Energy management method and device for micro-grid group energy storage system

Abstract

The invention provides an energy management method and device for a micro-grid group energy storage system, and the method comprises the steps: building an energy management model for the micro-grid group energy storage system; establishing an objective function and a constraint condition of the micro-grid group based on the cost of the energy storage system; and solving the established energy management model of the energy storage system of the micro-grid group by using an improved artificial hummingbird algorithm, and determining an optimal energy management strategy. According to the embodiment of the invention, the constructed micro-grid group energy storage system energy management model is solved by fusing the local escape operator and the improved artificial bee-bird algorithm based on the opposite learning technology, so that the solution space of the micro-grid group energy management model is better explored, the convergence speed is accelerated, and the problem that the solution falls into local optimum is solved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of energy management of microgrids, and in particular to an energy management method and device for a microgrid group energy storage system. Background Art

[0002] A microgrid cluster is a collection of multiple microgrids that can be interconnected and coordinated to form a larger and more complex energy system. By combining multiple microgrids to form a microgrid cluster, resource sharing and complementary utilization can be achieved, the efficiency and reliability of the overall system can be improved, and the problems faced by microgrids, such as energy waste and system instability, can be solved. A microgrid cluster composed of multiple microgrids can effectively absorb distributed power sources, improve power supply flexibility and reliability, reduce the rate of abandoned light and wind, and reduce economic costs. The energy management model of the microgrid energy storage system has become one of the key issues in the comprehensive control of microgrids.

[0003] The existing technology has the following problems when solving the objective function with the lowest comprehensive operating cost: it often only considers a single microgrid, and does not consider the microgrid group system composed of multiple groups of microgrids, or does not consider the optimal solution problem in the energy management of the microgrid group, or the algorithm converges slowly, or is prone to fall into the problem of local optimality, but the microgrid scenarios faced during the application are not considered in the application. Summary of the invention

[0004] In view of this, the present disclosure aims to provide an energy management method and device for a microgrid group energy storage system to solve the above-mentioned technical problems in the prior art.

[0005] One aspect of the present disclosure provides an energy management method for a microgrid group energy storage system, comprising:

[0006] Establish energy management models for microgrid cluster energy storage systems;

[0007] Establish the objective function and constraints of the microgrid group based on the energy storage system cost;

[0008] The improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system and determine the optimal energy management strategy.

[0009] In some embodiments, in the energy management model established for the microgrid group energy storage system, the energy management model at least includes an intraday optimization objective function of microgrid i, which is expressed as:

[0010]

[0011] In the above formula, C pv (P pvi,t) is the photovoltaic maintenance cost of microgrid i in time period t; C wt (P wti,t ) is the wind turbine maintenance cost of microgrid i in time period t; C bat (P bati,t ) is the battery operation and maintenance cost of microgrid i in time period t; C de (P dei,t ) is the diesel generator operating cost of microgrid i in time period t; C cut (P cuti,t ) is the cost of shedding load when microgrid i has insufficient power supply in time period t.

[0012] In some embodiments, in the objective function and constraint conditions for establishing a microgrid group based on the energy storage system cost, the objective function is:

[0013]

[0014] In the above formula, F1 is the daily overall operating cost; C grid (P gridi,t ) is the transaction fee between microgrid i and the large grid in time period t.

[0015] In some embodiments, in the objective function and constraint conditions for establishing a microgrid group based on the energy storage system cost, the constraint conditions include at least power balance constraints, system operation constraints, and renewable energy utilization rate constraints.

[0016] In some embodiments, the power balance constraint is expressed as follows:

[0017]

[0018] Where: P dei,t is the power generation of the diesel generator in microgrid i during time period t; P loadi,t is the load power of microgrid i in time period t; P i,j,t is the power flowing from microgrid i to microgrid j in time period t.

[0019] In some embodiments, the system operation constraints include at least that the transmission power of the interconnection line between the microgrid and the large power grid cannot exceed the maximum transmission power; the output of the diesel generator cannot be lower than the minimum power generation power, nor can it exceed the maximum output power, and the climbing power cannot exceed the maximum value; the SOC value of the battery during the charging and discharging process must not exceed its limit, and the battery cannot exceed the maximum charging and discharging power during the charging and discharging process.

[0020] In some embodiments, the improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system to determine the optimal energy management strategy, and the basic artificial hummingbird algorithm is improved by integrating the local escape operator and the opposition-based learning technology.

[0021] In some embodiments, the method of solving the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm to obtain the optimal energy management strategy includes:

[0022] Input cost information, power interaction information of interconnection lines between microgrid groups, and iteration-related data to determine relevant operating parameters of the improved artificial hummingbird algorithm;

[0023] Initialize the population and perform an adversarial-based learning technique upon initialization;

[0024] Initialize hummingbird visit tables, execute flight strategies, and guide foraging;

[0025] Conduct migratory foraging and further update hummingbird visitation tables;

[0026] Execute the local escape operator and determine the solution calculated by it as the fitness, and judge whether the fitness meets the requirements;

[0027] If it meets the requirements, the position is updated to the position that meets the fitness requirements calculated by the local escape operator;

[0028] Obtain the optimal solution of the improved artificial hummingbird algorithm and determine the optimal energy scheduling strategy for the microgrid group energy storage system.

[0029] In some embodiments, the initializing the hummingbird access table, executing the flight strategy and guiding foraging further includes: updating the position according to the foraging situation, and updating the hummingbird access table.

[0030] One aspect of the present disclosure provides an energy management device for a microgrid group energy storage system, comprising:

[0031] A model building module, used to build an energy management model for a microgrid group energy storage system;

[0032] A function building module is used to build the objective function and constraint conditions of the microgrid group based on the energy storage system cost;

[0033] The strategy determination module is used to solve the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm to determine the optimal energy management strategy.

[0034] The disclosed embodiment solves the constructed energy management model of the microgrid group energy storage system by integrating the local escape operator and the improved artificial hummingbird algorithm based on the adversarial learning technology, so as to better explore the solution space of the microgrid group energy management model, accelerate the convergence speed, and overcome the problem of the solution falling into the local optimum.

[0035] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In the drawings that are not necessarily drawn to scale, the same reference numerals may describe similar parts in different views. The same reference numerals with letter suffixes or different letter suffixes may represent different instances of similar parts. The drawings generally illustrate various embodiments by way of example and not limitation, and together with the specification and claims, are used to illustrate the disclosed embodiments. When appropriate, the same reference numerals are used throughout the drawings to refer to the same or similar parts. Such embodiments are illustrative and are not intended to be exhaustive or exclusive embodiments of the present apparatus or method. The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0037] Figure 1 It is a schematic diagram of the steps of the energy management method of the microgrid group energy storage system provided by the embodiment of the present disclosure;

[0038] Figure 2 is a flow chart of an improved artificial hummingbird algorithm provided by an embodiment of the present disclosure;

[0039] Figure 3 It is an energy optimization management diagram of a microgrid group energy storage system based on an improved artificial bee colony algorithm, an artificial hummingbird algorithm, and a particle swarm algorithm provided in an embodiment of the present disclosure;

[0040] Figure 4 It is a comparative analysis diagram of the convergence speeds of the improved artificial hummingbird algorithm, the artificial hummingbird algorithm, and the particle swarm algorithm provided in the embodiments of the present disclosure. DETAILED DESCRIPTION

[0041] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, but are not intended to limit the present disclosure.

[0042] It should be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0043] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0044] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example, with reference to the attached drawings.

[0045] It should also be understood that, although the present disclosure has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0046] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0047] Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant details. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of ways with substantially any suitable detailed structure.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0049] This specification may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0050] The first embodiment of the present disclosure provides an energy management method for a microgrid group energy storage system, which is implemented based on an improved artificial hummingbird algorithm. The present disclosure embodiment takes an interconnected microgrid group as the management object, establishes an energy management model of the microgrid group energy storage system and determines the objective function and constraints of the microgrid group, and then solves the constructed energy management model through an improved artificial hummingbird algorithm (mAHA) to achieve lower economic costs for the microgrid group and improve the economy of energy management of the microgrid group.

[0051] In this embodiment, if Figure 1 As shown, the energy management method comprises the following steps:

[0052] S101, establishing an energy management model for a microgrid energy storage system.

[0053] In this step, an energy management model for the microgrid group energy storage system is established. Specifically, in this step, an energy management model for the microgrid group energy storage system is established with the interconnected microgrid group as the object. The microgrid group involved in this embodiment includes a diesel generator, a power connection line between microgrids, and a communication line between controllers. The microgrid group generally includes n microgrids, wherein the difference between the cumulative renewable energy power generated by microgrid i and the load power within a period of time t is the power difference, which is expressed as:

[0054] ΔP i,t =P pvi,t +P wti,t -P li,t ;

[0055] Where: P pvi,t is the photovoltaic output of microgrid i in time period t; P wti,t is the wind turbine output of microgrid i in time period t; P li,t is the load power consumption of microgrid i in time period t. i,t > 0, it is defined as the energy surplus of microgrid i; when ΔP i,t When ΔP < 0 i,t <0 is defined as the energy default of microgrid i; when ΔP i,t =0, it is defined as the energy self-sufficiency of microgrid i.

[0056] The energy management model in this embodiment at least includes the intra-day optimization objective function of microgrid i, which is expressed as:

[0057]

[0058] Where: C pv (P pvi,t ) is the photovoltaic maintenance cost of microgrid i in time period t; C wt(P wti,t ) is the wind turbine maintenance cost of microgrid i in time period t; C bat (P bati,t ) is the battery operation and maintenance cost of microgrid i in time period t; C de (P dei,t ) is the diesel generator operating cost of microgrid i in time period t; C cut (P cuti,t ) is the cost of load shedding when microgrid i has insufficient power supply in time period t. The reliability objectives and constraints are consistent with the day-ahead dispatch.

[0059] S102, establishing the objective function and constraint conditions of the microgrid group based on the energy storage system cost.

[0060] After the energy management model for the microgrid group energy storage system is established through the above step S101, in this step, the objective function and constraints of the microgrid group are established based on the cost of the energy storage system. Specifically, in this step, the objective function of the microgrid group is established with the lowest cost of the microgrid group energy storage system as the objective function.

[0061] The energy management of microgrid groups aims to minimize the overall operating costs. Therefore, when performing energy management on an already built microgrid group, it is not necessary to consider the initial construction cost of the system. However, it is necessary to consider the operation and maintenance costs of renewable energy units in the microgrid group, the operation and maintenance costs of batteries, the operation costs of diesel generators, the cost of purchasing and selling electricity from the large power grid, and the cost of load shedding when power supply is insufficient. The economic objective function is:

[0062]

[0063] Where: F1 is the daily overall operating cost; C grid (P gridi,t ) is the transaction fee between microgrid i and the large grid in time period t.

[0064] The constraints of the objective function of the microgrid group here include at least power balance constraints, system operation constraints and renewable energy utilization constraints.

[0065] The power balance constraint is expressed as follows:

[0066]

[0067] Where: P dei,t is the power generation of the diesel generator in microgrid i during time period t; P loadi,t is the load power of microgrid i in time period t; P i,j,t is the power flowing from microgrid i to microgrid j in time period t.

[0068] The system operation constraints include at least (1) the transmission power limit of the interconnection line between the microgrid and the large grid, which cannot exceed the maximum transmission power (2) Considering the operating cost, the output of the diesel generator cannot be lower than the minimum power generation power P demin , nor can it exceed the maximum output power P demax , the climbing power cannot exceed the maximum value (3) The SOC value of the battery during the charging and discharging process shall not exceed its limit, and the battery shall not exceed the maximum charging and discharging power during the charging and discharging process, as shown below:

[0069]

[0070] P demin ≤P dei,t ≤P demax

[0071]

[0072] b SOCmin <b SOC <b SOCmax

[0073] -P batmax ≤P bati,t ≤P batmax

[0074]

[0075] L REE (j)≥L REE,min

[0076]

[0077] Furthermore, in order to reflect the superiority of microgrids, the renewable energy utilization rate constraint in the microgrid group is defined, where L REE,min The renewable energy utilization rate L is set REE The lower limit of F e is the environmental pollution control cost generated by diesel generators; a is different exhaust gases (including carbon dioxide, nitrogen oxides and sulfur dioxide, etc.); W diesel,a is the production coefficient of pollutant gas a; P diesel,t is the power emitted in time period t; C a is the unit weight control cost of polluted gas a; b soc is the state of charge of the battery; P REG(t,j) is the power generated by renewable energy source j (including photovoltaic and wind turbine) in the microgrid at time t.

[0078] To this end, through the above steps S101 and 102, an energy management model of the microgrid group energy storage system is established after the environment is initialized, and the objective function and constraint conditions are determined and later input into the improved artificial hummingbird algorithm.

[0079] S103, using the improved artificial hummingbird algorithm to solve the established energy management model of the microgrid group energy storage system and determine the optimal energy management strategy.

[0080] After the objective function and constraint conditions of the microgrid group are established based on the energy storage system cost through the above step S102, in this step, the improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system to obtain the optimal energy management strategy. Specifically, in this step, the basic artificial hummingbird algorithm (AHA) is improved by integrating the local escape operator (LEO) and the opposition-based learning technology (OBL), wherein the opposition-based learning technology promotes population diversity by creating new opposition individuals to accelerate the convergence speed; the local escape operator can help the algorithm jump out of the local optimal solution, expand the search range by adding a certain amount of randomness or disturbance, improve the quality of the solution, avoid the algorithm from falling into the local optimum, and thus better explore the solution space. The above improvements to the artificial hummingbird algorithm can enable the algorithm to explore the solution space more effectively, overcome the local optimum, and enhance the convergence speed and global search ability of the algorithm, so as to finally solve the energy management model of the microgrid group energy storage system through the improved artificial hummingbird algorithm.

[0081] First, here is a brief introduction to the artificial hummingbird algorithm:

[0082] The artificial hummingbird algorithm first needs to be initialized to establish N hummingbird populations on N food sources. Random initialization is represented by the following method:

[0083] Xb i =lb i +rand×(ub i -lb i ); i=1,2,...,N

[0084] Among them, Xb i represents the solution of n population sets, lb i andub i are the upper and lower boundaries,

[0085] Initialize the food source access table using the following formula:

[0086]

[0087] The three foraging behaviors or foraging strategies of hummingbirds are guided foraging, territorial foraging, and migratory foraging.

[0088] (1) Guided foraging means that in order for a hummingbird to exhibit guided foraging behavior, it must identify the food source with the highest visitation level and select the food source with the fastest nectar replenishment as its target. Once identified, the bird can navigate to the desired food source.

[0089] The artificial hummingbird algorithm combines three flight modes to guide the search space during foraging: omnidirectional flight mode, diagonal flight mode, and axial flight mode.

[0090] The expression of the axial flight mode is:

[0091]

[0092] The expression for the diagonal flight mode is:

[0093]

[0094] The expression of omnidirectional flight mode is:

[0095] D i =1,i={1,2,...,d}

[0096] Among them, randi([1,d]) can obtain a random integer between 1 and d, randperm(l) can obtain a random integer arrangement between 1 and 1, and r1 is a random number between [0,1].

[0097] Using different flight modes, directed foraging behavior is simulated by allowing each food source to update its position relative to the target food source in the following equation, and the foraging activities of the hummingbird are depicted.

[0098] ζ(t+1)=Xb i,targ (t)+a×D×(Xb i (t)-Xb i,targ (t))

[0099] a~N(0,1)

[0100] In the formula, Xb i (t) represents the i-th position, Xb i,targ (t) represents the location of the target food source, a represents the guidance vector, and the following formula can also be used to update the location:

[0101]

[0102] In the formula, f(.) is the objective function.

[0103] (2) Territorial foraging refers to the migration of hummingbirds to nearby locations within their territory and finding a new food source. The local search of hummingbirds in the territorial foraging strategy is modeled using the following equation, which helps to identify candidate food sources through the following methods:

[0104] ζ(t+1)=Xb i (t)+b×D×Xb i (t)

[0105] b~N(0,1)

[0106] Where b is a geographical variable and the visit table must be updated according to the territorial foraging method.

[0107] (3) Migration foraging means that once the number of iterations exceeds the predefined value of the migration coefficient, the hummingbird located at the food source with the lowest nectar replenishment rate will randomly migrate to a new food source established in the entire search space. The hummingbird's foraging journey starting from the source with the lowest nectar replenishment rate can be modeled as follows:

[0108] X wors =lb+rand×(ub-lb)

[0109] Among them, X wors Indicates the food source with the worst honey replenishment rate.

[0110] In this step, the search strategy of the artificial hummingbird algorithm is improved based on the local escape operator. When a local optimal solution is encountered during the swarm search process, local perturbations or random operations are used to help the hummingbird jump out of the current local optimal solution and search in a more favorable direction, thereby ultimately improving the quality of the solution and preventing the algorithm from falling into the local optimum, thereby better exploring the solution space.

[0111] The improvement of the artificial hummingbird algorithm based on oppositional learning technology means that new oppositional individuals are created to compete or cooperate with the original individuals, and the diversity of the population is maintained and the global search capability is improved through information exchange and competitive advantages.

[0112] Specifically, in the process of improving the artificial hummingbird algorithm based on adversarial learning techniques, when using metaheuristic algorithms, the convergence speed is usually fast when the initial solution is close to the optimal position, and the convergence speed is slow in other cases. However, adversarial learning techniques can find more valuable solutions in the opposite search area, which may be closer to the global optimum. To achieve this, adversarial learning techniques search in two directions of the search space. One of the initial solutions is used for both directions, and the opposite solution represents the other direction. The adversarial learning technique then selects the most suitable solution from all the solutions found.

[0113] The opposite number represents the learning based on the opposite. Assume that Q0 is a real number on the interval: the inverse number Q0 is as follows and Q0∈[a,b]:

[0114]

[0115] The pair of points in D-dimensional space is determined by:

[0116] Q=q1,q2,q3,...,q D

[0117]

[0118] The terms in are calculated by

[0119]

[0120] Opposition-based optimization refers to the optimization strategy that combines opposite Replace with the corresponding Q0. If Q0 is more suitable Then Q0 remains unchanged; otherwise, according to Q and The optimal value of is used to update the overall solution.

[0121] In the improvement of the artificial hummingbird algorithm based on the local escape operator, the local escape operator was initially used to improve the effectiveness of the gradient-based optimizer algorithm in solving complex real-world problems. It improves the quality of the solution based on the local escape operator by changing the location of the solution according to specific criteria, thus avoiding the algorithm from falling into the local optimum. LEO selects new solutions through various techniques. If the best position (Xb best ), two randomly selected solutions and The other two randomly selected solutions ( and ), and a newly generated random solution therefore, The solution can be obtained from the following formula:

[0122]

[0123] In the formula, f1 and f2 are random values ​​uniformly distributed in [-1,1], and p r is a probability number and its value is 0.5. u1, u2 and u3 are random numbers obtained by the following formula:

[0124]

[0125] Where randN is a random value between 0 and 1. μ1 is between 0 and 1. The equations for u1, u2, and u3 are simplified into the following mathematical expressions:

[0126] u1=L1×2×randN+(1-L1)

[0127] u2=L1×randN+(1-L1)

[0128] u3=L1×randN+(1-L1)

[0129] Wherein, L1 is a parameter with a value of 0 or 1. (If μ1<0.5, L1=1, otherwise it is 0).

[0130] The following scheme is proposed to obtain the solution:

[0131]

[0132] where x randN is a new solution, which is calculated by the following formula. is a random solution (p∈[1,2,…N]) selected from the population. μ2 is a random number in the range [0,1].

[0133] x randN =lb+randN(0,1)×(ub-lb)

[0134] In addition, ρ1 is used to balance the exploration phase and the mining phase. It is defined as:

[0135] ρ1=2×rand×α-α

[0136]

[0137] Among them, β min and β max are equal to 0.2 and 1.2 respectively, t is the current step size, t max is the maximum number of step changes for α that balances the exploration phase and the production phase according to the sine function.

[0138]

[0139] Where w2 is a parameter with a value of 0 or 1. When the parameter μ1 is less than 0.5, the value of L1 is 1; otherwise, the value of L1 is 0.

[0140] Furthermore, the improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system to obtain the optimal energy management strategy, including:

[0141] S201, input the cost information of diesel generators, wind turbines, photovoltaic maintenance, etc., input the power interaction information of the interconnection lines between microgrid groups; input the overall size, maximum number of iterations and other iteration-related data, and determine the relevant operating parameters of the improved artificial hummingbird algorithm;

[0142] S202: Initialize the population, and perform an adversarial learning technique during initialization;

[0143] S203, initializing the hummingbird access table, executing the flight strategy and guiding foraging;

[0144] This step also includes: updating the location according to the foraging situation and updating the hummingbird visit table.

[0145] S204, perform migration foraging and further update the visit table;

[0146] S205, executing the local escape operator and determining the solution calculated by the operator as the fitness, judging whether the fitness meets the requirement, and if not, returning to initializing the hummingbird access table;

[0147] S206, updating the position to a position that meets the fitness calculated by the local escape operator;

[0148] S207, obtaining the optimal solution of the improved artificial hummingbird algorithm, and determining the optimal energy scheduling strategy of the microgrid group energy storage system.

[0149] Figure 2 The flowchart of the improved artificial hummingbird algorithm is shown. First, an optimization model for the microgrid group is established, and the required objective function and constraints are determined, the relevant parameters of the improved artificial bee colony algorithm are determined, and the algorithm is initialized; secondly, the artificial hummingbird algorithm is optimized based on the oppositional learning technology, and the flight strategy is started to guide foraging; then, it is determined whether the hummingbird's position needs to be updated, and the hummingbird position and seal access table that need to be updated are updated, and migration foraging continues and the position is updated; finally, the local escape operator is executed to calculate the hummingbird's position, and finally the feasibility of the calculated new position is judged by the fitness, and the feasible position is updated to finally determine the optimal solution.

[0150] Figure 3 It is an energy optimization management diagram of a microgrid energy storage system based on improved artificial bee colony algorithm, artificial hummingbird algorithm, and particle swarm algorithm. Figure 3It can be seen that from 0:00 to 9:00, the diesel generator in the microgrid is in shutdown state, the interconnection line interaction power is positive, and the distribution network transmits electric energy to the microgrid; from 11:00 to 14:00, the interconnection line interaction power is negative, and the microgrid transmits electric energy to the distribution network, and the diesel generator is in working state; from 19:00 to 21:00, the energy storage battery power is positive, and the energy storage battery is in discharge state; from 23:00 to 03:00 and 05:00 to 06:00, the energy storage battery power is negative, and the energy storage battery is in charging state. Comparing the energy management of the three algorithms of improved artificial hummingbird algorithm, artificial hummingbird algorithm, and particle swarm algorithm, when the improved artificial hummingbird algorithm is used, the microgrid group is more economical after scheduling, which ensures the economy of the microgrid group energy plating model.

[0151] Figure 4 It is a comparative analysis diagram of the convergence speed of the improved artificial hummingbird algorithm, the artificial hummingbird algorithm, and the particle swarm algorithm. In the process of solving the energy management model of the microgrid group energy storage system, the particle swarm algorithm is close to the optimal solution after about 600 iterations, and the artificial hummingbird algorithm before the improvement is close to the optimal solution after about 400 iterations. Compared with the particle swarm algorithm, the convergence speed of the artificial hummingbird algorithm is significantly improved. The improved artificial hummingbird algorithm proposed in the present invention has the best convergence, and is close to the optimal solution after the 300th iteration. Compared with the artificial hummingbird algorithm before the improvement, the convergence speed has been further improved. This is because the artificial hummingbird algorithm is improved based on the oppositional learning technology, and because the artificial hummingbird algorithm is improved by the local escape operator in this embodiment, it can be seen that the solution is closer to the optimal solution, overcoming the disadvantage that the artificial hummingbird algorithm is easy to fall into the local optimum. The experimental results show that the improved artificial hummingbird algorithm has a faster convergence speed, is closer to the optimal solution, and is not easy to fall into the local optimum, and can quickly and effectively solve the energy management of the microgrid group energy storage system.

[0152] The disclosed embodiment solves the constructed energy management model of the microgrid group energy storage system by integrating the local escape operator and the improved artificial hummingbird algorithm based on the adversarial learning technology, so as to better explore the solution space of the microgrid group energy management model, accelerate the convergence speed, and overcome the problem of the solution falling into the local optimum.

[0153] Based on the same inventive concept as the first embodiment above, the second embodiment of the present disclosure provides an energy management device for a microgrid group energy storage system, comprising:

[0154] A model building module, used to build an energy management model for a microgrid group energy storage system;

[0155] A function building module is used to build the objective function and constraints of the microgrid group based on the energy storage system cost;

[0156] The strategy determination module is used to solve the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm to determine the optimal energy management strategy.

[0157] Furthermore, the energy management model includes at least an intraday optimization objective function of microgrid i, which is expressed as:

[0158]

[0159] In the above formula, C pv (P pvi,t ) is the photovoltaic maintenance cost of microgrid i in time period t; C wt (P wti,t ) is the wind turbine maintenance cost of microgrid i in time period t; C bat (P bati,t ) is the battery operation and maintenance cost of microgrid i in time period t; C de (P dei,t ) is the diesel generator operating cost of microgrid i in time period t; C cut (P cuti,t ) is the cost of shedding load when microgrid i has insufficient power supply in time period t.

[0160] Furthermore, the objective function is:

[0161]

[0162] In the above formula, F1 is the daily overall operating cost; C grid (P gridi,t ) is the transaction fee between microgrid i and the large grid in time period t.

[0163] Furthermore, in the objective function and constraint conditions for establishing the microgrid group based on the energy storage system cost, the constraint conditions at least include power balance constraints, system operation constraints, and renewable energy utilization rate constraints.

[0164] Further, the power balance constraint is expressed as follows:

[0165]

[0166] Where: P dei,t is the power generation of the diesel generator in microgrid i during time period t; P loadi,t is the load power of microgrid i in time period t; P i,j,t is the power flowing from microgrid i to microgrid j in time period t.

[0167] Furthermore, the system operation constraints include at least that the transmission power of the interconnection line between the microgrid and the large power grid cannot exceed the maximum transmission power; the output of the diesel generator cannot be lower than the minimum power generation power, nor can it exceed the maximum output power, and the climbing power cannot exceed the maximum value; the SOC value of the battery during the charging and discharging process must not exceed its limit, and the battery cannot exceed the maximum charging and discharging power during the charging and discharging process.

[0168] Furthermore, in the process of solving the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm and determining the optimal energy management strategy, the basic artificial hummingbird algorithm is improved by integrating the local escape operator and the opposition-based learning technology.

[0169] Furthermore, the strategy determination module is used to:

[0170] Input cost information, power interaction information of interconnection lines between microgrid groups, and iteration-related data to determine relevant operating parameters of the improved artificial hummingbird algorithm;

[0171] Initialize the population and perform an adversarial-based learning technique upon initialization;

[0172] Initialize hummingbird visit tables, execute flight strategies, and guide foraging;

[0173] Conduct migratory foraging and further update hummingbird visitation tables;

[0174] Execute the local escape operator and determine the solution calculated by it as the fitness, and judge whether the fitness meets the requirements;

[0175] If it meets the requirements, the position is updated to the position that meets the fitness requirements calculated by the local escape operator;

[0176] Obtain the optimal solution of the improved artificial hummingbird algorithm and determine the optimal energy scheduling strategy for the microgrid group energy storage system.

[0177] Furthermore, the initializing of the hummingbird access table, executing the flight strategy and guiding foraging also includes: updating the position according to the foraging situation, and updating the hummingbird access table.

[0178] The disclosed embodiment solves the constructed energy management model of the microgrid group energy storage system by integrating the local escape operator and the improved artificial hummingbird algorithm based on the adversarial learning technology, so as to better explore the solution space of the microgrid group energy management model, accelerate the convergence speed, and overcome the problem of the solution falling into the local optimum.

[0179] A third embodiment of the present disclosure provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of implementing the above method include:

[0180] S11, establishing an energy management model for a microgrid group energy storage system;

[0181] S12, establishing the objective function and constraints of the microgrid group based on the energy storage system cost;

[0182] S13, using the improved artificial hummingbird algorithm to solve the established energy management model of the microgrid group energy storage system and determine the optimal energy management strategy.

[0183] Of course, other steps of the control method can also be used to implement the above embodiment.

[0184] The disclosed embodiment solves the constructed energy management model of the microgrid group energy storage system by integrating the local escape operator and the improved artificial hummingbird algorithm based on the adversarial learning technology, so as to better explore the solution space of the microgrid group energy management model, accelerate the convergence speed, and overcome the problem of the solution falling into the local optimum.

[0185] A fourth embodiment of the present disclosure provides an electronic device, the electronic device comprising at least a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above method when executing the computer program on the memory, specifically comprising:

[0186] S21, establishing an energy management model for a microgrid group energy storage system;

[0187] S22, establish the objective function and constraints of the microgrid group based on the energy storage system cost;

[0188] S23, using the improved artificial hummingbird algorithm to solve the established energy management model of the microgrid group energy storage system and determine the optimal energy management strategy.

[0189] The disclosed embodiment solves the constructed energy management model of the microgrid group energy storage system by integrating the local escape operator and the improved artificial hummingbird algorithm based on the adversarial learning technology, so as to better explore the solution space of the microgrid group energy management model, accelerate the convergence speed, and overcome the problem of the solution falling into the local optimum.

[0190] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0191] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0192] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0193] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0196] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned motor torque control method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0197] In addition, the features of the embodiments shown in the drawings of the present application or the various embodiments mentioned in this specification are not necessarily understood as independent embodiments. Instead, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0198] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An energy management method for a microgrid energy storage system, characterized in that: include: Establish energy management models for microgrid cluster energy storage systems; Establish the objective function and constraints of the microgrid group based on the energy storage system cost; The improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system and determine the optimal energy management strategy.

2. The energy management method according to claim 1, characterized in that: In the energy management model established for the microgrid group energy storage system, the energy management model at least includes the intraday optimization objective function of microgrid i, which is expressed as: In the above formula, C pv (P pvi,t ) is the photovoltaic maintenance cost of microgrid i in time period t; C wt (P wti,t ) is the wind turbine maintenance cost of microgrid i in time period t; C bat (P bati,t ) is the battery operation and maintenance cost of microgrid i in time period t; C de (P dei,t ) is the diesel generator operating cost of microgrid i in time period t; C cut (P cuti,t ) is the cost of shedding load when microgrid i has insufficient power supply in time period t.

3. The energy management method according to claim 1, characterized in that: In the objective function and constraint conditions for establishing a microgrid group based on the energy storage system cost, the objective function is: In the above formula, F1 is the daily overall operating cost; C grid (P gridi,t ) is the transaction fee between microgrid i and the large grid in time period t.

4. The energy management method according to claim 3, characterized in that: In the objective function and constraint conditions for establishing a microgrid group based on the energy storage system cost, the constraint conditions at least include power balance constraints, system operation constraints, and renewable energy utilization rate constraints.

5. The energy management method according to claim 4, characterized in that: The power balance constraint is expressed as follows: Where: P dei,t is the power generation of the diesel generator in microgrid i during time period t; P loadi,t is the load power of microgrid i in time period t; P i,j,t is the power flowing from microgrid i to microgrid j in time period t.

6. The energy management method according to claim 4, characterized in that: The system operation constraints include at least that the transmission power of the interconnection line between the microgrid and the large grid cannot exceed the maximum transmission power; the output of the diesel generator cannot be lower than the minimum power generation power, nor can it exceed the maximum output power, and the climbing power cannot exceed the maximum value; the SOC value of the battery during the charging and discharging process must not exceed its limit, and the battery cannot exceed the maximum charging and discharging power during the charging and discharging process.

7. The energy management method according to claim 1, characterized in that: In the process of solving the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm and determining the optimal energy management strategy, the basic artificial hummingbird algorithm is improved by integrating the local escape operator and the opposition-based learning technology.

8. The energy management method according to claim 7, characterized in that: The improved artificial hummingbird algorithm is used to solve the established energy management model of the microgrid group energy storage system to determine the optimal energy management strategy, including: Input cost information, power interaction information of interconnection lines between microgrid groups, and iteration-related data to determine relevant operating parameters of the improved artificial hummingbird algorithm; Initialize the population and perform an adversarial-based learning technique upon initialization; Initialize hummingbird visit tables, execute flight strategies, and guide foraging; Conduct migratory foraging and further update hummingbird visitation tables; Execute the local escape operator and determine the solution calculated by it as the fitness, and judge whether the fitness meets the requirements; If it meets the requirements, the position is updated to the position that meets the fitness requirements calculated by the local escape operator; Obtain the optimal solution of the improved artificial hummingbird algorithm and determine the optimal energy scheduling strategy for the microgrid group energy storage system.

9. The energy management method according to claim 8, characterized in that: The initialization of the hummingbird access table, execution of the flight strategy and guidance of foraging also includes: updating the position according to the foraging situation and updating the hummingbird access table.

10. An energy management device for a microgrid energy storage system, characterized in that: include: A model building module, used to build an energy management model for a microgrid group energy storage system; A function building module is used to build the objective function and constraint conditions of the microgrid group based on the energy storage system cost; The strategy determination module is used to solve the established energy management model of the microgrid group energy storage system using the improved artificial hummingbird algorithm to determine the optimal energy management strategy.

Images