is high in robustness and can be suitable for coal mine data in different scenes.

Description

Technical Field

[0001] The invention belongs to the technical field of energy system optimization, and in particular relates to an optimization method for a coal mine integrated energy system based on multi-task optimization at different times. Background Art

[0002] An integrated energy system (IES) can seamlessly and coordinately convert heterogeneous energy subsystems by deeply integrating various energy resources such as electricity, coal, oil, and biomass energy, demonstrating excellent characteristics of high energy efficiency, environmental friendliness, and cost-effectiveness. Compared with traditional IESs, a series of associated energy sources are generated during coal mining, including air thermal energy, methane released during ventilation, abundant mine water resources, and geothermal energy stored underground. Effectively exploiting and utilizing these associated energy sources can not only greatly avoid energy waste but also significantly reduce the degree of damage to the natural ecosystem. Therefore, it is particularly important to construct a highly efficient coal mine integrated energy system (CMIES).

[0003] The optimization of CMIES requires reasonably scheduling the energy supply of each device on the premise of meeting the constraints of supply-demand balance and the constraints of the system itself, so as to reduce costs and emissions. However, characteristics such as strong constraints caused by the supply-demand balance of electric, thermal, and cooling energy, large-scale optimization variables caused by hourly scheduling, non-linearity caused by indicator variables, and strong coupling relationships between multiple devices make the optimization of CMIES very difficult. Although some optimization methods have been proposed to solve this problem, the characteristics of large-scale constraints and multi-objectives of the problem itself still prevent the existing methods from providing better solutions. Summary of the Invention

[0004] In order to solve the above problems, the invention provides an optimization method for a coal mine integrated energy system based on multi-task optimization at different times, providing a better solution for the energy scheduling of CMIES.

[0005] The technical solution adopted by the invention is as follows: An optimization method for a coal mine integrated energy system based on multi-task optimization at different times, comprising the following steps:

[0006] S1. Establish a CMIES optimization model. The CMIES optimization model includes photovoltaic (PV), wind turbine (WT), power grid (PG), gas turbine (GT), vent oxidation heat pump (VOHP), water source heat pump (WSHP), ground source heat pump (GSHP), air source heat pump (ASHP), absorption chiller (AC), electric chiller (EC), electricity storage device (ES), and heat storage device (HS). The VOHP, WSHP, GSHP, and ASHP are coal mine associated energy devices. PV and WT generate electricity by converting solar energy and wind energy, and are integrated with other power sources through the PG. GT provides electricity and uses waste heat to provide heat energy. AC and EC provide cooling energy. ES and HS are used to store excess electrical energy and heat energy.

[0007] S2. Take minimizing cost and minimizing waste energy cost as the optimization objectives of the CMIES optimization model.

[0008] S3. Determine the constraint conditions according to the optimization objectives of the CMIES optimization model and the operation requirements of the coal mine integrated energy system.

[0009] S4. Use the multi-task optimization method at different times to perform operations on the optimization objectives.

[0010] Furthermore, the optimization objectives include minimizing cost and minimizing waste energy cost.

[0011] The minimizing cost includes purchase cost C buy,t and equipment maintenance cost C opma,t :

[0012]

[0013] In the formula, T represents the scheduling period, α is the cost coefficient, P, H, and Q respectively represent the output electrical energy, heat energy, and cooling energy power of each device, x es_in,t and x es_out,t respectively represent the charge and discharge states of the electricity storage device, and x ts_in,t and x ts_out,t respectively represent the charge and heat release states of the heat storage device.

[0014] The minimizing waste energy cost includes waste renewable energy cost and waste coal mine associated energy cost:

[0015]

[0016] In the formula, λ is the penalty coefficient of waste energy, P max and H max respectively represent the maximum output electrical energy power and heat energy power of each device.

[0017] Furthermore, the constraint conditions include electrical balance constraint, thermal balance constraint, cold balance constraint, device output constraint, energy conversion constraint, gas turbine ramp constraint, thermal energy storage device constraint, and electrical energy storage device constraint;

[0018] The electrical balance constraint:

[0019]

[0020] In the formula, P load,t represents the electrical load at time t;

[0021] The thermal balance constraint:

[0022]

[0023] In the formula, H load,t represents the thermal load at time t;

[0024] The cold balance constraint:

[0025] Q ec,t +Q ac,t =Q load,t (5)

[0026] In the formula, Q load,t represents the cold load at time t;

[0027] The device output constraint and energy conversion constraint:

[0028]

[0029] In the formula: P max and P min respectively represent the maximum and minimum output electric power of each device, and τ represents the energy conversion coefficient of each device;

[0030] The gas turbine ramp constraint:

[0031]

[0032] In the formula, R up and R down respectively represent the maximum and minimum limits of the gas turbine ramp;

[0033] The thermal energy storage device constraint:

[0034]

[0035] In the formula, when x ts_out,t equals 1 and x ts_in,t equals 0, the device is in the heat release state; when x ts_out,t equals 0 and x ts_in,tWhen it is equal to 1, the device is in the heat charging state; x ts_out,t When it is equal to 0 and x ts_in,t When it is equal to 0, the device is in the static state; and respectively represent the maximum heat release and heat charging power of the device, and respectively represent the maximum and minimum heat storage limits of the device;

[0036] The constraints of the electricity storage device are as follows:

[0037]

[0038] In the formula, x es_out,t When it is equal to 1 and x es_in,t When it is equal to 0, the device is in the discharging state; x es_out,t When it is equal to 0 and x es_in,t When it is equal to 1, the device is in the charging state; x es_out,t When it is equal to 0 and x es_in,t When it is equal to 0, the device is in the static state; and respectively represent the maximum discharging and charging power of the device, and respectively represent the maximum and minimum electricity storage limits of the device.

[0039] Furthermore, the S4 includes the following steps:

[0040] S401, decompose the objective function and the constraint function into N scheduling moments, and the tasks at each scheduling moment are called sub-problems, which are represented by formula 10:

[0041]

[0042] S402, set t = 0;

[0043] S403, set t = t + 1, if t is greater than N, jump to S408, otherwise initialize the populations SDAP t and SSAP t , and evaluate the populations on the t-th sub-problem;

[0044] S404, record the computational resources used FES = 2 * NP, and set the counter T = 0;

[0045] S405, set the initial constraint boundary values where CV outputs the constraint violation degree of the population;

[0046] S406, evolve the population SDAP on the t-th sub-problem through offspring generation and environmental selection operationst and SSAP t ;

[0047] S407, Determine whether the set maximum evaluation times is reached. If so, jump to S403 and output SDAP t and SSAP t , otherwise jump to S406;

[0048] S408, Use the random splicing method to splice the N SDAPs and N SSAPs output in step S407 respectively to obtain the initial populations DAP and SAP in the second stage;

[0049] S409, Randomly initialize a population MP of size NP;

[0050] S410, Evaluate the three populations on the original problem, record FES = 3 * NP, and set the counter T = 0;

[0051] S411, Set the initial constraint boundary value ∈ DAP,max = max(CV(DAP)), ∈ SAP,max = max(CV(SAP));

[0052] S412, Through offspring generation and environmental selection operations, evolve the populations DAP and SAP on the t-th sub-problem;

[0053] S413, Determine whether the set maximum evaluation times is reached. If so, the optimization ends and output DAP, otherwise jump to S412.

[0054] Furthermore, the specific steps of S406 include:

[0055] S4061, Set T = T + 1 and update the constraint boundary value using the following formula:

[0056]

[0057] In the formula: MaxT represents the maximum number of evolutionary generations;

[0058] S4062, SDAP t Generate NP / 2 offspring individuals through the offspring generation strategy, denoted as OSDAP t ;

[0059] S4063, SSAP t Generate NP / 2 offspring individuals through the offspring generation strategy, denoted as OSSAP t ;

[0060] S4064, Set FES = FES + NP;

[0061] S4065, set TOP = [OSDAP t ∪OSSAP t ;

[0062] S4066, SDAP selects NP individuals from SDAP and TOP using the improved epsilon method to form a new SDAP;

[0063] S4067, SSAP selects NP individuals from SSAP and TOP using the improved epsilon method to form a new SDAP, where the f 2 value of all individuals is set to 0.

[0064] Furthermore, the specific steps of the random splicing method in S408 include:

[0065] S4081, set the counter i = 1;

[0066] S4082, for each moment t ∈ {1, 2,..., N}, randomly select an individual from the corresponding population P t and denote it as X t ;

[0067] S4083, splice the N Xs in order to obtain a new individual Q i ;

[0068] S4084, i = i + 1. If i is greater than NP, then S408 stops; otherwise, jump to S4082.

[0069] Furthermore, the specific steps of S412 include:

[0070] S4121, set T = T + 1 and update the constraint boundary value using the following formula:

[0071]

[0072] S4122, MP generates NP / 2 offspring individuals through the offspring generation strategy and denotes them as OMP;

[0073] S4123, DAP generates NP / 2 offspring individuals through the offspring generation strategy and denotes them as ODAP;

[0074] S4124, SAP generates NP / 2 offspring individuals through the offspring generation strategy and denotes them as OSAP;

[0075] S4125, set FES = FES + 1.5 * NP;

[0076] S4126. The MP selects NP individuals from the set {MP, OMP, ODAP, OSAP} using the constraint domination criterion method to form a new MP;

[0077] S4127. The DAP selects NP individuals from the set {DAP, ODAP, OMP, OSAP} using the improved epsilon method to form a new DAP;

[0078] S4128. The SAP selects NP individuals from the set {DAP, OSAP, ODAP} using the improved epsilon method to form a new SAP, where the f value of all individuals is set to 0. 2 Value is set to 0.

[0079] The beneficial effects of the present invention are as follows:

[0080] (1) By decoupling the problem and setting sub - problems, the optimization difficulty is reduced;

[0081] (2) Through the two - stage optimization strategy, the convergence speed of the algorithm is improved;

[0082] (3) By setting a single - objective auxiliary population, the diversity of the algorithm is improved to provide more solutions;

[0083] (4) The method has strong robustness and can be applied to coal mine data under different scenarios. Brief Description of the Drawings

[0084] Figure 1 It is the CMIES optimization model of the present invention;

[0085] Figure 2 It is the flowchart of the optimization method in the present invention. Detailed Embodiment

[0086] The present invention will be further described below with reference to the drawings.

[0087] The present invention is an optimization method for a coal mine integrated energy system based on multi - task optimization at different times, including the following steps:

[0088] S1. Establish a CMIES optimization model; as Figure 1As shown, the CMIES optimization model includes photovoltaic (PV), wind turbine (WT), power grid (PG), gas turbine (GT), waste air oxidation heat pump (VOHP), water source heat pump (WSHP), ground source heat pump (GSHP), air source heat pump (ASHP), absorption chiller (AC), electric chiller (EC), electricity storage device (ES) and heat storage device (HS); the waste air oxidation heat pump (VOHP), water source heat pump (WSHP), ground source heat pump (GSHP) and air source heat pump (ASHP) are coal mine associated energy devices; PV and WT generate electricity by converting solar energy and wind energy, and are integrated with other power sources through the power grid PG; the gas turbine GT not only provides electricity, but also provides heat energy using waste heat. The waste air oxidation heat pump (VOHP), water source heat pump (WSHP), ground source heat pump (GSHP) and air source heat pump (ASHP) utilize the heat energy resources associated with coal mines to effectively improve energy utilization efficiency. The absorption chiller (AC) and electric chiller (EC) provide cooling energy according to demand. The electricity storage device (ES) and heat storage device (HS) are used to store excess electrical energy and heat energy to cope with load fluctuations.

[0089] S2. Take minimizing cost and minimizing waste energy cost as the optimization objectives of the CMIES optimization model;

[0090] Minimizing cost includes purchase cost C buy,t and equipment maintenance cost C opma,t :

[0091]

[0092] In the formula, T represents the scheduling period (considering the scheduling for a single hour within a day, so T is 24), α is the cost coefficient, P, H and Q respectively represent the output electrical energy, heat energy and cooling energy power of each device, x es_in,t and x es_out,t respectively represent the charge and discharge states of the electricity storage device, and x ts_in,t and x ts_out,t respectively represent the charge and heat release states of the heat storage device;

[0093] The minimizing waste energy cost includes waste renewable energy cost and waste coal mine associated energy cost:

[0094]

[0095] In the formula, λ is the penalty coefficient for waste energy, P max and H max respectively represent the maximum output electrical energy power and heat energy power of each device.

[0096] S3. Determine the constraint conditions according to the optimization objectives of the CMIES optimization model and the operation requirements of the coal mine integrated energy system, including power balance constraints, heat balance constraints, cold balance constraints, device output constraints, energy conversion constraints, gas turbine ramp constraints, heat storage device constraints, and electricity storage device constraints;

[0097] Power balance constraint:

[0098]

[0099] In the formula, P load,t represents the electrical load at time t;

[0100] Heat balance constraint:

[0101]

[0102] In the formula, H load,t represents the heat load at time t;

[0103] Cold balance constraint:

[0104] Q ec,t +Q ac,t =Q load,t (5)

[0105] In the formula, Q load,t represents the cold load at time t;

[0106] Device output constraints and energy conversion constraints:

[0107]

[0108] In the formula: P max and P min respectively represent the maximum and minimum output electric power of each device, and τ represents the energy conversion coefficient of each device;

[0109] Gas turbine ramp constraint:

[0110]

[0111] In the formula, R up and R down respectively represent the maximum and minimum limits of the gas turbine ramp;

[0112] Heat storage device constraint:

[0113]

[0114] In the formula, x ts_out,t equals 1 and x ts_in,t equals 0, the device is in the heat release state; x ts_out,t equals 0 and xts_in,t When it is equal to 1, the device is in the heat charging state; x ts_out,t When it is equal to 0 and x ts_in,t is equal to 0, the device is in the static state; and respectively represent the maximum heat release and heat charging power of the device, and respectively represent the maximum and minimum heat storage limits of the device;

[0115] Constraints of the electrical energy storage device:

[0116]

[0117] In the formula, x es_out,t is equal to 1 and x es_in,t is equal to 0, the device is in the discharging state; x es_out,t is equal to 0 and x es_in,t is equal to 1, the device is in the charging state; x es_out,t is equal to 0 and x es_in,t is equal to 0, the device is in the static state; and respectively represent the maximum discharging and charging power of the device, and respectively represent the maximum and minimum electrical energy storage limits of the device.

[0118] S4. Use the multi-task optimization method at different times to perform operations on the optimization objective, such as Figure 2 shown, including the following steps:

[0119] S401. Decompose the objective function (Formula 1-2) and the constraint function (Formula 3-9) into N scheduling times. The tasks at each scheduling time are called sub-problems, and are represented by Formula 10:

[0120]

[0121] S402. As Figure 2 shown in the box numbered q1, set t = 0;

[0122] S403. As Figure 2 shown in the boxes numbered q2-q4, set t = t + 1. If t is greater than N, jump to S408. Otherwise, initialize the populations SDAP t and SSAP t with a size of NP, and evaluate the populations on the sub-problems;

[0123] S404. Record the computational resources used FES = 2*NP, and set the counter T = 0;

[0124] S405. Set the initial constraint boundary values where CV outputs the constraint violation degree of the population;

[0125] S406, as Figure 2 shown in the box numbered q5, evolve the population SDAP on the t-th sub-problem through offspring generation and environmental selection operations t and SSAP t ; including the following steps:

[0126] S4061, set T = T + 1, and update the constraint boundary value using the following formula:

[0127]

[0128] In the formula: MaxT represents the maximum number of evolutionary generations;

[0129] S4062, SDAP t generate NP / 2 offspring individuals through the offspring generation strategy, denoted as OSDAP t ;

[0130] S4063, SSAP t generate NP / 2 offspring individuals through the offspring generation strategy, denoted as OSSAP t ;

[0131] S4064, set FES = FES + NP;

[0132] S4065, set TOP = [OSDAP t ∪OSSAP t ;

[0133] S4066, SDAP selects NP individuals from SDAP and TOP using the improved epsilon method to form a new SDAP;

[0134] S4067, SSAP selects NP individuals from SSAP and TOP using the improved epsilon method to form a new SDAP, where the f 2 value of all individuals is set to 0;

[0135] S407, as Figure 2 shown in the box numbered q6, determine whether the set maximum number of evaluations is reached. If so, jump to S403 and output SDAP t and SSAP t , otherwise jump to S406;

[0136] S408, as Figure 2As shown in the box numbered q7, using the random splicing method, splice the N SDAPs and N SSAPs output in step S407 respectively to obtain the initial populations DAP and SAP in the second stage, including the following steps:

[0137] S4081, set the counter i = 1;

[0138] S4082, for each moment t ∈ {1, 2, …, N}, randomly select an individual from the corresponding population P t , denoted as X t (P t corresponding to the SDAP in step S408 t or SSAP t );

[0139] S4083, splice the N Xs in order to obtain a new individual Q i ;

[0140] S4084, i = i + 1, if i is greater than NP, then S408 stops, otherwise jump to S4082;

[0141] S409, as Figure 2 shown in the box numbered q7, randomly initialize a population MP of size NP;

[0142] S410, evaluate the three populations on the original problem, record FES = 3 * NP, and set the counter T = 0;

[0143] S411, set the initial constraint boundary value ∈ DAP,max = max(CV(DAP)), ∈ SAP,max = max(CV(SAP));

[0144] S412, as Figure 2 shown in the box numbered q8, through the offspring generation and environmental selection operations, evolve the populations DAP and SAP on the t-th sub-problem; including the following steps:

[0145] S4121, set T = T + 1, and update the constraint boundary value using the following formula:

[0146]

[0147] S4122, MP generates NP / 2 offspring individuals through the offspring generation strategy, denoted as OMP;

[0148] S4123, DAP generates NP / 2 offspring individuals through the offspring generation strategy, denoted as ODAP;

[0149] S4124, SAP generates NP / 2 offspring individuals through the offspring generation strategy, denoted as OSAP;

[0150] S4125, set FES = FES + 1.5 * NP;

[0151] S4126, MP uses the constraint domination criterion method to select NP individuals from the set {MP, OMP, ODAP, OSAP} to form a new MP;

[0152] S4127, DAP uses the improved epsilon method to select NP individuals from the set {DAP, ODAP, OMP, OSAP} to form a new DAP;

[0153] S4128, SAP uses the improved epsilon method to select NP individuals from the set {DAP, OSAP, ODAP,} to form a new SAP, where the f 2 value of all individuals is set to 0.

[0154] S413, as Figure 2 shown in the box numbered q9, determine whether the set maximum evaluation times have been reached. If so, the optimization ends and MP is output, as Figure 2 shown in the box numbered q10. Otherwise, jump to S412.

[0155] To verify the effectiveness of the present invention, the present invention is used to optimize the data of a real coal mine in Shanxi. Among them, the parameters of the present invention are: the population size NP is set to 100, the maximum evaluation times in the first stage is 100000, and the maximum evaluation times in the second stage is 900000.

[0156] The optimization method of the present invention is respectively compared with the existing centralized methods, namely CCMO, TriP, ICMA, IMTCMO, MMDE_EKT_ANM. All algorithms are run 30 times to obtain statistical results.

[0157] The Inverted Generational Distance (IGD) values obtained by the algorithms are shown in Table 1. Among them, the smaller the IGD value, the better the algorithm effect. Analyzing the data in Table 1, it can be seen that the method of the present invention has achieved better results than the five comparison methods in the four indicators of average value, standard deviation, maximum value and minimum value. This is attributed to the proposed sub-problem strategy, two-stage optimization strategy and single-objective auxiliary population strategy, which jointly balance the diversity and convergence of the population, enabling the algorithm to obtain better results within limited computing resources. In actual production operations, users can fully combine these solutions according to their own situations to plan a satisfactory energy scheduling and allocation plan.

[0158] Table 1 Comparison results of the IGD index of the present invention and five other advanced evolutionary algorithms for the optimization problem of the coal mine integrated energy system

[0159] algorithm average value standard deviation maximum value minimum value CCMO 5.37E+02 1.08E+02 7.98E+02 3.03E+02 TriP 4.23E+02 8.68E+01 5.44E+02 1.93E+02 ICMA 3.19E+02 9.14E+01 4.95E+02 1.25E+02 IMTCMO 1.84E+02 9.30E+01 4.62E+02 1.23E+02 MMDE_EKT_ANM 1.87E+02 9.73E+01 5.41E+02 1.23E+02 the method of the present invention 5.55E+01 5.42E+00 6.49E+01 4.34E+01

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Other modifications or equivalent replacements made by those of ordinary skill in the art to the technical solutions of the present invention shall be covered by the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solutions of the present invention.

Claims

1. A coal mine comprehensive energy system optimization method based on time-sharing multi-task optimization, characterized in that: The following steps are involved: S1, establish a CMIES optimization model; the CMIES optimization model includes photovoltaic pv, wind turbine wt, power grid pg, gas turbine gt, exhaust air oxidation heat pump vohp, water source heat pump wshp, ground source heat pump gshp, gas source heat pump ashp, absorption refrigerator ac, electric refrigerator ec, electricity storage device es and heat storage device hs; the exhaust air oxidation heat pump vohp, water source heat pump wshp, ground source heat pump gshp and gas source heat pump ashp are coal mine associated energy devices; photovoltaic pv and wind turbine wt generate electricity by converting solar energy and wind energy, and integrate with other power sources through power grid pg; gas turbine gt provides electricity and uses waste heat to provide heat energy; The absorption refrigerator AC and the electric refrigerator EC provide cold energy; the electric storage device ES and the heat storage device HS are used to store excess electric energy and heat energy; S2, minimizing the cost and minimizing the waste energy cost are taken as the optimization objectives of the CMIES optimization model; S3, determine the constraint conditions according to the optimization objectives of the CMIES optimization model and the operation requirements of the coal mine integrated energy system; S4, using the time-sharing multi-task optimization method to perform operations on the optimization target.

2. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 1, characterized in that: The optimization objectives include minimizing cost and minimizing waste energy cost; The minimization cost includes the purchase cost C buy,t and equipment maintenance cost C opma,t : Where T represents the scheduling period, α is the cost coefficient, P, H and Q represent the output power of each device, heat energy and cooling energy respectively, and x es_in,t and x es_out,t Respectively represent the charging and discharging state of the storage device, x ts_in,t and x ts_out,t They represent the charging and discharging states of the heat storage device respectively; The minimization of the waste energy cost includes the waste renewable energy cost and the waste coal mine associated energy cost: Where λ is the penalty coefficient for waste energy, P max and H max Represent the maximum output electrical power and thermal power of each device respectively.

3. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 1 is characterized in that: The constraints include electrical balance constraints, thermal balance constraints, cold balance constraints, device output constraints and energy conversion constraints, gas turbine ramp constraints, thermal storage device constraints and electrical storage device constraints; The electrical balance constraint: Where P load,t represents the electrical load at time t; The thermal balance constraint: In the formula, H load,t represents the heat load at time t; The cold balance constraint: Q ec,t +Q ac,t =Q load,t (5) In the formula, Q load,t represents the cooling load at time t; The device output constraints and energy conversion constraints are: Where: P max and P min Respectively represent the maximum and minimum output electric power of each device, and τ represents the energy conversion coefficient of each device; The gas turbine ramping constraint: In the formula, R up and R down They represent the maximum and minimum limits of the gas turbine ramping, respectively; The heat storage device constraints: In the formula, x ts_out,t is equal to 1 and x ts_in,t When x is equal to 0, the device is in the exothermic state; ts_out,t is equal to 0 and x ts_in,t When x is equal to 1, the device is in the hot state; ts_out,t is equal to 0 and x ts_in,t When it is equal to 0, the device is in a static state; and Represent the maximum heat release and heat charging power of the device, and Respectively represent the maximum and minimum heat storage limits of the device; The power storage device constraints: In the formula, x es_out,t is equal to 1 and x es_in,t When x is equal to 0, the device is in the discharge state; es_out,t is equal to 0 and x es_in,t When it is equal to 1, the device is in charging state; x es_out,t is equal to 0 and x es_in,t When it is equal to 0, the device is in a stationary state; and Represent the maximum discharge and charge power of the device, and Represent the maximum and minimum power storage limits of the device respectively.

4. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 1 is characterized in that: The S4 comprises the following steps: S401, decompose the objective function and constraint function into N scheduling moments, and the task at each scheduling moment is called a sub-problem, which is expressed by Formula 10: S402, set t=0; S403, set t = t + 1, if t is greater than N, jump to S408, otherwise initialize the population SDAP of size NP t and SSAP t , and evaluate the population on the t-th sub-problem; S404, record the used computing resources FES=2*NP, and set the counter T=0; S405, setting initial constraint boundary value Among them, CV outputs the constraint violation degree of the population; S406, Evolving the population SDAP on the tth subproblem through offspring generation and environmental selection operations t and SSAP t ; S407, determine whether the set maximum number of evaluations has been reached. If so, jump to S403 and output SDAP t and SSAP t Otherwise, jump to S406; S408, using a random splicing method, splicing the N SDAPs and N SSAPs outputted in step S407 respectively to obtain the initial population DAP and SAP of the second stage; S409, randomly initialize a population MP of size NP; S410, evaluate the three populations on the original problem, record FES=3*NP, and set the counter T=0; S411, set the initial constraint boundary value ∈ DAP,max =max(CV(DAP)),∈ SAP,max =max(CV(SAP)); S412, evolving population DAP and SAP on the t-th subproblem through offspring generation and environmental selection operations; S413, judging whether the set maximum number of evaluation times has been reached, if so, the optimization ends and the DAP is output, otherwise, jumping to S412.

5. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 4 is characterized in that: The specific steps of S406 include: S4061, set T = T + 1, and use the following formula to update the constraint boundary value: Where: MaxT represents the maximum evolutionary generation; S4062, SDAP t The offspring generation strategy produces NP / 2 offspring individuals, denoted as OSDAP t ; S4063, SSAP t The offspring generation strategy generates NP / 2 offspring individuals, denoted as OSSAP t ; S4064, set FES=FES+NP; S4065, set TOP = [OSDAP t ∪OSSAP t ]; S4066, SDAP uses the improved epsilon method to select NP individuals from SDAP and TOP to form a new SDAP; S4067, SSAP uses the improved epsilon method to select NP individuals from SSAP and TOP to form a new SDAP, in which the f2 values ​​of all individuals are set to 0.

6. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 4 is characterized in that: The specific steps of the random splicing method in S408 include: S4081, set counter i=1; S4082, for each time t∈{1,2,…,N}, from the corresponding population P t Randomly select an individual from t ; S4083, splice N Xs in order to get a new individual Q i ; S4084, i=i+1, if i is greater than NP, then S408 stops, otherwise jumps to S4082.

7. The method for optimizing a coal mine comprehensive energy system based on time-sharing multi-task optimization according to claim 4 is characterized in that: The specific steps of S412 include: S4121, set T = T + 1, and use the following formula to update the constraint boundary value: S4122, MP produces NP / 2 offspring individuals through the offspring generation strategy, denoted as OMP; S4123, DAP produces NP / 2 offspring individuals through the offspring generation strategy, recorded as ODAP; S4124, SAP produces NP / 2 offspring individuals through the offspring generation strategy, recorded as OSAP; S4125, set FES=FES+1.5*NP; S4126, MP uses the constraint dominance criterion method to select NP individuals from the set {MP, OMP, ODAP, OSAP} to form a new MP; S4127, DAP uses the improved epsilon method to select NP individuals from the set {DAP, ODAP, OMP, OSAP} to form a new DAP; S4128, SAP uses the improved epsilon method to select NP individuals from the set {DAP, OSAP, ODAP,} to form a new SAP, where the f2 values ​​of all individuals are set to 0.

Images