Renewable energy integrated power supply method and system of portable emergency shelter

Abstract

The invention provides a renewable energy integrated power supply method and system for a portable emergency shelter, and the method comprises the steps: installing a renewable energy power generation device on the emergency shelter, and adjusting the mode according to the change of a surrounding environment, and collecting natural energy; the output of renewable energy sources is predicted through an algorithm in combination with historical and current meteorological conditions; comparing the renewable energy output prediction result with the internal load demand of the emergency shelter; when it is detected that the renewable energy source supply does not meet the power demand, a built-in hybrid energy storage system is started, and the charging rate is adjusted by adopting a self-adaptive charging control strategy; the optimized charging state and the instant power demand of the portable emergency shelter are analyzed through the edge computing technology, meanwhile, an external power grid is accessed through an intelligent power grid interface to serve as standby power supply supplement, bidirectional energy flow is supported, the optimal power supply state is obtained, high efficiency and environmental protection of energy utilization are achieved, and the energy utilization efficiency is improved. And powerful support is provided for emergency response and field operation.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of portable emergency shelters, and in particular to a renewable energy integrated power supply method for a portable emergency shelter. Background Art

[0002] Portable emergency shelters play a vital role in modern emergency response and field operations. Traditional emergency shelters usually rely on limited fossil fuels or external power grids, which not only increases operating costs but also limits their application in remote areas or extreme environments. With the development of renewable energy technology, more and more research and practice are devoted to integrating natural energy such as solar energy, wind energy and thermal energy into the power supply system of emergency shelters.

[0003] However, the portable emergency shelter power supply system in the prior art usually adopts a fixed energy collection mode, and fails to automatically adjust the working state according to changes in the surrounding environment, resulting in low energy utilization efficiency; on the other hand, the lack of intelligent energy management and scheduling system makes it difficult for the emergency shelter to generate the best energy management plan when facing complex and changeable usage scenarios, thus affecting the stability and reliability of power supply; especially when the renewable energy supply does not meet the immediate power demand, the existing system fails to effectively start the hybrid energy storage system for supplementation, nor optimizes the charging rate through adaptive charging control strategy; in addition, the existing power distribution scheme fails to fully consider the immediate power demand and energy storage status, resulting in waste or shortage of power resources. Summary of the invention

[0004] The embodiment of the present invention provides a renewable energy integrated power supply method and system for a portable emergency shelter, which is used to solve the problem of low energy utilization efficiency in the prior art and the failure of the existing power distribution scheme to fully consider the immediate power demand and energy storage status, resulting in waste or shortage of power resources.

[0005] In a first aspect, an embodiment of the present invention provides a method for integrating renewable energy power supply for a portable emergency shelter, comprising:

[0006] Various types of renewable energy power generation devices are installed on the emergency shelter, which automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy and generate natural energy data, wherein the renewable energy power generation devices include: solar photovoltaic panels, micro wind turbines and thermoelectric converters;

[0007] Based on the natural energy data, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the output of renewable energy within a preset time node to obtain a renewable energy output prediction result;

[0008] Compare the predicted renewable energy output results with the internal load demand of the emergency shelter, use deep reinforcement learning technology to simulate different usage scenarios, and generate an optimal energy management plan;

[0009] Based on the optimal energy management plan, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system composed of the built-in supercapacitor and lithium-ion battery is started, and the charging rate is adjusted by using an adaptive charging control strategy to obtain an optimized charging state;

[0010] The optimized charging status and the instantaneous power demand of the portable emergency shelter are analyzed in real time through edge computing technology to obtain the optimal power distribution plan. At the same time, the external power grid is connected through the smart grid interface as a backup power supply, and bidirectional energy flow is supported to obtain the optimal power supply status.

[0011] Optionally, the renewable energy output prediction result is compared with the internal load demand of the emergency shelter, and deep reinforcement learning technology is used to simulate different usage scenarios to generate an optimal energy management plan, including:

[0012] Using the renewable energy output prediction results and combining them with historical data of the internal load of the emergency shelter, a dynamic balance model between energy demand and supply is constructed through deep reinforcement learning technology to obtain dynamic balance model parameters;

[0013] Based on the dynamic balance model parameters, simulate the energy demand and supply conditions of the emergency shelter under different climate conditions, time periods and usage scenarios to generate a collection of simulation scenarios;

[0014] Evaluate each simulation scenario in the simulation scenario collection, comprehensively calculate energy efficiency, cost savings, and environmental impact, select the best energy configuration plan using a multi-objective optimization algorithm, and obtain an initial energy management plan;

[0015] The initial energy management plan is applied in a virtual simulation environment, and the initial energy management plan is verified and optimized by simulating actual operation conditions to obtain an optimal energy management plan.

[0016] Optionally, each simulation scenario in the simulation scenario collection is evaluated, energy efficiency, cost savings and environmental impact are comprehensively calculated, and the best energy configuration scheme is selected using a multi-objective optimization algorithm to obtain an initial energy management plan, including:

[0017] Using a multi-dimensional evaluation system, for each simulation scenario in the simulation scenario collection, the energy efficiency index, the cost saving index and the environmental impact index under different conditions are calculated to obtain a comprehensive evaluation result of each simulation scenario;

[0018] Based on the comprehensive evaluation results and in combination with the preset weight distribution, each simulation scenario is comprehensively evaluated to obtain a comprehensive score for each simulation scenario;

[0019] Using a multi-objective evolutionary algorithm, all simulation scenarios are screened according to the comprehensive scores to select the best energy configuration solution;

[0020] The optimal energy configuration scheme is input into an advanced decision support system, the current energy storage level of the emergency shelter and the availability of the external power grid are comprehensively calculated, the optimal energy configuration scheme is refined, and an initial energy management plan is obtained.

[0021] Optionally, based on the comprehensive evaluation results and in combination with a preset weight distribution, a comprehensive evaluation is performed on each simulation scenario to obtain a comprehensive score for each simulation scenario, including:

[0022] Using the comprehensive evaluation results, combined with the preset weight allocation scheme, based on the operating characteristics of the emergency shelter and the pre-set external environmental conditions, the relative importance of each indicator is determined by using the hierarchical analysis method, and the energy efficiency indicator, cost saving indicator and environmental impact indicator of each simulation scenario are weighted to obtain the optimal weighted evaluation value;

[0023] The optimal weighted evaluation value is revised twice by using the entropy weight method, and the uncertainty of each indicator under different simulation scenarios is calculated to obtain a revised evaluation value;

[0024] Using the fuzzy comprehensive evaluation method, combined with the revised evaluation value, the uncertainty and subjectivity in the evaluation process are calculated, each simulation scenario is evaluated, and an initial comprehensive score is obtained;

[0025] Using a grey correlation analysis method, based on the initial comprehensive score, analyzing the similarities and differences between the simulation scenarios, adjusting the initial comprehensive score of each simulation scenario, and obtaining an adjusted comprehensive score;

[0026] The adjusted comprehensive score is deeply learned using a neural network model to identify underlying rules and patterns between simulation scenarios and optimize the accuracy of the comprehensive score to obtain a target comprehensive score for each simulation scenario.

[0027] Optionally, the comprehensive evaluation results are used in combination with a preset weight distribution scheme, based on the operation characteristics of the emergency shelter and the external environmental conditions, and the relative importance of each indicator is determined by using the hierarchical analysis method. The energy efficiency indicator, cost saving indicator and environmental impact indicator of each simulation scenario are weighted and calculated to obtain the optimal weighted evaluation value, including:

[0028] Using the data on the operation characteristics of the emergency shelter and external environmental conditions, a multi-level indicator system is constructed;

[0029] Based on the multi-level indicator system, combined with expert knowledge and historical data, the analytic hierarchy process is used to determine the relative importance of each indicator and form a preliminary weight allocation plan;

[0030] Using the preliminary weight allocation scheme and combining the comprehensive evaluation results, the energy efficiency index, cost saving index and environmental impact index of each simulation scenario are weighted for the first time to obtain an initial weighted evaluation value;

[0031] The initial weighted evaluation value is reviewed by using the Delphi method, and the weight allocation scheme is corrected according to the review result to obtain a corrected weight allocation scheme;

[0032] The corrected weight distribution scheme is applied to the preliminary weighted evaluation value, and a secondary weighted calculation is performed to obtain an optimal weighted evaluation value.

[0033] Optionally, based on the natural energy data, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the output of renewable energy within a preset time node to obtain a renewable energy output prediction result, including:

[0034] Using the natural energy data, combined with historical weather data and current meteorological conditions, the natural energy data is processed through time series analysis technology to extract the time characteristics of energy output and the correlation characteristics of meteorological conditions to obtain a feature data set;

[0035] Based on the feature data set, an ensemble learning method is used to construct a multi-model prediction framework;

[0036] Applying the multi-model prediction framework to the feature data set, optimizing the multi-model prediction framework parameters by cross-validation technology, and obtaining an optimized multi-model prediction framework;

[0037] Using the optimized multi-model forecasting framework, the renewable energy output within a preset time node is forecasted, and the impact of seasonal fluctuations and short-term weather changes is calculated to obtain preliminary renewable energy output forecast results;

[0038] The Bayesian updating method is used to perform real-time correction on the preliminary renewable energy output forecast result according to the latest meteorological conditions to obtain the renewable energy output forecast result.

[0039] Optionally, the optimized charging state and the instantaneous power demand of the portable emergency shelter are analyzed in real time by edge computing technology to obtain the best power distribution plan, and the external power grid is connected to the smart grid interface as a backup power supply supplement, while supporting bidirectional energy flow to obtain the best power supply state, including:

[0040] Using edge computing technology to perform real-time analysis on the optimized charging state and the instantaneous power demand of the portable emergency shelter to obtain a real-time power demand analysis result;

[0041] Based on the real-time power demand analysis results and the renewable energy output forecast results, the optimal power distribution ratio is calculated through a dynamic programming algorithm to obtain a preliminary optimal power distribution plan;

[0042] Comprehensively optimizing the preliminary optimal power distribution plan through a multi-objective optimization algorithm to obtain an optimized optimal power distribution plan;

[0043] Through the smart grid interface, according to the optimized best power distribution plan, the connection state with the external power grid is dynamically adjusted to realize the supplementary function of the external power grid as a backup power source, while supporting the two-way flow of power, and obtaining a dynamically adjusted external power grid connection state;

[0044] The optimized best power distribution scheme is combined with the dynamically adjusted external power grid connection state, and the best power supply state is obtained through real-time monitoring and feedback mechanism.

[0045] In a second aspect, an embodiment of the present application provides a renewable energy integrated power supply system for a portable emergency shelter, comprising:

[0046] The collection unit is equipped with various types of renewable energy generation devices on the emergency shelter, which automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy and generate natural energy data, wherein the renewable energy generation devices include: solar photovoltaic panels, micro wind turbines and thermoelectric converters;

[0047] A prediction module, based on the natural energy data, combined with historical weather data and current meteorological conditions, predicts the renewable energy output within a preset time node through a machine learning algorithm to obtain a renewable energy output prediction result;

[0048] A simulation module compares the predicted renewable energy output results with the internal load demand of the emergency shelter, uses deep reinforcement learning technology to simulate different usage scenarios, and generates an optimal energy management plan;

[0049] A regulating module, based on the optimal energy management plan, starts a hybrid energy storage system composed of a built-in supercapacitor and a lithium-ion battery when it is detected that the renewable energy supply does not meet the immediate power demand, and uses an adaptive charging control strategy to adjust the charging rate to obtain an optimized charging state;

[0050] The analysis module uses edge computing technology to perform real-time analysis on the optimized charging status and the immediate power demand of the portable emergency shelter to obtain the optimal power distribution plan. At the same time, it accesses the external power grid through the smart grid interface as a backup power supplement, supports two-way energy flow, and obtains the optimal power supply state.

[0051] In a third aspect, an embodiment of the present invention provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a renewable energy integrated power supply method for a portable emergency cabin as described in any one of the first aspects.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement a renewable energy integrated power supply method for a portable emergency shelter as described in any one of the first aspects.

[0053] In an embodiment of the present invention, various types of renewable energy power generation devices are installed on the emergency shelter, and the working mode is automatically adjusted according to changes in the surrounding environment to collect solar energy, wind energy and thermal energy to generate natural energy data; based on the natural energy data combined with historical weather data and current meteorological conditions, the renewable energy output within a preset time node is predicted by a machine learning algorithm to obtain a renewable energy output prediction result; the renewable energy output prediction result is compared with the internal load demand of the emergency shelter, and deep reinforcement learning technology is used to simulate different usage scenarios to generate an optimal energy management plan; based on the optimal energy management plan, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system composed of built-in supercapacitors and lithium-ion batteries is started, and the charging rate is adjusted by an adaptive charging control strategy to obtain an optimized charging state; the optimized charging state and the immediate power demand of the portable emergency shelter are analyzed in real time by edge computing technology to obtain the optimal power distribution plan, and at the same time, the external power grid is connected through the smart grid interface as a backup power supplement, and bidirectional energy flow is supported to obtain the optimal power supply state. The technical solution provided by the present invention realizes efficient collection and accurate prediction of natural energy by automatically adjusting the working mode and applying machine learning algorithms, thereby improving energy utilization efficiency; dynamic response capability: based on deep reinforcement learning technology, it can dynamically generate the best energy management plan according to different usage scenarios, thereby enhancing the flexibility and adaptability of the system; the introduction of hybrid energy storage system and adaptive charging control strategy provides stable power support when renewable energy is insufficient, thereby ensuring the continuous operation of the emergency shelter; the use of edge computing technology and smart grid interface realizes real-time analysis and optimal allocation of power demand, thereby improving the utilization efficiency of power resources; by making full use of renewable energy, it reduces dependence on traditional fossil fuels and reduces carbon emissions, which is in line with the concept of green development;

[0054] Furthermore, by constructing a dynamic equilibrium model, the relationship between energy demand and supply can be accurately modeled, thereby improving the accuracy of energy management. Comprehensive scenario simulation takes into account different climate conditions, time periods, and usage scenarios, generating a rich collection of simulation scenarios, and enhancing the universality and practicality of the solution. By comprehensively calculating energy efficiency, cost savings, and environmental impact, the comprehensiveness and scientificity of the evaluation results are ensured, avoiding the limitations of single indicator evaluation. The multi-objective optimization algorithm is used to select the best energy configuration solution, and the initial energy management plan is verified and optimized through a virtual simulation environment, providing scientific and reasonable decision-making support and improving the feasibility and reliability of the solution. Through continuous simulation and optimization, the optimal energy management plan finally generated can significantly improve the energy utilization efficiency and overall performance of the emergency shelter, ensuring its stable operation in various complex environments.

[0055] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A flowchart of a renewable energy integrated power supply method for a portable emergency shelter provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the structure of a renewable energy integrated power supply system for a portable emergency shelter provided by an embodiment of the present invention;

[0059] Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0061] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0063] The portable emergency shelter power supply system in the prior art usually adopts a fixed energy collection mode, fails to automatically adjust the working state according to changes in the surrounding environment, resulting in low energy utilization efficiency; on the other hand, the lack of intelligent energy management and scheduling system makes it difficult for the emergency shelter to generate the best energy management plan when facing complex and changeable usage scenarios, thereby affecting the stability and reliability of power supply; especially when the renewable energy supply does not meet the immediate power demand, the existing system fails to effectively start the hybrid energy storage system for supplementation, and does not optimize the charging rate through an adaptive charging control strategy; in addition, the existing power distribution scheme fails to fully consider the immediate power demand and energy storage status, resulting in waste or shortage of power resources. Based on this, the present invention provides a renewable energy integrated power supply method for a portable emergency shelter, such as Figure 1 ,include:

[0064] Step 101: Install various types of renewable energy power generation devices on the emergency shelter, automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy, and generate natural energy data;

[0065] In this step, various types of renewable energy power generation devices are installed on the emergency shelter, including solar photovoltaic panels, micro wind turbines and thermoelectric converters. These devices can automatically adjust their working modes according to changes in the surrounding environment to maximize the collection of solar energy, wind energy and thermal energy. Through integrated sensors and monitoring systems, real-time data on natural energy is collected, and the amount of energy collected and its changing trends are recorded, providing a basis for subsequent analysis. Natural energy data not only includes immediate energy output, but also covers the working status and environmental parameters of the equipment, ensuring the comprehensiveness and accuracy of the data.

[0066] Step 102: Based on the natural energy data, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the output of renewable energy within a preset time node to obtain a renewable energy output prediction result;

[0067] In this step, based on the natural energy data generated in step 101, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the renewable energy output within a preset time node. The prediction model comprehensively considers factors such as seasonal changes, climate patterns, and short-term weather forecasts to improve the accuracy of the prediction. Through continuously updated historical data and real-time meteorological information, the machine learning algorithm can dynamically adjust the prediction model to adapt to different environmental conditions. The final renewable energy output prediction results provide an important basis for subsequent energy management.

[0068] Step 103: Compare the renewable energy output prediction result with the internal load demand of the emergency shelter, use deep reinforcement learning technology to simulate different usage scenarios, and generate an optimal energy management plan;

[0069] In this step, the renewable energy output prediction result obtained in step 102 is compared with the internal load demand of the emergency shelter. The deep reinforcement learning technology is used to simulate the deep reinforcement learning algorithm under different usage scenarios to build an intelligent decision-making system. The system can automatically generate the best energy management plan according to the energy demand and supply conditions under different scenarios. The simulation scenario collection contains various possible operating conditions, such as different climatic conditions, time periods and usage scenarios, to ensure the wide applicability of the solution. Each simulation scenario is evaluated, and the energy efficiency, cost savings and environmental impact are comprehensively calculated to select the optimal energy configuration plan to form an initial energy management plan. Finally, the initial plan is verified and optimized through a virtual simulation environment to finally generate the best energy management plan.

[0070] Step 104: Based on the optimal energy management plan, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system consisting of the built-in supercapacitor and the lithium-ion battery is started, and the charging rate is adjusted by using an adaptive charging control strategy to obtain an optimized charging state;

[0071] In this step, based on the optimal energy management plan generated in step 103, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system composed of the built-in supercapacitor and lithium-ion battery is immediately started. The hybrid energy storage system can provide a large amount of electricity in a short period of time to make up for the insufficient supply of renewable energy. At the same time, an adaptive charging control strategy is used to adjust the charging rate to ensure efficient utilization of the energy storage system and extend its service life. The adaptive charging control strategy will dynamically adjust the charging rate according to the actual power demand and energy storage status to avoid overcharging or undercharging, thereby obtaining an optimized charging state.

[0072] Step 105: The optimized charging state and the instantaneous power demand of the portable emergency shelter are analyzed in real time by edge computing technology to obtain the best power distribution plan, and the external power grid is connected to the smart grid interface as a backup power supply, and bidirectional energy flow is supported to obtain the best power supply state;

[0073] In this step, the optimized charging status in step 104 and the immediate power demand of the portable emergency shelter are analyzed in real time through edge computing technology. The edge computing device is deployed close to the data source and can quickly process and respond to changes in power demand. The results of the real-time analysis are used to generate the best power distribution plan to ensure the rational allocation and efficient use of power resources. At the same time, the external power grid is connected through the smart grid interface as a backup power supplement to support two-way energy flow. This approach not only improves the reliability and flexibility of power supply, but also can sell excess power to the external power grid when necessary, ultimately achieving the best power supply state.

[0074] The embodiments of the present invention improve the power supply capacity and operating efficiency of the portable emergency shelter in various environments through the above steps, and also ensure the high efficiency and environmental protection of energy utilization through intelligent management and optimized configuration, providing strong support for emergency response and field operations.

[0075] Based on this, the present invention provides a specific embodiment, wherein the step 103 compares the renewable energy output prediction result with the internal load demand of the emergency shelter, uses deep reinforcement learning technology to simulate different usage scenarios, and generates an optimal energy management plan, which specifically includes the following steps:

[0076] Step 201: Using the renewable energy output prediction result and combining it with the historical data of the internal load of the emergency shelter, a dynamic balance model between energy demand and supply is constructed through deep reinforcement learning technology to obtain dynamic balance model parameters;

[0077] In this step, the renewable energy output prediction results are used in combination with the historical data of the internal load of the emergency shelter. The dynamic balance model between energy demand and supply is constructed through deep reinforcement learning technology. The obtained dynamic balance model parameters can accurately reflect the relationship between energy supply and demand under different conditions. These parameters not only take into account the current natural energy output prediction, but also combine the load change pattern in the historical data. The deep reinforcement learning algorithm continuously optimizes the model parameters to ensure that it adapts to various possible operating conditions and environmental changes.

[0078] Step 202: Based on the dynamic balance model parameters, simulate the energy demand and supply conditions of the emergency shelter under different climate conditions, time periods and usage scenarios to generate a collection of simulation scenarios;

[0079] In this step, based on the dynamic balance model parameters obtained in step 201, the energy demand and supply conditions of the emergency shelter under different climate conditions, time periods and usage scenarios are simulated to generate a collection of simulation scenarios covering a variety of possible operating conditions, including extreme weather, peak power consumption periods and different usage patterns. Each simulation scenario records the specific data of energy demand and supply in detail, providing rich basic information for subsequent evaluation.

[0080] Step 203: Evaluate each simulation scenario in the simulation scenario collection, comprehensively calculate energy efficiency, cost savings and environmental impact, select the best energy configuration plan using a multi-objective optimization algorithm, and obtain an initial energy management plan;

[0081] In this step, each simulation scenario in the simulation scenario collection is evaluated, and the energy efficiency, cost savings and environmental impact are comprehensively calculated. The multi-objective optimization algorithm is used to select the best energy configuration plan to obtain the initial energy management plan. The multi-objective optimization algorithm ensures the comprehensiveness and scientificity of the evaluation results and avoids the limitations of single indicator evaluation. The evaluation process fully considers multiple dimensions such as energy utilization efficiency, economic cost and environmental protection to ensure the optimality of the plan.

[0082] Step 204: applying the initial energy management plan in a virtual simulation environment, verifying and optimizing the initial energy management plan by simulating actual operation conditions, and obtaining an optimal energy management plan;

[0083] In this step, the initial energy management plan is applied in a virtual simulation environment, and the initial energy management plan is verified and optimized by simulating actual operating conditions. The virtual simulation environment can realistically reproduce various operating conditions and test the feasibility and effect of the initial plan in actual application. Based on the simulation results, the initial energy management plan is further adjusted and optimized to finally obtain the optimal energy management plan. This method ensures that the plan is not only optimal in theory, but also achieves the expected effect in actual application.

[0084] The embodiment of the present invention realizes the whole process from dynamic balance modeling of energy demand and supply, to simulation scenario generation, to multi-objective optimization selection of the best configuration scheme, and finally through virtual simulation verification and optimization through the above steps, thereby ensuring the scientificity and reliability of energy management.

[0085] Based on this, the present invention provides a specific embodiment, wherein the step 203 evaluates each simulation scenario in the simulation scenario collection, comprehensively calculates energy efficiency, cost savings and environmental impact, selects the best energy configuration scheme using a multi-objective optimization algorithm, and obtains an initial energy management plan, specifically comprising the following steps:

[0086] Step 301: using a multi-dimensional evaluation system, calculating the energy efficiency index, cost saving index and environmental impact index under different conditions for each simulation scenario in the simulation scenario collection, and obtaining a comprehensive evaluation result for each simulation scenario;

[0087] In this step, a multi-dimensional evaluation system is used to calculate the energy efficiency index, cost saving index and environmental impact index under different conditions for each simulation scenario in the simulation scenario collection to obtain a comprehensive evaluation result of each simulation scenario. The evaluation system covers multiple aspects such as energy utilization efficiency, economic cost and environmental protection, ensuring the comprehensiveness and scientificity of the evaluation. The specific value of each indicator is calculated through a precise algorithm, providing detailed data support for subsequent evaluation.

[0088] In order to make the evaluation results more detailed and comprehensive, a multi-level weighted summation method can be used and a nonlinear adjustment factor can be introduced to enhance the expressiveness of the model. For each simulation scenario j, its comprehensive evaluation result Z j It can be defined as:

[0089]

[0090] Where n is the number of evaluation indicators.

[0091] w i is the weight of the i-th evaluation index, and all weights satisfy

[0092] F i (X j 0 is the scoring function of the i-th evaluation index, X j is a set of variables related to this indicator.

[0093] A i (Z j ) is an adaptive adjustment factor for each evaluation indicator, which is used to adjust the comprehensive evaluation result Z in the current situation. jDynamically adjust the score, which can be expressed as Here k i and σ i These are the parameters that control the adjustment strength and sensitivity respectively.

[0094] Specifically, each F i (X j ) is defined as follows:

[0095] Energy Efficiency E (X j ):

[0096]

[0097] REU j : Renewable energy utilization rate in the jth scenario.

[0098] SEL j : System energy loss rate in the jth scenario.

[0099] λ E :Control the rate of diminishing marginal returns.

[0100] Cost Savings C (X j ):

[0101] F C (X j )=log(1+C j )+β C ·sin(ω C ·t j

[0102] C j : Cost savings in the jth scenario.

[0103] β C : Amplitude coefficient of cost fluctuation term.

[0104] ω C : Frequency coefficient of cost fluctuation term.

[0105] t j : The time point of simulation.

[0106] Environmental Impact I (X j ):

[0107]

[0108] CO2R j : The amount of carbon dioxide emissions reduced under the jth scenario.

[0109] POPR j : Reduction of other pollutants in the jth scenario.

[0110] w co2 and w pop :Weights of carbon dioxide and other pollutants.

[0111] η: Parameter that controls the strength of the quadratic term.

[0112] γ I : Parameters controlling temperature effects.

[0113] μ I : Parameter that controls the attenuation rate of the temperature effect on the environment.

[0114] T j : The temperature in the jth situation.

[0115] Energy storage system status F S (X j ):

[0116]

[0117] HSS j : The health status of the hybrid energy storage system in the jth scenario.

[0118] CHL j : The charging level of the energy storage system in the jth scenario.

[0119] δ S : Parameter that controls the cosine modulation intensity.

[0120] φ S : Parameters that control the cosine modulation period.

[0121] External grid availability F G (X j ):

[0122] F G (X j )=GCT j ×GF j ×(1+θ·sin(π·GCT j ))+ψ

[0123] ·arctan(ν·GCT j )

[0124] GCT j : The proportion of external grid connection time in the jth scenario.

[0125] GF j : The friendliness of the external power grid in the jth scenario.

[0126] θ: Parameter that controls the intensity of the sine wave modulation.

[0127] ψ: Parameter that controls the strength of the inverse tangent function.

[0128] ν: controls the scaling factor of the inverse tangent function input.

[0129] Step 302: Based on the comprehensive evaluation results and in combination with the preset weight distribution, each simulation scenario is comprehensively evaluated to obtain a comprehensive score for each simulation scenario;

[0130] In this step, based on the comprehensive evaluation results obtained in step 301 and combined with the preset weight distribution, a comprehensive evaluation is performed on each simulation scenario to obtain a comprehensive score for each simulation scenario. The weight distribution is pre-set according to the actual needs and operating characteristics of the emergency shelter, ensuring the pertinence and rationality of the evaluation. The comprehensive score not only reflects the performance of each simulation scenario on different indicators, but also considers the relative importance of each indicator through weighted calculation, and finally generates a comprehensive score for each simulation scenario.

[0131] Based on the above comprehensive evaluation results Z j , the comprehensive score CS can be calculated through a multi-stage optimization process j This process not only takes into account the standardized evaluation results, but also incorporates learning and prediction mechanisms based on historical data, as well as possible reward or penalty mechanisms:

[0132]

[0133] CS j : The comprehensive score of the jth simulation scenario.

[0134] λ Z : Exponential factor to adjust the shape of the normalized score distribution.

[0135] m: The number of reward / penalty items.

[0136] p k : The weight of the kth reward / penalty item, satisfying

[0137] R k (X j ): The specific function of the kth reward / penalty item depends on whether a specific condition is met.

[0138] Ω: Parameter that controls the effect of long-term dependencies.

[0139] ξ: Parameter that controls the strength of the long-term dependent effect.

[0140] D j: Long-term dependencies, such as user behavior patterns or the impact of technological advances.

[0141] Through this design, the comprehensive score CS j Not only directly depends on the comprehensive evaluation results Z j , and also takes into account multiple additional factors, making the entire evaluation system more complex, detailed and creative.

[0142] Step 303: using a multi-objective evolutionary algorithm to screen all simulation scenarios according to the comprehensive score and select the best energy configuration solution;

[0143] In this step, a multi-objective evolutionary algorithm is used to screen all simulation scenarios according to the comprehensive score to select the best energy configuration solution. The multi-objective evolutionary algorithm can optimize multiple objectives at the same time to ensure that the selected solution is optimal in terms of energy efficiency, cost savings, and environmental impact. In addition, the algorithm can quickly find the global optimal solution in a large number of simulation scenarios, avoiding the problem of local optimality. Through multiple iterations and screening, the best energy configuration solution is finally determined to have the highest comprehensive score and the best overall performance.

[0144] Step 304: Input the optimal energy configuration plan into the advanced decision support system, comprehensively calculate the current energy storage level of the emergency shelter and the availability of the external power grid, refine the optimal energy configuration plan, and obtain an initial energy management plan.

[0145] In this step, the optimal energy configuration plan is input into the advanced decision support system, the current energy storage level of the emergency shelter and the availability of the external power grid are comprehensively calculated, the optimal energy configuration plan is refined, and the initial energy management plan is obtained. The advanced decision support system takes into account dynamic factors in actual operation, such as the charging and discharging status of the energy storage system and the real-time electricity price of the external power grid. These factors are incorporated into the final energy management plan to ensure its feasibility and optimality in actual application. After the initial energy configuration plan is refined, it can better adapt to the specific operating conditions of the emergency shelter and provide more accurate and reliable energy management guidance.

[0146] The embodiment of the present invention can achieve the technical effect of automatically selecting and optimizing the best energy configuration scheme from a variety of simulation scenarios through the above steps, ensuring the efficient, economical and environmentally friendly operation of the emergency shelter under different conditions.

[0147] Based on this, the present invention provides a specific embodiment, wherein step 302, based on the comprehensive evaluation result and in combination with a preset weight distribution, performs a comprehensive evaluation on each simulation scenario to obtain a comprehensive score for each simulation scenario, specifically comprising the following steps:

[0148] Step 401: using the comprehensive evaluation results, combined with a preset weight distribution scheme, based on the operation characteristics of the emergency shelter and the external environmental conditions pre-set, using the hierarchical analysis method to determine the relative importance of each indicator, and performing weighted calculation on the energy efficiency indicator, cost saving indicator and environmental impact indicator of each simulation scenario to obtain the optimal weighted evaluation value;

[0149] In this step, the comprehensive evaluation results are used in combination with a preset weight distribution scheme, based on the operating characteristics of the emergency shelter and the pre-set external environmental conditions, and the relative importance of each indicator is determined by the hierarchical analysis method. The energy efficiency index, cost saving index and environmental impact index of each simulation scenario are weighted and calculated to obtain the optimal weighted evaluation value. The hierarchical analysis method ensures the scientificity and rationality of the weight distribution by constructing a judgment matrix, quantifying expert opinions and historical data. The weighted calculation takes into account the importance of different indicators in the overall evaluation, making the evaluation results more accurate and comprehensive.

[0150] Step 402: The optimal weighted evaluation value is revised twice by using the entropy weight method, and the uncertainty of each indicator under different simulation scenarios is calculated to obtain a revised evaluation value;

[0151] In this step, the optimal weighted evaluation value is revised twice by the entropy weight method, and the uncertainty of each indicator in different simulation scenarios is calculated to obtain the revised evaluation value. The entropy weight method measures the amount of information of each indicator by calculating the information entropy and automatically adjusts the weight. This method can effectively deal with the uncertainty and randomness in the data, improve the stability and reliability of the evaluation value, and the revised evaluation value more truly reflects the actual performance of each simulation scenario.

[0152] Step 403: using the fuzzy comprehensive evaluation method, combined with the revised evaluation value, calculating the uncertainty and subjectivity in the evaluation process, evaluating each simulation scenario, and obtaining an initial comprehensive score;

[0153] In this step, the fuzzy comprehensive evaluation method is used, combined with the revised evaluation value, to calculate the uncertainty and subjectivity in the evaluation process, evaluate each simulation scenario, and obtain an initial comprehensive score. The fuzzy comprehensive evaluation method introduces a membership function to deal with the fuzziness and subjectivity in the evaluation process. This method can comprehensively consider the influence of multiple factors and provide a more flexible and comprehensive evaluation result. The initial comprehensive score not only reflects the specific performance of each simulation scenario, but also takes into account the uncertainty in the evaluation process.

[0154] Step 404: using a grey correlation analysis method, based on the initial comprehensive score, analyzing the similarities and differences between the simulation scenarios, adjusting the initial comprehensive score of each simulation scenario, and obtaining an adjusted comprehensive score;

[0155] In this step, a grey correlation analysis method is used to analyze the similarities and differences between the simulation scenarios based on the initial comprehensive score, adjust the initial comprehensive score of each simulation scenario, and obtain an adjusted comprehensive score. Grey correlation analysis calculates the correlation between the simulation scenarios and identifies the similarities and differences between them. This method can effectively handle situations with small amounts of data, improving the accuracy and credibility of the evaluation results. The adjusted comprehensive score more comprehensively reflects the relative advantages and disadvantages of each simulation scenario.

[0156] Step 405: Use a neural network model to perform deep learning on the adjusted comprehensive score, identify potential rules and patterns between simulation scenarios, and optimize the accuracy of the comprehensive score to obtain a target comprehensive score for each simulation scenario.

[0157] In this step, the neural network model is used to perform deep learning on the adjusted comprehensive score to identify the underlying rules and patterns between the simulation scenarios and optimize the accuracy of the comprehensive score to obtain the target comprehensive score for each simulation scenario. The neural network model automatically identifies and learns the complex relationships between simulation scenarios through a large amount of training data, which improves the accuracy and robustness of the evaluation results. The target comprehensive score not only reflects the current performance of each simulation scenario, but also predicts possible future development trends.

[0158] The embodiment of the present invention uses the analytic hierarchy process combined with a preset weight distribution scheme to accurately determine the relative importance of different indicators in the operation of the emergency shelter, thereby ensuring the scientificity and rationality of the evaluation results;

[0159] The entropy weight method was used for secondary correction, which effectively dealt with the uncertainty of each indicator in different simulation scenarios and improved the stability and reliability of the evaluation value. The fuzzy comprehensive evaluation method was used to fully consider the uncertainty and subjectivity in the evaluation process, provide more flexible and comprehensive evaluation results, and enhance the flexibility and adaptability of the evaluation. The grey correlation analysis method was used to analyze the similarities and differences between the simulation scenarios, adjust the initial comprehensive score, improve the accuracy and credibility of the evaluation results, and ensure the meticulousness and discrimination of the evaluation results. The neural network model was used to conduct deep learning on the adjusted comprehensive score, identify the potential laws and patterns between the simulation scenarios, and greatly improve the accuracy and predictive ability of the comprehensive score.

[0160] Based on this, the present invention provides a specific embodiment, wherein the step 401 uses the comprehensive evaluation result, combines a preset weight distribution scheme, pre-sets based on the operating characteristics of the emergency shelter and external environmental conditions, uses a hierarchical analysis method to determine the relative importance of each indicator, and performs weighted calculation on the energy efficiency indicator, cost saving indicator, and environmental impact indicator of each simulation scenario to obtain the optimal weighted evaluation value, specifically including the following steps:

[0161] Step 501: Using the data of the operation characteristics of the emergency shelter and the external environmental conditions, a multi-level indicator system is constructed;

[0162] In this step, a multi-level indicator system is constructed using the data on the operating characteristics of the emergency shelter and the external environmental conditions. This system covers multiple dimensions such as energy efficiency, cost savings, and environmental impact. The indicators at each level are refined according to the specific needs and operating environment of the emergency shelter, ensuring the comprehensiveness and pertinence of the evaluation. By constructing a multi-level indicator system, a solid foundation is provided for the subsequent weight allocation and comprehensive evaluation.

[0163] Step 502: Based on the multi-level indicator system, combined with expert knowledge and historical data, the relative importance of each indicator is determined by using the hierarchical analysis method to form a preliminary weight allocation scheme;

[0164] In this step, based on the multi-level indicator system, combined with expert knowledge and historical data, the hierarchical analysis method is used to determine the relative importance of each indicator to form a preliminary weight distribution scheme. The hierarchical analysis method ensures the scientificity and rationality of weight distribution by constructing a judgment matrix and quantifying expert opinions and historical data. This step not only considers the importance of different indicators in the overall evaluation, but also combines the experience of experts and historical data to improve the accuracy and reliability of weight distribution.

[0165] Step 503: using the preliminary weight allocation scheme and combining the comprehensive evaluation results, perform a first weighted calculation on the energy efficiency index, cost saving index and environmental impact index of each simulation scenario to obtain an initial weighted evaluation value;

[0166] In this step, the energy efficiency index, cost saving index and environmental impact index of each simulation scenario are weighted for the first time in combination with the comprehensive evaluation results using the preliminary weight allocation scheme to obtain the initial weighted evaluation value. The weighted calculation takes into account the relative importance of different indicators in the overall evaluation, making the evaluation results more accurate and comprehensive. The initial weighted evaluation value reflects the comprehensive performance of each simulation scenario under the current weight allocation, providing basic data for subsequent review and correction.

[0167] Step 504: using the Delphi method to review the initial weighted evaluation value, and correcting the weight allocation scheme according to the review result to obtain a corrected weight allocation scheme;

[0168] In this step, the Delphi method is used to review the initial weighted evaluation value, and the weight distribution scheme is corrected according to the review results to obtain the corrected weight distribution scheme. The Delphi method gradually reaches a consensus through multiple rounds of anonymous review and feedback from experts, ensuring the objectivity and authority of the review results. The corrected weight distribution scheme is more in line with the actual situation, which improves the scientificity and credibility of the evaluation results.

[0169] Step 505: applying the corrected weight distribution scheme to the preliminary weighted evaluation value, performing secondary weighted calculation, and obtaining an optimal weighted evaluation value;

[0170] In this step, the corrected weight distribution scheme is applied to the preliminary weighted evaluation value, and a secondary weighted calculation is performed to obtain the optimal weighted evaluation value. The secondary weighted calculation further optimizes the evaluation result and ensures the accuracy and rationality of the evaluation value. The optimal weighted evaluation value not only reflects the comprehensive performance of each simulation scenario under the latest weight distribution, but also takes into account the problems and improvements found in the review process, and ultimately provides the most scientific and reliable evaluation result.

[0171] Based on this, the present invention provides a specific embodiment, wherein step 102, based on the natural energy data, combined with historical weather data and current meteorological conditions, predicts the renewable energy output within a preset time node through a machine learning algorithm to obtain a renewable energy output prediction result, specifically comprising the following steps:

[0172] Step 601: using the natural energy data, combined with historical weather data and current meteorological conditions, the natural energy data is processed by time series analysis technology to extract the time characteristics of energy output and the correlation characteristics of meteorological conditions to obtain a feature data set;

[0173] In this step, the natural energy data is used, combined with historical weather data and current meteorological conditions, and the natural energy data is processed through time series analysis technology to extract the time characteristics of energy output and the correlation characteristics of meteorological conditions, and obtain a characteristic data set. Time series analysis technology can identify the periodic and trend components in the data, and at the same time reveal the relationship between natural energy output and meteorological conditions. The characteristic data set not only contains real-time energy output information, but also covers various meteorological factors that affect energy output, providing rich basic data for subsequent predictions.

[0174] Step 602: Based on the feature data set, a multi-model prediction framework is constructed using an ensemble learning method;

[0175] In this step, based on the feature data set, an ensemble learning method is used to construct a multi-model prediction framework. The ensemble learning method improves the accuracy and robustness of the prediction by combining multiple different prediction models, such as random forests, gradient boosting trees, and support vector machines. Each model focuses on a specific feature or time period. By integrating the results of these models, the changing patterns of natural energy output can be captured more comprehensively. The multi-model prediction framework not only considers the advantages of a single model, but also integrates the advantages of multiple models to improve the overall prediction performance.

[0176] Step 603: applying the multi-model prediction framework to the feature data set, optimizing the multi-model prediction framework parameters by cross-validation technology, and obtaining an optimized multi-model prediction framework;

[0177] In this step, the multi-model prediction framework is applied to the feature data set, and the multi-model prediction framework parameters are optimized through cross-validation technology to obtain the optimized multi-model prediction framework. The cross-validation technology divides the training set and the validation set multiple times to ensure that the selection of model parameters is not affected by the specific data set. The optimization process includes adjusting the model hyperparameters, selecting the best feature subset, etc., and finally determines a set of optimal model parameters. The optimized multi-model prediction framework shows stable high performance on different data sets, providing reliable guarantee for subsequent predictions.

[0178] Step 604: using the optimized multi-model prediction framework, predicting the renewable energy output within a preset time node, and calculating the impact of seasonal fluctuations and short-term weather changes, to obtain a preliminary renewable energy output prediction result;

[0179] In this step, the optimized multi-model prediction framework is used to predict the renewable energy output within the preset time node, and the impact of seasonal fluctuations and short-term weather changes is calculated to obtain preliminary renewable energy output prediction results. This step not only takes into account long-term trends and cyclical changes, but also combines short-term weather forecast information to ensure the timeliness and accuracy of the prediction results. The preliminary prediction results reflect the expected situation of natural energy output in the future, which provides an important reference for the energy management of emergency shelters.

[0180] Step 605: using the Bayesian update method to perform real-time correction on the preliminary renewable energy output forecast result according to the latest meteorological conditions to obtain a renewable energy output forecast result;

[0181] In this step, the Bayesian update method is used to perform real-time correction on the preliminary renewable energy output forecast results according to the latest meteorological conditions to obtain the renewable energy output forecast results. The Bayesian update method dynamically adjusts the parameters of the forecast model by continuously introducing new observation data to make the forecast results closer to the actual situation. The real-time correction not only improves the accuracy of the forecast, but also enhances the adaptability of the system, ensuring that reliable forecasts can be provided even in rapidly changing environments. The improved forecast results provide a scientific basis for the energy scheduling and management of emergency shelters.

[0182] Based on this, the present invention provides a specific embodiment, in which step 105, the optimized charging state and the instant power demand of the portable emergency shelter are analyzed in real time through edge computing technology to obtain the best power distribution plan, and the external power grid is connected through the smart grid interface as a backup power supply supplement, and bidirectional energy flow is supported to obtain the best power supply state, which specifically includes the following steps:

[0183] Step 701: Analyze the optimized charging state and the instant power demand of the portable emergency shelter in real time by using edge computing technology to obtain a real-time power demand analysis result;

[0184] In this step, edge computing technology is used to perform real-time analysis on the optimized charging status and the instant power demand of the portable emergency cabin to obtain real-time power demand analysis results. Edge computing technology reduces latency and improves response speed by processing data at a location close to the data source. Real-time analysis not only takes into account the current charging status, but also combines the changes in instant power demand. The analysis results provide accurate data support for subsequent power distribution.

[0185] Step 702: Based on the real-time power demand analysis results and in combination with the renewable energy output forecast results, the optimal power distribution ratio is calculated through a dynamic programming algorithm to obtain a preliminary optimal power distribution plan;

[0186] In this step, based on the real-time power demand analysis results and combined with the renewable energy output forecast results, the optimal power distribution ratio is calculated through the dynamic programming algorithm to obtain a preliminary optimal power distribution plan. The dynamic programming algorithm can find the optimal resource allocation path according to the current and future power demand and supply conditions. The preliminary optimal power distribution plan not only takes into account the immediate demand, but also takes into account the supply and demand balance in the future, ensuring the efficiency and foresight of power distribution.

[0187] Step 703: comprehensively optimizing the preliminary optimal power distribution plan through a multi-objective optimization algorithm to obtain an optimized optimal power distribution plan;

[0188] In this step, the preliminary optimal power distribution plan is comprehensively optimized through a multi-objective optimization algorithm to obtain the optimized optimal power distribution plan. The multi-objective optimization algorithm simultaneously considers multiple objectives such as energy efficiency, cost savings and environmental impact. By weighing and optimizing multiple objectives, the comprehensiveness and scientificity of the final plan are ensured. The optimized optimal power distribution plan is more in line with actual operating conditions and improves the overall performance of the system.

[0189] Step 704: dynamically adjusting the connection state with the external power grid according to the optimized optimal power distribution plan through the smart grid interface, realizing the supplementary function of the external power grid as a backup power source, and supporting the two-way flow of power, thereby obtaining a dynamically adjusted external power grid connection state;

[0190] In this step, through the smart grid interface, according to the optimized best power distribution plan, the connection status with the external power grid is dynamically adjusted to realize the supplementary function of the external power grid as a backup power source, while supporting the two-way flow of electricity to obtain the dynamically adjusted external power grid connection status. The smart grid interface can monitor the power supply and demand situation in real time, and automatically adjust the connection status as needed. The dynamic adjustment ensures that the external power grid can provide reliable power supplement when necessary, and also supports the resale of excess electricity, which improves the flexibility and economy of power supply.

[0191] Step 705: combining the optimized optimal power distribution scheme with the dynamically adjusted external power grid connection state, and obtaining the optimal power supply state through real-time monitoring and feedback mechanism;

[0192] In this step, the optimized best power distribution scheme and the dynamically adjusted external grid connection status are combined, and the best power supply status is obtained through real-time monitoring and feedback mechanism. The real-time monitoring system continuously collects operating data and adjusts the power distribution strategy in time through the feedback mechanism. The best power supply status not only reflects the current optimal configuration, but also can be dynamically adjusted according to actual conditions to ensure the stability and reliability of power supply.

[0193] Figure 2 A schematic diagram of a structure of a portable emergency shelter integrated renewable energy power supply system is provided in an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0194] The collection unit 21 is used to install various types of renewable energy power generation devices on the emergency shelter, automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy, and generate natural energy data, wherein the renewable energy power generation device includes: solar photovoltaic panels, micro wind turbines and thermoelectric converters;

[0195] A prediction module 22 is used to predict the output of renewable energy within a preset time node based on the natural energy data, combined with historical weather data and current meteorological conditions, through a machine learning algorithm to obtain a renewable energy output prediction result;

[0196] A simulation module 23 is used to compare the renewable energy output prediction result with the internal load demand of the emergency shelter, simulate different usage scenarios using deep reinforcement learning technology, and generate an optimal energy management plan;

[0197] The regulating module 24 is used to start the hybrid energy storage system composed of the built-in supercapacitor and lithium-ion battery based on the optimal energy management plan, and adopt an adaptive charging control strategy to adjust the charging rate to obtain an optimized charging state when it is detected that the renewable energy supply does not meet the immediate power demand;

[0198] The analysis module 25 is used to perform real-time analysis on the optimized charging status and the instant power demand of the portable emergency cabin through edge computing technology to obtain the optimal power distribution plan, and at the same time access the external power grid as a backup power supply through the smart grid interface, while supporting two-way energy flow to obtain the optimal power supply state.

[0199] Figure 2 The renewable energy integrated power supply system for a portable emergency shelter can be implemented Figure 1 The implementation principle and technical effect of the xx method described in the embodiment shown will not be repeated. The specific way in which each module and unit performs operations in the portable emergency shelter integrated renewable energy power supply system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0200] Figure 2 The renewable energy integrated power supply system for a portable emergency shelter in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0201] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0202] The processing component 32 is used to install various types of renewable energy power generation devices on the emergency shelter, automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy, and generate natural energy data, wherein the renewable energy power generation device includes: solar photovoltaic panels, micro wind turbines and thermoelectric converters; based on the natural energy data, combined with historical weather data and current meteorological conditions, the renewable energy output within a preset time node is predicted by a machine learning algorithm to obtain a renewable energy output prediction result; the renewable energy output prediction result is compared with the internal load demand of the emergency shelter, and the deep reinforcement learning technology is used to simulate different usage scenarios to generate an optimal energy management plan; based on the optimal energy management plan, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system composed of the built-in supercapacitor and lithium-ion battery is started, and the charging rate is adjusted by an adaptive charging control strategy to obtain an optimized charging state; the optimized charging state and the immediate power demand of the portable emergency shelter are analyzed in real time by edge computing technology to obtain an optimal power distribution plan, and the external power grid is connected to the smart grid interface as a backup power supplement, and bidirectional energy flow is supported to obtain an optimal power supply state.

[0203] The processing component 32 includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (AICs), digital signal processors (DPs), digital signal processing devices (DPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0204] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0205] Computing devices also include other components, such as input / output interfaces, display components, and communication components.

[0206] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device or an input device.

[0207] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0208] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0209] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The illustrated embodiment provides a renewable energy integrated power supply method and system for a portable emergency shelter.

[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0211] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0212] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0213] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A renewable energy integrated power supply method for a portable emergency shelter, characterized in that: include: Various types of renewable energy power generation devices are installed on the emergency shelter, which automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy and generate natural energy data, wherein the renewable energy power generation devices include: solar photovoltaic panels, micro wind turbines and thermoelectric converters; Based on the natural energy data, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the output of renewable energy within a preset time node to obtain a renewable energy output prediction result; Compare the predicted renewable energy output results with the internal load demand of the emergency shelter, use deep reinforcement learning technology to simulate different usage scenarios, and generate an optimal energy management plan; Based on the optimal energy management plan, when it is detected that the renewable energy supply does not meet the immediate power demand, the hybrid energy storage system composed of the built-in supercapacitor and lithium-ion battery is started, and the charging rate is adjusted by using an adaptive charging control strategy to obtain an optimized charging state; The optimized charging status and the instantaneous power demand of the portable emergency shelter are analyzed in real time through edge computing technology to obtain the optimal power distribution plan. At the same time, the external power grid is connected through the smart grid interface as a backup power supply, and bidirectional energy flow is supported to obtain the optimal power supply status.

2. The method according to claim 1, characterized in that The predicted renewable energy output results are compared with the internal load demand of the emergency shelter, and deep reinforcement learning technology is used to simulate different usage scenarios to generate the best energy management plan, including: Using the renewable energy output prediction results and combining them with historical data of the internal load of the emergency shelter, a dynamic balance model between energy demand and supply is constructed through deep reinforcement learning technology to obtain dynamic balance model parameters; Based on the dynamic balance model parameters, simulate the energy demand and supply conditions of the emergency shelter under different climate conditions, time periods and usage scenarios to generate a collection of simulation scenarios; Evaluate each simulation scenario in the simulation scenario collection, comprehensively calculate energy efficiency, cost savings, and environmental impact, and select the best energy configuration plan using a multi-objective optimization algorithm to obtain an initial energy management plan; The initial energy management plan is applied in a virtual simulation environment, and the initial energy management plan is verified and optimized by simulating actual operation conditions to obtain an optimal energy management plan.

3. The method according to claim 2, characterized in that Each simulation scenario in the simulation scenario collection is evaluated, energy efficiency, cost savings and environmental impact are comprehensively calculated, and the best energy configuration scheme is selected using a multi-objective optimization algorithm to obtain an initial energy management plan, including: Using a multi-dimensional evaluation system, for each simulation scenario in the simulation scenario collection, the energy efficiency index, the cost saving index and the environmental impact index under different conditions are calculated to obtain a comprehensive evaluation result of each simulation scenario; Based on the comprehensive evaluation results and in combination with the preset weight distribution, each simulation scenario is comprehensively evaluated to obtain a comprehensive score for each simulation scenario; Using a multi-objective evolutionary algorithm, all simulation scenarios are screened according to the comprehensive scores to select the best energy configuration solution; The optimal energy configuration scheme is input into an advanced decision support system, the current energy storage level of the emergency shelter and the availability of the external power grid are comprehensively calculated, the optimal energy configuration scheme is refined, and an initial energy management plan is obtained.

4. The method according to claim 3, characterized in that: Based on the comprehensive evaluation results and in combination with the preset weight distribution, each simulation scenario is comprehensively evaluated to obtain a comprehensive score for each simulation scenario, including: Using the comprehensive evaluation results, combined with the preset weight allocation scheme, based on the operating characteristics of the emergency shelter and the pre-set external environmental conditions, the relative importance of each indicator is determined by using the hierarchical analysis method, and the energy efficiency indicator, cost saving indicator and environmental impact indicator of each simulation scenario are weighted to obtain the optimal weighted evaluation value; The optimal weighted evaluation value is revised twice by using the entropy weight method, and the uncertainty of each indicator under different simulation scenarios is calculated to obtain a revised evaluation value; Using the fuzzy comprehensive evaluation method, combined with the revised evaluation value, the uncertainty and subjectivity in the evaluation process are calculated, and each simulation scenario is evaluated to obtain an initial comprehensive score; Using a grey correlation analysis method, based on the initial comprehensive score, analyzing the similarities and differences between the simulation scenarios, adjusting the initial comprehensive score of each simulation scenario, and obtaining an adjusted comprehensive score; The adjusted comprehensive score is deeply learned using a neural network model to identify underlying rules and patterns between simulation scenarios and optimize the accuracy of the comprehensive score to obtain a target comprehensive score for each simulation scenario.

5. The method according to claim 4, characterized in that Using the comprehensive evaluation results, combined with the preset weight allocation scheme, based on the operating characteristics of the emergency shelter and the pre-set external environmental conditions, the hierarchical analysis method is used to determine the relative importance of each indicator, and the energy efficiency indicator, cost saving indicator and environmental impact indicator of each simulation scenario are weighted to obtain the optimal weighted evaluation value, including: Using the data on the operation characteristics of the emergency shelter and external environmental conditions, a multi-level indicator system is constructed; Based on the multi-level indicator system, combined with expert knowledge and historical data, the analytic hierarchy process is used to determine the relative importance of each indicator and form a preliminary weight allocation plan; Using the preliminary weight allocation scheme and combining the comprehensive evaluation results, the energy efficiency index, cost saving index and environmental impact index of each simulation scenario are weighted for the first time to obtain an initial weighted evaluation value; The initial weighted evaluation value is reviewed by using the Delphi method, and the weight allocation scheme is corrected according to the review result to obtain a corrected weight allocation scheme; The corrected weight distribution scheme is applied to the preliminary weighted evaluation value, and a secondary weighted calculation is performed to obtain an optimal weighted evaluation value.

6. The method according to claim 1, characterized in that Based on the natural energy data, combined with historical weather data and current meteorological conditions, a machine learning algorithm is used to predict the output of renewable energy within a preset time node to obtain a renewable energy output prediction result, including: Using the natural energy data, combined with historical weather data and current meteorological conditions, the natural energy data is processed through time series analysis technology to extract the time characteristics of energy output and the correlation characteristics of meteorological conditions to obtain a feature data set; Based on the feature data set, an ensemble learning method is used to construct a multi-model prediction framework; Applying the multi-model prediction framework to the feature data set, optimizing the multi-model prediction framework parameters by cross-validation technology, and obtaining an optimized multi-model prediction framework; Using the optimized multi-model forecasting framework, the renewable energy output within a preset time node is forecasted, and the impact of seasonal fluctuations and short-term weather changes is calculated to obtain preliminary renewable energy output forecast results; The Bayesian updating method is used to perform real-time correction on the preliminary renewable energy output forecast result according to the latest meteorological conditions to obtain the renewable energy output forecast result.

7. The method according to claim 1, characterized in that The optimized charging status and the instantaneous power demand of the portable emergency shelter are analyzed in real time through edge computing technology to obtain the best power distribution plan. At the same time, the external power grid is connected through the smart grid interface as a backup power supply supplement, and bidirectional energy flow is supported to obtain the best power supply status, including: Using edge computing technology to perform real-time analysis on the optimized charging state and the instantaneous power demand of the portable emergency shelter to obtain a real-time power demand analysis result; Based on the real-time power demand analysis results and the renewable energy output forecast results, the optimal power distribution ratio is calculated through a dynamic programming algorithm to obtain a preliminary optimal power distribution plan; Comprehensively optimizing the preliminary optimal power distribution plan through a multi-objective optimization algorithm to obtain an optimized optimal power distribution plan; Through the smart grid interface, according to the optimized best power distribution plan, the connection state with the external power grid is dynamically adjusted to realize the supplementary function of the external power grid as a backup power source, while supporting the two-way flow of power, and obtaining a dynamically adjusted external power grid connection state; The optimized best power distribution scheme is combined with the dynamically adjusted external power grid connection state, and the best power supply state is obtained through real-time monitoring and feedback mechanism.

8. A renewable energy integrated power supply system for a portable emergency shelter, characterized in that: include: A collection unit is used to install various types of renewable energy power generation devices on the emergency shelter, automatically adjust the working mode according to the changes in the surrounding environment to collect solar energy, wind energy and thermal energy, and generate natural energy data, wherein the renewable energy power generation device includes: solar photovoltaic panels, micro wind turbines and thermoelectric converters; A prediction module is used to predict the output of renewable energy within a preset time node based on the natural energy data, combined with historical weather data and current meteorological conditions, through a machine learning algorithm to obtain a renewable energy output prediction result; A simulation module, for comparing the predicted output of renewable energy with the internal load demand of the emergency shelter, using deep reinforcement learning technology to simulate different usage scenarios and generate an optimal energy management plan; A regulating module is used to start the hybrid energy storage system composed of a built-in supercapacitor and a lithium-ion battery based on the optimal energy management plan, and to adjust the charging rate by adopting an adaptive charging control strategy to obtain an optimized charging state when it is detected that the renewable energy supply does not meet the immediate power demand; The analysis module is used to perform real-time analysis on the optimized charging status and the instant power demand of the portable emergency shelter through edge computing technology to obtain the optimal power distribution plan, and at the same time access the external power grid as a backup power supply through the smart grid interface, while supporting two-way energy flow to obtain the optimal power supply state.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a renewable energy integrated power supply method for a portable emergency shelter as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a renewable energy integrated power supply method for a portable emergency shelter as described in any one of claims 1 to 7 is implemented.

Images