Self-adaptive load management and optimization control method for micro-grid

Abstract

The invention discloses a self-adaptive load management and optimization control method for a micro-grid, and relates to the technical field of micro-grids. A storage battery-supercapacitor hybrid energy storage unit is arranged in the micro-grid; comprising the following steps: acquiring load data and renewable energy power generation data in a micro-grid, respectively calculating load demand and power generation prediction values by adopting a machine learning algorithm, and acquiring system operation state data to calculate hybrid energy storage of a hybrid energy storage unit; establishing an optimization management objective function and constraint conditions according to the load demand, the power generation capacity prediction value, the hybrid energy storage capacity, the system operation state data and the hybrid energy storage coordination control strategy; and solving the optimization management objective function by adopting an improved genetic algorithm according to the constraint condition, and obtaining a scheduling instruction. The problems of load fluctuation and renewable energy source intermittency in the operation process of the micro-grid are solved, the working state of loads such as a charging pile or an air conditioner is optimally controlled, and the operation efficiency and reliability of the micro-grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrids, and more particularly to an adaptive load management and optimization control method for microgrids. Background Art

[0002] At present, with the transformation of energy structure and the rapid development of distributed energy, microgrid, as a new form of power system, has high flexibility and reliability. Microgrid is a small power generation, distribution and consumption system composed of distributed power sources, energy storage systems, energy conversion devices, monitoring and protection devices, loads, etc. It is a self-consistent system with self-control and self-energy management. It can be connected to the external power grid or run in isolation. However, the distributed power sources in the microgrid, such as photovoltaic power generation systems and wind power generation systems, have output power that changes with changes in climatic conditions and environmental factors, and have strong randomness, and cannot guarantee the continuity of power supply. At the same time, the microgrid faces problems such as load fluctuations during operation, which seriously affects the working efficiency and stability of the microgrid and causes energy waste.

[0003] Therefore, how to effectively perform load management and optimization control of microgrids is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of this, the present invention provides an adaptive load management and optimization control method for a microgrid, aiming to solve the problems of load fluctuation and intermittent renewable energy faced by the microgrid during operation, and to improve the operation efficiency and reliability of the microgrid.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A method for adaptive load management and optimization control of a microgrid, wherein a battery-supercapacitor hybrid energy storage unit is provided in the microgrid, comprises the following steps:

[0007] Step 1: Collect load data, renewable energy generation data, and system operation status data in the microgrid in real time through sensors and communication networks;

[0008] Step 2: Use machine learning algorithms to predict loads based on load data to obtain load demand; use machine learning algorithms to predict power generation based on renewable energy power generation data to obtain power generation forecast values; calculate the hybrid storage energy of the battery-supercapacitor hybrid energy storage unit based on system operating status data;

[0009] Step 3: According to the load demand, power generation forecast, hybrid energy storage and system operation status data, the optimal management objective function and constraint conditions are established in combination with the preset hybrid energy storage coordinated control strategy;

[0010] Step 4: According to the constraints, an improved genetic algorithm is used to solve the optimal solution of the optimization management objective function and obtain the scheduling instructions.

[0011] Preferably, step 1 also includes preprocessing the collected data, including data cleaning, outlier processing and feature extraction.

[0012] Preferably, the battery-supercapacitor hybrid energy storage unit includes a plurality of groups of batteries and supercapacitors arranged in a distributed manner, and one battery corresponds to one supercapacitor.

[0013] Preferably, the system operation status data includes supercapacitor status parameters, battery status parameters, real-time load and power demand, ambient temperature, etc., and the hybrid energy storage capacity is calculated based on the supercapacitor status parameters and battery status parameters.

[0014] Preferably, the hybrid energy storage coordination control strategy is: when the battery is discharged, the charge state of the supercapacitor is lower than the set minimum charge threshold and is at a lower level. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the main and the battery is used as the auxiliary to smooth the power distribution. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution; when the battery is charged, the charge state of the supercapacitor is higher than the set maximum charge threshold and is at a higher level. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution.

[0015] Preferably, when smoothing power distribution according to real-time load and power demand, a high-pass filter is used in the microgrid to smooth the microgrid power P of the battery-supercapacitor hybrid energy storage unit in the real-time load and power demand. ST Filter and obtain the required smoothing power P ref The high frequency component P ref_sc , as the supercapacitor's smoothing power, the required smoothing power P ref The remaining low-frequency components P ref_b As the battery's smoothing power, when the smoothing power P ref >0, the battery-supercapacitor hybrid energy storage unit discharges, and the power P needs to be smoothed ref <0, the battery-supercapacitor hybrid energy storage unit is charged; the high frequency component P ref_sc and low frequency component P ref_b The expressions are:

[0016]

[0017] Among them, T f is the filtering time constant determined according to the supercapacitor's smoothing power, P ref_sc Follow P ST Fluctuating and violent fluctuations, P ref_b Follow P ST Fluctuating and slowly fluctuating, s represents the moment of power fluctuation.

[0018] Preferably, a power purchase cost model is constructed according to load demand, a power generation income model is constructed according to power generation forecast value and hybrid energy storage capacity, and an optimization management objective function and constraint conditions are established in combination with the constructed hybrid energy storage cost model, real-time load and power demand and hybrid energy storage coordinated control strategy; the optimization management objective function is expressed as:

[0019]

[0020] C in =C in_t (D f_t +D h_t );

[0021] C out =C out_t D out_t ;

[0022] C b_sc =C1+C2+C3;

[0023] Among them, C total represents the comprehensive cost of microgrid; C in represents the power generation revenue model; C out represents the electricity purchase cost model; C b_sc represents the hybrid energy storage cost model; t represents time; C in_t represents the electricity price at time t; D f_t represents the predicted value of power generation at time t; D h_t represents the mixed energy storage at time t; C out_t represents the electricity purchase price at time t; D out_t represents the load demand at time t; C1 represents the initial investment cost of the battery-supercapacitor hybrid energy storage unit; C2 represents the replacement cost of the battery-supercapacitor hybrid energy storage unit; C3 represents the recovery cost of the battery-supercapacitor hybrid energy storage unit;

[0024] The constraints include power balance constraint, energy storage balance constraint and exchange power limit. The power balance constraint when the microgrid is operating independently is expressed as:

[0025]

[0026] P Gi represents the power generated by the i-th distributed generation unit in the microgrid in real-time load and power demand; L represents the number of distributed generation units in the microgrid; P ref_sc,j represents the smoothing power of the jth group of supercapacitors, P ref_b,j represents the smoothing power of the jth battery group; M represents the number of batteries and supercapacitor groups; P L is the power required by the load;

[0027] The power balance constraint when the microgrid is connected to the grid is expressed as:

[0028]

[0029] P GRID It represents the power absorbed or emitted by the grid to which the microgrid is connected in real-time load and power demand. When the output microgrid outputs power to the grid, P GRID ≥0, when the output microgrid outputs power to the grid, P GRID <0;

[0030] The energy balance constraint of energy storage is expressed as:

[0031]

[0032]

[0033] B SOC Indicates the battery state of charge obtained based on the battery state parameters, Respectively represent the lower limit of battery state of charge and the upper limit of battery state of charge; SC SOC Indicates the state of charge of the supercapacitor obtained according to the supercapacitor state parameters, They represent the lower limit of the supercapacitor state of charge and the upper limit of the supercapacitor state of charge respectively;

[0034] The switching power limit is expressed as:

[0035]

[0036] and They represent the lower power limit and upper power limit of energy exchange between the microgrid and the grid respectively.

[0037] Preferably, the improved genetic algorithm, based on the existing genetic algorithm, clusters the individuals whose fitness values ​​are greater than the set fitness threshold when generating the initial population to form a direct genetic sub-population. The direct genetic sub-population is not subjected to crossover and mutation processing, and is mixed with the individuals of the second-generation to form a second-generation initialization population.

[0038] Preferably, the method further comprises step 5, wherein a bandwidth control strategy is adopted to further optimize the control instructions, wherein the bandwidth expression is:

[0039]

[0040] Among them, k l and k h are the lower limit control bandwidth coefficient and the upper limit control bandwidth coefficient respectively; C min (t) and C max (t) respectively represent the lower limit and upper limit of the optimization management objective function at time t; C(t) represents the value of the optimization management objective function at time t;

[0041] Compare the minimum values ​​of the optimization management objective function at time t and time t+1. If the optimization management objective function value C(t+1) at time t+1 is within the bandwidth range, the improved genetic algorithm is not used to solve the optimal solution, and the dispatching instruction at the previous moment is used to control the microgrid. Otherwise, the optimal solution is solved and a new dispatching instruction is obtained to control the microgrid.

[0042] Preferably, the loads in the microgrid include charging piles and / or air conditioners, the load data include charging pile power consumption and / or air conditioner power consumption, and the real-time load and power demand in the system operation status data include the charging pile connection status, charging pile operating power, and the air conditioner connection status, and air conditioner operating power.

[0043] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method for adaptive load management and optimization control of a microgrid, which has strong adaptability. Through real-time data collection and load prediction, it can perform adaptive load management and optimization control according to the operating status and load changes of the microgrid; high reliability: through load scheduling and optimization, the load can be reasonably distributed to improve the operating efficiency and reliability of the microgrid; high utilization rate of renewable energy: through energy management, it can maximize the utilization of renewable energy and reduce energy consumption and environmental pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0045] Figure 1 A schematic diagram of an adaptive load management and optimization control method for a microgrid provided by the present invention;

[0046] Figure 2A schematic diagram of the optimization management objective function structure provided by the present invention;

[0047] Figure 3 This is a schematic diagram of the constraint condition structure provided by the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The embodiment of the present invention discloses a method for adaptive load management and optimization control of a microgrid, such as Figure 1 As shown, a battery-supercapacitor hybrid energy storage unit is provided in the microgrid, including the following steps:

[0050] S1: Collect load data, renewable energy generation data and system operation status data in the microgrid in real time through sensors and communication networks;

[0051] S2: Based on the load data, a machine learning algorithm is used to perform load forecasting to obtain the load demand; based on the renewable energy power generation data, a machine learning algorithm is used to perform power generation forecasting to obtain the power generation forecast value; based on the system operation status data, the hybrid storage energy of the battery-supercapacitor hybrid energy storage unit is calculated;

[0052] S3: According to the load demand, power generation forecast value, hybrid energy storage and system operation status data, combined with the preset hybrid energy storage coordinated control strategy, the optimization management objective function and constraint conditions are established;

[0053] S4: According to the constraints, an improved genetic algorithm is used to solve the optimal solution of the optimization management objective function and obtain the scheduling instructions.

[0054] Furthermore, step 1 also includes preprocessing the collected data, including data cleaning, outlier processing and feature extraction.

[0055] Furthermore, the battery-supercapacitor hybrid energy storage unit includes a plurality of groups of batteries and supercapacitors arranged in a distributed manner, and one battery corresponds to one supercapacitor.

[0056] Furthermore, the system operation status data includes supercapacitor status parameters, battery status parameters, real-time load and power demand, ambient temperature, etc., and the hybrid energy storage capacity is calculated based on the supercapacitor status parameters and battery status parameters.

[0057] Furthermore, the hybrid energy storage coordination control strategy is: when the battery is discharging, the charge state of the supercapacitor is at a lower level. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the main power distribution and the battery is used as the auxiliary power distribution to smooth the power. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary power distribution and the battery is used as the main power distribution to smooth the power. When the battery is charging, the charge state of the supercapacitor is at a higher level. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary power distribution and the battery is used as the main power distribution to smooth the power. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary power distribution and the battery is used as the auxiliary power distribution to smooth the power. Batteries have a short lifespan and respond slowly to power fluctuations. They mainly bear the low-frequency part of fluctuating power. In order to make full use of the fast response characteristic of supercapacitors, they are made to bear the high-frequency part of fluctuating power. However, the capacity of supercapacitors is relatively low, which can easily affect the smoothing results. Based on the complementary characteristics of their capacity and response time, a hybrid energy storage coordinated control strategy is set to improve the smoothing effect of the hybrid energy storage unit. Through the coordination of the charging and discharging states of supercapacitors and batteries, the advantages of both can be further utilized to improve the technical and economic performance of the system.

[0058] Furthermore, when smoothing power distribution according to the system operation status data, a high-pass filter is used in the microgrid to smooth the microgrid power P of the battery-supercapacitor hybrid energy storage unit in the real-time load and power demand. ST Filter and obtain the required smoothing power P ref The high frequency component P ref_sc , as the supercapacitor's smoothing power, the required smoothing power P ref The remaining low-frequency components P ref_b As the battery's smoothing power, when the smoothing power P ref >0, the battery-supercapacitor hybrid energy storage unit discharges, and the power P needs to be smoothed ref <0, the battery-supercapacitor hybrid energy storage unit is charged; the high frequency component P ref_sc and low frequency component P ref_b The expressions are:

[0059]

[0060] Among them, T f is the filtering time constant determined according to the supercapacitor's smoothing power, P ref_sc Follow P ST Fluctuating and violent fluctuations, P ref_b Follow P ST Fluctuating and slowly fluctuating, s represents the moment of power fluctuation.

[0061] Furthermore, a power purchase cost model is constructed according to load demand, a power generation income model is constructed according to power generation forecast and hybrid energy storage, and an optimization management objective function and constraint conditions are established by combining the constructed hybrid energy storage cost model, real-time load and power demand, and hybrid energy storage coordinated control strategy; the optimization management objective function is as follows: Figure 2 As shown, it is expressed as:

[0062]

[0063] C in =C in_t (D f_t +D h_t );

[0064] C out =C out_t D out_t ;

[0065] C b_sc =C1+C2+C3;

[0066] Among them, C total represents the comprehensive cost of microgrid; C in represents the power generation revenue model; C out represents the electricity purchase cost model; C b_sc represents the hybrid energy storage cost model; t represents time; C in_t represents the electricity price at time t; D f_t represents the predicted value of power generation at time t; D h_t represents the mixed energy storage at time t; C out_t represents the electricity purchase price at time t; C out_t represents the load demand at time t; C1 represents the initial investment cost of the battery-supercapacitor hybrid energy storage unit; C2 represents the replacement cost of the battery-supercapacitor hybrid energy storage unit; C3 represents the recovery cost of the battery-supercapacitor hybrid energy storage unit;

[0067] The constraints include power balance constraints, energy storage energy balance constraints and exchange power limits, e.g. Figure 3 As shown in the figure, the power balance constraint when the microgrid operates independently is expressed as:

[0068]

[0069] P Gi represents the power generated by the i-th distributed generation unit in the microgrid in real-time load and power demand; L represents the number of distributed generation units in the microgrid; P ref_sc,j represents the smoothing power of the jth group of supercapacitors, P ref_b,jrepresents the smoothing power of the jth battery group; M represents the number of batteries and supercapacitor groups; P L is the power required by the load;

[0070] The power balance constraint when the microgrid is connected to the grid is expressed as:

[0071]

[0072] P GRID It represents the power absorbed or emitted by the grid to which the microgrid is connected in real-time load and power demand. When the output microgrid outputs power to the grid, R GRID ≥0, when the output microgrid outputs power to the grid, R GRID <0;

[0073] The energy balance constraint of energy storage is expressed as:

[0074]

[0075] B SOC Indicates the battery state of charge obtained based on the battery state parameters, Respectively represent the lower limit of battery state of charge and the upper limit of battery state of charge; SC SOC Indicates the state of charge of the supercapacitor obtained according to the supercapacitor state parameters, They represent the lower limit of the supercapacitor state of charge and the upper limit of the supercapacitor state of charge respectively;

[0076] The switching power limit is expressed as:

[0077]

[0078] and They represent the lower power limit and upper power limit of energy exchange between the microgrid and the grid respectively.

[0079] Furthermore, based on the existing genetic algorithm, when generating the initial population, the improved genetic algorithm clusters the individuals whose fitness values ​​are greater than the set fitness threshold to form a direct genetic sub-population, and does not perform crossover and mutation on the direct genetic sub-population, but mixes it with the individuals of the second generation to form the second generation initialization population. The improved genetic algorithm can effectively improve the convergence speed and make better use of microgrid information.

[0080] Furthermore, the method further includes step 5, wherein a bandwidth control strategy is used to further optimize the control instructions, and the bandwidth expression is:

[0081]

[0082] Among them, k l and k hare the lower limit control bandwidth coefficient and the upper limit control bandwidth coefficient respectively; C min (t) and C max (t) respectively represent the lower limit and upper limit of the optimization management objective function at time t; C(t) represents the value of the optimization management objective function at time t; compare the minimum value of the optimization management objective function at time t and time t+1. If the value of the optimization management objective function C(t+1) at time t+1 is within the bandwidth range, the improved genetic algorithm is not used to solve the optimal solution, and the dispatching instruction at the previous moment is used to control the microgrid. Otherwise, the optimal solution is solved and a new dispatching instruction is obtained to control the microgrid. The bandwidth control strategy can avoid the calculation of the optimal output power instruction in each dispatching cycle, effectively reduce the calculation amount of the control system, and eliminate the high requirements of the actual control calculation speed caused by the excessively high control frequency by reducing the control frequency without affecting the control effect of the microgrid, thereby effectively improving the control efficiency.

[0083] In a specific embodiment, the load in the microgrid includes charging piles and / or air conditioners, the load data includes charging pile power consumption and / or air conditioner power consumption, and the real-time load and power demand in the system operation status data include the charging pile connection status, charging pile working power, and the air conditioner connection status, and air conditioner working power.

[0084] The present invention can be applied to microgrid systems, and by deploying sensors and communication networks, real-time collection and transmission of load data can be achieved. By real-time monitoring of system operating status and load changes, load scheduling and optimization strategies are adjusted and optimized according to feedback information, scheduling instructions are generated, and power supply and storage of renewable energy generation and energy storage units are managed and scheduled, thereby maximizing the utilization of renewable energy and improving the operating efficiency, stability and reliability of microgrids.

[0085] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0086] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for adaptive load management and optimization control of a microgrid, characterized in that: A battery-supercapacitor hybrid energy storage unit is provided in the microgrid, which includes the following steps: Step 1: Collect load data, renewable energy generation data, and system operation status data in the microgrid; Step 2: Use machine learning algorithms to predict loads based on load data to obtain load demand; use machine learning algorithms to predict power generation based on renewable energy power generation data to obtain power generation forecast values; calculate the hybrid storage energy of the battery-supercapacitor hybrid energy storage unit based on system operating status data; Step 3: According to the load demand, power generation forecast, hybrid energy storage and system operation status data, the optimal management objective function and constraint conditions are established in combination with the preset hybrid energy storage coordinated control strategy; Step 4: According to the constraints, an improved genetic algorithm is used to solve the optimal solution of the optimization management objective function and obtain the scheduling instructions.

2. The method for adaptive load management and optimization control of a microgrid according to claim 1, characterized in that: Step 1 also includes preprocessing of the collected data, including data cleaning, outlier processing and feature extraction.

3. The method for adaptive load management and optimization control of a microgrid according to claim 1, characterized in that: The battery-supercapacitor hybrid energy storage unit includes a plurality of distributed groups of batteries and supercapacitors, with one battery corresponding to one supercapacitor.

4. The method for adaptive load management and optimization control of a microgrid according to claim 3, characterized in that: The system operation status data includes supercapacitor status parameters, battery status parameters, real-time load and power demand, and ambient temperature. The hybrid energy storage capacity is calculated based on the supercapacitor status parameters and battery status parameters.

5. The method for adaptive load management and optimization control of a microgrid according to claim 3 is characterized in that The hybrid energy storage coordination control strategy is: when the battery is discharging, the charge state of the supercapacitor is lower than the set minimum charge threshold. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the main and the battery is used as the auxiliary to smooth the power distribution. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution; when the battery is charging, the charge state of the supercapacitor is higher than the set maximum charge threshold. If the battery-supercapacitor hybrid energy storage unit needs to be charged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution. If the battery-supercapacitor hybrid energy storage unit needs to be discharged to smooth the power fluctuation of the microgrid, the supercapacitor is used as the auxiliary and the battery is used as the main to smooth the power distribution.

6. The method for adaptive load management and optimization control of a microgrid according to claim 5, characterized in that: When smoothing power distribution according to system operation status data, a high-pass filter is used in the microgrid to smooth the microgrid power P of the battery-supercapacitor hybrid energy storage unit. ST Filter and obtain the required smoothing power P ref The high frequency component P ref_sc , as the supercapacitor's smoothing power, the required smoothing power P ref The remaining low-frequency components P ref_b As the battery's smoothing power, when the smoothing power P ref >0, the battery-supercapacitor hybrid energy storage unit discharges, and the power P needs to be smoothed ref <0, the battery-supercapacitor hybrid energy storage unit is charged; the high frequency component P ref_sc and low frequency component P ref_b The expressions are: Among them, T f is the filtering time constant determined according to the supercapacitor's smoothing power, P ref_sc Follow P ST Fluctuating and violent fluctuations, P ref_b Follow P ST Fluctuating and slowly fluctuating, s represents the moment of power fluctuation.

7. The method for adaptive load management and optimization control of a microgrid according to claim 6, characterized in that: The power purchase cost model is constructed according to the load demand, and the power generation income model is constructed according to the power generation forecast value and the hybrid energy storage capacity. In addition, the optimization management objective function and constraint conditions are established by combining the constructed hybrid energy storage cost model, system operation status data and hybrid energy storage coordinated control strategy. The optimization management objective function is expressed as: C in =C in_t (D f_t +D h_t ); C out =C out_t D out_t ; C b_sc =C1+C2+C3; Among them, C total represents the comprehensive cost of microgrid; C in represents the power generation revenue model; C out represents the electricity purchase cost model; C b_sc represents the hybrid energy storage cost model; t represents time; C in_t represents the electricity price at time t; D f_t represents the predicted value of power generation at time t; D h_t represents the mixed energy storage at time t; C out_t represents the electricity purchase price at time t; D out_t represents the load demand at time t; C1 represents the initial investment cost of the battery-supercapacitor hybrid energy storage unit; C2 represents the replacement cost of the battery-supercapacitor hybrid energy storage unit; C3 represents the recovery cost of the battery-supercapacitor hybrid energy storage unit; The constraints include power balance constraint, energy storage balance constraint and exchange power limit. The power balance constraint when the microgrid is operating independently is expressed as: P Gi It is represented by the power generated by the i-th distributed generation unit in the microgrid in the system operation status data; L represents the number of distributed generation units in the microgrid; P ref_sc,j represents the smoothing power of the jth group of supercapacitors, P ref_b,j represents the smoothing power of the jth battery group; M represents the number of batteries and supercapacitor groups; P L is the power required by the load; The power balance constraint when the microgrid is connected to the grid is expressed as: P GRID Indicates the power absorbed or emitted by the grid to which the microgrid is connected in the system operation status data. When the output microgrid outputs power to the grid, P GRID ≥0, when the output microgrid outputs power to the grid, P GRID <0; The energy balance constraint of energy storage is expressed as: B SOC Indicates the battery charge state obtained based on the system operation status data. Respectively represent the lower limit of battery state of charge and the upper limit of battery state of charge; SC SOC Indicates the supercapacitor charge state obtained based on the system operation status data. They represent the lower limit of the supercapacitor state of charge and the upper limit of the supercapacitor state of charge respectively; The switching power limit is expressed as: and They represent the lower power limit and upper power limit of energy exchange between the microgrid and the grid respectively.

8. The method for adaptive load management and optimization control of a microgrid according to claim 1, characterized in that: When generating the initial population, the improved genetic algorithm clusters the individuals whose fitness values ​​are greater than the set fitness threshold to form a direct genetic sub-population. The direct genetic sub-population is not subjected to crossover and mutation processing, but is mixed with the individuals of the second-generation to form the second-generation initialization population.

9. The method for adaptive load management and optimization control of a microgrid according to claim 7, characterized in that: The method further includes step 5, wherein a bandwidth control strategy is used to further optimize the control instructions, wherein the bandwidth expression is: Among them, k l and k h are the lower limit control bandwidth coefficient and the upper limit control bandwidth coefficient respectively; C min (t) and C max (t) respectively represent the lower limit and upper limit of the optimization management objective function at time t; C(t) represents the value of the optimization management objective function at time t; Compare the minimum values ​​of the optimization management objective function at time t and time t+1. If the optimization management objective function value C(t+1) at time t+1 is within the bandwidth range, the improved genetic algorithm is not used to solve the optimal solution, and the dispatching instruction at the previous moment is used to control the microgrid. Otherwise, the optimal solution is solved and a new dispatching instruction is obtained to control the microgrid.

Images