Distributed new energy regulation and control method, system and equipment based on swarm intelligence and medium

Abstract

The invention discloses a distributed new energy regulation and control method, system and device based on swarm intelligence and a medium, and the method comprises the steps: generating a feature factor for each new energy node according to the energy characteristics of the new energy nodes; generating a preference factor for each demand node according to the use characteristics of the demand nodes; on the basis of energy supply of the new energy nodes, competitive capacity is given to each new energy node; based on the competitive capacity, enabling the new energy node to perform energy supply simulation on the demand node, and applying abrupt change offset to the new energy node in the simulation process; and performing demand evaluation and strategy optimization based on the simulated supply strategy. According to the method, the quality perception level of energy distribution is effectively improved, global dynamic optimization of an energy distribution scheme is finally realized through an iterative solution mechanism of strategy optimization, and resource waste and scheduling cost are reduced while multiple load requirements are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of regulation and distribution, in particular to a distributed new energy regulation method, system and device based on swarm intelligence and a medium. BACKGROUND

[0002] With the continuous progress of renewable energy technology, new energy forms such as wind energy and solar energy are rapidly deployed worldwide, and distributed energy systems have become an important development direction of power systems. However, due to the intermittent, volatile and widely distributed characteristics of new energy, traditional centralized regulation methods cannot meet the real-time, stability and personalized energy supply needs. Especially in the complex environment where multiple new energy nodes and multiple load demand nodes coexist, how to realize efficient and intelligent energy supply and demand matching has become a core problem in new energy dispatching.

[0003] Existing regulation methods generally use fixed proportion, distance priority or historical experience models for power distribution, which cannot take into account the specific preferences of users for power quality, and lack real-time adaptability to changes in new energy characteristics. In addition, most methods ignore the attenuation and variation of waveform characteristics in the process of power transmission, resulting in actual power supply waveform that cannot meet the precise needs of terminal devices for frequency, amplitude, etc., affecting power supply quality and system stability. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is that the existing new energy regulation method has too large a difference in power characteristics between power output and supply, so that in the matching process, it needs to be used normally after frequency adjustment multiple times and other problems.

[0006] To solve the above technical problems, the present application provides the following technical scheme: a distributed new energy regulation method based on swarm intelligence, comprising:

[0007] Obtaining the energy supply power of each new energy node and the energy demand power of each demand node; at the same time, generating a characteristic factor in each new energy node according to the energy characteristics of the new energy node; generating a preference factor in each demand node according to the use characteristics of the demand node;

[0008] Based on the energy supply of the new energy node, each new energy node is given a competitive ability;

[0009] Based on the competitive ability, the new energy node simulates energy supply to the demand node, and applies a mutation offset to the new energy node during the simulation;

[0010] Based on the simulation-based supply strategy, the demand assessment is carried out, if all demand nodes meet the corresponding use characteristics, the supply strategy is output, and the new energy regulation is carried out according to the output supply strategy; if there is a demand node that does not meet the corresponding use characteristics, the strategy optimization is carried out according to the deviation of the simulation result and the use characteristics until the satisfaction is met.

[0011] As a preferred scheme of the distributed new energy regulation method based on swarm intelligence, the new energy node includes a control unit for distributing the electric energy converted by the new energy.

[0012] The demand node includes a power consumption unit with power consumption demand.

[0013] As a preferred scheme of the distributed new energy regulation method based on swarm intelligence, the characteristic factor includes a typical waveform output by the new energy node during power output; the preference factor includes a most suitable waveform for demand during power consumption of the demand node; and the most suitable waveform is a preselected waveform for each demand node.

[0014] The typical waveform is obtained by selecting the waveform in the time-frequency domain according to the characteristics of each node, and the specific steps are as follows:

[0015] Step 1: cutting the complete waveform with a fixed time window to obtain a plurality of waveform segments;

[0016] Step 2: calculating the similarity with other segments and summing up for each waveform segment;

[0017] Step 3: screening the waveform segment corresponding to the maximum value in the summing result as the selection result of the time-frequency domain waveform;

[0018] The beneficial effect of the preferred scheme is that the characteristic factor is generated at the new energy node, which can clearly represent the waveform characteristics such as frequency, amplitude and stability of the electric energy output; and the preference factor is generated at the demand node, which can express the adaptation preference of the terminal device to the electric energy waveform, thereby improving the accuracy of the regulation.

[0019] As a preferred scheme of the distributed new energy regulation method based on swarm intelligence, the competition ability includes three-dimensional parameters: the characteristic factor of the new energy node, the distance between the new energy node and each demand node, and the output power of the new energy node.

[0020] As a preferred scheme of the distributed new energy regulation method based on swarm intelligence, the simulation of energy supply includes:

[0021] The characteristic factor and output power of the new energy node attenuate with the transmission distance when the new energy node outputs power; the power supply of each demand node is performed by using the attenuated output power;

[0022] The constraint condition in the supply is expressed as:

[0023]

[0024] Wherein, n represents the index of the new energy node, N represents the node quantity of the new energy node, m represents the index of the demand node, M represents the quantity of the demand node; e n,m represents the output power of the nth new energy node to the mth demand node, and the result after attenuation; E m represents the demand power of the mth demand node; f m,n represents the output power of the nth new energy node to the mth demand node; F n represents the output power of the nth new energy node.

[0025] As a preferred scheme of the distributed new energy regulation method based on swarm intelligence, wherein: the mutation offset of the new energy node in the simulation process comprises:

[0026] According to the selection process of the typical waveform, the mutation offset of the output power of the new energy node is obtained by analyzing the waveform variability:

[0027] After calculating the average power of each waveform segment, the probability distribution of the difference between the average power of each waveform segment and the average output power is obtained, and the combination of the difference and the corresponding probability (P r , C r ) is obtained.

[0028] The output power is mutated, and is expressed as:

[0029]

[0030] Wherein, F n + represents the output power of the nth new energy node, and the result after mutation; R represents the total number of values, r represents the index of the difference, P r represents the probability corresponding to the rth difference, C r represents the rth difference; g(P r ) represents a conversion function, and the output result is 1 or 0; g(P r ) determines whether to trigger according to P r , if triggered, 1 is output, otherwise 0 is output.

[0031] In each simulation, F n is replaced by Fn +, via F n + Redefine the constraints during supply; according to the redefined constraints: and Simulate energy supply;

[0032] The attenuation modeling of the characteristic factors and output power includes: obtaining an attenuation model of output power by fitting the relationship between output power and transmission distance in historical data;

[0033] By using historical data, the amplitude and frequency of the characteristic factors are fitted with the transmission distance to obtain attenuation models in the amplitude and frequency domains, respectively.

[0034] The beneficial effect of this preferred scheme is that by constructing a probability distribution of the power difference of typical waveform segments, the probability of occurrence of different offset situations is simulated, thereby introducing a physically based power mutation mechanism into the model, so that each round of energy supply simulation includes the reproduction of the "fluctuation" of power generation.

[0035] As a preferred embodiment of the distributed new energy regulation method based on swarm intelligence described in this invention, wherein:

[0036] The requirements assessment includes:

[0037] During the simulation, the input quantities obtained by each demand node are aggregated into waveforms, and the aggregated waveforms are analyzed. The aggregated waveforms are then compared with the waveforms corresponding to the preference factors. If the similarity reaches a preset value, it is determined that the usage characteristics of the current demand node are met; if the similarity does not reach the preset value, it is determined that the usage characteristics of the current demand node are not met.

[0038] Let m be the current demand node; where waveform aggregation includes amplitude and frequency aggregation processes, expressed as: Among them, JH d The result after aggregation is represented by d; the index of amplitude and frequency is represented by u; the index of the renewable energy node that inputs power to the demand node is represented by U; and the number of renewable energy nodes that input power to the demand node is represented by V. d,u E represents the amplitude or frequency of the input power of the u-th renewable energy node for the condition d; u This represents the input power of the u-th renewable energy node to the demand node;

[0039] The strategy optimization includes:

[0040] Extract the demand nodes that do not meet the usage characteristics, and redistribute the power of the extracted demand nodes. If the maximum number of iterations is still not enough to make all demand nodes meet the usage characteristics, then redistribute the power of all demand nodes.

[0041] Repeat the above strategy optimization process until all demand nodes meet the usage characteristics, then stop the iteration and output the final energy supply simulation strategy.

[0042] A distributed new energy regulation and control system based on swarm intelligence, wherein:

[0043] The data acquisition unit obtains the energy supply power of each new energy node and the energy demand power of each demand node. Based on the energy characteristics of the new energy nodes, it generates a feature factor for each new energy node and a preference factor for each demand node based on the usage characteristics of the demand nodes.

[0044] The analysis unit assigns competitive capabilities to each new energy node based on its energy supply.

[0045] The simulation unit, based on the aforementioned competitive capability, enables the new energy node to simulate the energy supply to the demand node, and applies abrupt shifts to the new energy node during the simulation process;

[0046] The optimization unit performs demand assessment based on the simulated supply strategy. If all demand nodes meet the corresponding usage characteristics, it outputs the supply strategy and adjusts the new energy source according to the output supply strategy. If there are demand nodes that do not meet the corresponding usage characteristics, it optimizes the strategy based on the deviation between the simulation results and the usage characteristics until the requirements are met.

[0047] A computer device includes: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, it implements the steps of the method described in any one of the present invention.

[0048] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of the present invention.

[0049] The beneficial effects of the present application: the distributed new energy regulation method based on swarm intelligence provided by the present application realizes accurate modeling and matching of supply and demand characteristics by introducing characteristic factors of new energy nodes and preference factors of demand nodes, breaks through the traditional extensive distribution mode based on power, and fundamentally improves the personalization and adaptability of energy regulation. By introducing the mutation offset modeling mechanism in the regulation process, the energy supply has dynamic disturbance and self-adaptive adjustment capability, and the robustness of the system to load fluctuation and new energy output uncertainty is enhanced. At the same time, the present application introduces the evaluation mode of waveform aggregation and similarity analysis, not only considers power matching, but also pays attention to the adaptation effect of waveform quality on terminal equipment, effectively improves the quality perception level of energy distribution. Finally, through the iterative solution mechanism of strategy optimization, the global dynamic optimization of the energy distribution scheme is realized, which meets the demand of multiple loads while reducing resource waste and scheduling cost. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor.

[0051] Figure 1 The overall flowchart of the distributed new energy regulation method based on swarm intelligence provided by the first embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0053] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a distributed new energy regulation method based on swarm intelligence is provided, comprising:

[0054] S101, obtaining the energy supply power of each new energy node and the energy demand power of each demand node, generating a characteristic factor for each new energy node according to the energy characteristics of the new energy node, and generating a preference factor for each demand node according to the use characteristics of the demand node.

[0055] Further, the new energy node includes a control unit for distributing the converted electric energy, and is usually in the form of a micro-grid or a small power station, including but not limited to the following structures: a photovoltaic power station or a solar conversion subsystem, a wind power station or an independent wind power unit, an energy storage combined system (containing a lithium battery pack and a power regulation module), an integrated energy routing node capable of receiving and scheduling external new energy input, and a local energy management station with VPP (virtual power plant) interface capability, etc.

[0056] The demand node includes a power consumption unit with power consumption demand, and the power consumption unit refers to equipment or systems that actually consume electric energy, such as industrial production lines, commercial building loads, residential power terminals, data centers, etc. Each power consumption unit has a clear load characteristic and operation mode.

[0057] The characteristic factor refers to the typical waveform output by the new energy node during power output; and the preference factor refers to the most suitable waveform for the demand during power consumption by the demand node, wherein the most suitable waveform is a pre-selected waveform for each demand node, and the typical waveform is obtained by selecting the waveform in the time-frequency domain according to the characteristics of each node. The specific steps are as follows:

[0058] Step 1: cutting the complete waveform with a fixed time window to obtain multiple waveform segments;

[0059] Step 2: calculating the similarity with other segments and summing up for each waveform segment;

[0060] Step 3: selecting the waveform segment corresponding to the maximum value in the summing result as the selection result of the time-frequency domain waveform.

[0061] It should be noted that by generating the characteristic factor in the new energy node, the frequency, amplitude, stability, and other waveform characteristics of the electric energy output can be clearly represented; and by generating the preference factor in the demand node, the adaptation preference of the terminal equipment to the electric energy waveform can be expressed. This extension from "power size" to "waveform form" upgrades the energy matching from traditional power matching to deep-level matching driven by waveform quality, improving the accuracy of regulation and control.

[0062] Due to the high heterogeneity of new energy nodes (such as photovoltaic, wind power, energy storage) and power consumption units (such as industrial loads, residential loads) in the system, if not normalized modeling, it will lead to the incoordination of supply and demand scheduling. By uniformly extracting "typical waveform" and "optimal waveform", a general measurement system is established in the waveform space, so that various nodes can be compared and integrated in the same dimension, and the coordination ability of the whole system is improved. The extraction results of characteristic factors and preference factors will be the core parameters for evaluating similarity and performing mutation offset in subsequent energy supply simulation; at the same time, they are also important criteria for judging the effectiveness of optimization iteration. Therefore, this step is not only data acquisition, but also the core modeling entrance of the regulation model, and its accuracy and representativeness directly affect the regulation performance of the whole system.

[0063] S102, based on the energy supply of the new energy node, each new energy node is given a competitive ability.

[0064] The competitive ability includes three-dimensional parameters: the characteristic factor of the new energy node, the distance between the new energy node and each demand node, and the output power of the new energy node.

[0065] Each new energy node supplies each demand node according to the competitive force, calculates the similarity between the characteristic factor of each new energy node and the preference factor of each demand node; for each demand node, design three probability coefficients β, γ, δ, use the weight coefficient, design the allocation probability of the demand node for each unit of power in the new energy node, and allocate power according to the allocation probability. The allocation probability of the new energy node n to the demand node m is expressed as:

[0066] P t =β×K n,m +γ×X n,m +δ×EE n

[0067] Wherein, K n,m represents the similarity between the characteristic factor of the new energy node n and the preference factor of the demand node m, X n,m represents the distance between the new energy node n and the demand node m; EE n represents the output energy of the new energy node n, when the energy of the new energy node is exhausted or the energy of the demand node reaches the maximum value, stop distribution.

[0068] It is to be noted that the traditional resource allocation is mostly based on the hard decision mode such as "maximum priority" or "shortest distance priority", which leads to the lack of flexibility of the system in the dynamic environment. The present step introduces the allocation probability mechanism based on the three-dimensional competitiveness of the feature factor similarity, distance and power capacity, and integrates the three types of information by weighting to construct the "allocation probability" of each new energy node to the demand node, so as to realize the flexible scheduling and probability-driven dynamic matching of power supply and avoid the rigidity of resource allocation. The similarity of the feature factor and the preference factor is taken as one of the core factors affecting the allocation probability, which means that the system not only makes the decision of "whether it can supply", but also considers the matching degree of "whether the power supply quality is the most suitable". This mechanism realizes the leap from "quantity satisfaction" to "quality adaptation" of power supply, and is especially suitable for high-end power consumption units (such as data centers and precision manufacturing equipment) with clear demand for power quality, which significantly improves the power consumption experience of end users.

[0069] S103, based on the competitiveness, simulating the energy supply of the new energy node to the demand node, and applying mutation offset to the new energy node in the simulation process.

[0070] The simulation of the energy supply includes that when the new energy node outputs power, the feature factor and the output power of the new energy node attenuate with the transmission distance; and the power supply of each demand node is performed by using the attenuated output power.

[0071] The constraint condition in the supply is expressed as:

[0072] Wherein, n represents the index of the new energy node, N represents the number of the new energy nodes, m represents the index of the demand node, M represents the number of the demand nodes; e n,m represents the result of the output power of the nthnew energy node to the mthdemand node after attenuation; E m represents the demand power of the mthdemand node; f m,n represents the output power of the nthnew energy node to the mthdemand node; F n represents the output power of the nthnew energy node.

[0073] Further, according to the selection process of the typical waveform, the waveform variability is analyzed to obtain the mutation offset of the output power of the new energy node, including:

[0074] After calculating the average power of each waveform segment, the probability distribution of the difference between the average power of each waveform segment and the average output power is calculated to obtain the combination of the difference and the corresponding probability (P r , C r ).

[0075] The output power is mutated:

[0076] wherein F n + represents the output power of the nth new energy node, the result after mutation; R represents the total number of values, r represents the index of the difference value, P r represents the probability corresponding to the rth difference value, C r represents the rth difference value; g(P r ) represents a conversion function, and the output result is 1 or 0; g(P r ) determines whether to trigger according to P r , if triggered, 1 is output, otherwise 0 is output. The conversion function is not determined by simple'single judgment' or 'fixed threshold judgment' to determine whether mutation occurs, but by a cumulative and single probability triggering mechanism, and the probability event is modeled to realize the control of the mutation behavior. When the probability of each difference value is judged, there is a probability of generation and a probability of non-generation, and the accumulation of the difference value is carried out on this basis, which conforms to the actual situation of power supply and can most truly reflect the power supply characteristics.

[0077] In each simulation, F n is replaced by F n +, and the constraint condition in the supply is redefined by F n +, and the simulation of energy supply is carried out according to the redefined constraint condition: and .

[0078] The output power of new energy nodes (such as photovoltaic and wind power) often fluctuates and mutates in actual operation due to factors such as climate, shading and equipment aging. Using only static average power modeling will mask this uncertainty. This step simulates the occurrence probability of different offset conditions by constructing a probability distribution of the power difference value of a typical waveform segment, thereby introducing a power mutation mechanism with a physical basis into the model, so that each round of energy supply simulation contains the reproduction of the 'volatility' of power generation. If the energy model always outputs fixed power, the energy supply distribution strategy may tend to a certain fixed structure, which is easy to fall into local optimum. The mutation mechanism can significantly widen the strategy search space by applying perturbation under certain probability conditions, so that the optimization algorithm can be trained under different power combinations, and the strategy is pushed to approach the global optimum.

[0079] The attenuation modeling of the characteristic factor and the output power includes: fitting the relationship between the output power and the transmission distance through historical data to obtain an attenuation model of the output power. That is, the amplitude and frequency of the characteristic factor (the output of the energy is electricity, and the two main characteristics of electricity are amplitude and frequency) are fitted with the transmission distance respectively to obtain the amplitude and frequency attenuation models respectively.

[0080] S104: based on the simulated supply strategy, performing demand assessment, if all demand nodes meet the corresponding use characteristics, output the supply strategy, and perform new energy regulation according to the output supply strategy; if the demand node does not meet the corresponding use characteristics, the strategy optimization is performed according to the deviation of the simulation result and the use characteristics until it is satisfied.

[0081] The demand assessment comprises:

[0082] In the simulation process, the input quantity obtained by each demand node is aggregated in a waveform, and the aggregated waveform is analyzed; the similarity of the aggregated waveform and the waveform corresponding to the preference factor is compared, if the similarity reaches a preset value, it is judged that the use characteristics of the current demand node are met; if the similarity does not reach the preset value, it is judged that the use characteristics of the current demand node are not met.

[0083] Let m be the current demand node; wherein the aggregation of the waveform comprises an aggregation process of amplitude and frequency, denoted as: Wherein, JH d denotes the aggregated result; d denotes the index of amplitude and frequency; u denotes the index of the new energy node inputting power to the demand node; U denotes the number of new energy nodes inputting power to the demand node; V d,u denotes the amplitude or frequency of the power input by the u-th new energy node to the demand node for d; E u denotes the power input by the u-th new energy node to the demand node.

[0084] The strategy optimization comprises:

[0085] The demand node that does not meet the use characteristics is extracted, and the power of the extracted demand node is redistributed, if the maximum iteration number is reached and the demand node still cannot meet the use characteristics, the power distribution of all demand nodes is re-performed.

[0086] In this embodiment, the weight β of similarity and the fixed step are increased in each iteration process. Thus, the attention is focused on the feature of "user demand".

[0087] The above strategy optimization process is repeated until the demand node meets the use characteristics, the iteration is stopped, and the final energy supply simulation strategy is output.

[0088] It is to be noted that, first, the waveform aggregation in amplitude and frequency dimensions is performed on the multi-source input, so that the system can truly reflect the actual energy superposition effect in the power supply process, and then the similarity comparison is performed with the preference factor of each demand node, the objective judgment of whether the "power supply quality" meets the use characteristics is realized, thereby breaking through the limitation of traditional regulation relying only on power matching.

[0089] Meanwhile, in order to improve the effectiveness and directionality of the optimization process, an increasing mechanism of the similarity weight β is introduced, simulating the focusing behavior of "regulating attention" in the iteration process, so that the system gradually enhances the attention to the preferred features in the optimization process. In addition, by setting the maximum number of iterations and the global redistribution mechanism, the system has global adjustment capability when local optimization cannot converge, enhancing the stability and robustness of the regulation strategy.

[0090] Embodiment 2 also provides a distributed new energy regulation system based on swarm intelligence, comprising:

[0091] The acquisition unit obtains the energy supply power of each new energy node and the energy demand power of each demand node, generates a characteristic factor for each new energy node according to the energy characteristics of the new energy node, and generates a preference factor for each demand node according to the use characteristics of the demand node;

[0092] The analysis unit assigns a competitive ability to each new energy node based on the energy supply of the new energy node;

[0093] The simulation unit causes the new energy node to simulate the energy supply to the demand node based on the competitive ability, and applies a mutation offset to the new energy node during the simulation;

[0094] The optimization unit performs demand assessment based on the simulated supply strategy, outputs the supply strategy if all demand nodes meet the corresponding use characteristics, and performs new energy regulation according to the output supply strategy; if there is a demand node that does not meet the corresponding use characteristics, the strategy is optimized according to the deviation between the simulation result and the use characteristics until it is satisfied.

[0095] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0096] The logic and / or steps represented in the flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber (optical), and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example via an optical scanner, then compiled, interpreted, or otherwise processed, and stored in a computer memory in a form that can be later executed by a computer. In this context, a "computer-readable medium" can be any means that can store the program for use by or in connection with the instruction execution system, apparatus, or device.

[0097] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of flowcharts, diagrams, and / or operational descriptions. Insofar as such individual embodiments contained herein involve functional steps, it is understood that the dis- crete functional steps can be implemented in software, firmware, hardware, or any combination thereof. In the context of software, the operations of the flowcharts and / or operational descriptions can represent computer- executable instructions stored on a computer-readable medium that, when executed by a computer, implement the described processes. When implemented in software, the said software can be executed by any computer, but will normally be executed by a specially-programmed computer or microprocessor. In the context of firmware and / or hardware, the said processes can take the form of program instructions and / or logic implemented in circuitry, which can be fixed or programmable. Although the foregoing detailed description has set forth various embodiments using specific

[0098] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application-specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field-programmable gate arrays (FPGA), and so forth.

[0099] It should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application but not limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A distributed new energy regulation method based on swarm intelligence, characterized in that, include: Obtain the energy supply power of each new energy node and the energy demand power of each demand node. Based on the energy characteristics of the new energy nodes, generate a feature factor for each new energy node. Based on the usage characteristics of the demand nodes, generate a preference factor for each demand node. Based on the energy supply of the new energy nodes, each new energy node is given competitive capability; Based on the aforementioned competitive capability, the new energy nodes simulate energy supply to the demand nodes, and apply abrupt shifts to the new energy nodes during the simulation process. Based on the simulated supply strategy, demand assessment is performed. If all demand nodes meet the corresponding usage characteristics, a supply strategy is output, and new energy regulation is carried out according to the output supply strategy. If the demand node does not meet the corresponding usage characteristics, the strategy will be optimized based on the deviation between the simulation results and the usage characteristics until the requirements are met.

2. The distributed new energy regulation method based on swarm intelligence as described in claim 1, characterized in that: The new energy node includes a control unit that distributes the electrical energy converted from new energy sources; The demand nodes include power-consuming units that have electricity demand.

3. The distributed new energy regulation method based on swarm intelligence as described in claim 2, characterized in that: The characteristic factors include the typical waveforms output by the new energy nodes during the power output process; the preference factors include the optimal waveforms of the demand nodes during the power consumption process; the optimal waveforms are the pre-selected waveforms for each demand node. The typical waveform is obtained by selecting waveforms in the time-frequency domain based on the characteristics of each node. The specific steps are as follows: Step 1: Trim the complete waveform within a fixed time window to obtain multiple waveform segments; Step 2: For each waveform segment, calculate the similarity to other segments and sum them; Step 3: Select the waveform segment corresponding to the maximum value in the summation result as the selection result of the time-frequency domain waveform.

4. The distributed new energy regulation method based on swarm intelligence as described in claim 3, characterized in that: The competitive capability includes parameters in three dimensions: the characteristic factors of the new energy node, the distance between the new energy node and each demand node, and the output power of the new energy node.

5. The distributed new energy regulation method based on swarm intelligence as described in claim 4, characterized in that: The simulation of the energy supply includes: Assuming that when a new energy node outputs electricity, the characteristic factor and output power of the new energy node decrease with the transmission distance, the decreased output power is used to supply electricity to each demand node. The constraints on supply are expressed as follows: Where n represents the index of the new energy node, N represents the number of new energy nodes, m represents the index of the demand node, and M represents the number of demand nodes; e n,m E represents the attenuated output power of the nth renewable energy node to the mth demand node; m f represents the power demand of the m-th demand node; m,n F represents the output power of the nth renewable energy node to the mth demand node; n This represents the output power of the nth renewable energy node.

6. The distributed new energy regulation method based on swarm intelligence as described in claim 5, characterized in that, Applying abrupt offsets to new energy nodes during the simulation includes: Based on the selection process of the typical waveform, waveform variability analysis is performed to obtain the abrupt shift in the output power of the new energy node, including: Calculate the average power of each waveform segment, calculate the probability distribution of the difference between the average power of each waveform segment and the average output power, and obtain the combination of the difference and the corresponding probability (P). r C r ); A sudden change in output power is represented as: Among them, F n + indicates the output power of the nth renewable energy node, the result after the mutation; R represents the total number of values, r represents the index of the difference, and P r Let C represent the probability corresponding to the r-th difference. r Represents the r-th difference; g(P) r ) represents a conversion function, and the output result is 1 or 0; g(P r According to P r The probability determines whether the event is triggered. If it is triggered, output 1; otherwise, output 0. In each simulation, F n Replace with F n +, via F n + Redefine the constraints during supply, and apply the redefined constraints: Simulate energy supply; The attenuation modeling of the characteristic factors and output power includes: obtaining an attenuation model of output power by fitting the relationship between output power and transmission distance in historical data; By using historical data, the amplitude and frequency of the characteristic factors are fitted to the transmission distance to obtain attenuation models in the amplitude and frequency domains, respectively.

7. The distributed new energy regulation method based on swarm intelligence as described in claim 6, characterized in that: The requirements assessment includes: During the simulation, the input quantities obtained by each demand node are aggregated into waveforms, and the aggregated waveforms are analyzed. The aggregated waveforms are then compared with the waveforms corresponding to the preference factors. If the similarity reaches a preset value, it is determined that the usage characteristics of the current demand node are met; if the similarity does not reach the preset value, it is determined that the usage characteristics of the current demand node are not met. Let m be the current demand node; where waveform aggregation includes amplitude and frequency aggregation processes, expressed as: Among them, JH d The result after aggregation is represented by d; the index of amplitude and frequency is represented by u; the index of the renewable energy node that inputs power to the demand node is represented by U; and the number of renewable energy nodes that input power to the demand node is represented by V. d,u E represents the amplitude or frequency of the input power of the u-th renewable energy node for the given d; u This represents the input power of the u-th renewable energy node to the demand node; The strategy optimization includes: Extract the demand nodes that do not meet the usage characteristics, and redistribute the power of the extracted demand nodes. If the maximum number of iterations is still not enough to make all demand nodes meet the usage characteristics, then redistribute the power of all demand nodes. Repeat the above strategy optimization process until all demand nodes meet the usage characteristics, then stop the iteration and output the final energy supply simulation strategy.

8. A distributed new energy regulation system based on swarm intelligence, employing the distributed new energy regulation method based on swarm intelligence as described in any one of claims 1-7, characterized in that: The data acquisition unit obtains the energy supply power of each new energy node and the energy demand power of each demand node. Based on the energy characteristics of the new energy nodes, it generates a feature factor for each new energy node and a preference factor for each demand node based on the usage characteristics of the demand nodes. The analysis unit assigns competitive capabilities to each new energy node based on its energy supply. The simulation unit, based on the aforementioned competitive capability, enables the new energy node to simulate the energy supply to the demand node, and applies abrupt shifts to the new energy node during the simulation process; The optimization unit performs demand assessment based on the simulated supply strategy. If all demand nodes meet the corresponding usage characteristics, it outputs the supply strategy and adjusts the new energy source according to the output supply strategy. If there are demand nodes that do not meet the corresponding usage characteristics, it optimizes the strategy based on the deviation between the simulation results and the usage characteristics until the requirements are met.

9. A computer device, comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images