Energy storage and power generation equipment scheduling method based on improved Harris eagle optimization algorithm
By improving the Harris Eagle optimization algorithm and DBSCAN clustering analysis, combined with deep learning prediction model, optimizing the scheduling of photovoltaic power generation and energy storage equipment, the problems of power abandonment and power shortage of photovoltaic power generation systems in power grid scheduling in the existing technology are solved. Achieve more efficient and economical power grid scheduling.
Patent Information
- Application Number
- CN202411428279.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2025-02-07
AI Technical Summary
The existing photovoltaic energy storage scheduling methods are difficult to maximize economic benefits in complex and changeable environments, and are prone to extreme value problems, resulting in problems such as power abandonment and insufficient power in power grid scheduling of photovoltaic power systems.
Using the improved Harris Eagle optimization algorithm, the photovoltaic power generation and load demand prediction model is constructed through DBSCAN clustering analysis and deep learning prediction model, comprehensively considering the operating rules of the power grid, economic costs and environmental costs, and optimizing the charging and discharging power of energy storage equipment and Power generation power scheduling of power generation equipment.
Improve the accuracy and generalization capabilities of the photovoltaic power generation prediction model and the load demand prediction model, realize more efficient energy storage and power generation equipment scheduling, enhance the real-time and economical power grid scheduling, and reduce the occurrence of extreme value problems. .
Smart Images
Figure CN119401393A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power grid dispatching planning, and in particular to an energy storage and power generation equipment dispatching method based on an improved Harris Hawk optimization algorithm. Background Art
[0002] Photovoltaic power generation systems are greatly affected by external factors such as weather and seasons. Distributed photovoltaic power generation output is the largest when the solar irradiance is the highest at noon, but the power demand of the power grid is often low at this time, and the current will flow in reverse, resulting in voltage exceeding the limit when photovoltaic power is connected to the distribution network, which brings difficulties to the grid dispatch. As an important means of regulation, the energy storage system relies on the characteristics of energy storage battery equipment to regulate the difference between the electric load and the photovoltaic output, so as to quickly achieve demand response, and can effectively alleviate the problems of power abandonment and power shortage in photovoltaic power generation systems. During the low load period of the power grid, the photovoltaic output is greater than the load, and the electric energy can be stored in the energy storage device; during the peak load period of the power grid, the electric energy can be sold to the distribution network operator to promote the grid connection and consumption of photovoltaic power generation. However, the existing photovoltaic energy storage scheduling methods are mostly based on simple parameter comparisons or single models, which are difficult to maximize economic benefits in a complex and changing environment, and are prone to extreme value problems. Summary of the invention
[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present invention provides an energy storage and power generation equipment scheduling method based on an improved Harris Hawk optimization algorithm.
[0004] In a first aspect, the present invention provides a method for scheduling energy storage and power generation equipment using an improved Harris Hawk optimization algorithm, comprising: Collect environmental data and historical operation data of the power grid including photovoltaic and energy storage equipment; use DBSCAN algorithm to perform cluster analysis on the collected environmental data and historical operation data, and divide the environmental data and historical operation data points under similar conditions into different clusters; based on the clustering results, build a photovoltaic power generation prediction model and a load demand prediction model for each cluster; predict photovoltaic power generation and load demand in the future; Based on the prediction results of photovoltaic power generation and load demand, taking into account photovoltaic power generation, power generation equipment power generation, load demand, and characteristics of energy storage equipment, the operation law of the power grid is comprehensively considered, and the economic cost and environmental cost are sorted out. The cost objective function of the power grid affected by the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is determined; using the improved Harris Hawk optimization algorithm, the scheduling tasks of the energy storage equipment and the power generation equipment are regarded as Harris Hawk and prey, and the optimal scheduling plan is found, and the scheduling strategy of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is formulated; the improved Harris Hawk optimization algorithm includes: initializing the population with a good point set, and introducing the Harris Hawk state optimization exploration stage.
[0005] Furthermore, the environmental data includes solar radiation, temperature, and cloud coverage at different time periods, and the historical operation data includes: photovoltaic power generation power, load demand, and energy storage device charging and discharging power at different time periods.
[0006] Furthermore, the optimal point set strategy is used to initialize the population of the charging and discharging power of the energy storage device and the power generation power of the power generation device; The following process is executed cyclically until the maximum number of iterations is reached or the convergence condition is met: Randomly generate prey escape energy based on the current iteration number ; when , enter the exploration phase: During the exploration phase, random probabilities are generated and , and The value range is in the interval (0, 1); like Then, update the individual's position as follows: ; in, , is the optimal individual position and the suboptimal individual position in the current iteration; The individual position to be updated in the current iteration; for Harris Eagle State; like Then, update the individual's position as follows: ; in, It means that the matrix elements are multiplied in sequence by position.
[0007] in: and is a d-dimensional vector, and Each element of is a random number in the range [0,1] that follows a standard normal distribution; ; The calculation formula is: ; when When the development phase begins, and When , Harris's hawk adopts a soft siege strategy to search for prey, and the position update formula is: ; in, For the prey location, , Represents a random number in the interval (0, 1); when and When , Harris's hawk adopts a hard siege strategy to search for prey, and the position update formula is: ; when and When the Harris Hawk adopts a gradual rapid dive soft siege strategy to search for prey, the position update formula is: , in, , , Where: is the fitness function, then is a random vector of the dimension corresponding to the problem, is the Lévy flight function; when and When the Harris Hawk adopts a progressive fast dive hard siege strategy to search for prey, the position update formula is: , in, , , In the formula, is the average position of the population.
[0008] Furthermore, define The unit cube in dimensional Euclidean space is ,like , , for a point set with n points , whose deviation satisfies ,in, is a constant, and any positive number Decide, then For the best point collection, For the best point; when ,and exist Under the constraints of , we can select the smallest prime number. For the best point, use Initialize the good point set. After the good point set is initialized, the good point set is mapped to the initial search space of the improved Harris Hawk optimization algorithm, and its expression is: ; Where: is the upper bound of the j-th dimension, is the lower bound of the j-th dimension, The element that is the best point to focus on.
[0009] Furthermore, the Harris Hawk state is randomly generated according to the following formula based on the current iteration number: : ; and represents a random variable in [-1, 1], represents a random number in the interval (0, 1). is the control parameter.
[0010] Furthermore, the process of determining the cost objective function of the power grid affected by the charging and discharging power of the energy storage device and the power generation power of the power generation device includes: For power generation equipment, the unit economic cost and unit environmental cost in the power generation process are expressed as: ; in, For power generation equipment Fuel used The unit quality cost, For power generation equipment Fuel consumed per unit of generated power Quality, For power generation equipment Consumption fuel produce The quality of waste To manage unit quality The cost of waste For power generation equipment Maintenance cost per unit of power generation; for clean power generation equipment, , All are zero; For energy storage equipment, the cost of the dispatch process is expressed as: ; The overall unit cost of grid electricity generation is expressed as: ; The time integral of the overall unit cost of power generation in the power grid is taken as the objective function, and the improved Harris optimization algorithm is used to optimize the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment.
[0011] Furthermore, the load demand of the power grid of energy storage equipment and power generation equipment needs to be balanced with the total power generation of the power grid: ,in, For the moment The load demand power at time is predicted by the load demand prediction model. For the moment Time generating equipment The power generation of photovoltaic power in the power grid is predicted by the photovoltaic power prediction model, and the power generation of the power generation equipment meets the minimum power generation and maximum power generation constraints of the power generation equipment: , For power generation equipment The minimum power generation capacity, For power generation equipment Maximum power generation capacity; For the moment Time storage equipment The charging power of the energy storage meets the maximum charging power constraint of the energy storage device: , For energy storage devices The maximum charging power of the energy storage device meets the maximum power consumption constraint of the energy storage device: , For energy storage devices Maximum power generation.
[0012] Furthermore, for energy storage, when charging, the charging SOC constraint is met: ; When discharging, the discharge SOC constraint is met: ; in, is the time variation, For energy storage devices Charging efficiency, For energy storage devices Discharge efficiency; The SOC of the energy storage device is greater than zero.
[0013] In the second aspect, the present invention provides an energy storage and power generation equipment scheduling device based on an improved Harris Hawk optimization algorithm, comprising: at least one processing unit, the processing unit and the storage unit are interconnected through a bus unit, the storage unit stores a computer program, and when the computer program is executed by the processing unit, the energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm is implemented.
[0014] In a third aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the energy storage and power generation equipment scheduling method of the improved Harris Hawk optimization algorithm.
[0015] The above technical solution provided by the embodiment of the present invention has the following advantages compared with the prior art: This application uses DBSCAN cluster analysis to divide data points under similar conditions into the same cluster, thereby improving the accuracy and generalization of photovoltaic power generation prediction models and load demand prediction models. By introducing the improved Harris Eagle optimization algorithm and organically combining global search and local development, faster and more comprehensive coverage of the search space is achieved, and the power space of energy storage equipment and power generation equipment is searched more efficiently, improving overall efficiency and enhancing the real-time nature of scheduling. Adapt to actual load demand at the lowest cost and give full play to the advantages of energy storage. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] Figure 1 A flowchart of a method for scheduling energy storage and power generation equipment using an improved Harris Hawk optimization algorithm provided by an embodiment of the present invention; Figure 2 A flowchart of an improved Harris Hawk optimization algorithm provided by an embodiment of the present invention; Figure 3 A flowchart of the exploration phase of the improved Harris Hawk optimization algorithm provided by an embodiment of the present invention; Figure 4 A flowchart of the development phase of the improved Harris Hawk optimization algorithm provided by an embodiment of the present invention; Figure 5 A schematic diagram of an energy storage and power generation equipment scheduling device based on an improved Harris Hawk optimization algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0021] Example 1 like Figure 1 As shown, the technology of the present invention realizes a method for scheduling energy storage and power generation equipment based on an improved Harris Eagle optimization algorithm. Distributed power generation equipment and energy storage equipment need to accurately predict the grid-side load demand and photovoltaic output conditions in a certain period of time before scheduling, so as to better achieve the effect of peak shaving and valley filling.
[0022] Collect environmental data and historical operation data of the photovoltaic and energy storage equipment power grid. The environmental data includes solar radiation, temperature, and cloud coverage at different time periods. The historical operation data includes: photovoltaic power generation power, load demand, and energy storage equipment charging and discharging power at different time periods.
[0023] The DBSCAN algorithm is used to perform cluster analysis on the collected environmental data and historical operation data, and the data points of environmental data and historical operation data under similar conditions are divided into different clusters to reflect the energy supply and demand characteristics under different time periods and preset environmental conditions.
[0024] Based on the clustering results, a photovoltaic power generation prediction model and a load demand prediction model are constructed for each cluster. The photovoltaic power generation prediction model and the load demand prediction model use deep learning algorithms, use historical operation data and environmental data as training data samples, learn the photovoltaic output and load demand rules under different environmental conditions, predict photovoltaic power generation and load demand in the future, and obtain energy supply and demand in the future time period.
[0025] Based on the prediction results of photovoltaic power generation and load demand, taking into account photovoltaic power generation, load demand, characteristics of energy storage equipment, comprehensive consideration of the operation law of the power grid, overall economic cost and environmental cost, the cost objective function affected by the charging and discharging power of energy storage equipment and the power generation power of power generation equipment is determined.
[0026] For a grid that includes energy storage and generation, the load demand needs to be balanced with the total generation of the grid: ,in, For the moment The load demand power at time is predicted by the load demand prediction model. For the moment Time generating equipment The power generation of photovoltaic power in the power grid is predicted by the photovoltaic power prediction model, and the power generation of the power generation equipment meets the minimum power generation and maximum power generation constraints of the power generation equipment: , For power generation equipment The minimum power generation capacity, For power generation equipment Maximum power generation capacity; For the moment Time storage equipment The charging power of the energy storage meets the maximum charging power constraint of the energy storage device: , For energy storage devices The maximum charging power of the energy storage device meets the maximum power consumption constraint of the energy storage device: , For energy storage devices Maximum power generation.
[0027] And for energy storage, when charging, the charging SOC constraint is met: ; When discharging, the discharge SOC constraint is met: ; in, is the time variation, For energy storage devices Charging efficiency, For energy storage devices Discharge efficiency; The SOC of the energy storage device is greater than zero.
[0028] For power generation equipment, the unit economic cost and unit environmental cost in the power generation process are expressed as: ; in, For power generation equipment Fuel used The unit quality cost, For power generation equipment Fuel consumed per unit of generated power Quality, For power generation equipment Consumption fuel produce The quality of waste To manage unit quality The cost of waste For power generation equipment Maintenance cost per unit of generated power.
[0029] For clean power generation equipment, , All are zero.
[0030] For energy storage equipment, the cost of the dispatch process is expressed as: ; The overall unit cost of grid electricity generation is expressed as: ; The time integral of the overall unit cost of power generation in the power grid is taken as the cost objective function, and the improved Harris optimization algorithm is used to optimize the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment to minimize the cost objective function.
[0031] Using the improved Harris Hawk optimization algorithm, the scheduling tasks of energy storage equipment and power generation equipment are regarded as Harris Hawk and prey. Through two stages of global search and local development, the optimal scheduling plan that minimizes the cost objective function is found, and the charging and discharging power of energy storage equipment and the power generation power scheduling strategy of power generation equipment are formulated.
[0032] The original Harris Hawk optimization algorithm has two significant limitations: First, the random method is used to initialize the population, which cannot ensure that the initial population has sufficient diversity and extensive coverage of the entire solution space. As a result, the algorithm cannot effectively explore the solution space in the initial stage, which in turn affects its search efficiency, causing the algorithm to show a low search speed and exploration ability in the initial stage. Second, the monotonicity of the energy decay mechanism: In the original Harris Hawk optimization algorithm, the energy parameter decreases linearly from 2 to 0. Although this monotonic decay method helps the algorithm gradually focus on potential high-quality solutions during the iteration process, it may also cause the algorithm to be too conservative in the later stages of the iteration and lack sufficient exploration ability to jump out of the local optimal area. Therefore, the algorithm is prone to fall into the dilemma of local optimal solutions, which limits its global search performance.
[0033] Based on the above problems of Harris Hawk algorithm, an improved Harris Hawk optimization algorithm is proposed: like Figure 2 As shown, the improved Harris Hawk optimization algorithm is as follows: Use the optimal point set strategy to initialize the population of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment; In order to prevent the randomness of population initialization solutions from causing uneven distribution of search space, the best point set strategy is used to improve population initialization to improve the traversal of algorithm search.
[0034] A good point set is a point set that can be evenly distributed in a multidimensional space.
[0035] definition The unit cube in dimensional Euclidean space is ,like , , for a point set with n points , whose deviation satisfies ,in, is a constant, and any positive number Decide, then For the best point collection, For the best point. when ,and exist Under the constraints of , we can select the smallest prime number. is the best point. Initialize the good point set. After the good point set is initialized, the good point set is mapped to the initial search space of the improved Harris Hawk optimization algorithm, and its expression is: ; Where: is the upper bound of the j-th dimension, is the lower bound of the j-th dimension, is an element in the good point set. Compared with the randomly initialized population, the population generated by the good point set is more evenly distributed when the population size is the same. After mapping the good point set to the original search space for optimization, a better global optimal solution can be obtained.
[0036] The following process is executed cyclically until the maximum number of iterations is reached or the convergence condition is met: Calculate the fitness of the current population; the fitness described in this application is a cost objective function; determine the optimal individual position and suboptimal individual position of the current population according to the fitness.
[0037] Randomly generate prey escape energy based on the current iteration number , using the prey's escape energy The control algorithm enters the search phase or the development phase.
[0038] Among them, the prey escape energy : ; In the formula, is a random variable in [-1, 1]; is the current iteration number; is the total number of iterations.
[0039] when When , it enters the exploration phase. In the exploration phase, the Harris Hawk state is introduced to optimize the position update in the exploration phase.
[0040] like Figure 3 As shown, in the exploration phase, a random probability is generated and , and The value range is in the interval (0, 1); like Then, update the individual's position as follows: ; in, , is the optimal individual position and the suboptimal individual position in the current iteration; The individual position to be updated in the current iteration; for Harris Eagle State; The Harris Hawk state is randomly generated according to the following formula based on the current number of iterations : ; and represents a random variable in [-1, 1], represents a random number in the interval (0, 1). is the control parameter.
[0041] like Then, update the individual's position as follows: ; in, It means that the matrix elements are multiplied in sequence by position.
[0042] in: and is a d-dimensional vector, and Each element of is a random number in the range [0,1] that follows a standard normal distribution; ; The calculation formula is: .
[0043] when When the target is 1, it enters the development stage. In the development stage, local search is the main method. The improved Harris Hawk optimization algorithm uses four strategies: soft siege, hard siege, soft encirclement and hard encirclement to capture the prey. The choice of encirclement method is determined by the escape energy. and Decide, is a random number in (0, 1), when When , it means the prey can break through the siege of Harris's hawk, but not vice versa.
[0044] like Figure 4 As shown, during the development phase, and When , the prey has sufficient physical strength to break through the siege. Harris Hawk adopts the soft siege strategy to search for prey, and the position update formula is: ; in, For the prey location, , Represents a random number in the interval (0, 1); when and When the prey breaks through the siege, it runs out of energy. Harris's hawk uses the hard siege strategy to search for prey, and the position update formula is: ; when and When the prey has sufficient physical strength, it will use Levy flight to simulate escape behavior to try to break through the siege. Harris Hawk adopts a gradual rapid dive soft siege strategy to search for prey. The position update formula is: , in, , , Where: is the fitness function, then is a random vector of the dimension corresponding to the problem, is the Levy flight function.
[0045] when and When the prey is not strong enough and cannot break through the siege, Harris's hawk adopts a gradual and rapid dive hard siege strategy to search for prey.
[0046] , in, , , In the formula, is the average position of the population.
[0047] According to the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment of the improved Harris Eagle optimization algorithm, the scheduling strategy is adjusted to adapt to the actual load demand at the lowest cost and give full play to the advantages of energy storage.
[0048] Example 2 See also Figure 5 As shown, an embodiment of the present invention provides an energy storage and power generation equipment scheduling device of an improved Harris Hawk optimization algorithm, including: at least one processing unit, the processing unit and the storage unit are interconnected through a bus unit, and the storage unit is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the software programs, computer executable programs and modules corresponding to the energy storage and power generation equipment scheduling method of an improved Harris Hawk optimization algorithm in the embodiment of the present invention. The processing unit implements the above-mentioned energy storage and power generation equipment scheduling method of an improved Harris Hawk optimization algorithm by running the software programs, computer executable programs and modules stored in the storage unit, including: Collect environmental data and historical operation data of the power grid including photovoltaic and energy storage equipment; use DBSCAN algorithm to perform cluster analysis on the collected environmental data and historical operation data, and divide the environmental data and historical operation data points under similar conditions into different clusters; based on the clustering results, build a photovoltaic power generation prediction model and a load demand prediction model for each cluster; predict photovoltaic power generation and load demand in the future; Based on the prediction results of photovoltaic power generation and load demand, taking into account photovoltaic power generation, power generation equipment power generation, load demand, and characteristics of energy storage equipment, the operation law of the power grid is comprehensively considered, and the economic cost and environmental cost are sorted out. The cost objective function of the power grid affected by the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is determined; using the improved Harris Hawk optimization algorithm, the scheduling tasks of the energy storage equipment and the power generation equipment are regarded as Harris Hawk and prey, and the optimal scheduling plan is found, and the scheduling strategy of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is formulated; the improved Harris Hawk optimization algorithm includes: initializing the population with a good point set, and introducing the Harris Hawk state optimization exploration stage.
[0049] Of course, the computer program stored in the storage unit of the energy storage and power generation equipment scheduling device of the improved Harris Hawk optimization algorithm provided in the embodiment of the present invention is not limited to the method operation as described above, and can also execute the relevant operations in the energy storage and power generation equipment scheduling method of the improved Harris Hawk optimization algorithm provided in any embodiment of the present invention.
[0050] Example 3 An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed, the method for scheduling energy storage and power generation equipment using the improved Harris Hawk optimization algorithm is implemented, including: Collect environmental data and historical operation data of the power grid including photovoltaic and energy storage equipment; use DBSCAN algorithm to perform cluster analysis on the collected environmental data and historical operation data, and divide the environmental data and historical operation data points under similar conditions into different clusters; based on the clustering results, build a photovoltaic power generation prediction model and a load demand prediction model for each cluster; predict photovoltaic power generation and load demand in the future; Based on the prediction results of photovoltaic power generation and load demand, taking into account photovoltaic power generation, power generation equipment power generation, load demand, and characteristics of energy storage equipment, the operation law of the power grid is comprehensively considered, and the economic cost and environmental cost are sorted out. The cost objective function of the power grid affected by the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is determined; using the improved Harris Hawk optimization algorithm, the scheduling tasks of the energy storage equipment and the power generation equipment are regarded as Harris Hawk and prey, and the optimal scheduling plan is found, and the scheduling strategy of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is formulated; the improved Harris Hawk optimization algorithm includes: initializing the population with a good point set, and introducing the Harris Hawk state optimization exploration stage.
[0051] A computer-readable storage medium provided in an embodiment of the present invention stores a computer program which is not limited to the method operations described above, but can also execute related operations in an energy storage and power generation equipment scheduling method of an improved Harris Hawk optimization algorithm provided in any embodiment of the present invention.
[0052] In the embodiments provided by the present invention, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the structural embodiments described above are only schematic. For example, the division of the 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 an indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.
[0053] 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.
[0054] In addition, each functional unit in each embodiment of the present invention 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.
[0055] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for scheduling energy storage and power generation equipment based on an improved Harris Hawk optimization algorithm, characterized in that: include: Collect environmental data and historical operation data of the power grid including photovoltaic and energy storage equipment; use DBSCAN algorithm to perform cluster analysis on the collected environmental data and historical operation data, and divide the environmental data and historical operation data points under similar conditions into different clusters; based on the clustering results, build a photovoltaic power generation prediction model and a load demand prediction model for each cluster; predict photovoltaic power generation and load demand in the future; Based on the prediction results of photovoltaic power generation and load demand, taking into account photovoltaic power generation, power generation equipment power generation, load demand, and characteristics of energy storage equipment, the operation law of the power grid is comprehensively considered, and the economic cost and environmental cost are sorted out. The cost objective function of the power grid affected by the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is determined; using the improved Harris Hawk optimization algorithm, the scheduling tasks of the energy storage equipment and the power generation equipment are regarded as Harris Hawk and prey, and the optimal scheduling plan is found, and the scheduling strategy of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment is formulated; the improved Harris Hawk optimization algorithm includes: initializing the population with a good point set, and introducing the Harris Hawk state optimization exploration stage.
2. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 1 is characterized in that: The environmental data includes solar radiation, temperature, and cloud coverage at different time periods, and the historical operation data includes: photovoltaic power generation power, load demand, and energy storage device charging and discharging power at different time periods.
3. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 1 is characterized in that: Use the optimal point set strategy to initialize the population of the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment; The following process is executed cyclically until the maximum number of iterations is reached or the convergence condition is met: Randomly generate prey escape energy based on the current iteration number ; when , enter the exploration phase: During the exploration phase, random probabilities are generated and , and The value range is in the interval (0, 1); like Then, update the individual's position as follows: ; in, , is the optimal individual position and the suboptimal individual position in the current iteration; The individual position to be updated in the current iteration; for Harris Eagle State; like Then, update the individual's position as follows: ； in, It means that the matrix elements are multiplied in sequence by position. in: and is a d-dimensional vector, and Each element of is a random number in the range [0,1] that follows a standard normal distribution; ; The calculation formula is: ； when When the development phase begins, and When , Harris's hawk adopts a soft siege strategy to search for prey, and the position update formula is: ； in, For the prey location, , Represents a random number in the interval (0, 1); when and When , Harris's hawk adopts a hard siege strategy to search for prey, and the position update formula is: ； when and When the Harris Hawk adopts a gradual rapid dive soft siege strategy to search for prey, the position update formula is: ， in, , ， Where: is the fitness function, then is a random vector of the dimension corresponding to the problem, is the Lévy flight function; when and When the Harris Hawk adopts a progressive fast dive hard siege strategy to search for prey, the position update formula is: ， in, , ， In the formula, is the average position of the population.
4. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 3 is characterized in that: definition The unit cube in dimensional Euclidean space is ,like , , for a point set with n points , whose deviation satisfies ,in, is a constant, and any positive number Decide, then For the best point collection, For the best point; when ,and exist Under the constraints of , we can select the smallest prime number. For the best point, use Initialize the good point set. After the good point set is initialized, the good point set is mapped to the initial search space of the improved Harris Hawk optimization algorithm, and its expression is: ； Where: is the upper bound of the j-th dimension, is the lower bound of the j-th dimension, The element that is the best point to focus on.
5. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 3 is characterized in that: The Harris Hawk state is randomly generated according to the following formula based on the current number of iterations : ； and represents a random variable in [-1, 1], represents a random number in the interval (0, 1). is the control parameter.
6. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 1 is characterized in that: The process of determining the cost objective function of the power grid affected by the charging and discharging power of the energy storage device and the power generation power of the power generation device includes: For power generation equipment, the unit economic cost and unit environmental cost in the power generation process are expressed as: ； in, For power generation equipment Fuel used The unit quality cost, For power generation equipment Fuel consumed per unit of generated power Quality, For power generation equipment Consumption fuel produce The quality of waste To manage unit quality The cost of waste For power generation equipment Maintenance cost per unit of power generation; for clean power generation equipment, , All are zero; For energy storage equipment, the cost of the dispatch process is expressed as: ； The overall unit cost of grid electricity generation is expressed as: ； The time integral of the overall unit cost of power generation in the power grid is taken as the objective function, and the improved Harris optimization algorithm is used to optimize the charging and discharging power of the energy storage equipment and the power generation power of the power generation equipment.
7. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 6 is characterized in that: The load demand of the power grid of energy storage equipment and power generation equipment needs to be balanced with the total power generation of the power grid: ,in, For the moment The load demand power at time is predicted by the load demand prediction model. For the moment Time generating equipment The power generation of photovoltaic power in the power grid is predicted by the photovoltaic power prediction model, and the power generation of the power generation equipment meets the minimum power generation and maximum power generation constraints of the power generation equipment: , For power generation equipment The minimum power generation capacity, For power generation equipment Maximum power generation capacity; For the moment Time storage equipment The charging power of the energy storage meets the maximum charging power constraint of the energy storage device: , For energy storage devices The maximum charging power of the energy storage device meets the maximum power consumption constraint of the energy storage device: , For energy storage devices Maximum power generation.
8. The energy storage and power generation equipment scheduling method based on the improved Harris Hawk optimization algorithm according to claim 6 is characterized in that: For energy storage, when charging, the charging SOC constraint is met: ； When discharging, the discharge SOC constraint is met: ； in, is the time variation, For energy storage devices Charging efficiency, For energy storage devices Discharge efficiency; The SOC of the energy storage device is greater than zero.
9. An energy storage and power generation equipment scheduling device with an improved Harris Hawk optimization algorithm, characterized in that: include: At least one processing unit, the processing unit and the storage unit are interconnected through a bus unit, the storage unit stores a computer program, and when the computer program is executed by the processing unit, the energy storage and power generation equipment scheduling method of the improved Harris Hawk optimization algorithm as described in any one of claims 1-8 is implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the energy storage and power generation equipment scheduling method of the improved Harris Hawk optimization algorithm as described in any one of claims 1 to 8 is implemented.