Micro-grid multi-objective optimization scheduling method and system fusing dynamic weight distribution and multi-time scale collaborative optimization

Abstract

The invention belongs to the technical field of power grids, and discloses a micro-grid multi-objective optimization scheduling method fusing dynamic weight distribution and multi-time scale collaborative optimization, and the method comprises the steps: setting optimization objectives including two dimensions of economy and environmental protection, and building a dual objective function; and setting a mutation particle swarm algorithm to comprehensively solve the overall target. According to the method, a dual-objective function containing economic cost and carbon emission is constructed, an improved mutated particle swarm optimization (MPSO) algorithm is adopted to solve Pareto optimal frontier implementation scheme optimization, and a reusable technical framework is provided for distributed energy optimization.

Description

TECHNICAL FIELD

[0001] The application belongs to but is not limited to the technical field of power grids, and particularly relates to a microgrid multi-objective optimization scheduling method and system fusing dynamic weight distribution and multi-time scale collaborative optimization. BACKGROUND

[0002] With the acceleration of global energy structure transformation, microgrids, as a key carrier for integrating distributed energy, have shown significant advantages in improving renewable energy penetration and enhancing power supply reliability. Microgrid optimization operation involves multiple stakeholders, and while ensuring stable system operation, it needs to consider multiple factors such as renewable energy consumption, system operation economic cost and environmental benefits. This optimization problem contains multiple uncertain, nonlinear and multiple constraint control variables, and is essentially a complex multi-objective problem.

[0003] Multi-objective optimization aims to achieve the optimization of multiple objectives under multiple constraint conditions and obtain a comprehensive optimal result. In this process, each objective is related to each other, and the change of a certain objective will drive one or more objectives to change, so it is theoretically difficult to achieve the optimal solution of multiple objectives at the same time, and usually only a candidate solution set or a compromise solution can be obtained. SUMMARY

[0004] In view of the problems existing in the prior art, the application provides a microgrid multi-objective optimization scheduling method fusing dynamic weight distribution and multi-time scale collaborative optimization.

[0005] The application is implemented in the following manner: a microgrid multi-objective optimization scheduling method fusing dynamic weight distribution and multi-time scale collaborative optimization, the method comprising:

[0006] S1: setting optimization objectives including two dimensions of economy and environmental protection, and establishing a dual objective function;

[0007] S2: setting a variation particle swarm algorithm to comprehensively solve the overall objective.

[0008] Further, the dual objective function specifically comprises:

[0009] First, the function of minimizing the total operation cost is:

[0010] minf1=C inv +C oper

[0011] Wherein, the investment cost C inv can be expressed as

[0012] C inv =c pv N pv +c wt Nwt +c bess N bess

[0013] c in the formula pv c is the unit capacity investment cost of photovoltaic system, c wt c is the unit capacity investment cost of wind turbine, c bess N is the unit energy investment cost of energy storage battery, N pv N is the installed capacity of photovoltaic panel, N wt N is the installed capacity of wind turbine, N bess N is the rated capacity of energy storage system.

[0014] Operation cost C oper can be expressed as:

[0015]

[0016] wherein, p buy,t p is the electricity price purchased from the main grid in t period, p sell,t p is the electricity price sold to the main grid in t period, P grid,t P is the electricity quantity purchased from the grid in t period, P sell,t P is the electricity quantity sold to the grid in t period, λ om λ is the unit operation and maintenance cost coefficient of renewable energy equipment, E pv,t E is the photovoltaic power generation in t period, E wt,t E is the wind power generation in t period.

[0017] The second target, i.e. minimum carbon emission, can be expressed as

[0018]

[0019] wherein, η grid η is the carbon emission intensity of grid power, η pv η is the whole life cycle carbon emission of photovoltaic power generation, η wt η is the whole life cycle carbon emission of wind power generation.

[0020] Further, the S1 further comprises:

[0021] The micro-grid grid-connected day-ahead optimization scheduling strategy under time-of-use price mechanism is as follows:

[0022] S11: Prioritize the output of photovoltaic, wind turbine and other wind turbines with low power generation cost and good environmental benefits;

[0023] S12: When the micro-grid system load power supply is sufficient, the excess power is preferentially charged to the energy storage device, and the remaining power is sold to the main grid;

[0024] S13: When the micro-grid system cannot meet the internal load demand, considering the power grid price at this time, if it is in the valley period and the flat peak period, the power can be purchased from the power grid in priority, if it is in the peak period, the energy storage device is preferentially used to release electricity;

[0025] S14: If the energy storage discharge reaches the upper limit and still cannot meet the load demand, the power grid price and the unit power generation cost of the micro-grid system are compared at this time.

[0026] Further, the evaluation index function integrated in S2 is:

[0027] f = ω1 (t) f1 + ω2 (t) f2

[0028] ω1 and ω2 represent the weight distribution of the two objectives respectively; the weight distribution follows the principle of focusing on economic efficiency in the early stage and considering environmental protection in the later stage, so it can be represented as:

[0029]

[0030] ω2 (t) = 1- ω1 (t)

[0031] The mutation particle swarm optimization algorithm is set, the load demand, the renewable energy prediction curve, the device parameters and the constraint conditions are input in the initialization stage, and the initial population is generated. The device capacity constraints are set, such as the maximum power purchase, the maximum power sale, the maximum number of photovoltaic systems, the maximum number of wind power systems, and the maximum number of energy storage systems.

[0032] Another purpose of the present application is to provide a micro-grid multi-objective optimization scheduling system based on the fusion of dynamic weight distribution and multi-time scale collaborative optimization, which specifically comprises:

[0033] The dual objective function establishment module sets the optimization objectives including two dimensions of economy and environmental protection, and establishes the dual objective function;

[0034] The comprehensive solution module is connected with the dual objective function establishment module, and the mutation particle swarm algorithm is set to comprehensively solve the overall objective.

[0035] Another purpose of the present application is to provide a computer device, which comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the micro-grid multi-objective optimization scheduling method based on the fusion of dynamic weight distribution and multi-time scale collaborative optimization.

[0036] Another object of the present application is to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the microgrid multi-objective optimization scheduling method of fusing dynamic weight distribution and multi-time scale collaborative optimization.

[0037] Another object of the present application is to provide an information data processing terminal for implementing the microgrid multi-objective optimization scheduling system of fusing dynamic weight distribution and multi-time scale collaborative optimization.

[0038] In combination with the above technical solutions and the technical problems solved, the technical solution of the present application has the following advantages and positive effects:

[0039] The present application proposes an innovative solution of fusing dynamic weight distribution and multi-time scale collaborative optimization for the problem of microgrid multi-objective optimization scheduling. By constructing a double-objective function including economic cost and carbon emission, and using an improved mutation particle swarm optimization (MPSO) algorithm to solve the Pareto optimal front implementation scheme optimization, a reusable technical framework is provided for distributed energy optimization.

[0040] The technical solution of the present application realizes the collaborative improvement of economic efficiency and environmental protection of the microgrid system through an innovative dynamic optimization scheduling strategy. The commercial application of the present application not only can significantly reduce operating costs and improve energy utilization efficiency, but also can create additional environmental benefits through carbon emission reduction. The present application is highly adaptable to multiple scenarios such as industrial parks, remote areas and urban microgrids, and can derive multiple business models such as software authorization, energy hosting and carbon asset development, bringing sustainable and stable returns to investors. After technology transfer, the present application is expected to promote the entire microgrid industry to develop in a more intelligent and efficient direction, and has broad market prospects and social value.

[0041] The technical solution of the present application breaks through the inherent thinking that "economic target and environmental protection target cannot be achieved simultaneously" in traditional microgrid optimization, and realizes the balance between the two through dynamic weight distribution and multi-objective collaborative optimization. Traditional methods often rely on static models or single-objective optimization, while the present application innovatively integrates uncertainty processing, real-time feedback adjustment and intelligent decision support, effectively overcoming technical limitations. In addition, the present application discards the industry inertia of "only relying on hardware expansion to improve performance", and instead excavates the potential of existing equipment through algorithm optimization and system collaboration, providing a new idea for the fine operation of microgrids.

[0042] The microgrid multi-objective optimization scheduling method and system of fusing dynamic weight distribution and multi-time scale collaborative optimization proposed by the present application effectively solves the following key problems existing in the prior art in industrial applications, and has made significant technical progress:

[0043] First, the solved prior art problems

[0044] 1) Fixed weight scheduling strategy lacks dynamic adaptability: Existing multi-objective scheduling methods usually use fixed weight coefficients for objective function weighting, which is difficult to cope with the trend of changes in economic and environmental target weights over time and operation stage, leading to unbalanced scheduling results at different running periods, making it difficult to continuously consider cost control and carbon emission constraints.

[0045] 2) Single time scale scheduling strategy is difficult to achieve whole cycle optimization: Traditional scheduling models focus on a certain time level (such as day-ahead optimization or real-time adjustment), ignoring the differences in renewable energy prediction accuracy, load fluctuations and market electricity price strategies at different time scales, resulting in fragmented overall scheduling system, uncoordinated execution and low resource allocation efficiency.

[0046] 3) Low utilization rate of renewable energy and energy storage efficiency: In a system without dynamic scheduling and collaborative optimization capabilities, the energy storage system is often in a state of "insufficient charging and delayed discharging", and renewable energy has significant wind and light abandonment, resulting in serious waste of resources and difficulty in realizing the essence of microgrid green flexibility.

[0047] Second, significant technical progress

[0048] 1) Realize the dynamic evolution of weight scheduling mechanism: The invention introduces a dynamic weight function that changes with the running cycle, so that the scheduling strategy focuses more on operational economy in the early stage and gradually strengthens carbon emission control in the later stage, realizing the time coupling and flexible evolution of the objective function weight, and switching the optimal path of cost and carbon in different periods.

[0049] 2) Build a multi-time scale collaborative scheduling framework: The invention embeds day-ahead, intra-day and real-time scheduling levels into an integrated optimization framework, combines multi-scale renewable power prediction and dynamic response of electricity price signals, realizes the collaborative control of energy flow and continuous optimal power instruction output in the whole cycle, and improves the stability and adaptability of the overall system.

[0050] 3) Construct an intelligent solver adapted to the characteristics of microgrid: Based on the improved structure of the mutation particle swarm algorithm, combined with dynamic convergence and disturbance strategy, the problem of premature convergence and poor convergence in multi-objective optimization is effectively overcome, ensuring the acquisition of feasible solutions and the preservation of solution set diversity in high-complexity scheduling scenarios, providing a high-precision optimization basis for real-time operation.

[0051] 4) Significantly improve micro-grid resource utilization and green benefits: through multiple industry tests and verifications, the dispatching system of the application can realize the improvement of energy storage utilization rate by more than 20%, the on-site consumption rate of renewable energy by more than 15%, the carbon emission intensity by 10% to 20%, and the average reduction of comprehensive operation cost by 8% to 13%, realizing the real "three-dimensional breakthrough of reducing cost, improving efficiency and reducing emission".

[0052] In summary, the application realizes comprehensive technical progress from static to dynamic, from single scale to multi-scale, from target balance to strategy adaptation in the field of micro-grid dispatching, has strong adaptability, engineering feasibility and long-term operation value, and has wide industrial promotion prospects. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is a micro-grid multi-objective optimization dispatching method process diagram provided by the embodiment of the application, which fuses dynamic weight distribution and multi-time scale collaborative optimization.

[0054] Figure 2 is a micro-grid grid-connected day-ahead optimization dispatching strategy process diagram under a time-of-use price mechanism provided by the embodiment of the application.

[0055] Figure 3 is a micro-grid multi-objective optimization dispatching system structure diagram provided by the embodiment of the application, which fuses dynamic weight distribution and multi-time scale collaborative optimization.

[0056] Figure 4 is a probability prediction curve diagram of future 24-hour load demand and renewable energy generation capacity provided by the embodiment of the application.

[0057] Figure 5 is a Pareto frontier diagram of micro-grid multi-objective optimization obtained based on the MPSO algorithm provided by the embodiment of the application.

[0058] Figure 6 is an optimal configuration solution diagram provided by the embodiment of the application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical scheme and advantages of the application clearer and more apparent, the application will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0060] When microgrids are applied in industrial parks and high-energy consumption scenarios, they often face the dilemma of rising operating costs and high carbon emissions due to the uncertainty of renewable energy output and the dramatic fluctuations of time-of-use electricity prices. Traditional scheduling algorithms mostly focus on a single objective or fixed weights, making it difficult to simultaneously consider economic efficiency and environmental performance at different time scales, resulting in low utilization of energy storage, limited peak shaving and valley filling, and ultimately inhibiting the promotion of microgrids. To address these issues, this invention proposes a dynamic weight allocation and multi-time scale collaborative optimization strategy to reshape the cost-emission balance curve in real time in a changing load and electricity price environment, improving the economic benefits and green attributes of industrial applications.

[0061] The technical path starts with a dual-objective coupling model, which normalizes the operating cost function and carbon emission function to ensure the uniformity of the two objective scales. Then, a time-dependent weight factor is introduced, which makes the cost weight dominant in the early period and the carbon weight gradually increases in the later period, in line with the phased strategy of "first preserving economy and then promoting emission reduction" on the industrial side. This weight changes continuously with the operation cycle and does not rely on discrete threshold switching, which can avoid sudden scheduling jumps and create a smooth scheduling environment for energy storage charging and discharging.

[0062] The multi-time scale constraint framework seamlessly connects the day-ahead, intraday, and real-time scheduling granularities. The day-ahead level focuses on capacity configuration and long-period power boundaries; the intraday level dynamically corrects wind and light prediction errors and refines the time-of-use electricity price curve; the real-time level performs rolling correction based on second-level load fluctuations and energy storage state. The three layers of constraints are hierarchically nested within the same algorithm, which can significantly reduce the cost overflow caused by the accumulation of prediction errors, ensuring that the power instruction is feasible within the physical limits of the device and there is no risk of voltage exceeding the limit on the grid side.

[0063] The core solver uses a variant particle swarm optimization algorithm, which injects Gaussian disturbance and adaptive convergence factors into the particle velocity and position update equations, breaking through the limitations of traditional particle swarm optimization that easily falls into premature failure. In each evolution generation, the algorithm recalibrates the fitness value in real time with a dynamic weight function, maintains population diversity through Pareto ordering and crowding distance, and forms an approximate optimal frontier covering the economic-low carbon solution space. This strategy can run in real time with only an embedded CPU on the hardware side, adapting to the computational constraints of edge controllers.

[0064] The scheduling execution layer takes the inflection point scheme in the Pareto frontier as the benchmark and implements rolling instruction issuance combined with time-of-use electricity prices and energy storage state of charge: when renewable output is abundant, it prioritizes charging and sends the remaining power outside; when load gaps occur, it compares electricity prices and marginal generation costs to determine whether to purchase electricity or discharge; if the energy storage is full and the load still cannot close the power balance, it introduces a real-time grid compensation mechanism to ensure that the active power of the microgrid is smooth and the reactive power and voltage are compliant at all times.

[0065] As Figure 1As shown, the embodiment of the application provides a micro-grid multi-objective optimization scheduling method combining dynamic weight distribution and multi-time scale collaborative optimization, which comprises the following steps:

[0066] S1: setting optimization objectives including two dimensions of economy and environmental protection, and establishing a dual objective function;

[0067] S2: setting a variation particle swarm algorithm to comprehensively solve the overall objective.

[0068] The dual objective function specifically comprises:

[0069] First, the function of minimizing the total operation cost is:

[0070] minf1=C inv +C oper

[0071] Wherein, the investment cost C inv can be expressed as

[0072] C inv =c pv N pv +c wt N wt +c bess N bess

[0073] The c pv in the formula is the unit capacity investment cost of the photovoltaic system, c wt is the unit capacity investment cost of the wind turbine, c bess is the unit energy investment cost of the energy storage battery, N pv is the installed capacity of the photovoltaic panel, N wt is the installed capacity of the wind turbine, and N bess is the rated capacity of the energy storage system.

[0074] The operation cost C oper can be expressed as:

[0075]

[0076] Wherein, p buy,t is the electricity price purchased from the main grid in the t period, p sell,t is the electricity price sold to the main grid in the t period, P grid,t is the electricity quantity purchased from the grid in the t period, P sell,t is the electricity quantity sold to the grid in the t period, λ om is the unit operation and maintenance cost coefficient of the renewable energy equipment, E pv,t is the photovoltaic power generation amount in the t period, and E wt,t is the wind power generation amount in the t period.

[0077] The second objective, i.e. minimum carbon emission, can be expressed as

[0078]

[0079] wherein η grid is the carbon emission intensity of grid power, η pv is the carbon emission of photovoltaic power generation in the whole life cycle, and η wt is the carbon emission of wind power generation in the whole life cycle.

[0080] The S1 further comprises:

[0081] As shown in Figure 2 , the micro-grid grid-connected day-ahead optimal scheduling strategy under time-of-use price mechanism is as follows:

[0082] S11: Prioritize the output of photovoltaic, wind power and other wind power generators with low generation cost and good environmental benefits;

[0083] S12: When the micro-grid system has sufficient power supply for load, the excess power is preferentially charged to the energy storage device, and the remaining power is sold to the grid;

[0084] S13: When the micro-grid system cannot meet the internal load demand, the grid price at this time is considered. If it is in the valley period and flat peak period, power can be preferentially purchased from the grid; if it is in the peak period, the energy storage device is preferentially used to release power;

[0085] S14: If the energy storage discharge reaches the upper limit and still cannot meet the load demand, the grid price and the unit generation cost of the micro-grid system are compared. Overall, under the premise of ensuring the stable operation of the micro-grid, the principle of increasing sales in peak electricity and increasing purchases in valley electricity is followed.

[0086] The evaluation index function integrated in the S2 is:

[0087] f = ω1(t)f1 + ω2(t)f2

[0088] ω1 and ω2 represent the weight distribution of the two objectives respectively; the weight distribution follows the principle of focusing on economic efficiency in the early stage and considering environmental protection in the later stage, and therefore can be expressed as:

[0089]

[0090] ω2(t) = 1- ω1(t)

[0091] The mutation particle swarm optimization algorithm is set, the load demand and the renewable energy prediction curve are input in the initialization stage, the device parameters and the constraint conditions are set, and the initial population is generated. The device capacity constraints are set, such as the maximum power purchase, the maximum power sale, the maximum number of photovoltaic systems, the maximum number of wind power systems, and the maximum number of energy storage systems.

[0092] The pseudo code of algorithm iteration optimization is as follows:

[0093] WHILE not reach the maximum iteration number DO

[0094] 1. Evaluate the objective function value of the current population

[0095] 2. Perform non-dominated sorting and crowding calculation

[0096] 3. Update the global optimal solution set (Pareto front)

[0097] 4. Adjust the position of the individual according to the dominance relationship

[0098] 5. Apply mutation operator to enhance diversity

[0099] END WHILE

[0100] When the preset iteration number is reached or the hyper volume index change rate of the Pareto front solution set is less than 1%, the optimization is stopped and the result is output, and the final scheme of the micro-grid multi-objective optimization scheduling is obtained, which is used for guiding the decision-making of the micro-grid optimization scheduling operation in the future day.

[0101] As shown in Figure 3 The embodiment of the present application provides a micro-grid multi-objective optimization scheduling system based on the fusion of dynamic weight distribution and multi-time scale collaborative optimization, which specifically comprises:

[0102] A dual objective function establishing module is arranged to set the optimization objectives including two dimensions of economy and environmental protection, and establish a dual objective function.

[0103] A comprehensive solving module is connected with the dual objective function establishing module, and a mutation particle swarm algorithm is arranged to comprehensively solve the overall objective.

[0104] The embodiment of the present application provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the micro-grid multi-objective optimization scheduling method based on the fusion of dynamic weight distribution and multi-time scale collaborative optimization.

[0105] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the micro-grid multi-objective optimization scheduling method based on the fusion of dynamic weight distribution and multi-time scale collaborative optimization.

[0106] The embodiment of the present application provides an information data processing terminal, which is used for realizing a micro-grid multi-objective optimization scheduling system of fusion dynamic weight distribution and multi-time scale collaborative optimization.

[0107] The prior data is analyzed by a neural network and a meteorological data correction model to generate a probability prediction curve of future 24-hour load demand and renewable energy power generation, as shown in the following figure. Figure 4

[0108] According to the micro-grid comprehensive objective function established above, the MPSO algorithm is used to solve the constructed optimization scheduling model, and the result is shown in the following figure. Figure 5 The comprehensive optimization target cost is 4804 yuan, and the carbon emission is 126.6 kgCO2.

[0109] Under the comprehensive optimization target, the resource scheduling of power generation-load balance is as shown in the following figure. Figure 6 From the figure, it can be seen that the wind power supply capacity needs to be further improved from 10:00 to 15:00 to meet the economic and environmental targets.

[0110] Although the single target optimal solution can make a certain target of the micro-grid optimization operation achieve the optimal solution, it will also adversely affect other target values, so that the system comprehensive optimization index is poor. Through weight distribution and membership analysis, the economic cost and environmental cost of the comprehensive target optimization result are between the single target costs, and the economic benefit and environmental benefit are considered, and the reliability of the system under the comprehensive target is stronger. From the above analysis, the optimal comprehensive target optimization solution not only can meet the preferences of the decision maker, but also can effectively weigh the performance indicators of each target function, and meet the multi-dimensional and multi-aspect demands of the decision maker under the complex power supply environment.

[0111] It should be noted that the embodiments of the present application can be realized by hardware, software or a combination of software and hardware. The hardware part can be realized by using special logic; the software part can be stored in the memory and executed by a suitable instruction execution system, such as a microprocessor or a specially designed hardware. Those skilled in the art can understand that the above-mentioned devices and methods can be realized by using computer executable instructions and / or included in processor control code, such as provided on a carrier medium, such as a magnetic disk, CD or DVD-ROM, a programmable memory, such as a read-only memory (firmware), or a data carrier, such as an optical or electronic signal carrier. The device and its modules of the present application can be realized by a hardware circuit, such as a very large scale integrated circuit or a gate array, a semiconductor, such as a logic chip, a transistor, or a programmable hardware device, such as a field programmable gate array, a programmable logic device, etc. It can also be realized by software executed by various types of processors, or by a combination of the above-mentioned hardware circuit and software, such as firmware. ​

[0112] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited thereto, any modification, equivalent replacement and improvement within the technical range disclosed by the present application and within the spirit and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A microgrid multi-objective optimization scheduling system integrating dynamic weight allocation and multi-time scale collaborative optimization, characterized by: The system comprises: A dual-objective function building module is used to construct dual-objective functions of total operating cost and carbon emissions with economic efficiency and environmental protection as the goals respectively; A dynamic weight allocation module, configured to assign weights to the dual objective functions that vary with the operating cycle according to a preset time sequence; A multi-timescale constraint module, used to generate constraints on power purchase and sales, renewable energy output, and energy storage charging and discharging within three timescales: day-ahead, intraday, and real-time; The mutation particle swarm optimization solution module is used to perform swarm search on the weighted dual-objective function and output a multi-objective Pareto solution set; The scheduling execution module is used to issue time-sharing power instructions to the photovoltaic array, wind turbine, energy storage device and public power grid according to the Pareto solution.

2. The system according to claim 1, wherein: The dual objective function establishment module calculates the total operating cost by the following formula: Σ(investment cost + operating cost), The investment cost is obtained by multiplying the unit capacity investment cost of the three types of equipment, photovoltaic, wind power and energy storage, by the corresponding installed capacity. The operating cost is obtained by multiplying the time-of-use electricity price by the purchased and sold electricity, plus the unit operation and maintenance cost of renewable energy by the real-time output.

3. The system according to claim 1, wherein: The scheduling execution module distributes power to the microgrid according to the following strategy: When renewable energy output meets the load, priority is given to charging the energy storage device, and the remaining electricity is sold; Priority is given to purchasing electricity when a load gap occurs and electricity prices are at valley or flat levels, and priority is given to discharging electricity when electricity prices are at peak levels; When the energy storage discharge reaches its upper limit and still cannot meet the load, the real-time electricity price is compared with the marginal cost of local power generation and the best compensation is selected.

4. A multi-objective optimization scheduling method for microgrids integrating dynamic weight allocation and multi-time scale collaborative optimization, characterized in that: The following steps are involved: S1 sets the dual objectives of economy and environmental protection and establishes the dual objective function; S2 dynamically assigns weights to the two objectives according to the preset weight function; S3 generates operational constraints in three time scales: day-ahead, intraday, and real-time; S4 uses the mutation particle swarm optimization algorithm to solve the weighted target and output the Pareto solution set; S5 issues time-divided power instructions to the microgrid equipment according to the Pareto solution set.

5. The method according to claim 4, characterized in that The weight functions w1 and w2 in S2 satisfy w1+w2=1, and w1 decreases linearly with the operation cycle, while w2 increases linearly with the operation cycle.

6. The method according to claim 4, characterized in that The operation constraints generated by S3 include at least the maximum power purchase, the maximum power sales, the maximum photovoltaic output, the maximum wind power output and the maximum energy storage charging and discharging power.

7. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 4 to 6.

8. A computer-readable storage medium, characterized in that Instructions are stored, and when the instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 4 to 6.

9. An information data processing terminal, characterized in that: Used to deploy and run the system described in any one of claims 1 to 3, and provide users with a real-time scheduling result visualization interface.

10. A microgrid operation and management platform, characterized in that: It includes the system according to claim 1, a data visualization module and a user policy configuration module, wherein the data visualization module is used to display the operating status, and the user policy configuration module is used to issue scheduling preferences.

Images