Dispatching method of biomass energy multi-energy utilization system
By building a biomass energy conversion model and multi-energy intelligent system, the problems of insufficient dynamic adjustment and incomplete energy efficiency optimization in traditional scheduling methods are solved, and efficient scheduling and resource optimization of biomass energy multi-energy system are achieved.
Patent Information
- Application Number
- CN202411192245.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional biomass energy multi-energy system scheduling methods have problems such as insufficient dynamic adjustment capabilities, insufficient energy efficiency optimization and limited data utilization, which is difficult to deal with dynamic changes in energy supply and demand, and a single local optimization ignores the overall benefits of the system.
By obtaining energy type data, building a biomass energy conversion model, obtaining energy set joint regulation data for energy equipment linkage processing, using a multi-energy reinforcement learning system to optimize and process the multi-energy regulation incentive data, generating a multi-energy intelligent system, and consuming The material energy multi-energy scheduling scheme strategy evaluates the degree of guarantee and utilization.
The dynamic scheduling optimization of the biomass energy multi-energy utilization system has been achieved, the overall efficiency and energy efficiency of the system have been improved, the adaptability to complex environments has been enhanced, and the scientificity and feasibility of the scheduling strategy has been improved through intelligent support.
Smart Images

Figure CN119090217A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of multi-energy utilization system scheduling, and in particular to a biomass energy multi-energy utilization system scheduling method. Background Art
[0002] In the current energy system, biomass energy, as a renewable energy source, has gradually gained attention and together with other energy forms such as solar energy, wind energy and traditional fossil energy, has formed a multi-energy system. The biomass multi-energy utilization system aims to optimize the overall energy utilization efficiency and reduce environmental impact by comprehensively utilizing multiple energy forms. However, in practical applications, such systems face some significant challenges. Traditional multi-energy system scheduling methods usually rely on fixed scheduling strategies and static models, which are optimized based on simplified assumptions and historical data. However, traditional biomass multi-energy system scheduling methods have problems such as insufficient dynamic adjustment capabilities, insufficient energy efficiency optimization and limited data utilization. Specifically, fixed scheduling rules are difficult to cope with the dynamic changes in energy supply and demand, single local optimization ignores the overall benefits of the system, and simple data analysis fails to fully explore and utilize the real-time and historical data of multiple energy sources. These deficiencies limit the flexibility, overall energy efficiency and accuracy of scheduling strategies. Summary of the invention
[0003] Based on this, it is necessary to provide a biomass energy multi-energy utilization system scheduling method to solve at least one of the above technical problems.
[0004] To achieve the above object, a biomass energy multi-energy utilization system scheduling method is provided, the method comprising the following steps:
[0005] Step S1: Obtain energy type data, and construct a biomass energy conversion model according to the energy type data;
[0006] Step S2: Acquire energy set joint control data; perform energy equipment linkage processing on the energy set joint control data to generate energy equipment linkage data; perform multi-energy control incentive calculation on the energy equipment linkage data to generate multi-energy control incentive data;
[0007] Step S3: Performing learning system optimization processing on the multi-energy regulation incentive data through a preset multi-energy reinforcement learning system to generate a multi-energy intelligent system; using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy;
[0008] Step S4: Perform biomass energy security level assessment on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
[0009] The beneficial effect of the present invention is that by acquiring energy type data and constructing a biomass energy conversion model, the accuracy of the energy conversion process and the operability of the model are ensured. This lays a solid foundation for subsequent data processing and scheduling optimization. The acquisition of energy set joint control data and the linkage processing of energy equipment, and further the incentive data generated by multi-energy control incentive calculation, realize the coordinated optimization between different energy sources. This collaborative optimization not only improves the overall efficiency of the system, but also ensures the linkage and mutual cooperation of various types of energy equipment, and provides necessary data support for the subsequent generation of scheduling strategies. Subsequently, the multi-energy control incentive data is optimized by the multi-energy reinforcement learning system, and the generated multi-energy intelligent system can dynamically adapt to different scheduling requirements and continuously optimize and improve itself in practical applications. This optimization processing by the learning system not only enhances the system's adaptability to complex environments, but also provides intelligent support for the generation of scheduling strategies for biomass energy conversion models. Finally, by evaluating the degree of security and utilization of the biomass energy multi-energy scheduling scheme strategy, the system can accurately judge the feasibility of the scheduling scheme and the efficiency of resource utilization based on data, thereby effectively completing the scheduling optimization of the biomass energy multi-energy utilization system. Therefore, the present invention solves the problems of insufficient dynamic adjustment, incomplete energy efficiency optimization and insufficient data utilization of traditional scheduling methods by introducing dynamic scheduling algorithms, comprehensive energy efficiency optimization and advanced data analysis technology, thereby improving the flexibility and overall energy efficiency of the system.
[0010] Preferably, step S1 comprises the following steps:
[0011] Step S11: Acquire energy type data and regional biomass resource distribution data;
[0012] Step S12: Modeling is performed according to the energy type data through the input-output analysis method, thereby constructing a regional biomass energy balance model;
[0013] Step S13: Generate biomass combustion energy release data, biomass energy conversion efficiency data and biomass gasification product prediction data through combustion chemical kinetics analysis, energy conversion efficiency calculation and thermochemical conversion analysis according to the regional biomass resource distribution data;
[0014] Step S14: using the regional biomass energy balance model to perform parameter calibration processing on the biomass combustion energy release data, the biomass energy conversion efficiency data and the biomass gasification product prediction data, thereby generating biomass energy conversion calibration information;
[0015] Step S15: construct a biomass energy conversion model based on the biomass energy conversion calibration information to generate a biomass energy conversion model.
[0016] The present invention provides key basic data for the entire modeling and analysis process by obtaining energy type data and regional biomass resource distribution data. These data not only reflect the types and distribution of biomass resources available in the region, but also provide basic input for subsequent modeling and analysis. The input-output analysis method is used for modeling, and a regional biomass energy balance model is constructed. This process not only realizes the theoretical framework of the model through scientific analysis of energy type data, but also provides a reliable reference framework for subsequent energy conversion efficiency and combustion analysis. By using combustion chemical kinetics analysis, energy conversion efficiency calculation and thermochemical conversion analysis, biomass combustion energy release data, biomass energy conversion efficiency data and biomass gasification product prediction data are further generated. These data are obtained through sophisticated analysis methods, which greatly improves the accuracy and scientificity of the biomass energy conversion process. The regional biomass energy balance model is used to perform parameter calibration processing on the above-generated data, and biomass energy conversion calibration information is generated through mutual verification and optimization calibration between data. This calibration information not only improves the accuracy of the data, but also lays a solid data foundation for the final energy conversion model construction. Finally, based on the aforementioned calibration information, a biomass energy conversion model is successfully constructed. The construction of this model, supported by multi-level data calibration and analysis, not only reflects the accuracy and reliability of the model, but also provides important theoretical basis and data support for the efficient utilization of regional biomass energy.
[0017] Preferably, step S2 comprises the following steps:
[0018] Step S21: Acquire energy set joint control data;
[0019] Step S22: performing load balancing adjustment on the energy set joint control data according to the control rules to generate biomass energy load demand data;
[0020] Step S23: Perform energy cost tracing analysis on the biomass energy load demand data to generate energy cost tracing data; use particle swarm optimization technology to perform multi-energy regulation incentive calculation on the energy cost tracing data to generate multi-energy regulation incentive data.
[0021] The present invention ensures the basic data source of the entire control process by obtaining energy set joint control data. These data reflect the joint operation status of the multi-energy system under different conditions, and provide real and reliable input for subsequent load balancing adjustment. By adjusting the energy set joint control data for load balancing according to the control rules, biomass energy load demand data is generated. This process realizes the dynamic balance of loads between different energy sources through the application of control rules, effectively avoids excessive consumption of resources and unnecessary energy waste, and ensures the stable operation of the biomass energy system. Energy cost tracing analysis is performed on the biomass energy load demand data to further generate energy cost tracing data. This analysis not only reveals the cost structure of biomass energy load demand, but also provides a key cost basis for subsequent optimization. Multi-energy control incentive calculation is performed on energy cost tracing data using particle swarm optimization technology to generate multi-energy control incentive data. This optimization process not only improves the accuracy and efficiency of control incentives through the application of advanced algorithms, but also ensures the economy and stability of multi-energy systems in complex environments. The beneficial effect of this series of steps is that through accurate data acquisition, load balancing adjustment, cost tracing analysis and the application of optimization algorithms, efficient regulation and cost optimization of biomass energy load demand are successfully achieved.
[0022] Preferably, step S22 includes the following steps:
[0023] Step S221: dividing the activation priority of the energy set joint control data according to efficiency and response speed, and generating high activation priority devices and low activation priority devices;
[0024] Step S222: using the pre-scheduling load pre-distribution method to predict the load demand of the high-activation priority equipment and generate predicted load demand data; performing load pre-distribution on the predicted load demand data and generating high-activation equipment load pre-distribution data;
[0025] Step S223: using the sleep smoothing allocation method to determine the sleep priority of the low enablement priority device, and generating sleep determination data of the low enablement priority device; based on the sleep determination data of the low enablement priority device, gradually put the low enablement priority device into sleep mode, and generate sleep data of the low enablement device;
[0026] Step S224: Obtain total load demand data; perform energy equipment linkage processing on high-enabled equipment load pre-allocation data and low-enabled equipment sleep data to generate energy equipment linkage data; perform load balancing adjustment on energy equipment linkage data based on total load demand data to generate biomass energy load demand data.
[0027] The present invention divides the activation priority of the energy set joint control data according to efficiency and response speed to generate high activation priority devices and low activation priority devices. This step not only ensures that the system can respond to the demand quickly when the efficient devices are enabled first, but also provides a data basis for the dormancy of inefficient devices by scientifically dividing the priorities of the devices. The pre-scheduling load pre-distribution method is used to predict the load demand of the high activation priority devices, generate predicted load demand data, and perform load pre-distribution on these data to generate high activation device load pre-distribution data. This process ensures the rationality and efficiency of load distribution by accurately predicting the load demand of high priority devices, thereby maximizing the response efficiency of the system. In addition, step S223 determines the sleep priority of the low activation priority devices through the sleep smoothing distribution method, and generates sleep determination data of the low activation priority devices. Based on these data, the low activation priority devices are gradually put to sleep, and the sleep data of the low activation devices are generated, which not only avoids unnecessary energy consumption, but also realizes the smooth load distribution of the system through the gradual sleep strategy, further improving the overall energy efficiency. Finally, the total load demand data is obtained, and the load pre-allocation data of high-activation equipment and the sleep data of low-activation equipment are processed in energy equipment linkage to generate energy equipment linkage data; based on the total load demand data, the energy equipment linkage data is load balanced and adjusted to generate biomass energy load demand data. This step finally achieves balanced distribution of system load by comprehensively considering the load demand of high-priority equipment and the sleep state of low-priority equipment.
[0028] Preferably, step S3 comprises the following steps:
[0029] Step S31: extracting historical characteristic data from energy type data to obtain historical utilization characteristic data of biomass energy;
[0030] Step S32: Use the historical utilization feature data of biomass energy to build a reinforcement learning system to generate a multi-energy reinforcement learning system; use the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system;
[0031] Step S33: Utilize the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy.
[0032] The present invention obtains biomass energy historical utilization characteristic data by tracing and extracting historical characteristic data of energy type data. This step extracts key features by analyzing historical data, which not only provides accurate data support for subsequent model construction, but also ensures that the system has a deep understanding of the biomass energy utilization mode, thereby laying a solid foundation for optimized scheduling. The reinforcement learning system is constructed using the biomass energy historical utilization characteristic data, and a multi-energy reinforcement learning system is generated. This process introduces reinforcement learning technology to enable the system to self-adjust and optimize based on historical data, and continuously improve its adaptability to complex energy regulation scenarios. At the same time, the multi-energy reinforcement learning system generates a multi-energy intelligent system by self-adjusting the learning parameters of the multi-energy regulation incentive data. Through this parameter self-adjustment mechanism, the system can gradually optimize the regulation strategy during operation, enhance its response speed and accuracy under different environments, and further improve the overall intelligence level of the multi-energy system. The multi-energy intelligent system is used to generate a scheduling strategy for the biomass energy conversion model, and finally a biomass energy multi-energy scheduling plan strategy is generated. By applying the intelligent system to the generation of actual scheduling strategies, the system can dynamically adjust based on real-time data to ensure the rationality and effectiveness of the scheduling plan.
[0033] Preferably, step S32 includes the following steps:
[0034] Step S321: constructing a regularity and correlation feature space for the biomass energy historical utilization feature data, and generating a historical utilization two-dimensional data coordinate graph;
[0035] Step S322: Acquire actual energy utilization characteristic data; perform point-to-point fitting analysis on the historical utilization two-dimensional data coordinate graph using the actual energy utilization characteristic data to generate multi-energy utilization related data; construct a reinforcement learning system for the multi-energy utilization related data to generate a multi-energy reinforcement learning system;
[0036] Step S323: Utilize the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system.
[0037] The present invention constructs a regularity and correlation feature space for the historical utilization feature data of biomass energy, and generates a historical utilization two-dimensional data coordinate map. This step presents its regularity and correlation in a visual way through a systematic analysis of historical data, which not only makes the structure of the data clearer, but also provides an intuitive reference framework for subsequent analysis and model construction. The actual energy utilization feature data are obtained, and these data are used to perform point-to-point fitting analysis on the historical utilization two-dimensional data coordinate map to generate multi-energy utilization related data. This process reveals the deep correlation between the actual data and the historical data by accurately matching the actual data with the historical data. This fitting analysis not only ensures efficient linkage between the data, but also improves the system's understanding of the multi-energy utilization mode, thereby providing key correlation data support for the construction of the reinforcement learning system. Based on this, the multi-energy utilization related data is used to build a reinforcement learning system to generate a multi-energy reinforcement learning system. This reinforcement learning system can dynamically adapt to the changing energy regulation needs through deep learning and self-optimization of the associated data, and improves the system's coping ability and efficiency in complex scenarios. Finally, the multi-energy reinforcement learning system is used to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system. Through this self-adjustment of learning parameters, the system can continuously optimize its control strategy in actual operation to ensure the accuracy and efficiency of scheduling.
[0038] Preferably, step S33 includes the following steps:
[0039] Step S331: Using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model, generating a biomass energy multi-energy scheduling plan strategy; using the preset multi-dimensional evaluation criteria to divide the biomass energy multi-energy scheduling plan strategy, generating an energy efficiency priority strategy and an environmental impact minimization strategy;
[0040] Step S332: When the energy efficiency priority strategy is classified, the conversion rate and loss rate are extracted from the historical utilization characteristic data of biomass energy, and the optimal working range of the conversion rate and loss rate is predicted by energy efficiency curve fitting to generate the optimal working range data; the energy allocation ratio is dynamically adjusted for the optimal working range data and the actual energy utilization characteristic data, thereby completing the energy efficiency priority strategy;
[0041] Step S333: When it is classified as the environmental impact minimization strategy, the energy type traceability is performed on the biomass energy conversion model to generate biomass energy traceability type data; carbon capture simulation is performed on the biomass energy traceability type data to generate biomass energy carbon capture data; and the biomass energy carbon capture data is used with carbon priority emission priority, thereby completing the environmental impact minimization strategy.
[0042] The present invention uses a multi-energy intelligent system, and data is used to construct a complex biomass energy conversion model scheduling strategy. This not only improves the adaptability of the system to different energy inputs, but also realizes the refined classification of scheduling schemes, such as energy efficiency priority and environmental impact minimization strategy, through the preset of multi-dimensional evaluation criteria. This data processing method ensures the pertinence and effectiveness of the strategy and reduces the waste of resources caused by blind decision-making. The application of data analysis technology, such as extracting the conversion rate and loss rate from historical data and predicting through energy efficiency curve fitting, provides the optimal working range for biomass energy utilization. This process uses statistical and data science methods to make energy allocation decisions based on scientific analysis, significantly improving the efficiency of energy utilization. The operation of dynamically adjusting the energy allocation ratio, based on real-time data feedback, ensures that the system can self-optimize according to actual conditions, reduces energy waste, and improves the economic benefits of the overall system. Focusing on minimizing environmental impact, data is used to quantify and manage the environmental footprint of biomass energy through energy type traceability tracking and carbon capture simulation. This strategy not only realizes accurate tracking and estimation of carbon emissions at the data level, but also promotes the application of low-carbon energy technology through the implementation of carbon priority emission strategy. Such a data-driven approach enables the quantitative assessment and implementation of environmental protection measures, thereby reducing the negative impact on the environment during energy utilization.
[0043] Preferably, step S4 comprises the following steps:
[0044] Step S41: collecting biomass energy security data for the biomass energy multi-energy scheduling strategy to obtain a biomass energy security data set; generating a data set analysis report for the biomass energy security data set to generate a biomass energy security data set analysis report;
[0045] Step S42: Performing a biomass energy security level assessment process on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information;
[0046] Step S43: Perform scheduling efficiency analysis on the biomass energy security data set analysis report and the biomass energy multi-energy utilization degree assessment information to generate biomass energy multi-energy utilization system scheduling efficiency data, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
[0047] The present invention collects and analyzes biomass energy security data, and the generated biomass energy security data set and its analysis report lay a solid data foundation for subsequent evaluation and optimization. The generation of the biomass energy security data set and the generation of the analysis report can provide detailed data on the current operating status of the system, including key information such as the availability, distribution and potential utilization of resources. This data-driven analysis report can not only reveal the bottlenecks and deficiencies in the system, but also provide data support for the improvement of the scheduling strategy. Through the evaluation of the biomass energy multi-energy scheduling scheme, the generated biomass energy multi-energy utilization degree evaluation information further deepens the understanding of the system utilization degree. This evaluation process can quantify the actual contribution of biomass energy in the multi-energy system, evaluate its impact on the overall energy utilization efficiency, and identify the improvement points. This quantitative evaluation information can help decision makers identify and optimize the synergistic effect between biomass energy and other energy forms, thereby improving the overall energy utilization efficiency of the system. Through the scheduling efficiency analysis, the biomass energy security data set analysis report generated in the above steps and the utilization degree evaluation information are combined to generate the scheduling efficiency data of the biomass energy multi-energy utilization system. This process aims to find the best scheduling strategy through comprehensive analysis to maximize the overall efficiency of the system. This optimization process can ensure the efficient and sustainable use of biomass energy in the multi-energy system, while minimizing resource waste and costs, thereby improving the economy and environmental protection of the system.
[0048] Preferably, step S41 includes the following steps:
[0049] Step S411: screening the multi-level data of energy conversion efficiency for the biomass energy security data set to generate high-consumption biomass energy data and low-consumption biomass energy data;
[0050] Step S412: performing cross-comparison analysis on high-consumption biomass energy data and low-consumption biomass energy data to generate biomass energy cross-comparison analysis data; performing energy flow dynamic simulation on the biomass energy cross-comparison analysis data to generate a biomass energy multi-energy utilization data set;
[0051] Step S413: Generate a data set analysis report for the biomass energy multi-energy utilization data set, and generate a biomass energy security data set analysis report.
[0052] The present invention generates high-consumption and low-consumption biomass energy data by performing multi-level data screening of energy conversion efficiency on the biomass energy guarantee data set. This process can effectively distinguish the performance differences of different biomass energy resources in the conversion process. Through this data screening, the system can identify which biomass energy resources have higher consumption characteristics under current conditions and which resources are relatively low-consumption, thereby providing an accurate data basis for subsequent optimization analysis. By performing cross-comparison analysis on high-consumption and low-consumption biomass energy data, the generated biomass energy cross-comparison analysis data can reveal the relationship between different biomass energy resources and their impact on the overall system energy efficiency. This cross-comparison analysis can not only identify potential problems in resource utilization, but also provide a basis for optimizing resource allocation. By performing dynamic simulation of energy flow on the biomass energy cross-comparison analysis data, the generated biomass energy multi-energy utilization data set can simulate the energy flow and conversion process in actual operation. This simulation process helps to predict and evaluate the performance of different resource allocation schemes in actual operation, thereby providing data support for formulating more scientific and reasonable scheduling strategies. The generation of an analysis report on the biomass energy multi-energy utilization data set can further summarize and refine the key performance indicators of the entire system. The generated biomass energy security data set analysis report provides decision makers with a comprehensive and detailed data reference.
[0053] Preferably, step S42 includes the following steps:
[0054] Step S421: quantify the biomass energy multi-energy scheduling strategy using a preset multi-dimensional indicator system to generate a biomass energy multi-energy scheduling quantitative factor, wherein the biomass energy multi-energy scheduling quantitative factor includes an energy conversion efficiency factor, a load balance degree factor, and an equipment response speed factor;
[0055] Step S422: performing efficiency weight matching on the energy conversion efficiency factor and the actual energy utilization characteristic data to generate a biomass energy conversion efficiency factor; performing Fourier curve generation on the load balance degree factor to generate a load balance curve; performing abnormal fluctuation detection on the load balance curve to generate load balance abnormality data; performing Kalman filtering correction on the load balance abnormality data to generate load balance abnormality correction data; performing balance factor generation on the load balance abnormality correction data to generate a biomass energy load balance degree factor; performing response time recording on the equipment response speed factor to generate response time series data; performing slope identification correction on the response time series data to generate response time series correction data; performing equipment response time factor generation on the response time series correction data to generate a biomass energy equipment response speed factor;
[0056] Step S423: performing a weight difference comparison analysis on the biomass energy conversion efficiency factor, the biomass energy load balance factor and the biomass energy equipment response speed factor to generate biomass energy multi-energy utilization weight data;
[0057] Step S424: Perform biomass energy security level assessment processing on the biomass energy multi-energy utilization weight data to generate biomass energy multi-energy utilization level assessment information.
[0058] The present invention quantifies the biomass energy multi-energy scheduling strategy through a preset multi-dimensional index system, and the generated quantitative factors include energy conversion efficiency factor, load balance degree factor and equipment response speed factor. These factors quantify the key performance indicators of the system from different dimensions, and provide a multi-dimensional data basis for subsequent refined analysis. This process can ensure the comprehensiveness and multi-dimensionality of the scheduling scheme evaluation, thereby providing a more accurate basis for optimization. The energy conversion efficiency factor is matched with the actual energy utilization characteristic data by efficiency weight, and the generated biomass energy conversion efficiency factor can reflect the actual efficiency of the energy in the conversion process. Through weight matching, the accuracy and representativeness of the energy conversion efficiency factor are ensured. The generation and correction process of the load balance degree factor ensures the stability and accuracy of the load balance data through Fourier curve generation, abnormal fluctuation detection and Kalman filter correction. This complex data processing process can effectively filter out abnormal fluctuations and noise in the system, and provide high-quality data input for the subsequent generation of balance factors. The generation of the equipment response speed factor also ensures the accuracy of the equipment response time data by identifying and correcting the slope of the response time series data, which is of great significance for the evaluation of the response capability of the system under dynamic conditions. By benchmarking the weight differences of the multiple factors generated above, the generated biomass energy multi-energy utilization weight data can comprehensively reflect the contribution of each factor to the overall performance of the system. This process can not only reveal the relative importance of each factor, but also provide a clear direction for the optimization of the system. Finally, by evaluating the biomass energy collection guarantee degree of the biomass energy multi-energy utilization weight data, the generated biomass energy multi-energy utilization degree evaluation information provides a scientific basis for the overall scheduling optimization of the system. This evaluation process can ensure that in actual applications, the system can achieve the best resource allocation and utilization effect, thereby maximizing the utilization efficiency of biomass energy and the overall effectiveness of the system.
[0059] The beneficial effect of the present invention is that by acquiring energy type data and constructing a biomass energy conversion model, the accuracy of the energy conversion process and the operability of the model are ensured. This lays a solid foundation for subsequent data processing and scheduling optimization. The acquisition of energy set joint control data and the linkage processing of energy equipment, and further the incentive data generated by multi-energy control incentive calculation, realize the coordinated optimization between different energy sources. This collaborative optimization not only improves the overall efficiency of the system, but also ensures the linkage and mutual cooperation of various types of energy equipment, and provides necessary data support for the subsequent generation of scheduling strategies. Subsequently, the multi-energy control incentive data is optimized by the multi-energy reinforcement learning system, and the generated multi-energy intelligent system can dynamically adapt to different scheduling requirements and continuously optimize and improve itself in practical applications. This optimization processing by the learning system not only enhances the system's adaptability to complex environments, but also provides intelligent support for the generation of scheduling strategies for biomass energy conversion models. Finally, by evaluating the degree of security and utilization of the biomass energy multi-energy scheduling scheme strategy, the system can accurately judge the feasibility of the scheduling scheme and the efficiency of resource utilization based on data, thereby effectively completing the scheduling optimization of the biomass energy multi-energy utilization system. Therefore, the present invention solves the problems of insufficient dynamic adjustment, incomplete energy efficiency optimization and insufficient data utilization of traditional scheduling methods by introducing dynamic scheduling algorithms, comprehensive energy efficiency optimization and advanced data analysis technology, thereby improving the flexibility and overall energy efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 A schematic diagram of the steps of a biomass multi-energy utilization system scheduling method;
[0061] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;
[0062] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.
[0063] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.
[0064] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0065] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0066] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0067] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0068] To achieve this, please refer to Figures 1 to 4 , a biomass energy multi-energy utilization system scheduling method, the method comprising the following steps:
[0069] Step S1: Obtain energy type data, and construct a biomass energy conversion model according to the energy type data;
[0070] Step S2: Acquire energy set joint control data; perform energy equipment linkage processing on the energy set joint control data to generate energy equipment linkage data; perform multi-energy control incentive calculation on the energy equipment linkage data to generate multi-energy control incentive data;
[0071] Step S3: Performing learning system optimization processing on the multi-energy regulation incentive data through a preset multi-energy reinforcement learning system to generate a multi-energy intelligent system; using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy;
[0072] Step S4: Perform biomass energy security level assessment on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
[0073] The beneficial effect of the present invention is that by acquiring energy type data and constructing a biomass energy conversion model, the accuracy of the energy conversion process and the operability of the model are ensured. This lays a solid foundation for subsequent data processing and scheduling optimization. The acquisition of energy set joint control data and the linkage processing of energy equipment, and further the incentive data generated by multi-energy control incentive calculation, realize the coordinated optimization between different energy sources. This collaborative optimization not only improves the overall efficiency of the system, but also ensures the linkage and mutual cooperation of various types of energy equipment, and provides necessary data support for the subsequent generation of scheduling strategies. Subsequently, the multi-energy control incentive data is optimized by the multi-energy reinforcement learning system, and the generated multi-energy intelligent system can dynamically adapt to different scheduling requirements and continuously optimize and improve itself in practical applications. This optimization processing by the learning system not only enhances the system's adaptability to complex environments, but also provides intelligent support for the generation of scheduling strategies for biomass energy conversion models. Finally, by evaluating the degree of security and utilization of the biomass energy multi-energy scheduling scheme strategy, the system can accurately judge the feasibility of the scheduling scheme and the efficiency of resource utilization based on data, thereby effectively completing the scheduling optimization of the biomass energy multi-energy utilization system. Therefore, the present invention solves the problems of insufficient dynamic adjustment, incomplete energy efficiency optimization and insufficient data utilization of traditional scheduling methods by introducing dynamic scheduling algorithms, comprehensive energy efficiency optimization and advanced data analysis technology, thereby improving the flexibility and overall energy efficiency of the system.
[0074] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a biomass energy multi-energy utilization system scheduling method of the present invention. In this example, the biomass energy multi-energy utilization system scheduling method includes the following steps:
[0075] Step S1: Obtain energy type data, and construct a biomass energy conversion model according to the energy type data;
[0076] In the embodiment of the present invention, it is necessary to collect and organize data on the types of energy, including information such as the source, classification, and characteristics of biomass energy. These data are obtained from various sources, such as literature, experimental data, and industry reports. The collected data should include, but are not limited to, the type, calorific value, carbon content, hydrogen content, oxygen content, nitrogen content, sulfur content, and other physical and chemical properties of biomass energy, as well as economic and environmental indicators such as the production cost, transportation cost, storage cost, and environmental impact of the biomass energy. On the basis of collecting data, these data are processed and processed using data analysis and modeling techniques, and machine learning algorithms are used to classify and cluster the data to identify the characteristics and patterns of different types of biomass energy. Statistical analysis methods are used to describe and infer the data to understand the basic characteristics and laws of different types of biomass energy. Through the analysis and modeling of data, a biomass energy conversion model is established, which simulates and predicts the energy conversion process and efficiency of different types of biomass energy under different conditions, as well as its impact on the environment and economy. In addition, computer simulation technology is used to simulate and optimize the energy conversion process of biomass energy, and discrete element method, finite element method and other methods are used to simulate and analyze the pyrolysis, gasification, combustion and other processes of biomass energy to optimize the energy conversion efficiency of biomass energy and reduce environmental pollution. Optimization algorithms are used to optimize the production, transportation and storage processes of biomass energy to minimize costs and environmental impacts.
[0077] Step S2: Acquire energy set joint control data; perform energy equipment linkage processing on the energy set joint control data to generate energy equipment linkage data; perform multi-energy control incentive calculation on the energy equipment linkage data to generate multi-energy control incentive data;
[0078] In the embodiment of the present invention, it is necessary to collect and organize data related to the joint regulation of energy sets, including information such as the operating status, load data, and energy consumption data of energy equipment. These data are obtained from various sources, such as energy management systems, smart meters, and sensors. The collected data should include but are not limited to information such as the type, capacity, operating status, energy consumption, and load rate of energy equipment, as well as information such as the total load, total energy consumption, and total efficiency of the energy set. On the basis of collecting data, data fusion technology is used to integrate and process data from different sources, and spatial and temporal correlation analysis methods are used to calibrate and match data to ensure data consistency and accuracy. Data mining technology is used to analyze and process the integrated data, and association rule algorithms are used to discover the relationship between energy equipment to identify the coupling relationship and energy transfer path between different devices. On the basis of analyzing and processing data, a data-driven method is used to link energy equipment, and a state estimation algorithm is used to estimate the state of energy equipment to predict the energy consumption and load changes of the equipment. An optimization algorithm is used to optimize the operation strategy of energy equipment to minimize energy consumption and maximize efficiency. Energy equipment linkage data is generated through energy equipment linkage processing, and these data are used for multi-energy regulation incentive calculation. In the calculation of multi-energy regulation incentives, machine learning algorithms are used to train historical data to build a model for joint regulation of energy sets. The model is used to predict real-time data to calculate multi-energy regulation incentives. These incentives are used to guide the operation and control of energy devices to achieve efficient utilization and optimal regulation of energy sets.
[0079] Step S3: Performing learning system optimization processing on the multi-energy regulation incentive data through a preset multi-energy reinforcement learning system to generate a multi-energy intelligent system; using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy;
[0080] In the embodiment of the present invention, it is necessary to use a reinforcement learning algorithm to learn and optimize the multi-energy regulation incentive data, and use Q learning, deep Q network (DQN) and other algorithms to learn the data to generate a multi-energy intelligent system. These algorithms automatically learn and optimize the multi-energy regulation strategy through trial and error and exploration process to maximize the efficiency of the system and minimize energy consumption. In the reinforcement learning process, it is necessary to define a reward function and a state space to evaluate the performance of the system and guide the learning process. Indicators such as energy consumption, efficiency, and cost are used as reward functions to encourage the system to optimize energy utilization and minimize costs. It is necessary to define a state space to describe the state and behavior of the system, and the operating status, load data, energy consumption data, etc. of the energy equipment are used as the state space. On the basis of the optimization processing of the learning system, a multi-energy intelligent system is used to generate a scheduling strategy for the biomass energy conversion model. The biomass energy conversion model is predicted and optimized using a model predictive control (MPC) algorithm to generate a scheduling strategy. These algorithms generate scheduling strategies in real time through online optimization and prediction to maximize the energy conversion efficiency of biomass energy and minimize energy consumption. In the process of generating the dispatch strategy, it is necessary to define the objective function and constraints to evaluate the pros and cons of the dispatch strategy and meet the needs of the system. The energy conversion efficiency, cost, environmental impact and other indicators of biomass energy are used as the objective function to optimize the dispatch strategy. Constraints need to be defined to meet the needs and limitations of the system, using the capacity and load limit of energy equipment as constraints.
[0081] Step S4: Perform biomass energy security level assessment on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
[0082] In an embodiment of the present invention, it is necessary to use a biomass energy collective security degree assessment model to evaluate the biomass energy multi-energy scheduling plan strategy, and use probability theory and statistical methods to evaluate the reliability and safety of biomass energy to generate biomass energy collective security degree assessment information. These models can predict the supply risk and security capacity of biomass energy through the analysis of historical data and real-time data to evaluate the reliability and effectiveness of the scheduling plan. In the evaluation process, it is necessary to define evaluation indicators and weights to describe different aspects of the biomass energy collective security degree. Indicators such as the supply quantity, quality, reliability, and safety of biomass energy are used as evaluation indicators to comprehensively evaluate the biomass energy collective security degree. At the same time, weights need to be defined to reflect the importance and impact of different indicators. Use methods such as the analytic hierarchy process (AHP) or the entropy weight method to assign weights to indicators to ensure the objectivity and accuracy of the evaluation results. On the basis of the assessment of the degree of biomass energy security, the multi-energy utilization degree assessment model is used to evaluate the degree of biomass energy multi-energy utilization, and the multi-criteria decision analysis method (MCDM) or grey correlation analysis method are used to evaluate the indicators such as energy conversion efficiency, economy, and environmental impact of biomass energy to generate the assessment information of biomass energy multi-energy utilization degree. These models can provide a comprehensive assessment result of the degree of biomass energy multi-energy utilization through a comprehensive assessment of different indicators to guide scheduling optimization and decision-making. In the assessment process, it is necessary to define the assessment criteria and thresholds to describe the different levels of biomass energy multi-energy utilization. Use high, medium, and low assessment criteria to describe the different levels of biomass energy multi-energy utilization. At the same time, it is necessary to define thresholds to determine the validity and reliability of the assessment results.
[0083] Preferably, step S1 comprises the following steps:
[0084] Step S11: Acquire energy type data and regional biomass resource distribution data;
[0085] Step S12: Modeling is performed according to the energy type data through the input-output analysis method, thereby constructing a regional biomass energy balance model;
[0086] Step S13: Generate biomass combustion energy release data, biomass energy conversion efficiency data and biomass gasification product prediction data through combustion chemical kinetics analysis, energy conversion efficiency calculation and thermochemical conversion analysis according to the regional biomass resource distribution data;
[0087] Step S14: using the regional biomass energy balance model to perform parameter calibration processing on the biomass combustion energy release data, the biomass energy conversion efficiency data and the biomass gasification product prediction data, thereby generating biomass energy conversion calibration information;
[0088] Step S15: construct a biomass energy conversion model based on the biomass energy conversion calibration information to generate a biomass energy conversion model.
[0089] In the embodiment of the present invention, energy type data and regional biomass resource distribution data are obtained, which include the geographical distribution, physical and chemical properties of different types of biomass, and the demand and supply of various types of energy. These basic data provide key inputs for subsequent modeling and analysis. Through the input-output analysis method (Input-OutputAnalysis), the acquired energy type data is mathematically modeled to construct a regional biomass energy balance model. The input-output analysis method is mainly used in this application to quantify the conversion relationship and energy flow between different energy forms, ensure the supply and demand balance of various types of biomass resources within the regional scope, and the distribution and loss of energy in different conversion processes. The regional biomass resource distribution data is further processed through combustion chemical kinetic analysis, energy conversion efficiency calculation and thermochemical conversion analysis. These analysis methods are used to predict the energy release of biomass during combustion, calculate the efficiency of biomass energy conversion from one form to another, and predict the products produced by biomass during gasification. This step generates biomass combustion energy release data, biomass energy conversion efficiency data and biomass gasification product prediction data, which provides a basis for subsequent parameter calibration. By integrating the above generated data with the regional biomass energy balance model, the parameters in the model are calibrated using these data to generate more accurate biomass energy conversion calibration information. Parameter calibration is to ensure that the model can accurately reflect the actual energy conversion process and reduce the error between the model prediction and the actual situation. Based on the calibrated biomass energy conversion calibration information, a biomass energy conversion model is constructed. This model integrates data on the distribution of biomass resources, conversion efficiency, combustion and gasification characteristics, and can simulate the conversion process of biomass energy under different conditions.
[0090] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:
[0091] Step S21: Acquire energy set joint control data;
[0092] Step S22: performing load balancing adjustment on the energy set joint control data according to the control rules to generate biomass energy load demand data;
[0093] Step S23: Perform energy cost tracing analysis on the biomass energy load demand data to generate energy cost tracing data; use particle swarm optimization technology to perform multi-energy regulation incentive calculation on the energy cost tracing data to generate multi-energy regulation incentive data.
[0094] In an embodiment of the present invention, energy set joint control data is obtained. These data include coordinated scheduling information, load demand, supply capacity and related control rules and strategies between different energy forms. These data provide basic input for subsequent load balancing and energy cost analysis. The obtained energy set joint control data is load balanced according to predetermined control rules. The purpose of load balancing adjustment is to reasonably distribute load demand among multiple energy forms, ensure the balance of supply and demand of various energy sources, and maximize the overall efficiency of the system. Through this process, biomass energy load demand data is generated, which reflects the demand for biomass energy after balanced adjustment, including load demand in different time periods and corresponding control strategies. The generated biomass energy load demand data is further analyzed for energy cost tracing. Energy cost tracing analysis aims to track the cost structure of different energy forms in the entire supply chain, including cost factors in various links such as production, conversion, transmission and consumption. Through this analysis, energy cost tracing data is generated, which provides an economic basis for further optimization and regulation. Particle swarm optimization (PSO) technology is used to perform multi-energy regulation incentive calculation on energy cost tracing data. Particle swarm optimization technology is an optimization algorithm based on swarm intelligence. It simulates the information exchange and collaborative behavior between individuals in a group to find the optimal solution. In this application, PSO technology is used to find a control strategy that can minimize costs or maximize benefits in a multi-energy system, thereby generating multi-energy control incentive data.
[0095] Preferably, step S22 includes the following steps:
[0096] Step S221: dividing the activation priority of the energy set joint control data according to efficiency and response speed, and generating high activation priority devices and low activation priority devices;
[0097] Step S222: using the pre-scheduling load pre-distribution method to predict the load demand of the high-activation priority equipment and generate predicted load demand data; performing load pre-distribution on the predicted load demand data and generating high-activation equipment load pre-distribution data;
[0098] Step S223: using the sleep smoothing allocation method to determine the sleep priority of the low enablement priority device, and generating sleep determination data of the low enablement priority device; based on the sleep determination data of the low enablement priority device, gradually put the low enablement priority device into sleep mode, and generate sleep data of the low enablement device;
[0099] Step S224: Obtain total load demand data; perform energy equipment linkage processing on high-enabled equipment load pre-allocation data and low-enabled equipment sleep data to generate energy equipment linkage data; perform load balancing adjustment on energy equipment linkage data based on total load demand data to generate biomass energy load demand data.
[0100] In the embodiment of the present invention, the joint control data of the energy set is prioritized according to efficiency and response speed to generate high-activation priority devices and low-activation priority devices. This means that by analyzing the performance and response time of the device, it is determined which devices should be activated first in energy distribution to improve the efficiency and response speed of the overall system. The pre-scheduling load pre-distribution method is used to analyze the predicted load demand of the high-activation priority device and generate corresponding predicted load demand data. The core of this step is to estimate the load demand of the high-priority device in advance so as to meet its demand more accurately in the actual energy distribution. Thereafter, the predicted load demand data is load pre-distributed to generate the load pre-distribution data of the high-activation device. This process ensures that the device can operate according to the expected load in the actual execution, thereby optimizing the use of resources. For the low-activation priority device, the sleep smoothing allocation method is used to determine the sleep priority and generate the sleep determination data of the low-activation priority device. This method determines which devices can enter the sleep state by analyzing the current state of the device and the expected load demand, thereby reducing unnecessary energy consumption. On this basis, the low-activation priority devices are gradually put into sleep mode to generate the sleep data of the low-activation device. This process helps to reduce the overall energy consumption of the system and improve energy utilization. Obtain the total load demand data, and based on this data, perform energy equipment linkage processing on the load pre-allocation data of high-enabled devices and the sleep data of low-enabled devices to generate energy equipment linkage data. This step achieves coordinated operation between energy devices by comprehensively considering the load demand and current status of all devices. Based on the total load demand data, perform load balancing adjustment on the energy equipment linkage data to generate biomass energy load demand data.
[0101] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:
[0102] Step S31: extracting historical characteristic data from energy type data to obtain historical utilization characteristic data of biomass energy;
[0103] Step S32: Use the historical utilization feature data of biomass energy to build a reinforcement learning system to generate a multi-energy reinforcement learning system; use the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system;
[0104] Step S33: Utilize the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy.
[0105] In an embodiment of the present invention, historical characteristic data of biomass energy is extracted by tracing the historical characteristic data of energy type data to obtain historical utilization characteristic data of biomass energy. This process involves an in-depth analysis of the past use of biomass energy, and mining the key utilization characteristics in the historical data, thereby providing important basic data for subsequent model construction and optimization. This data extraction includes not only the analysis of energy usage, but also the consideration of usage time, usage efficiency and related environmental factors, aiming to build a comprehensive historical utilization feature set. The extracted historical utilization characteristic data of biomass energy is used to construct a reinforcement learning system to generate a multi-energy reinforcement learning system. The reinforcement learning system learns and optimizes multi-energy regulation strategies by simulating different energy utilization scenarios. Through trial and learning in different scenarios, it can gradually adjust the learning parameters of the system to achieve the optimal energy regulation strategy. In addition, the system is also combined with multi-energy regulation incentive data to generate a multi-energy intelligent system by self-adjusting learning parameters. This process utilizes the adaptability and optimization capabilities of reinforcement learning, enabling the system to dynamically adapt to changing energy environments and needs. The generated multi-energy intelligent system is used to generate scheduling strategies for the biomass energy conversion model, and finally generate a biomass energy multi-energy scheduling strategy. The core of this step is to use the computing power and optimization algorithm of the intelligent system to analyze the current state and demand of biomass energy and formulate the optimal energy scheduling strategy.
[0106] Preferably, step S32 includes the following steps:
[0107] Step S321: constructing a regularity and correlation feature space for the biomass energy historical utilization feature data, and generating a historical utilization two-dimensional data coordinate graph;
[0108] Step S322: Acquire actual energy utilization characteristic data; perform point-to-point fitting analysis on the historical utilization two-dimensional data coordinate graph using the actual energy utilization characteristic data to generate multi-energy utilization related data; construct a reinforcement learning system for the multi-energy utilization related data to generate a multi-energy reinforcement learning system;
[0109] Step S323: Utilize the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system.
[0110] In an embodiment of the present invention, the historical utilization characteristic data of biomass energy is first analyzed, and a two-dimensional data coordinate diagram of historical utilization is generated by constructing a regularity and correlation feature space. This process involves in-depth mining of biomass energy historical data, aiming to reveal the inherent laws and relationships therein. By establishing a feature space, complex historical data can be converted into a two-dimensional coordinate diagram that is easy to understand and analyze, so that energy utilization patterns under different time points and conditions can be intuitively represented and compared. The actual energy utilization characteristic data are obtained, and these data are used to perform point-to-point fitting analysis on the historical utilization two-dimensional data coordinate diagram. This step aims to compare the current actual energy usage with historical data, and identify the correlation between the current usage pattern and the historical pattern through fitting analysis. This fitting analysis can not only reveal the deviation between the current energy utilization and the historical trend, but also help identify potential optimization opportunities. Through this analysis, multi-energy utilization correlation data are generated, which reflect the mutual influence and synergy between different energy types. The multi-energy utilization correlation data is used for the construction of a reinforcement learning system to generate a multi-energy reinforcement learning system. The system uses an adaptive algorithm of reinforcement learning to learn how to optimize the efficiency and response speed of energy use in a changing energy environment through continuous trial and feedback. The reinforcement learning system simulates and learns different energy regulation scenarios and adjusts its internal parameters to achieve the optimal regulation strategy. The multi-energy reinforcement learning system is used to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system. This process ensures that the system can dynamically adapt to changes in energy demand and fluctuations in market conditions through continuous self-learning and optimization of the intelligent system, and achieve the optimal configuration and scheduling of energy utilization.
[0111] Preferably, step S33 includes the following steps:
[0112] Step S331: Using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model, generating a biomass energy multi-energy scheduling plan strategy; using the preset multi-dimensional evaluation criteria to divide the biomass energy multi-energy scheduling plan strategy, generating an energy efficiency priority strategy and an environmental impact minimization strategy;
[0113] Step S332: When the energy efficiency priority strategy is classified, the conversion rate and loss rate are extracted from the historical utilization characteristic data of biomass energy, and the optimal working range of the conversion rate and loss rate is predicted by energy efficiency curve fitting to generate the optimal working range data; the energy allocation ratio is dynamically adjusted for the optimal working range data and the actual energy utilization characteristic data, thereby completing the energy efficiency priority strategy;
[0114] Step S333: When it is classified as the environmental impact minimization strategy, the energy type traceability is performed on the biomass energy conversion model to generate biomass energy traceability type data; carbon capture simulation is performed on the biomass energy traceability type data to generate biomass energy carbon capture data; and the biomass energy carbon capture data is used with carbon priority emission priority, thereby completing the environmental impact minimization strategy.
[0115] In an embodiment of the present invention, a multi-energy intelligent system is used to generate a scheduling strategy for a biomass energy conversion model, thereby generating a biomass energy multi-energy scheduling strategy. This process uses the computing power of the intelligent system to analyze and optimize the use of biomass energy in a multi-energy system, and the generated scheduling scheme not only takes into account the satisfaction of energy demand, but also takes into account the overall efficiency of system operation. The generated scheduling strategy is divided by applying a preset multi-dimensional evaluation standard, thereby forming an energy efficiency priority strategy and an environmental impact minimization strategy. These standards include multiple dimensions such as energy conversion efficiency, environmental emission indicators, and economic costs to ensure that the scheduling scheme can adapt to different optimization goals. When the scheduling strategy is divided into an energy efficiency priority strategy, key indicators such as conversion rate and loss rate are extracted from the historical utilization characteristic data of biomass energy. Through energy efficiency curve fitting, the optimal working range of these indicators is predicted to generate optimal working range data. The fitting process identifies the optimal conversion and operation range of biomass energy under different conditions through the combination of historical data and mathematical models, providing data support for subsequent energy allocation. Next, the energy allocation ratio is dynamically adjusted for the optimal working range data and the actual energy utilization characteristic data, thereby realizing the implementation of the energy efficiency priority strategy. This step involves dynamic adjustment and optimization to ensure that it always remains within the optimal working range in actual operation and improves the overall energy utilization efficiency. At this point, the energy type of the biomass energy conversion model is traced to generate biomass energy traceability type data. This tracking process provides basic data for subsequent environmental impact assessments by identifying and recording the source and conversion path of biomass energy. Next, the biomass energy traceability type data is simulated for carbon capture to generate biomass energy carbon capture data. This process simulates carbon emissions and capture under different conditions to evaluate and optimize the environmental impact of biomass energy. Finally, the biomass energy carbon capture data is used with carbon priority emission priority to complete the environmental impact minimization strategy.
[0116] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:
[0117] Step S41: collecting biomass energy security data for the biomass energy multi-energy scheduling strategy to obtain a biomass energy security data set; generating a data set analysis report for the biomass energy security data set to generate a biomass energy security data set analysis report;
[0118] Step S42: Performing a biomass energy security level assessment process on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information;
[0119] Step S43: Perform scheduling efficiency analysis on the biomass energy security data set analysis report and the biomass energy multi-energy utilization degree assessment information to generate biomass energy multi-energy utilization system scheduling efficiency data, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
[0120] In an embodiment of the present invention, the biomass energy security data of the biomass energy multi-energy scheduling scheme strategy is collected to form a biomass energy security data set. This process involves extracting data related to the use of biomass energy from the scheduling strategy actually in operation, including but not limited to key information such as energy output, supply stability, and storage capacity. The systematic collection of these data makes the subsequent analysis more targeted and accurate. The data set analysis report is generated for the biomass energy security data set to generate a biomass energy security data set analysis report. This step reveals the security capability and potential risks of biomass energy in a multi-energy system through statistical analysis and pattern recognition of the data set, and provides detailed report support for decision-making. For the biomass energy multi-energy scheduling scheme strategy, the biomass energy set security degree is evaluated and processed to generate biomass energy multi-energy utilization degree evaluation information. This step identifies bottlenecks and room for improvement by evaluating the contribution, stability, and supply capacity of biomass energy in the entire energy system. The evaluation process involves a comprehensive analysis of multiple indicators, such as the availability, flexibility, and supply risk of biomass energy, in order to fully understand its actual performance in the multi-energy system. The above-mentioned biomass energy security data set analysis report and biomass energy multi-energy utilization evaluation information are used for scheduling efficiency analysis to generate biomass energy multi-energy utilization system scheduling efficiency data. This analysis integrates the dual perspectives of security capability and utilization, and evaluates the efficiency and effectiveness of the current scheduling strategy through data mining and model calculation. By identifying deficiencies and optimization opportunities in the scheduling strategy, the generated scheduling efficiency data provides a data-driven decision-making basis for scheduling optimization. Based on these optimization suggestions, the scheduling strategy of biomass energy in the multi-energy system can be adjusted and improved, thereby improving the overall scheduling efficiency of the system.
[0121] Preferably, step S41 includes the following steps:
[0122] Step S411: screening the multi-level data of energy conversion efficiency for the biomass energy security data set to generate high-consumption biomass energy data and low-consumption biomass energy data;
[0123] Step S412: performing cross-comparison analysis on high-consumption biomass energy data and low-consumption biomass energy data to generate biomass energy cross-comparison analysis data; performing energy flow dynamic simulation on the biomass energy cross-comparison analysis data to generate a biomass energy multi-energy utilization data set;
[0124] Step S413: Generate a data set analysis report for the biomass energy multi-energy utilization data set, and generate a biomass energy security data set analysis report.
[0125] In an embodiment of the present invention, a multi-level data screening of energy conversion efficiency is performed on a biomass energy guarantee data set. This process aims to extract high-consumption and low-consumption biomass energy data through screening technology. Multi-level data screening involves classifying and filtering data at different levels and dimensions to identify biomass energy components or systems that exhibit high-consumption and low-consumption characteristics during energy conversion. The purpose of this is to more accurately identify and distinguish the efficiency differences in energy utilization, thereby providing a more targeted data basis for subsequent analysis. Cross-comparison analysis is performed on high-consumption biomass energy data and low-consumption biomass energy data to generate biomass energy cross-comparison analysis data. Cross-comparison analysis reveals the differences and commonalities between different energy consumption patterns through a comprehensive comparison of high and low consumption data. This analysis not only helps to understand the performance of biomass energy under different conditions, but also identifies improved energy efficiency strategies and optimization directions. Subsequently, a dynamic simulation of energy flow is performed on the biomass energy cross-comparison analysis data to generate a biomass energy multi-energy utilization data set. Dynamic simulation simulates the energy flow process of biomass energy in different scenarios, and analyzes the flow path and efficiency changes of energy within the system through modeling and simulation technology. This simulation helps to identify bottlenecks and potential optimization nodes in energy flow, thus providing a scientific basis for improving the overall performance of the system. Generate a data set analysis report for the biomass energy multi-energy utilization data set, and generate a biomass energy security data set analysis report. This report combines the results of screening, comparative analysis and dynamic simulation, and comprehensively evaluates the utilization efficiency, flow characteristics and optimization potential of biomass energy.
[0126] Preferably, step S42 includes the following steps:
[0127] Step S421: quantify the biomass energy multi-energy scheduling strategy using a preset multi-dimensional indicator system to generate a biomass energy multi-energy scheduling quantitative factor, wherein the biomass energy multi-energy scheduling quantitative factor includes an energy conversion efficiency factor, a load balance degree factor, and an equipment response speed factor;
[0128] Step S422: performing efficiency weight matching on the energy conversion efficiency factor and the actual energy utilization characteristic data to generate a biomass energy conversion efficiency factor; performing Fourier curve generation on the load balance degree factor to generate a load balance curve; performing abnormal fluctuation detection on the load balance curve to generate load balance abnormality data; performing Kalman filtering correction on the load balance abnormality data to generate load balance abnormality correction data; performing balance factor generation on the load balance abnormality correction data to generate a biomass energy load balance degree factor; performing response time recording on the equipment response speed factor to generate response time series data; performing slope identification correction on the response time series data to generate response time series correction data; performing equipment response time factor generation on the response time series correction data to generate a biomass energy equipment response speed factor;
[0129] Step S423: performing a weight difference comparison analysis on the biomass energy conversion efficiency factor, the biomass energy load balance factor and the biomass energy equipment response speed factor to generate biomass energy multi-energy utilization weight data;
[0130] Step S424: Perform biomass energy security level assessment processing on the biomass energy multi-energy utilization weight data to generate biomass energy multi-energy utilization level assessment information.
[0131] In an embodiment of the present invention, a preset multidimensional index system is used to quantify the multidimensional index of the biomass energy multi-energy scheduling scheme strategy, and generate a biomass energy multi-energy scheduling quantification factor. These factors include energy conversion efficiency factor, load balance degree factor, and equipment response speed factor, each of which reflects the performance of the system in different performance dimensions. The core of multidimensional index quantification is to convert abstract performance indicators into quantifiable numerical factors, providing a basis for subsequent data analysis and optimization. The energy conversion efficiency factor is matched with the actual energy utilization characteristic data by efficiency weight to generate a biomass energy conversion efficiency factor. This process evaluates the energy conversion efficiency of the current system by weight matching the theoretical efficiency with the actual usage data. In the load balance analysis, the load balance degree factor is subjected to Fourier curve generation to generate a load balance curve. Fourier analysis is used to identify periodic and trend changes in load balance. Then, the load balance curve is subjected to abnormal fluctuation detection to generate load balance abnormal data. These abnormal data are corrected by Kalman filtering to generate load balance abnormal correction data, and finally generate a biomass energy load balance degree factor. Kalman filtering is an effective signal processing technology for data correction in an environment with noise and uncertainty. For the equipment response speed factor, record the response time of the equipment and generate response time series data. These data are corrected through slope identification to generate response time series correction data, and further generate the biomass energy equipment response speed factor. The slope identification correction process is used to capture the changing trends and mutations in the response time to ensure the accuracy of the equipment response speed factor. The weight data of biomass energy multi-energy utilization is generated by benchmarking the weight difference degree of the above-generated factors. This step identifies the relative importance and optimization requirements of each performance dimension in the system by comparing the weight differences of each factor. Finally, the biomass energy multi-energy utilization weight data is processed for the biomass energy collective security degree assessment to generate biomass energy multi-energy utilization degree assessment information.
[0132] The beneficial effect of the present invention is that by acquiring energy type data and constructing a biomass energy conversion model, the accuracy of the energy conversion process and the operability of the model are ensured. This lays a solid foundation for subsequent data processing and scheduling optimization. The acquisition of energy set joint control data and the linkage processing of energy equipment, and further the incentive data generated by multi-energy control incentive calculation, realize the coordinated optimization between different energy sources. This collaborative optimization not only improves the overall efficiency of the system, but also ensures the linkage and mutual cooperation of various types of energy equipment, and provides necessary data support for the subsequent generation of scheduling strategies. Subsequently, the multi-energy control incentive data is optimized by the multi-energy reinforcement learning system, and the generated multi-energy intelligent system can dynamically adapt to different scheduling requirements and continuously optimize and improve itself in practical applications. This optimization processing by the learning system not only enhances the system's adaptability to complex environments, but also provides intelligent support for the generation of scheduling strategies for biomass energy conversion models. Finally, by evaluating the degree of security and utilization of the biomass energy multi-energy scheduling scheme strategy, the system can accurately judge the feasibility of the scheduling scheme and the efficiency of resource utilization based on data, thereby effectively completing the scheduling optimization of the biomass energy multi-energy utilization system. Therefore, the present invention solves the problems of insufficient dynamic adjustment, incomplete energy efficiency optimization and insufficient data utilization of traditional scheduling methods by introducing dynamic scheduling algorithms, comprehensive energy efficiency optimization and advanced data analysis technology, thereby improving the flexibility and overall energy efficiency of the system.
[0133] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0134] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A biomass energy multi-energy utilization system scheduling method, characterized in that: The following steps are involved: Step S1: Obtain energy type data, and construct a biomass energy conversion model according to the energy type data; Step S2: Acquire energy set joint control data; perform energy equipment linkage processing on the energy set joint control data to generate energy equipment linkage data; perform multi-energy control incentive calculation on the energy equipment linkage data to generate multi-energy control incentive data; Step S3: Performing learning system optimization processing on the multi-energy regulation incentive data through a preset multi-energy reinforcement learning system to generate a multi-energy intelligent system; using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy; Step S4: Perform biomass energy security level assessment on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
2. The biomass multi-energy utilization system scheduling method according to claim 1 is characterized in that: Step S1 specifically includes: Step S11: Acquire energy type data and regional biomass resource distribution data; Step S12: Modeling is performed according to the energy type data through the input-output analysis method, thereby constructing a regional biomass energy balance model; Step S13: Generate biomass combustion energy release data, biomass energy conversion efficiency data and biomass gasification product prediction data through combustion chemical kinetics analysis, energy conversion efficiency calculation and thermochemical conversion analysis according to the regional biomass resource distribution data; Step S14: using the regional biomass energy balance model to perform parameter calibration processing on the biomass combustion energy release data, the biomass energy conversion efficiency data and the biomass gasification product prediction data, thereby generating biomass energy conversion calibration information; Step S15: construct a biomass energy conversion model based on the biomass energy conversion calibration information to generate a biomass energy conversion model.
3. The biomass energy multi-energy utilization system scheduling method according to claim 1 is characterized in that: Step S2 specifically includes: Step S21: Acquire energy set joint control data; Step S22: performing load balancing adjustment on the energy set joint control data according to the control rules to generate biomass energy load demand data; Step S23: Perform energy cost tracing analysis on the biomass energy load demand data to generate energy cost tracing data; use particle swarm optimization technology to perform multi-energy regulation incentive calculation on the energy cost tracing data to generate multi-energy regulation incentive data.
4. The biomass energy multi-energy utilization system scheduling method according to claim 3 is characterized in that: Step S22 specifically includes: Step S221: dividing the activation priority of the energy set joint control data according to efficiency and response speed, and generating high activation priority devices and low activation priority devices; Step S222: using the pre-scheduling load pre-distribution method to predict the load demand of the high-activation priority equipment and generate predicted load demand data; performing load pre-distribution on the predicted load demand data and generating high-activation equipment load pre-distribution data; Step S223: using the sleep smoothing allocation method to determine the sleep priority of the low enablement priority device, and generating sleep determination data of the low enablement priority device; based on the sleep determination data of the low enablement priority device, gradually put the low enablement priority device into sleep mode, and generate sleep data of the low enablement device; Step S224: Obtain total load demand data; perform energy equipment linkage processing on high-enabled equipment load pre-allocation data and low-enabled equipment sleep data to generate energy equipment linkage data; perform load balancing adjustment on energy equipment linkage data based on total load demand data to generate biomass energy load demand data.
5. The biomass energy multi-energy utilization system scheduling method according to claim 1, characterized in that: Step S3 specifically includes: Step S31: extracting historical characteristic data from energy type data to obtain historical utilization characteristic data of biomass energy; Step S32: Use the historical utilization feature data of biomass energy to build a reinforcement learning system to generate a multi-energy reinforcement learning system; use the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system; Step S33: Utilize the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model to generate a biomass energy multi-energy scheduling solution strategy.
6. The biomass energy multi-energy utilization system scheduling method according to claim 5 is characterized in that: Step S32 specifically includes: Step S321: constructing a regularity and correlation feature space for the biomass energy historical utilization feature data, and generating a historical utilization two-dimensional data coordinate graph; Step S322: Acquire actual energy utilization characteristic data; perform point-to-point fitting analysis on the historical utilization two-dimensional data coordinate graph using the actual energy utilization characteristic data to generate multi-energy utilization related data; construct a reinforcement learning system for the multi-energy utilization related data to generate a multi-energy reinforcement learning system; Step S323: Utilize the multi-energy reinforcement learning system to self-adjust the learning parameters of the multi-energy regulation incentive data to generate a multi-energy intelligent system.
7. The biomass energy multi-energy utilization system scheduling method according to claim 5 is characterized in that: Step S33 specifically includes: Step S331: Using the multi-energy intelligent system to perform scheduling strategy generation processing on the biomass energy conversion model, generating a biomass energy multi-energy scheduling plan strategy; using the preset multi-dimensional evaluation criteria to divide the biomass energy multi-energy scheduling plan strategy, generating an energy efficiency priority strategy and an environmental impact minimization strategy; Step S332: When the energy efficiency priority strategy is classified, the conversion rate and loss rate are extracted from the historical utilization characteristic data of biomass energy, and the optimal working range of the conversion rate and loss rate is predicted by energy efficiency curve fitting to generate the optimal working range data; the energy allocation ratio is dynamically adjusted for the optimal working range data and the actual energy utilization characteristic data, thereby completing the energy efficiency priority strategy; Step S333: When it is classified as the environmental impact minimization strategy, the energy type traceability is performed on the biomass energy conversion model to generate biomass energy traceability type data; carbon capture simulation is performed on the biomass energy traceability type data to generate biomass energy carbon capture data; and the biomass energy carbon capture data is used with carbon priority emission priority, thereby completing the environmental impact minimization strategy.
8. The biomass multi-energy utilization system scheduling method according to claim 1 is characterized in that: Step S4 specifically includes: Step S41: collecting biomass energy security data for the biomass energy multi-energy scheduling strategy to obtain a biomass energy security data set; generating a data set analysis report for the biomass energy security data set to generate a biomass energy security data set analysis report; Step S42: Performing a biomass energy security level assessment process on the biomass energy multi-energy scheduling strategy to generate biomass energy multi-energy utilization level assessment information; Step S43: Perform scheduling efficiency analysis on the biomass energy security data set analysis report and the biomass energy multi-energy utilization degree assessment information to generate biomass energy multi-energy utilization system scheduling efficiency data, thereby completing the scheduling optimization of the biomass energy multi-energy utilization system.
9. The biomass energy multi-energy utilization system scheduling method according to claim 8, characterized in that: Step S41 specifically includes: Step S411: screening the multi-level data of energy conversion efficiency for the biomass energy security data set to generate high-consumption biomass energy data and low-consumption biomass energy data; Step S412: performing cross-comparison analysis on high-consumption biomass energy data and low-consumption biomass energy data to generate biomass energy cross-comparison analysis data; performing energy flow dynamic simulation on the biomass energy cross-comparison analysis data to generate a biomass energy multi-energy utilization data set; Step S413: Generate a data set analysis report for the biomass energy multi-energy utilization data set, and generate a biomass energy security data set analysis report.
10. The biomass energy multi-energy utilization system scheduling method according to claim 8, characterized in that: Step S42 specifically includes: Step S421: quantify the biomass energy multi-energy scheduling strategy using a preset multi-dimensional indicator system to generate a biomass energy multi-energy scheduling quantitative factor, wherein the biomass energy multi-energy scheduling quantitative factor includes an energy conversion efficiency factor, a load balance degree factor, and an equipment response speed factor; Step S422: performing efficiency weight matching on the energy conversion efficiency factor and the actual energy utilization characteristic data to generate a biomass energy conversion efficiency factor; performing Fourier curve generation on the load balance degree factor to generate a load balance curve; performing abnormal fluctuation detection on the load balance curve to generate load balance abnormality data; performing Kalman filtering correction on the load balance abnormality data to generate load balance abnormality correction data; performing balance factor generation on the load balance abnormality correction data to generate a biomass energy load balance degree factor; performing response time recording on the equipment response speed factor to generate response time series data; performing slope identification correction on the response time series data to generate response time series correction data; performing equipment response time factor generation on the response time series correction data to generate a biomass energy equipment response speed factor; Step S423: performing a weight difference comparison analysis on the biomass energy conversion efficiency factor, the biomass energy load balance factor and the biomass energy equipment response speed factor to generate biomass energy multi-energy utilization weight data; Step S424: Perform biomass energy security level assessment processing on the biomass energy multi-energy utilization weight data to generate biomass energy multi-energy utilization level assessment information.
