Graph calculation driven renewable energy source distribution optimization method and system

Abstract

The invention discloses a graph calculation-driven renewable energy distribution optimization method and system, and relates to the technical field of energy management. The method comprises the steps of performing graph calculation according to a power grid, and establishing a power distribution model; according to the energy fault risk inspection channel, performing fault risk inspection on the non-renewable energy module to obtain a fault risk inspection result; when the failure risk inspection result is that the failure risk does not pass, performing distribution optimization on the renewable energy source module according to a load equipment set of the non-renewable energy source module, and establishing a renewable energy source distribution optimization first space; performing evaluation optimization to obtain a renewable energy distribution optimization second space; and performing variation optimization on the renewable energy distribution optimization second space to obtain a renewable energy distribution optimization result. The technical problem of low energy utilization efficiency caused by unreasonable renewable energy distribution in the prior art is solved, and the technical effect of improving the energy management efficiency is achieved by optimizing the renewable energy distribution.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a graph computing-driven renewable energy distribution optimization method and system. Background Art

[0002] With the continuous growth of energy demand and the increasing pressure of environmental protection, renewable energy has gradually become an important direction of energy development. However, in the actual operation of the power grid, due to the limitations of meteorological conditions and geographical distribution, the distribution and utilization of renewable energy are often not reasonable, and it is difficult to form efficient synergy with non-renewable energy. However, due to the uneven distribution of energy and the limitations of energy management strategies, the existing energy system still faces many challenges in balancing energy supply and demand and improving energy utilization efficiency. Especially with the trend of energy consumption gradually developing towards low-carbon and intelligent directions, how to achieve reasonable energy distribution and improve the utilization efficiency of renewable energy has become a core issue that needs to be solved urgently. Summary of the invention

[0003] The present application provides a graph computing-driven renewable energy distribution optimization method and system, which solves the technical problem in the prior art that the distribution of renewable energy is not reasonable, resulting in low energy utilization efficiency.

[0004] In view of the above problems, the present application provides a graph computing-driven renewable energy distribution optimization method and system.

[0005] In a first aspect of the present application, a graph computing-driven renewable energy distribution optimization method is provided, the method comprising:

[0006] A power distribution model is established by performing graph calculation according to the power grid, wherein the power grid includes a renewable energy module and a non-renewable energy module; a fault risk test is performed on the non-renewable energy module according to an energy fault risk test channel to obtain a fault risk test result; when the fault risk test result is failed, the distribution of the renewable energy module is optimized according to the load device set of the non-renewable energy module to establish a first space for renewable energy distribution optimization; based on the power distribution model, the first space for renewable energy distribution optimization is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain a second space for renewable energy distribution optimization; energy distribution variation constraint rules and an energy distribution fitness calculation network are introduced to perform variation optimization on the second space for renewable energy distribution optimization to obtain a renewable energy distribution optimization result.

[0007] A second aspect of the present application provides a renewable energy distribution optimization system driven by graph computing, the system comprising:

[0008] Model building component: perform graph calculations according to the power grid to establish a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module; fault risk inspection component: perform fault risk inspection on the non-renewable energy module according to the energy fault risk inspection channel to obtain a fault risk inspection result; distribution optimization component: when the fault risk inspection result is not passed, perform distribution optimization on the renewable energy module according to the load device set of the non-renewable energy module to establish a first space for renewable energy distribution optimization; evaluation and optimization component: based on the power distribution model, perform evaluation and optimization on the first space for renewable energy distribution optimization according to the renewable energy distribution evaluation channel to obtain a second space for renewable energy distribution optimization; variation optimization component: introduce energy distribution variation constraint rules and energy distribution fitness calculation network to perform variation optimization on the second space for renewable energy distribution optimization to obtain a renewable energy distribution optimization result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, a graph calculation is performed according to the power grid to establish a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module. Then, according to the energy fault risk test channel, a fault risk test is performed on the non-renewable energy module to obtain a fault risk test result; when the fault risk test result is not passed, the distribution of the renewable energy module is optimized according to the load device set of the non-renewable energy module to establish the first space for renewable energy distribution optimization. Further, based on the power distribution model, the first space for renewable energy distribution optimization is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for renewable energy distribution optimization. Finally, the energy distribution variation constraint rule and the energy distribution fitness calculation network are introduced to perform variation optimization on the second space for renewable energy distribution optimization to obtain the renewable energy distribution optimization result. The technical problem that the distribution of renewable energy is not reasonable in the prior art, resulting in low energy utilization efficiency, is solved, and the technical effect of improving energy management efficiency is achieved by optimizing the distribution of renewable energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a process flow of a graph computing-driven renewable energy distribution optimization method provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a renewable energy distribution optimization system driven by graph computing provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: model building component 11, fault risk verification component 12, distribution optimization component 13, evaluation optimization component 14, mutation optimization component 15. DETAILED DESCRIPTION

[0015] The present application solves the technical problem in the prior art that the distribution of renewable energy is not reasonable, resulting in low energy utilization efficiency, by providing a graph computing-driven renewable energy distribution optimization method and system.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a graph computing driven renewable energy distribution optimization method, wherein the method includes:

[0019] A power distribution model is established by performing graph calculation according to the power grid, wherein the power grid includes a renewable energy module and a non-renewable energy module.

[0020] The nodes (including renewable energy modules, non-renewable energy modules, load devices) and edges (power transmission lines) in the power grid are abstracted into a graph model, in which each node represents an energy module or device, and each edge represents the power transmission relationship between nodes. The connection relationship between nodes is analyzed through a graph computing algorithm to obtain the distribution characteristics of energy flow in the power grid, including the power supply range and power supply capacity of each energy module and its correlation with other modules or devices.

[0021] Based on graph calculation, the attribute data of renewable energy modules (such as wind farms and photovoltaic arrays) and non-renewable energy modules (such as coal-fired power plants and gas-fired generators) are labeled separately to form a complete power distribution model.

[0022] According to the energy failure risk inspection channel, a failure risk inspection is performed on the non-renewable energy module to obtain a failure risk inspection result.

[0023] The energy failure risk inspection channel is used to evaluate the operating status of non-renewable energy modules, identify possible failure risks, and generate failure risk inspection results, which can reflect whether these modules can meet the current load requirements or whether there are potential failures.

[0024] Furthermore, performing a fault risk test on the non-renewable energy module to obtain a fault risk test result includes:

[0025] The energy failure risk verification channel includes an energy failure risk prediction branch and a failure risk verification branch; the non-renewable energy module is monitored in real time to obtain an energy monitoring data stream; the energy monitoring data stream is input into the energy failure risk prediction branch to obtain an energy failure risk coefficient; the energy failure risk coefficient is input into the failure risk verification branch to generate the failure risk verification result, wherein the failure risk verification branch includes a failure risk verification operator, and the failure risk verification operator includes: if the energy failure risk coefficient is greater than or equal to an energy failure risk threshold, the failure risk verification result is failed, and if the energy failure risk coefficient is less than the energy failure risk threshold, the failure risk verification result is passed.

[0026] Specifically, the energy failure risk inspection channel consists of an energy failure risk prediction branch and a failure risk inspection branch. The energy failure risk prediction branch is used to calculate the energy failure risk coefficient, and the failure risk inspection branch is used to generate a failure risk inspection result based on the risk coefficient. The non-renewable energy module is monitored in real time, and the module's operating status data (such as output power, temperature, vibration, pressure, etc.) is collected through sensors and data acquisition equipment to generate an energy monitoring data stream. The collected energy monitoring data stream is input into the energy failure risk prediction branch to calculate the energy failure risk coefficient, which is used to quantify the possibility of module failure. The energy failure risk coefficient is input into the failure risk inspection branch, and the failure risk inspection operator is used to analyze and judge: when the energy failure risk coefficient is greater than or equal to the preset energy failure risk threshold, the failure risk inspection result is "failed", indicating that the module has a high failure risk; when the energy failure risk coefficient is less than the energy failure risk threshold, the failure risk inspection result is "passed", indicating that the module is operating normally.

[0027] Furthermore, the energy monitoring data stream is input into the energy failure risk prediction branch to obtain an energy failure risk coefficient, including:

[0028] The energy failure risk prediction branch includes K energy failure risk prediction models corresponding to the non-renewable energy module, wherein K is a positive integer greater than 1; the energy monitoring data stream is input into the K energy failure risk prediction models to obtain K energy failure risk prediction coefficients; and mean calculation is performed based on the K energy failure risk prediction coefficients to generate the energy failure risk coefficient.

[0029] The energy failure risk prediction branch includes K energy failure risk prediction models corresponding to the non-renewable energy modules, where K is a positive integer greater than 1. These models are constructed according to different fault characteristics and historical operation data. For example, separate models can be built for key operating conditions such as abnormal output power, excessive equipment temperature, and abnormal vibration to comprehensively cover different types of failure risks. The energy monitoring data stream collected in real time is input into these K energy failure risk prediction models. The model uses various operating parameters in the monitoring data (such as power, temperature, vibration, pressure, etc.) to independently calculate the failure risk, thereby outputting K energy failure risk prediction coefficients. These energy failure risk prediction coefficients respectively reflect the risk level of the non-renewable energy module under different failure types. The final energy failure risk coefficient is generated by calculating the mean of these K energy failure risk prediction coefficients to comprehensively consider the prediction results of each model.

[0030] When the fault risk inspection result is failure, the distribution of the renewable energy modules is optimized according to the load device set of the non-renewable energy modules, and a first space for renewable energy distribution optimization is established.

[0031] When the fault risk test result is not passed, the distribution optimization of renewable energy modules is required to ensure the stable operation of the power grid. Specifically, first, according to the load equipment set of non-renewable energy modules (usually including factories, residential areas or other power equipment), the range of affected load equipment is determined, including the type of equipment, current load demand and operation priority; then, combined with the energy supply capacity, geographical distribution characteristics and transmission loss of renewable energy modules, the energy supply scheme of renewable energy modules (such as solar power generation systems, wind power generation systems, hydropower generation systems, etc.) is redistributed, and its output capacity is adjusted to the affected load equipment set in priority to meet the power demand. In the optimization process, by introducing distributed optimization models such as linear programming or genetic algorithms, a preliminary optimized distribution plan is generated according to the demand priority of load equipment and the actual energy supply capacity of renewable energy, so as to minimize the impact of non-renewable energy module failures on the power grid. Finally, the optimization results form the first space of renewable energy distribution optimization, laying the foundation for subsequent further evaluation and optimization, thereby ensuring the stable operation of the power grid and the continuous power supply of load equipment in the event of a fault.

[0032] Based on the power distribution model, the first space for optimizing the distribution of renewable energy is evaluated and optimized according to a renewable energy distribution evaluation channel to obtain a second space for optimizing the distribution of renewable energy.

[0033] Through the renewable energy distribution evaluation channel, the distribution scheme of the first space is comprehensively analyzed and evaluated. The evaluation process combines the topological structure and real-time operation data of the power distribution model, considers key indicators such as the energy supply capacity of renewable energy, the satisfaction rate of load demand, transmission loss and overall system efficiency, and generates multi-dimensional evaluation results of the distribution scheme. The evaluation results are optimized using optimization algorithms (such as multi-objective optimization algorithms or particle swarm optimization algorithms), and the optimal balance point is sought in multiple evaluation dimensions through iterative calculations to generate an optimized distribution scheme. During the optimization process, priority can be given to goals such as meeting the needs of high-priority load equipment, minimizing energy waste and transmission losses. Finally, the optimized distribution scheme constitutes the second space of renewable energy distribution optimization, providing more accurate and efficient optimization results for the final adjustment of energy distribution, thereby improving the operating efficiency and stability of the power grid.

[0034] Furthermore, based on the power distribution model, the first space for optimizing the distribution of renewable energy is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for optimizing the distribution of renewable energy, including:

[0035] According to the first space of renewable energy distribution optimization, extract the nth decision of renewable energy distribution optimization, wherein n is a positive integer; evaluate the nth decision of renewable energy distribution optimization based on the power distribution model and the renewable energy distribution evaluation channel to obtain the nth energy distribution evaluation result; determine whether the nth energy distribution evaluation result satisfies the energy distribution evaluation constraints, wherein the energy distribution evaluation constraints include energy utilization efficiency constraints, power quality constraints and energy supply reliability constraints; if the nth energy distribution evaluation result satisfies the energy distribution evaluation constraints, add the nth decision of renewable energy distribution optimization to the second space of renewable energy distribution optimization; if the nth energy distribution evaluation result does not satisfy the energy distribution evaluation constraints, eliminate the nth decision of renewable energy distribution optimization.

[0036] Specifically, the nth distribution optimization decision (i.e., the nth decision for renewable energy distribution optimization, where n is a positive integer) is extracted from the first space of renewable energy distribution optimization, which represents a specific distribution scheme in the first space; then, combined with the power distribution model, the nth decision is evaluated through the renewable energy distribution evaluation channel to generate the nth energy distribution evaluation result corresponding to the decision, wherein the evaluation process will integrate multiple constraints, including energy utilization efficiency constraints (such as whether the energy conversion and transmission efficiency meet the requirements), power quality constraints (such as whether the voltage stability and frequency fluctuation meet the standards) and energy supply reliability constraints (such as whether the needs of load equipment can be continuously met). Subsequently, it is determined whether the nth energy distribution evaluation result meets these constraints: if the constraints are met, the nth decision is added to the second space of renewable energy distribution optimization as a qualified optimized distribution scheme; if the constraints are not met, the decision is eliminated to avoid its impact on subsequent optimization. Through this cyclic iteration, the distribution scheme that meets all constraints is screened and optimized from the first space, so as to finally construct a better second space for renewable energy distribution optimization, providing efficient and reliable decision support for the implementation of subsequent energy distribution.

[0037] Furthermore, evaluating the nth decision of the renewable energy distribution optimization based on the power distribution model and the renewable energy distribution evaluation channel to obtain the nth energy distribution evaluation result includes:

[0038] According to the nth decision of optimizing the renewable energy distribution, the power distribution model is simulated and optimized to obtain an nth energy distribution simulation data set; the nth energy distribution simulation data set is input into the renewable energy distribution evaluation channel, and the nth energy distribution evaluation result is output, wherein the renewable energy distribution evaluation channel includes an energy utilization efficiency evaluation model, a power quality evaluation model and an energy supply reliability evaluation model.

[0039] Specifically, the power distribution model is simulated and optimized according to the nth decision of renewable energy distribution optimization. By adjusting the parameters in the model (such as the distribution strategy of energy modules, energy supply ratio and transmission path), the energy distribution in the actual operation scenario is simulated, and the nth energy distribution simulation data set related to the nth decision is generated. The data set contains key operation data generated during the simulation process, such as the utilization rate of renewable energy, power loss rate, voltage fluctuation, and load demand satisfaction rate. Then, the nth energy distribution simulation data set is input into the renewable energy distribution evaluation channel, which includes the energy utilization efficiency evaluation model, the power quality evaluation model and the energy supply reliability evaluation model. Among them, the energy utilization efficiency evaluation model is responsible for calculating the conversion efficiency and transmission efficiency of renewable energy and evaluating the overall utilization level of energy; the power quality evaluation model analyzes the voltage stability, frequency fluctuation and power quality in the simulation data to determine whether the distribution scheme meets the power quality standard; the energy supply reliability evaluation model evaluates the reliability of the distribution scheme under different load conditions according to the load demand satisfaction rate and energy supply continuity. The renewable energy distribution evaluation channel comprehensively calculates the output results of the energy utilization efficiency evaluation model, the power quality evaluation model and the energy supply reliability evaluation model to generate the nth energy distribution evaluation result. The nth energy distribution evaluation result serves as a comprehensive evaluation of the nth decision and provides a reliable basis for the subsequent distribution plan screening and optimization.

[0040] The energy utilization efficiency evaluation model evaluates the energy utilization rate by calculating the power generation of renewable energy, transmission loss and actual load consumption. First, extract the energy supply data and the actual load consumption data, compare the total energy input with the effective energy utilization, and calculate the energy utilization efficiency (formula: energy utilization rate = actual consumption / total supply). At the same time, analyze the proportion of transmission loss to evaluate the efficiency of the energy supply process.

[0041] The power quality evaluation model analyzes power quality indicators such as voltage stability, frequency fluctuation and harmonic distortion. The voltage and frequency changes in the power grid operation are collected through simulation data and compared with the specified range (such as voltage deviation within ±5%). Furthermore, the harmonic distortion rate is analyzed by Fourier transform (such as whether the total harmonic distortion rate is less than the specified value) and the power quality score is calculated comprehensively.

[0042] The energy supply reliability evaluation model is evaluated based on the load demand satisfaction rate and supply continuity. The energy supply status of each load in the simulation data is extracted, the demand satisfaction rate is calculated (formula: demand satisfaction rate = actual supply / load demand), and the frequency and duration of energy supply interruptions are analyzed.

[0043] Energy distribution variation constraint rules and energy distribution fitness calculation network are introduced to perform variation optimization on the second space of renewable energy distribution optimization to obtain renewable energy distribution optimization results.

[0044] Energy distribution variation constraint rules are used to limit the scope and variation of renewable energy distribution adjustment. These rules are set based on the actual needs of grid operation and technical constraints, including the maximum energy supply capacity of renewable energy modules, the energy demand range of load equipment, the capacity limitations of transmission lines, and the dynamic balance requirements of energy distribution.

[0045] The energy distribution fitness calculation network is used to evaluate the fitness of the energy distribution scheme in the second space. The energy distribution fitness calculation network uses neural networks or other machine learning models to comprehensively analyze the performance of the distribution scheme in terms of multi-dimensional indicators such as energy utilization efficiency, power quality and supply reliability, and generates a fitness score for each scheme. The higher the fitness score, the more the distribution scheme meets the power grid operation objectives.

[0046] In the second space, the energy distribution scheme is mutated. Based on the mutation constraint rules, some distribution parameters (such as energy supply ratio, distribution path, etc.) are randomly selected for small adjustments to generate a new distribution scheme. The new scheme is re-evaluated through the fitness calculation network and compared with the original scheme based on the fitness score. If the fitness score of the new scheme is higher than that of the original scheme, the new scheme is retained as the optimization result, otherwise it is discarded. Through multiple iterations of mutation optimization, a distribution scheme with the highest global fitness is finally obtained, which is the optimization result of renewable energy distribution.

[0047] Furthermore, energy distribution variation constraint rules and energy distribution fitness calculation network are introduced to perform variation optimization on the second space of renewable energy distribution optimization to obtain renewable energy distribution optimization results, including:

[0048] The energy distribution variation constraint rules include energy distribution variation dimension thresholds and energy distribution variation step length thresholds; according to the energy distribution variation constraint rules, the second space of renewable energy distribution optimization is mutated to obtain a third space of renewable energy distribution optimization; according to the third space of renewable energy distribution optimization, the second space of renewable energy distribution optimization is expanded to obtain a fourth space of renewable energy distribution optimization; according to the energy distribution fitness calculation network, the fourth space of renewable energy distribution optimization is optimized by maximizing the energy distribution fitness to generate the renewable energy distribution optimization result, wherein the energy distribution fitness calculation network includes energy distribution fitness calculation weight conditions, and the energy distribution fitness calculation weight conditions include energy utilization efficiency weights, power quality weights and energy supply reliability weights.

[0049] Specifically, the energy distribution variation constraint rules include the energy distribution variation dimension threshold and the energy distribution variation asynchrony threshold. The energy distribution variation dimension threshold is used to limit the number (dimension) of energy distribution parameters that can be adjusted in each variation process; the energy distribution variation asynchrony threshold limits the maximum adjustment range of each adjusted parameter to ensure that the variation process does not cause drastic fluctuations or instability in the distribution results. According to the energy distribution variation constraint rules, the distribution schemes in the second space of renewable energy distribution optimization are mutated to generate the third space of renewable energy distribution optimization. The mutation operation randomly selects several distribution parameters (such as energy supply ratio, distribution path) and adjusts them within the threshold range to obtain a new set of distribution schemes. The schemes in the third space of renewable energy distribution optimization are added to the second space of renewable energy distribution optimization to form an extended fourth space of renewable energy distribution optimization.

[0050] The energy distribution fitness calculation network is used to evaluate the fitness of the distribution schemes in the fourth space and maximize the optimization. The fitness calculation network assigns weight values ​​to each scheme by setting the energy distribution fitness calculation weight conditions and combining the three key indicators of energy utilization efficiency, power quality and energy supply reliability. For example, the energy utilization efficiency weight reflects the effectiveness of energy conversion and transmission; the power quality weight evaluates the stability and safety of power grid operation; and the energy supply reliability weight evaluates the performance of the scheme in meeting load demand and supply continuity. The energy distribution fitness calculation network combines the weights of various indicators, calculates the fitness of all distribution schemes, and selects the scheme with the highest fitness.

[0051] Through multiple rounds of iterations and optimization, the optimization results of renewable energy distribution are generated, which meet the requirements of maximizing energy utilization efficiency, power quality compliance and energy supply reliability, while achieving the global optimization goal and providing support for the efficient operation of the power grid.

[0052] Furthermore, according to the energy distribution variation constraint rule, the second space for optimizing the distribution of renewable energy is varied to obtain the third space for optimizing the distribution of renewable energy, including:

[0053] According to the energy distribution variation constraint rule, the second space of renewable energy distribution optimization is mutated to establish an energy distribution variation decision domain; based on the power distribution model and the renewable energy distribution evaluation channel, each energy distribution variation decision in the energy distribution variation decision domain is evaluated to obtain a plurality of energy distribution evaluation results; it is determined whether the plurality of energy distribution evaluation results meet the energy distribution evaluation constraint to obtain a plurality of energy distribution evaluation verification results; according to the plurality of energy distribution evaluation verification results, the energy distribution variation decision domain is optimized and selected to generate the third space of renewable energy distribution optimization.

[0054] According to the energy distribution variation constraint rules (including the energy distribution variation dimension threshold and the energy distribution variation step length threshold), the distribution scheme in the second space of renewable energy distribution optimization is mutated to establish the energy distribution variation decision domain. During the variation process, the distribution parameters (such as the energy supply ratio of the energy module, the distribution path, etc.) are randomly selected for adjustment. The adjustment range and the number of parameters are strictly limited by the variation constraint rules to ensure that the variation operation is carried out within a reasonable range and avoid the instability or infeasibility of the distribution scheme.

[0055] Based on the power distribution model and renewable energy distribution evaluation channel, each energy distribution variation decision in the energy distribution variation decision domain is evaluated. The evaluation process combines indicators such as energy utilization efficiency, power quality and energy supply reliability to calculate the energy distribution evaluation results of each variation decision. These evaluation results reflect the performance of variation decisions in different dimensions and provide a basis for subsequent screening.

[0056] Judge multiple energy distribution evaluation results to verify whether they meet the preset energy distribution evaluation constraints. Energy distribution evaluation constraints include the following: whether the energy utilization efficiency meets the expected standards (such as energy conversion efficiency and transmission efficiency); whether the power quality meets the operating requirements (such as voltage deviation, frequency fluctuation and other indicators); and whether the energy supply reliability meets the needs of load equipment (such as load demand satisfaction rate, energy supply stability). Based on these constraints, generate multiple energy distribution evaluation verification results. According to the energy distribution evaluation verification results, the energy distribution variation decision domain is optimized and selected, and the distribution schemes that meet the evaluation constraints and perform best are retained, and these schemes are summarized to form the third space for renewable energy distribution optimization.

[0057] In summary, the embodiments of the present application have at least the following technical effects:

[0058] First, a graph calculation is performed according to the power grid to establish a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module. Then, according to the energy fault risk test channel, a fault risk test is performed on the non-renewable energy module to obtain a fault risk test result; when the fault risk test result is not passed, the distribution of the renewable energy module is optimized according to the load device set of the non-renewable energy module to establish the first space for renewable energy distribution optimization. Further, based on the power distribution model, the first space for renewable energy distribution optimization is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for renewable energy distribution optimization. Finally, the energy distribution variation constraint rule and the energy distribution fitness calculation network are introduced to perform variation optimization on the second space for renewable energy distribution optimization to obtain the renewable energy distribution optimization result. The technical problem that the distribution of renewable energy is not reasonable in the prior art, resulting in low energy utilization efficiency, is solved, and the technical effect of improving energy management efficiency is achieved by optimizing the distribution of renewable energy.

[0059] Embodiment 2, based on the same inventive concept as the renewable energy distribution optimization method driven by the above-mentioned calculation embodiment, Figure 2 As shown, the present application provides a renewable energy distribution optimization system driven by graph computing, wherein the system includes:

[0060] Model building component 11: perform graph calculation according to the power grid to establish a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module; fault risk inspection component 12: perform fault risk inspection on the non-renewable energy module according to the energy fault risk inspection channel to obtain a fault risk inspection result; distribution optimization component 13: when the fault risk inspection result is not passed, perform distribution optimization on the renewable energy module according to the load device set of the non-renewable energy module to establish a first space for renewable energy distribution optimization; evaluation and optimization component 14: based on the power distribution model, evaluate and optimize the first space for renewable energy distribution optimization according to the renewable energy distribution evaluation channel to obtain a second space for renewable energy distribution optimization; variation optimization component 15: introduce energy distribution variation constraint rules and energy distribution fitness calculation network to perform variation optimization on the second space for renewable energy distribution optimization to obtain a renewable energy distribution optimization result.

[0061] Furthermore, the evaluation optimization component 14 is used to perform the following method:

[0062] According to the first space of renewable energy distribution optimization, extract the nth decision of renewable energy distribution optimization, wherein n is a positive integer; evaluate the nth decision of renewable energy distribution optimization based on the power distribution model and the renewable energy distribution evaluation channel to obtain the nth energy distribution evaluation result; determine whether the nth energy distribution evaluation result satisfies the energy distribution evaluation constraints, wherein the energy distribution evaluation constraints include energy utilization efficiency constraints, power quality constraints and energy supply reliability constraints; if the nth energy distribution evaluation result satisfies the energy distribution evaluation constraints, add the nth decision of renewable energy distribution optimization to the second space of renewable energy distribution optimization; if the nth energy distribution evaluation result does not satisfy the energy distribution evaluation constraints, eliminate the nth decision of renewable energy distribution optimization.

[0063] Furthermore, the evaluation optimization component 14 is used to perform the following method:

[0064] According to the nth decision of optimizing the renewable energy distribution, the power distribution model is simulated and optimized to obtain an nth energy distribution simulation data set; the nth energy distribution simulation data set is input into the renewable energy distribution evaluation channel, and the nth energy distribution evaluation result is output, wherein the renewable energy distribution evaluation channel includes an energy utilization efficiency evaluation model, a power quality evaluation model and an energy supply reliability evaluation model.

[0065] Furthermore, the variation optimization component 15 is used to perform the following method:

[0066] The energy distribution variation constraint rules include energy distribution variation dimension thresholds and energy distribution variation step length thresholds; according to the energy distribution variation constraint rules, the second space of renewable energy distribution optimization is mutated to obtain a third space of renewable energy distribution optimization; according to the third space of renewable energy distribution optimization, the second space of renewable energy distribution optimization is expanded to obtain a fourth space of renewable energy distribution optimization; according to the energy distribution fitness calculation network, the fourth space of renewable energy distribution optimization is optimized by maximizing the energy distribution fitness to generate the renewable energy distribution optimization result, wherein the energy distribution fitness calculation network includes energy distribution fitness calculation weight conditions, and the energy distribution fitness calculation weight conditions include energy utilization efficiency weights, power quality weights and energy supply reliability weights.

[0067] Furthermore, the variation optimization component 15 is used to perform the following method:

[0068] According to the energy distribution variation constraint rule, the second space of renewable energy distribution optimization is mutated to establish an energy distribution variation decision domain; based on the power distribution model and the renewable energy distribution evaluation channel, each energy distribution variation decision in the energy distribution variation decision domain is evaluated to obtain a plurality of energy distribution evaluation results; it is determined whether the plurality of energy distribution evaluation results meet the energy distribution evaluation constraint to obtain a plurality of energy distribution evaluation verification results; according to the plurality of energy distribution evaluation verification results, the energy distribution variation decision domain is optimized and selected to generate the third space of renewable energy distribution optimization.

[0069] Furthermore, the fault risk verification component 12 is used to perform the following method:

[0070] The energy failure risk verification channel includes an energy failure risk prediction branch and a failure risk verification branch; the non-renewable energy module is monitored in real time to obtain an energy monitoring data stream; the energy monitoring data stream is input into the energy failure risk prediction branch to obtain an energy failure risk coefficient; the energy failure risk coefficient is input into the failure risk verification branch to generate the failure risk verification result, wherein the failure risk verification branch includes a failure risk verification operator, and the failure risk verification operator includes: if the energy failure risk coefficient is greater than or equal to an energy failure risk threshold, the failure risk verification result is failed, and if the energy failure risk coefficient is less than the energy failure risk threshold, the failure risk verification result is passed.

[0071] Furthermore, the fault risk verification component 12 is used to perform the following method:

[0072] The energy failure risk prediction branch includes K energy failure risk prediction models corresponding to the non-renewable energy module, wherein K is a positive integer greater than 1; the energy monitoring data stream is input into the K energy failure risk prediction models to obtain K energy failure risk prediction coefficients; and mean calculation is performed based on the K energy failure risk prediction coefficients to generate the energy failure risk coefficient.

[0073] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0075] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A graph computing-driven renewable energy distribution optimization method, characterized in that: The method comprises: Performing graph calculations based on the power grid to establish a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module; According to the energy failure risk inspection channel, a failure risk inspection is performed on the non-renewable energy module to obtain a failure risk inspection result; When the fault risk test result is failed, the renewable energy module is distributed optimized according to the load device set of the non-renewable energy module to establish a first space for renewable energy distribution optimization; Based on the power distribution model, the first space for optimizing the distribution of renewable energy is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for optimizing the distribution of renewable energy; Energy distribution variation constraint rules and energy distribution fitness calculation network are introduced to perform variation optimization on the second space of renewable energy distribution optimization to obtain renewable energy distribution optimization results.

2. The method according to claim 1, characterized in that Based on the power distribution model, the first space for optimizing the distribution of renewable energy is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for optimizing the distribution of renewable energy, including: Extracting the nth decision of renewable energy distribution optimization according to the first space of renewable energy distribution optimization, where n is a positive integer; Evaluate the nth decision of the renewable energy distribution optimization based on the power distribution model and the renewable energy distribution evaluation channel to obtain an nth energy distribution evaluation result; Determining whether the nth energy distribution evaluation result satisfies energy distribution evaluation constraints, wherein the energy distribution evaluation constraints include energy utilization efficiency constraints, power quality constraints, and energy supply reliability constraints; If the nth energy distribution evaluation result satisfies the energy distribution evaluation constraint, adding the nth decision of renewable energy distribution optimization to the second space of renewable energy distribution optimization; If the nth energy distribution evaluation result does not satisfy the energy distribution evaluation constraint, the nth decision of renewable energy distribution optimization is eliminated.

3. The method according to claim 2, characterized in that The nth decision of the renewable energy distribution optimization is evaluated based on the power distribution model and the renewable energy distribution evaluation channel to obtain an nth energy distribution evaluation result, including: Performing simulation optimization on the power distribution model according to the nth decision of the renewable energy distribution optimization to obtain an nth energy distribution simulation data set; The nth energy distribution simulation data set is input into the renewable energy distribution evaluation channel, and the nth energy distribution evaluation result is output, wherein the renewable energy distribution evaluation channel includes an energy utilization efficiency evaluation model, a power quality evaluation model and an energy supply reliability evaluation model.

4. The method according to claim 1, characterized in that Introducing energy distribution variation constraint rules and energy distribution fitness calculation network to perform variation optimization on the second space of renewable energy distribution optimization to obtain renewable energy distribution optimization results, including: The energy distribution variation constraint rules include an energy distribution variation dimension threshold and an energy distribution variation asynchronous length threshold; According to the energy distribution variation constraint rule, the second space for optimizing the distribution of renewable energy is varied to obtain a third space for optimizing the distribution of renewable energy; According to the third space for optimizing the distribution of renewable energy, the second space for optimizing the distribution of renewable energy is expanded to obtain a fourth space for optimizing the distribution of renewable energy; The energy distribution fitness is maximized in the fourth space of the renewable energy distribution optimization according to the energy distribution fitness calculation network to generate the renewable energy distribution optimization result, wherein the energy distribution fitness calculation network includes energy distribution fitness calculation weight conditions, and the energy distribution fitness calculation weight conditions include energy utilization efficiency weights, power quality weights and energy supply reliability weights.

5. The method according to claim 4, characterized in that According to the energy distribution variation constraint rule, the second space of renewable energy distribution optimization is varied to obtain a third space of renewable energy distribution optimization, including: According to the energy distribution variation constraint rule, the second space of renewable energy distribution optimization is mutated to establish an energy distribution variation decision domain; Based on the power distribution model and the renewable energy distribution evaluation channel, each energy distribution variation decision in the energy distribution variation decision domain is evaluated to obtain a plurality of energy distribution evaluation results; Determining whether the multiple energy distribution evaluation results meet the energy distribution evaluation constraints, and obtaining multiple energy distribution evaluation verification results; According to the multiple energy distribution evaluation and verification results, the energy distribution variation decision domain is optimized and selected to generate the renewable energy distribution optimization third space.

6. The method according to claim 1, characterized in that According to the energy failure risk inspection channel, the non-renewable energy module is subjected to a failure risk inspection to obtain a failure risk inspection result, including: The energy failure risk verification channel includes an energy failure risk prediction branch and a failure risk verification branch; Performing real-time monitoring on the non-renewable energy module to obtain an energy monitoring data stream; Inputting the energy monitoring data stream into the energy failure risk prediction branch to obtain an energy failure risk coefficient; The energy failure risk coefficient is input into the failure risk verification branch to generate the failure risk verification result, wherein the failure risk verification branch includes a failure risk verification operator, and the failure risk verification operator includes: if the energy failure risk coefficient is greater than or equal to an energy failure risk threshold, the failure risk verification result is failed; if the energy failure risk coefficient is less than the energy failure risk threshold, the failure risk verification result is passed.

7. The method according to claim 6, characterized in that Inputting the energy monitoring data stream into the energy failure risk prediction branch to obtain an energy failure risk coefficient includes: The energy failure risk prediction branch includes K energy failure risk prediction models corresponding to the non-renewable energy module, where K is a positive integer greater than 1; Inputting the energy monitoring data stream into the K energy failure risk prediction models to obtain K energy failure risk prediction coefficients; The energy failure risk coefficient is generated by performing mean calculation based on the K energy failure risk prediction coefficients.

8. A graph computing-driven renewable energy distribution optimization system, characterized in that: A method for optimizing renewable energy distribution driven by graph computing according to any one of claims 1 to 7, the system comprising: A model building component: performing graph calculations based on a power grid to build a power distribution model, wherein the power grid includes a renewable energy module and a non-renewable energy module; Fault risk inspection component: performing a fault risk inspection on the non-renewable energy module according to the energy fault risk inspection channel to obtain a fault risk inspection result; Distribution optimization component: when the fault risk test result is failed, the renewable energy module is distributed optimized according to the load device set of the non-renewable energy module to establish a first space for renewable energy distribution optimization; Evaluation and optimization component: Based on the power distribution model, the first space for optimizing the distribution of renewable energy is evaluated and optimized according to the renewable energy distribution evaluation channel to obtain the second space for optimizing the distribution of renewable energy; Mutation optimization component: introduce energy distribution variation constraint rules and energy distribution fitness calculation network to perform variation optimization on the second space of renewable energy distribution optimization to obtain renewable energy distribution optimization results.

Images