Resource allocation dynamic simulation optimization method based on energy condition constraint

Abstract

The invention relates to the technical field of energy management and optimization, and discloses a resource allocation dynamic simulation optimization method based on energy condition constraints, which comprises the following steps: step 1, deploying a sensor network and a data acquisition system, monitoring an energy supply condition and a consumption mode in real time, and performing multi-dimensional collection on data; 2, the collected data are cleaned and analyzed, a dynamic energy condition report is generated, and the report comprises energy supply and demand prediction, energy price fluctuation and carbon emission intensity information; and step 3, constructing a resource allocation dynamic simulation model according to the collected data and reports. The resource allocation dynamic simulation optimization method based on the combination of real-time energy state recognition and self-adaptive weight adjustment is adopted, the technical effect of flexible scheduling according to dynamic changes of energy conditions is achieved, and it is ensured that the resource allocation process can be responded in time, and the system operation efficiency is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and optimization, and in particular to a resource allocation dynamic simulation optimization method based on energy condition constraints. Background Art

[0002] With the continuous growth of global energy demand, especially the rapid development of renewable energy, the optimization of energy management systems has become particularly important. Traditional energy management systems rely on static models and fixed optimization rules for resource allocation. However, as the volatility of energy supply increases, traditional methods have gradually exposed their inability to adapt to energy changes in real time. In order to meet this challenge, more and more studies have begun to explore energy management methods based on dynamic data and real-time feedback, aiming to improve the accuracy and efficiency of resource allocation.

[0003] In the prior art, many energy management systems still use static simulation models and preset rules for resource allocation. Although optimizing resource allocation based on historical data or regular scheduling can improve energy efficiency to a certain extent, they often fail to respond in a timely manner when faced with dynamic factors such as real-time energy fluctuations and changes in supply and demand. In addition, some methods rely on manual presets or static scenario assumptions, which leads to inefficient and inaccurate resource allocation results. In particular, when supply and demand are extremely unbalanced or energy fluctuations are large, the errors in simulation results are more significant.

[0004] The existing technology fails to effectively combine the real-time energy supply and demand changes with the optimization process of resource allocation, and cannot automatically adjust the allocation strategy according to the dynamic fluctuations of energy supply, resulting in waste of energy resources or mismatch between supply and demand. Especially when faced with unpredictable energy fluctuations, traditional methods cannot adapt to these changes, thereby reducing the overall efficiency and stability of the system. In order to solve this problem, the present invention proposes a dynamic simulation optimization method for resource allocation based on energy condition constraints, which aims to provide a more flexible and accurate resource allocation solution through real-time energy status recognition and adaptive weight adjustment. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides a dynamic simulation optimization method for resource allocation based on energy condition constraints. The prior art cannot adapt to the resource allocation problem of energy supply and demand fluctuations in real time.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a resource allocation dynamic simulation optimization method based on energy condition constraints, comprising the following steps: Step 1: Deploy sensor networks and data collection systems to monitor energy supply conditions and consumption patterns in real time and collect data in multiple dimensions; Step 2: Clean and analyze the collected data to generate a dynamic energy condition report, which includes energy supply and demand forecasts, energy price fluctuations, and carbon emission intensity information; Step 3: Build a dynamic simulation model for resource allocation based on the collected data and reports, and adjust model parameters and boundary conditions based on the dynamic energy condition report generated in real time; Step 4: Process the adaptive weight adjustment algorithm according to the model parameters and boundary conditions, and automatically adjust the priority of various resource allocations based on the dynamic energy condition report; Step 5: Repeatedly run simulation experiments on the dynamic simulation model through dynamic iterative optimization, and correct the results according to the latest energy conditions until convergence to the optimal solution to obtain the optimization result; Step 6: Adjust the power generation plan according to the optimization results, optimize the energy storage system charging and discharging strategy, and guide user-side demand response.

[0007] Preferably, in step 1, the energy supply status includes power generation, grid load and energy storage status, the consumption mode includes user power consumption and equipment operating status, the sensor network includes distributed smart meters, power sensors and environmental monitoring equipment, the data acquisition system includes power generation, grid load, energy storage status, user power consumption and equipment operating status, and uploads the data to the edge computing node for preprocessing and storage.

[0008] Preferably, in step 2, the dynamic energy condition report includes: Energy supply and demand forecast information, which is used to describe changes in energy supply and demand over a period of time in the future; Energy price fluctuation information, used to predict energy market price trends; Carbon intensity information is used to quantify carbon emissions from energy production and consumption.

[0009] Preferably, in step 3, the dynamic simulation model adopts a system dynamics method or an agent modeling method to simulate the dynamic interaction between power generation, energy storage, transmission and distribution, and demand side in the energy system.

[0010] Preferably, the model parameters in step 3 include energy conversion efficiency, resource demand and price fluctuation sensitivity coefficient; the boundary conditions include maximum energy supply, energy storage capacity limit and carbon emission threshold.

[0011] Preferably, in step 4, the priority adjustment rules of the adaptive weight adjustment algorithm include: When renewable energy is in sufficient supply, clean energy will be allocated first; When energy supply is tight, energy storage resources are used first; Dynamically adjust the allocation weight of high-cost energy according to energy price fluctuations.

[0012] Preferably, in step 5, the dynamic iterative optimization performs parameter optimization through Monte Carlo simulation or genetic algorithm, and updates the energy condition constraints in the simulation model after each iteration until the resource allocation scheme meets the preset convergence conditions.

[0013] Preferably, in step 6, resource allocation scheduling includes: Adjust the proportion of thermal power, hydropower and renewable energy in power generation; Optimize the charging and discharging timing of the energy storage system to balance peak and valley loads; Guide users to adjust their electricity demand through price signals or incentive mechanisms.

[0014] Preferably, in step 5, the construction of the dynamic iterative optimization objective function includes the following steps: Calculate the production cost weights of different energy types based on the energy price fluctuation information in the dynamic energy condition report; According to the carbon emission intensity information, the carbon emission is converted into a penalty cost coefficient; Combine the charging and discharging efficiency and historical loss data of the energy storage system to establish an energy storage loss cost model; The goal is to minimize the total cost.

[0015] Preferably, in step 6, demand response scheduling includes dynamically adjusting the power load in different time periods according to the prediction of the user's power consumption behavior, and achieving the balance of the user's power demand through a real-time feedback mechanism.

[0016] The present invention provides a resource allocation dynamic simulation optimization method based on energy condition constraints. It has the following beneficial effects: 1. The present invention adopts a dynamic simulation optimization method for resource allocation based on real-time energy state recognition combined with adaptive weight adjustment, achieving the technical effect of flexible scheduling according to the dynamic changes of energy conditions. Compared with traditional static simulation methods, the existing technology often fails to effectively consider the problem of real-time energy supply and demand fluctuations, ensuring that the resource allocation process can respond in time and optimize the system operation efficiency.

[0017] 2. The present invention significantly improves the real-time and adaptability of the energy management system by combining real-time data collection and analysis technology with a dynamic simulation model. Unlike the traditional method of allocating resources based on preset rules, the solution of the present invention can dynamically adjust the strategy according to the actual situation during the operation of the system, effectively reducing the risk of resource waste and system overload, and improving the flexibility and stability of the system.

[0018] 3. The dynamic optimization method of the present invention effectively improves the accuracy of resource allocation and reduces energy costs and carbon emissions by repeatedly running simulation experiments and iterative optimization. Compared with existing static or partial optimization schemes, the present invention can more accurately perform optimal scheduling according to different energy conditions, achieve lower total energy costs and higher sustainability, and provide a new path for improving energy efficiency.

[0019] 4. The dynamic resource allocation optimization method proposed in the present invention uses accurate energy supply and demand prediction and adaptive adjustment mechanism to enable the system to maintain efficient operation in the face of unpredictable energy fluctuations. Traditional methods usually ignore the impact of energy supply instability, which easily leads to unreasonable resource allocation. The present invention effectively improves the robustness of resource allocation through intelligent adjustment and ensures the stable operation of the system in a complex environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Please refer to the attached Figure 1 The embodiment of the present invention provides a method for dynamic simulation optimization of resource allocation based on energy condition constraints, comprising: Data collection and processing obtains information such as energy supply and demand, energy consumption patterns, and system status in real time, providing the necessary basic data for subsequent dynamic simulation models and adaptive weight adjustment algorithms, ensuring that the system can respond flexibly and accurately in a dynamic and changing environment.

[0023] In this embodiment, various sensors are first deployed at key nodes of the energy system to monitor important parameters in real time. The type of sensor is selected according to the needs, for example, current and voltage sensors are used to monitor the load of the power grid, power sensors are used to monitor the power generation of various power generation equipment, such as wind power generation, solar power generation, etc., and the state sensor of the energy storage device is used to track the battery charging and discharging status in real time.

[0024] The data collected by these sensors will be transmitted to the data acquisition system in real time for preliminary processing. Data processing includes data cleaning, denoising, interpolation of missing data and other operations to ensure the quality and consistency of the collected data. The cleaned data will be used as input, analyzed and feature extracted, and finally generate a dynamic energy condition report.

[0025] First, the deployed sensors collect the following data in real time: Energy supply status: including the power generation of different energy types, such as wind energy, solar energy, traditional energy, etc., the real-time load of the power grid, the charging and discharging status of the energy storage system, etc.

[0026] Energy demand status: including user-side electricity demand data and real-time operation status of various equipment.

[0027] Environmental data: external environmental factors such as temperature and humidity, which directly affect the power generation capacity of renewable energy, such as wind power, solar radiation, etc.

[0028] After these data are transmitted to the data acquisition system in real time, they need to be further processed to ensure the validity and applicability of the data.

[0029] After data collection, the data will first be cleaned by the data cleaning module. Data cleaning includes: Noise removal: Remove abnormal or erroneous data points by setting a reasonable threshold.

[0030] Missing value interpolation: For missing data, interpolation methods are used to fill in to ensure data integrity.

[0031] Outlier detection and removal: Use statistical methods (such as standard deviation, mean, etc.) to identify and remove significantly abnormal measurements.

[0032] Once the data is cleaned, the system will extract features from the data. This process converts the raw data into more representative features to facilitate subsequent analysis and decision-making. Specifically, it includes: Energy supply and demand forecast: Based on historical data and real-time data, future energy demand is predicted based on time series analysis methods such as ARIMA model and long short-term memory network LSTM. The specific calculation is based on the following formula: ; in: Indicates time The predicted energy demand at the moment; For the previous moment actual needs; , is a model parameter, which represents the weight of historical data and external environmental influences (such as temperature, holidays, etc.); External disturbances, such as the impact of weather changes and economic activities on energy demand.

[0033] Energy price fluctuation analysis: Based on the fluctuation trend of historical market prices, predict the changes in energy prices within a certain period of time in the future. This data is crucial for optimizing resource allocation and reducing costs.

[0034] Carbon emission intensity calculation: Based on the carbon emission coefficients of different types of energy, such as coal, natural gas, renewable energy, etc., the carbon emission intensity of each energy source is calculated. This data is crucial for optimizing low-carbon solutions and achieving environmental protection goals, and is calculated using the following formula: ; in: is the total carbon emission intensity of the system at the time; For the first type of energy (such as coal, natural gas, wind power, etc.) at any time Amount of usage; For the Carbon emission coefficient of energy sources; is the total number of energy types.

[0035] The carbon emission intensity calculation formula can accurately reflect the impact of different energy uses on the environment and provide data support for subsequent optimization of resource allocation.

[0036] The data after feature extraction will be further summarized into an "energy condition report", which is the core input for the entire resource allocation optimization. The energy condition report includes the following parts: Based on real-time data and forecasting models, the report system reports the difference between current energy supply and demand, including the supply status of various energy sources, demand forecasts, etc. Market price fluctuation analysis includes historical trends in energy prices, current market prices, and predicted short-term fluctuation trends. Based on the current energy configuration, the carbon emission level of the entire system is calculated, and low-carbon development goals are formulated according to policy requirements.

[0037] After data processing and feature extraction, the system will generate a dynamic energy condition report, which includes: Real-time feedback on energy supply and demand; Forecasts of future energy demand; Analysis of energy price fluctuations; Calculation results of carbon emission intensity.

[0038] This information will be used as input for subsequent steps and for reference by dynamic simulation models and resource allocation algorithms. Report generation is a real-time, dynamic process that can be adjusted based on changes in energy supply and demand, prices, environmental conditions, and other conditions.

[0039] By deploying various types of sensors and processing data, the operating status of the energy system can be accurately understood at every moment. The energy data collected and processed in real time provides the basis and support for subsequent simulation optimization. Ultimately, the generated energy condition report will guide the optimization direction of resource allocation decisions and ensure that the system can operate efficiently under changing energy conditions.

[0040] The data collection and processing steps in this embodiment are the basic part of the entire system. It provides accurate and real-time data support for subsequent resource allocation and optimization, ensuring the accuracy and feasibility of the dynamic simulation optimization method.

[0041] After completing data collection and processing, the dynamic simulation model is constructed. This step is a key part of achieving resource allocation optimization. Its purpose is to convert the real-time energy supply and demand information obtained from the data acquisition system into model input, thereby simulating the interaction and evolution process between various factors in the energy system. Through the dynamic simulation model, resource allocation can be simulated under different energy conditions to foresee the possible operating status and resource allocation plan of the system.

[0042] In this embodiment, the construction of the simulation model adopts a combination of system dynamics and agent-based modeling. The system dynamics model is used to describe the continuous change relationship of various resources in the energy system, while the agent-based model can better simulate the behavior of each independent energy entity. The combination of the two can more accurately reflect the dynamic evolution and resource allocation process of the energy system.

[0043] In this embodiment, the basic idea of ​​the system dynamics model is to establish a dynamic feedback model to describe the changes of the system based on the causal relationship between various system variables. The typical system dynamics equation is as follows: ; in, Charging power for energy storage system, is the discharge power of the energy storage system, The charging or discharging status of the energy storage device indicates the current energy storage level of the energy storage system. The change of energy storage status is determined by the charging and discharging power. As the system status changes, the charging and discharging power will also be dynamically adjusted according to system requirements.

[0044] For renewable energy generation (such as wind and solar), its power generation can be expressed as a function of time: ; in, and They represent the power output of wind power generation and photovoltaic power generation, respectively, which change with changes in wind speed and light intensity.

[0045] Unlike the continuous variables of the system dynamics model, the agent-based model focuses on describing the behavior and decision-making process of each independent actor (i.e., "agent") in the system. Each agent's decision in the system will respond to its own goals, constraints, and perception of energy supply and demand. Specifically, agents may include: Power Plant Agent: Adjusts power generation plans based on grid demand and energy prices to optimize power generation and resource utilization as much as possible.

[0046] Consumer Agent: Adjusts its own electricity consumption pattern according to factors such as electricity demand and energy prices.

[0047] Energy storage system agent: Determines charging and discharging strategies to optimize energy storage efficiency based on grid demand and electricity price changes.

[0048] In the present invention, the core of the simulation model is to simulate the interaction between these agents. The behavior of each agent usually follows certain rules, and its decision-making is affected by the following factors: Energy prices: Higher energy prices can cause users to reduce demand or power plants to increase generation.

[0049] Load demand: When the demand is high, the system will give priority to fast-response energy resources (such as energy storage resources).

[0050] Environmental factors: such as wind speed and light intensity, affect the power generation of renewable energy.

[0051] The agent's behavior decision rules can be expressed in the following mathematical form: ; in, The Agent is at time decision, is the available generated power, is the load demand of the system, is the price in the energy market.

[0052] The simulation model is dynamic in this embodiment and is updated in real time based on the input data. Whenever a new energy condition report is generated, the parameters of the model are adjusted. For example, when the amount of renewable energy generation (wind, solar) changes, the model adjusts the power generation plan based on real-time data, optimizes the charging and discharging strategy of the energy storage system, and adjusts the load demand response strategy. Through this dynamic adjustment, the simulation model can reflect the state of the energy system in real time, thereby providing accurate prediction and optimization solutions for resource allocation.

[0053] After each simulation iteration, the model will output a resource allocation plan and compare it with the actual operating conditions. If there is a deviation, the parameters of the next round of simulation model will be adjusted based on the feedback. Through this repeated iteration, the optimal resource allocation strategy is gradually approached.

[0054] By combining system dynamics with agent-based models, this embodiment establishes a flexible and accurate dynamic simulation framework that can reflect the mutual influence and evolution process between various resources in the energy system in real time. On this basis, the system can optimize resource allocation and maximize energy utilization efficiency under dynamically changing energy conditions, and provide data support and decision-making basis for subsequent adaptive weight adjustment and resource scheduling.

[0055] In the previous steps, a dynamic report of energy conditions has been established through data collection and analysis, and the changes in the energy supply and demand system have been simulated in the simulation model. Next, the adaptive weight adjustment algorithm is introduced. This algorithm plays a core role in the optimization process of resource allocation. It dynamically adjusts the priority of resource allocation according to real-time energy conditions, thereby achieving flexible and efficient resource management.

[0056] In this embodiment, the adaptive weight adjustment algorithm determines the priority of various resources by analyzing key data in the energy condition report. When the energy supply is sufficient, clean energy is used first; when the energy supply is tight, energy storage resources are used first, and the emergency response mechanism is activated when necessary. In addition, this algorithm also takes into account factors such as energy prices and carbon emission intensity to minimize the cost and carbon emissions in resource allocation.

[0057] The core idea of ​​adaptive weight adjustment is to automatically adjust the priority of various types of resources according to the real-time changes in energy supply and demand. Specifically, the initial weight of each resource category is set, and these weights are dynamically updated according to real-time energy supply and demand reports and market changes. The following is the basic model of resource weight adjustment: ; in, For resource categories In time The weight of is the resource weight at the previous moment, It is the amount of weight adjustment caused by real-time data and market changes. The weight adjustment is based on the following factors: Renewable energy supply: If the power generation of renewable energy such as wind power and solar power exceeds a certain set threshold, the adaptive algorithm will increase the weight of clean energy. , and its weight adjustment formula is: ; in, is the adjustment factor, reflecting the sensitivity of the increase in clean energy priority.

[0058] Energy storage status: When the grid load is high, the priority of the energy storage system will increase to ensure stable energy supply. Therefore, the weight adjustment formula of the energy storage system is: ; in, It is a regulating factor, which indicates the degree of priority dispatch required by the energy storage system when energy is tight. Indicates at time The change of energy storage weight when is an adjustment coefficient used to control the sensitivity of energy storage weight changes. Indicates at time The energy storage state.

[0059] Energy price fluctuations: Energy price fluctuations are also an important basis for adjusting weights. Set a target price range. When the set price is exceeded, the resource allocation weight of the relevant energy category will be adjusted. The specific adjustment formula is: ; in, is the adjustment factor, is the target price, Represents the change in price weight at time.

[0060] Combining the above factors, the system will make global optimization adjustments based on the dynamic information of various resources to determine the final resource weights. In practical applications, weight adjustment is not only a linear change process, but also the interaction between feedback effect and market mechanism should be considered. In order to better capture this complex relationship, the present invention proposes an adaptive weight adjustment method based on feedback control theory.

[0061] Specifically, the system adjusts the weight of each type of resource by establishing a feedback control loop, the goal of which is to minimize the following objective function: ; in, Indicates Class resources in time The weight of is the cost of the resource, is the carbon emission intensity of the resource, is the weight factor of carbon emissions, is the total number of resource types. The objective function aims to minimize the combined impact of cost and carbon emissions by dynamically adjusting resource weights.

[0062] By optimizing this objective function, the system can adjust the resource allocation plan in real time, giving priority to the use of energy resources with lower costs and lower carbon emissions, thereby improving the economic and environmental benefits of the system.

[0063] Through the implementation of this step, the system can adjust the priority of resource allocation in real time and dynamically according to changes in energy supply and demand and market environment, ensuring that the system can make the best resource scheduling decision under different energy conditions. The core of the weight adjustment algorithm lies in its adaptability. It can not only adjust the priority of resource allocation according to factors such as energy supply and demand, price fluctuations, but also respond quickly to changes in various external environments, improving the flexibility and response speed of the entire energy system.

[0064] In the aforementioned steps, real-time data collection and analysis, dynamic simulation model construction, and adaptive weight adjustment have been completed. Next, the fourth step of the present invention is the dynamic iterative optimization stage. Through this stage, the system will continuously adjust the resource allocation strategy until the best resource allocation solution is found. Unlike traditional static optimization methods, the present invention adopts a dynamic iterative optimization strategy to ensure that resource allocation can not only adapt to current energy needs, but also cope with uncertain changes in the future.

[0065] In this embodiment, the dynamic iterative optimization method relies on real-time monitoring and adaptive adjustment of energy supply and demand. By repeatedly executing simulation experiments, the optimization scheme is corrected according to the latest energy conditions and market changes, ultimately ensuring that while maximizing energy utilization, carbon emissions are reduced and the economic benefits of the system are optimized.

[0066] In order to achieve the optimization of resource allocation, it is necessary to first establish an optimization model based on dynamic simulation. The goal of this model is to minimize the overall cost of resource allocation while meeting the constraints of energy supply and demand balance and carbon emissions. The mathematical description of the model is as follows: ; in, is the total cost of resource allocation, It is The unit cost of the class resource, It is The amount of class resources allocated, is the number of resource categories. The goal is to adjust To minimize the total cost , while satisfying the following constraints: ; in, Is the resource category The resource conversion coefficient, It is at the moment This constraint ensures that the total resource allocation at each moment can meet the total demand of the system.

[0067] ; in, It's time energy prices, is the maximum allowable price set, and this constraint ensures that the cost does not exceed a certain acceptable range.

[0068] Carbon emission intensity limit: ; in, It is Carbon emission intensity of resources, It is the maximum allowable carbon emission value, ensuring that the system's carbon emissions are within the limit.

[0069] The dynamic iterative optimization process of the present invention adopts a progressive adaptive adjustment mechanism. The specific process is as follows: Initialization: Set the initial weights of various resources based on the preliminary energy condition report and define the optimization objective function and constraints.

[0070] Simulation run: Run the simulation model through methods such as system dynamics and agent modeling to obtain resource allocation solutions.

[0071] Result correction: After each simulation result comes out, correction is made according to the latest energy condition report and market changes, resource allocation strategy is adjusted, and objective function is optimized.

[0072] Convergence check: When the optimization result meets the convergence criteria, that is, the total cost change is lower than the preset threshold, the optimization process is stopped.

[0073] In each round of optimization, the system dynamically adjusts the weight values ​​and resource allocation strategies based on real-time data feedback. Through the adaptive adjustment mechanism, the algorithm can flexibly respond to sudden energy fluctuations and ensure that the optimal resource allocation can be maintained in a dynamically changing environment.

[0074] After each round of optimization, the system will schedule resources according to the new resource allocation strategy. At this time, the simulation results can not only provide the optimal energy resource allocation plan, but also reflect the comprehensive effects of energy consumption, cost control and carbon emissions. After several rounds of iterations, the system will gradually approach the optimal solution and reflect higher energy utilization, lower economic costs and better environmental protection effects in practical applications.

[0075] In this embodiment, the iteration of the optimization process and the result feedback help to enhance the real-time response capability of the system and ensure that the energy management system can maintain efficient operation in a constantly changing environment.

[0076] In order to further improve the optimization effect, the present invention can also combine machine learning methods to optimize the model. Through deep learning and historical data analysis, the prediction accuracy and response speed of the optimization algorithm can be continuously improved. For example, by using methods such as convolutional neural networks or long short-term memory networks, energy supply and demand patterns can be learned from a large amount of historical data, and resource allocation decisions can be made in a more intelligent way.

[0077] By combining artificial intelligence technology, the system can not only perform real-time dynamic optimization in complex environments, but also continuously learn and improve, thereby enhancing the autonomy and intelligence of the energy management system.

[0078] Embodiment 1: In this embodiment, the resource allocation dynamic simulation optimization method based on energy condition constraints of the present invention is applied to optimize the energy resource scheduling of a smart grid system in a certain area.

[0079] Step 1: Real-time data collection and analysis: In the smart grid system, a sensor network is deployed to monitor the grid load, power production, energy storage system status, weather data, and user power demand in real time. The data collected by the sensors is transmitted to the data collection system via a wireless network. After data cleaning and feature extraction, a dynamic energy condition report is generated, which includes energy supply and demand forecasts for the next 12 hours, grid load fluctuations, and renewable energy generation estimates.

[0080] Step 2: Dynamic simulation model construction: Based on the collected data, a grid resource allocation simulation model based on system dynamics was constructed. The model includes multiple variables such as power demand, power generation, energy storage capacity, and grid connection. Real-time energy condition reports are used as model inputs, and the model parameters are dynamically adjusted according to the energy supply and demand in different time periods to ensure that the model accurately reflects the state of the grid.

[0081] Step 3: Adaptive weight adjustment: According to the dynamic energy condition report, when renewable energy generation is sufficient, priority is given to dispatching wind and solar power generation resources to increase the proportion of clean energy; when energy supply is insufficient, the dispatch priority of the energy storage system is increased, and the battery energy storage system is mobilized for power supply. The adaptive weight adjustment algorithm automatically adjusts the priority of various resources based on real-time data to ensure grid load balance and minimize costs.

[0082] Step 4: Dynamic iterative optimization: In the simulation engine, multiple iterations are run, and each iteration corrects the resource allocation plan based on the latest energy supply and demand conditions and resource availability. The simulation is continued until the system reaches the optimal resource allocation plan to ensure the load demand of the power grid while reducing overall energy costs and carbon emissions.

[0083] Step 5: Resource allocation and scheduling: Finally, the resource allocation strategy output by the optimization algorithm is used to adjust the power grid's power generation plan, energy storage charging and discharging strategy, and user-side demand response. By adjusting the charging and discharging time of the energy storage system and adjusting the user demand response plan, the power grid system is ensured to operate stably and meet environmental protection standards.

[0084] Embodiment 2: In this embodiment, the present invention is applied to an energy management system of an industrial park to optimize the allocation of energy resources in the park.

[0085] Step 1: Real-time data collection and analysis: In the industrial park, the sensor network monitors the power demand of various industrial equipment, the overall energy consumption of the park, and the production of renewable energy (such as solar energy and wind energy) in real time. The data collection system analyzes the data collected by the sensors in real time and generates dynamic energy condition reports based on energy consumption patterns and renewable energy generation.

[0086] Step 2: Dynamic simulation model construction: A resource allocation simulation model based on Agent-based Modeling is used to simulate the interaction between various factories, equipment and energy storage systems in the park. The model adjusts the operating parameters of industrial equipment and energy demand forecasts based on real-time energy data, and adjusts the energy use plan of the park in combination with the supply of renewable energy.

[0087] Step 3: Adaptive weight adjustment: When there is sufficient renewable energy generation, the system automatically increases the priority of clean energy and prioritizes the output of solar and wind energy. If the energy demand in the park is at its peak or the renewable energy generation is insufficient, the system automatically calls on the energy storage system. Through the adaptive weight adjustment algorithm, the system adjusts the priority in real time to ensure the rationality and cost-effectiveness of energy distribution in the park.

[0088] Step 4: Dynamic iterative optimization: In the park energy management system, by repeatedly running simulation experiments and correcting the resource allocation results according to the actual energy status and demand after each simulation iteration, the system will continuously optimize the energy allocation strategy based on the comparison of historical data and real-time data.

[0089] Step 5: Resource allocation and scheduling: Finally, the simulation results determine the energy allocation and scheduling plan for the park. This plan adjusts the power generation plan, energy storage equipment charging and discharging time, and power consumption patterns of enterprises in the park according to energy supply conditions and demand response, maximizing energy utilization and optimizing operating costs.

[0090] Embodiment three: In this embodiment, the dynamic simulation optimization method for resource allocation based on energy condition constraints of the present invention is used for resource optimization scheduling of electric vehicle charging piles.

[0091] Step 1: Real-time data collection and analysis: At multiple electric vehicle charging stations in the city, the sensor network monitors the grid load, the usage of electric vehicle charging piles, the charging demand of electric vehicles, etc. Through the data collected by the sensors, the system obtains the load demand of each charging station and the status of the energy storage system in real time, and generates a dynamic energy condition report, including information such as grid load fluctuations, charging pile usage rate, and available power.

[0092] Step 2: Dynamic simulation model construction: A simulation model based on system dynamics is used to simulate the interaction of factors such as grid load, electric vehicle charging demand, charging pile scheduling strategy, and renewable energy power supply. By dynamically inputting real-time energy condition reports, the model can be adjusted according to actual grid load and demand forecasts to simulate resource allocation plans under different scenarios.

[0093] Step 3: Adaptive weight adjustment: When the grid load is peak, the system will automatically mobilize the battery energy storage system to provide power for the charging piles, while giving priority to the charging needs of electric vehicles, especially those that are in urgent need of charging. When the grid load is low or renewable energy generation is sufficient, the system will prioritize clean energy to provide power for the charging piles. The adaptive weight adjustment algorithm adjusts the priority of resources according to real-time data changes to ensure that the resource allocation of charging piles is more intelligent and efficient.

[0094] Step 4: Dynamic iterative optimization: The simulation engine continuously adjusts the resource allocation strategy through multiple iterative optimizations based on the actual grid status, charging demand, and available energy. After each iteration, the system corrects the plan and achieves the best resource allocation plan through model optimization.

[0095] Step 5: Resource allocation and scheduling: The optimized resource allocation plan is used to adjust the resource scheduling of charging piles, reasonably plan the charging period, the switching time of charging piles and the distribution of power grid load, ensure the smooth charging of electric vehicles, and reduce the power grid load and operating costs. The scheduling plan can also provide users with charging pile reservation services to improve the efficiency of resource use.

[0096] The above three embodiments are run, and the data in the process are recorded and recorded in the following table: Table 1. Smart grid system resource allocation data index Before optimization (traditional static method) After optimization (dynamic simulation optimization method) Improvement (%) Renewable energy utilization rate (%) 45% 60% 33.33% Energy storage system utilization rate (%) 50% 70% 40% Total energy cost (yuan / kWh) 0.75 0.65 13.33% Carbon emissions (tons / year) 1500 1200 20% Grid load balance (%) 85% 95% 11.76% Power supply reliability (%) 90% 98% 8.89% Table 2. Industrial Park Energy Management Data index Before optimization (traditional static method) After optimization (dynamic simulation optimization method) Improvement (%) Renewable energy utilization rate (%) 40% 55% 37.50% Energy storage system utilization rate (%) 45% 65% 44.44% Total energy cost (yuan / kWh) 0.85 0.7 17.65% Carbon emissions (tons / year) 1800 1450 19.44% Factory production efficiency (unit electricity / output) 0.8 1.05 31.25% Demand response regulation accuracy (%) 75% 90% 20% Table 3. Building group energy dispatch data

[0097] Renewable energy utilization rate: refers to the proportion of renewable energy in total energy consumption. After optimization, the proportion of renewable energy use is increased through dynamic scheduling and resource allocation strategies.

[0098] Energy storage system utilization rate: refers to the proportion of energy storage systems used in overall energy dispatch. Through adaptive weight adjustment, the dispatch frequency and capacity utilization of energy storage systems have been improved.

[0099] Total energy cost: The energy cost per unit of electricity. After optimization, the overall cost is reduced through precise scheduling and reduced waste.

[0100] Carbon emissions: The amount of carbon emissions generated per unit time. The optimized strategy is more environmentally friendly and reduces carbon emissions.

[0101] Grid load balance / demand response regulation accuracy: measures the balance of grid load distribution and the accuracy of demand response regulation. After optimization, scheduling is more precise and can better adapt to energy fluctuations.

[0102] Production efficiency: Production efficiency converted to unit electricity consumption. After optimization, the system can use energy more efficiently and improve production efficiency.

[0103] It can be seen from the data of the three embodiments that after adopting the dynamic simulation optimization method of resource allocation based on energy condition constraints, all key indicators have been significantly improved, especially in energy utilization, carbon emissions, energy costs and system efficiency.

[0104] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic simulation optimization method for resource allocation based on energy condition constraints, characterized in that: The following steps are involved: Step 1: Deploy sensor networks and data collection systems to monitor energy supply conditions and consumption patterns in real time and collect data in multiple dimensions; Step 2: Clean and analyze the collected data to generate a dynamic energy condition report, which includes energy supply and demand forecasts, energy price fluctuations, and carbon emission intensity information; Step 3: Build a dynamic simulation model for resource allocation based on the collected data and reports, and adjust model parameters and boundary conditions based on the dynamic energy condition report generated in real time; Step 4: Process the adaptive weight adjustment algorithm according to the model parameters and boundary conditions, and automatically adjust the priority of various resource allocations based on the dynamic energy condition report; Step 5: Repeatedly run simulation experiments on the dynamic simulation model through dynamic iterative optimization, and correct the results according to the latest energy conditions until convergence to the optimal solution to obtain the optimization result; Step 6: Adjust the power generation plan according to the optimization results, optimize the energy storage system charging and discharging strategy, and guide user-side demand response.

2. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 1, the energy supply status includes power generation, grid load and energy storage status, the consumption mode includes user power consumption and equipment operation status, the sensor network includes distributed smart meters, power sensors and environmental monitoring equipment, the data acquisition system includes power generation, grid load, energy storage status, user power consumption and equipment operation status, and uploads the data to the edge computing node for preprocessing and storage.

3. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 2, the dynamic energy condition report includes: Energy supply and demand forecast information, which is used to describe changes in energy supply and demand over a period of time in the future; Energy price fluctuation information, used to predict energy market price trends; Carbon intensity information is used to quantify carbon emissions from energy production and consumption.

4. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 3, the dynamic simulation model uses a system dynamics method or an agent modeling method to simulate the dynamic interaction between power generation, energy storage, transmission and distribution, and demand in the energy system.

5. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: The model parameters in step 3 include energy conversion efficiency, resource demand and price fluctuation sensitivity coefficient; the boundary conditions include maximum energy supply, energy storage capacity limit and carbon emission threshold.

6. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 4, the priority adjustment rules of the adaptive weight adjustment algorithm include: When renewable energy is in sufficient supply, clean energy will be allocated first; When energy supply is tight, energy storage resources are used first; Dynamically adjust the allocation weight of high-cost energy according to energy price fluctuations.

7. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 5, the dynamic iterative optimization performs parameter optimization through Monte Carlo simulation or genetic algorithm, and updates the energy condition constraints in the simulation model after each iteration until the resource allocation solution meets the preset convergence conditions.

8. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1 is characterized in that: In step 6, resource allocation scheduling includes: Adjust the proportion of thermal power, hydropower and renewable energy in power generation; Optimize the charging and discharging timing of the energy storage system to balance peak and valley loads; Guide users to adjust their electricity demand through price signals or incentive mechanisms.

9. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1, characterized in that: In step 5, the construction of the dynamic iterative optimization objective function includes the following steps: Calculate the production cost weights of different energy types based on the energy price fluctuation information in the dynamic energy condition report; According to the carbon emission intensity information, the carbon emission is converted into a penalty cost coefficient; Combine the charging and discharging efficiency and historical loss data of the energy storage system to establish an energy storage loss cost model; The goal is to minimize the total cost.

10. The method for dynamic simulation optimization of resource allocation based on energy condition constraints according to claim 1, characterized in that: In step 6, the demand response scheduling includes dynamically adjusting the power load in different time periods according to the prediction of the user's power consumption behavior, and achieving the balance of the user's power demand through a real-time feedback mechanism.

Images