Intelligent allocation system and method for peak and valley values of biogas power generation control virtual power plant

Abstract

The invention relates to a biogas power generation control virtual power plant peak-valley value intelligent allocation system and method, and the method comprises the following specific steps: data collection: obtaining historical load data and related characteristic data from a sensor system; load prediction: predicting the power demand based on historical load data and related feature data; generating an allocation strategy, and formulating an optimal resource allocation strategy according to the predicted load demand and the actual resource condition; and control execution: executing the optimal resource allocation strategy formulated by the allocation strategy generation module. According to the invention, a scheduling algorithm with higher flexibility and higher adaptability is introduced, and power generation and energy storage strategies can be dynamically adjusted according to different conditions.

Description

Technical Field

[0001] The present application relates to the technical field of biogas power generation and virtual power plants, and specifically to a biogas power generation control virtual power plant peak and valley value intelligent allocation system and method. Background Art

[0002] The severity of national energy is reflected in the sustainability of energy supply, energy security, environmental impact and economic burden. With the depletion of fossil energy and the increasing greenhouse effect, it has become a consensus among countries around the world to develop clean and renewable energy and promote energy conservation and emission reduction. As one of the important renewable energy sources, biogas power generation not only provides clean and renewable electricity and heat, but also reduces greenhouse gas emissions, improves environmental sanitation, and improves the security and stability of energy supply. Through technological innovation, policy support and diversified applications, biogas power generation will continue to play an important role in promoting the development of the national energy structure in a greener and more sustainable direction.

[0003] Biogas is produced by the fermentation of biomass (such as organic waste, wastewater, crop residues, etc.) under anaerobic conditions by microorganisms. This process includes the following main steps: Hydrolysis: Organic matter is broken down into simple organic acids by the action of hydrolases. Acidification: Simple organic acids are further fermented into volatile fatty acids (VFAs) and other organic compounds. Hydrogen production and acetogenesis: VFAs are converted into acetic acid, hydrogen and carbon dioxide by the action of acetic acid fermenting bacteria. Methane production: Methanogenic bacteria convert acetic acid and hydrogen into methane and carbon dioxide.

[0004] At present, the coordination and optimization methods for virtual power plants mainly focus on the interaction of wind power, photovoltaic power, energy storage and user demand response to seek the best operation strategy for the coordination and optimization of different types of units. However, the above studies have not considered the power generation form of biogas power generation, and lack the impact of biogas power generation on the environment. Therefore, it is urgent to propose a virtual power plant structure coupled with biogas power generation for coordinated optimization. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a system and method for intelligently adjusting the peak and valley values ​​of a virtual power plant for biogas power generation control, which introduces a more flexible and adaptable scheduling algorithm and can dynamically adjust power generation and energy storage strategies according to different situations.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present application provides a peak-valley intelligent allocation system for controlling a virtual power plant for biogas power generation, comprising a data acquisition module, a load forecasting module, an allocation strategy generation module and a control execution module, wherein the data acquisition module obtains historical load data and related characteristic data from a sensor system, the load forecasting module predicts electricity demand based on historical load data and related characteristic data, the allocation strategy generation module formulates an optimal resource allocation strategy according to the predicted load demand and actual resource conditions, and the control execution module executes the optimal resource allocation strategy formulated by the allocation strategy generation module.

[0008] In a second aspect, the embodiment of the present application provides a method for intelligently allocating peak and valley values ​​of a virtual power plant for biogas power generation control, comprising the following specific steps:

[0009] Data collection, obtaining historical load data and related characteristic data from the sensor system;

[0010] Load forecasting, predicting power demand based on historical load data and related characteristic data;

[0011] Allocation strategy generation: formulate the optimal resource allocation strategy based on the predicted load demand and actual resource status;

[0012] Control execution and execute the optimal resource allocation strategy formulated by the allocation strategy generation module.

[0013] The data collection step also includes data preprocessing and model training. The data preprocessing includes cleaning and normalizing the data and deleting missing values. The model training includes using historical data to solve the regression formula through the least squares method to obtain the regression coefficient.

[0014] The load prediction formula in the load prediction step is:

[0015] L t+k =β0+β1x1+β2x2+β3x3+β4x4+…+β m x m

[0016] in:

[0017] L t+k The load forecast value at a certain moment in the future;

[0018] β0,β1,β2,β3,…β m is the regression coefficient to be sought;

[0019] x 1, x2,x3,…,x m is the characteristic variable that affects the load.

[0020] Electricity demand forecast calculation formula

[0021]

[0022] in, is the predicted value at time t, and Y is the historical electricity demand data;

[0023] The efficiency of biogas power generation can be calculated using the following formula:

[0024] Where η is the efficiency, P 出 is the electric power output by the power generation equipment, P 入 is the input energy;

[0025] Genetic Algorithm Optimization Algorithm:

[0026] The basic steps of genetic algorithms include selection, crossover and mutation. The fitness function can be calculated using the benefits:

[0027]

[0028] Among them, P i is the power generation, C i is the electricity price, F j It is the running cost.

[0029] In the deployment strategy generation step, the deployment strategy formula is: Let x i For the load distribution of each device, the supply and demand satisfy the following relationship: where D is the predicted total load demand,

[0030] Objective function: Minimize the total cost: where c i, is the unit load cost of equipment i.

[0031] In the deployment strategy generation step, the specific calculation process is as follows:

[0032] Input demand: load demand D obtained by load forecasting algorithm;

[0033] Get equipment information: Get the unit cost c of all available equipment i and maximum / minimum load capacity;

[0034] Construct a linear programming model: Use the above formulas and constraints to build a linear programming model;

[0035] Solution: Use the linear programming solver to solve the optimization problem and obtain the load distribution x of each device. i ;

[0036] Through load forecasting and efficient resource allocation, the system's operating efficiency and resource utilization can be effectively improved.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. Higher real-time performance and data accuracy

[0039] Real-time data collection: The present invention adopts more advanced sensors and data collection technology to ensure the real-time and accuracy of data collection.

[0040] Reduce delay: By optimizing the data transmission mechanism, the delay in transmitting sensor data to the control system is reduced, and the response speed of scheduling is improved.

[0041] 2. More efficient scheduling algorithm

[0042] Flexibility and adaptability: The present invention introduces a more flexible and adaptable scheduling algorithm that can dynamically adjust power generation and energy storage strategies according to different situations.

[0043] Multi-objective optimization: The scheduling algorithm of the present invention can balance scheduling objectives such as cost, efficiency and environmental protection to achieve a more optimized scheduling solution.

[0044] Computational efficiency: The use of efficient data processing and optimization algorithms improves computing efficiency and reduces response time.

[0045] 3. Stronger intelligent control capabilities

[0046] Automatic prediction and adjustment: The present invention uses machine learning and artificial intelligence technologies to perform load prediction and automatic adjustment, reducing reliance on manual intervention and improving the accuracy and efficiency of regulation.

[0047] High forecasting accuracy: Advanced forecasting models improve the accuracy of short-term and long-term load forecasts, ensuring that dispatch plans are more accurate and reliable.

[0048] 4. Better system integration

[0049] Information exchange: The present invention realizes data integration of different subsystems, ensures information exchange, and improves overall scheduling efficiency.

[0050] Compatibility: The use of unified software interfaces and standards improves the compatibility of equipment and systems and simplifies the integration process.

[0051] 5. Higher stability and reliability

[0052] Fault detection and processing: The present invention introduces advanced fault detection and automatic recovery mechanisms to improve the stability and reliability of the system.

[0053] Fault tolerance: Redundant design and intelligent monitoring enhance the system's fault tolerance and reduce downtime.

[0054] 6. Lower cost control

[0055] Cost optimization: The present invention reduces equipment and maintenance costs and improves economic benefits through cost optimization algorithms.

[0056] Energy saving and consumption reduction: The use of efficient energy conversion technology reduces energy consumption and reduces operating costs.

[0057] 7. Better user interface and operating experience

[0058] Simple interface: The present invention is designed with a simple and clear user interface, which the operator can quickly understand and use.

[0059] Visualization tools: Use advanced data visualization tools to intuitively display system operation status and scheduling results, improving operation experience and decision-making efficiency.

[0060] 8. Stronger environmental adaptability

[0061] Climate and geographical location adaptation: The present invention improves the climate and geographical location adaptability of the system through optimized design, so that it can operate stably in different environments.

[0062] Reduce carbon emissions: The use of efficient energy conversion and management technologies reduces carbon emissions during biogas power generation, meeting environmental protection requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 A flow chart of the method of this application;

[0065] Figure 2 This is a system block diagram of this application. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0067] The terms "comprises," "comprising," or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0068] The terms "first", "second", etc. are only used to distinguish one entity or operation from another entity or operation, and should not be understood as indicating or implying relative importance, nor should they be understood as requiring or implying any such actual relationship or order between these entities or operations.

[0069] like Figure 2 As shown, a biogas power generation control virtual power plant peak and valley value intelligent allocation system includes a data acquisition module 1, a load forecasting module 2, an allocation strategy generation module 3 and a control execution module 4. The data acquisition module obtains historical load data and related characteristic data from the sensor system, the load forecasting module predicts the power demand based on the historical load data and related characteristic data, the allocation strategy generation module formulates the optimal resource allocation strategy according to the predicted load demand and the actual resource status, and the control execution module executes the optimal resource allocation strategy formulated by the allocation strategy generation module.

[0070] like Figure 1 As shown, a method for intelligently adjusting the peak and valley values ​​of a virtual power plant for biogas power generation control includes the following specific steps:

[0071] Data collection, obtaining historical load data and related characteristic data from the sensor system;

[0072] Load forecasting, predicting power demand based on historical load data and related characteristic data;

[0073] Allocation strategy generation: formulate the optimal resource allocation strategy based on the predicted load demand and actual resource status;

[0074] Control execution and execute the optimal resource allocation strategy formulated by the allocation strategy generation module.

[0075] The data collection step also includes data preprocessing and model training. The data preprocessing includes cleaning and normalizing the data and deleting missing values. The model training includes using historical data to solve the above regression formula through the least squares method to obtain the regression coefficient.

[0076] The load prediction formula in the load prediction step is:

[0077] L t+k =β0+β1x1+β2x2+β3x3+β4x4+…+β m x m

[0078] in:

[0079] L t+k The load forecast value at a certain moment in the future;

[0080] β0,β1,β2,β3,…β m is the regression coefficient to be sought;

[0081] x 1, x2,x3,…,x m is the characteristic variable that affects the load.

[0082] Electricity demand forecast calculation formula

[0083]

[0084] in, is the predicted value at time t, and Y is the historical electricity demand data;

[0085] The efficiency of biogas power generation can be calculated using the following formula:

[0086] Where η is the efficiency, P 出 is the electric power output by the power generation equipment, P 入 is the input energy;

[0087] Genetic Algorithm Optimization Algorithm:

[0088] The basic steps of genetic algorithms include selection, crossover and mutation. The fitness function can be calculated using the benefits:

[0089]

[0090] Among them, P i is the power generation, C i is the electricity price, F j It is the running cost.

[0091] In the deployment strategy generation step, the deployment strategy formula is: Let x i For the load distribution of each device, the supply and demand satisfy the following relationship: where D is the predicted total load demand,

[0092] Objective function: Minimize the total cost: where c i, is the unit load cost of equipment i.

[0093] In the deployment strategy generation step, the specific calculation process is as follows:

[0094] Input demand: load demand D obtained by load forecasting algorithm;

[0095] Get equipment information: Get the unit cost c of all available equipment i and maximum / minimum load capacity;

[0096] Construct a linear programming model: Use the above formulas and constraints to build a linear programming model;

[0097] Solution: Use the linear programming solver to solve the optimization problem and obtain the load distribution x of each device. i ;

[0098] Through load forecasting and efficient resource allocation, the system's operating efficiency and resource utilization can be effectively improved.

[0099] In the embodiments of the present application,

[0100] Generator equipment: Biogas power generation usually uses a combined cycle gas turbine to convert biogas into electrical energy.

[0101] Generator performance: Power output: The power output of the generator depends on the flow rate and pressure of the biogas; Efficiency: The efficiency of the generator can be calculated by the following formula: Where: η engine is the generator efficiency. P elec is the electrical power output of the generator (in kW); E biogas is the biogas energy consumed (unit: kWh).

[0102] Combined Heat and Power (CHP) System: The CHP system can generate both electricity and heat, improving energy efficiency. Internal combustion engine CHP: The internal combustion engine generates a large amount of waste heat during operation, which can be recycled through a heat exchanger. Efficiency calculation formula: Where: η CHP is the overall efficiency of the CHP system, P elec is the electrical energy generated (unit: kWh), Q heat is the heat energy generated (unit: kWh), E biogas is the biogas energy consumed (unit: kWh).

[0103] The heat demand is calculated based on the heat load demand of the user. The following formula can be used: Q t =Q base +ΔQ t

[0104] Where: Q tis the heat demand in the first time period (in kW), Q base is the basic heat load (unit: kW), ΔQ t is the heat load change in the first time period (unit: kW).

[0105] Scheduling algorithms, which are used to optimize the scheduling of electrical and thermal energy,

[0106] Linear Programming (LP): Where: G t is the electricity cost in the first time period, G t is the power generation in the first time period.

[0107] Environmental technology, carbon emission control, in order to reduce environmental impact, carbon emission costs can be considered.

[0108] Carbon emission costs: Where: C c is the total carbon emission cost,

[0109] C C,t is the carbon emission cost coefficient in the tth time period (unit: yuan / kWh). biogas,t is the biogas consumption in time period t (unit: kWh).

[0110] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A biogas power generation control virtual power plant peak and valley value intelligent allocation system, characterized in that: It includes a data acquisition module, a load prediction module, a resource allocation strategy generation module and a control execution module. The data acquisition module obtains historical load data and related characteristic data from the sensor system. The load prediction module predicts the power demand based on the historical load data and related characteristic data. The resource allocation strategy generation module formulates the optimal resource allocation strategy according to the predicted load demand and the actual resource status. The control execution module executes the optimal resource allocation strategy formulated by the resource allocation strategy generation module.

2. A method for intelligently adjusting peak and valley values ​​of a virtual power plant for biogas power generation control, characterized in that: The specific steps include: Data collection, obtaining historical load data and related characteristic data from the sensor system; Load forecasting, predicting power demand based on historical load data and related characteristic data; Allocation strategy generation: formulate the optimal resource allocation strategy based on the predicted load demand and actual resource status; Control execution and execute the optimal resource allocation strategy formulated by the allocation strategy generation module.

3. According to claim 2, a biogas power generation control virtual power plant peak and valley value intelligent allocation method is characterized in that: The data collection step also includes data preprocessing and model training. The data preprocessing includes cleaning and normalizing the data and deleting missing values. The model training includes using historical data to solve the regression formula through the least squares method to obtain the regression coefficient.

4. According to claim 2, a method for intelligently adjusting peak and valley values ​​of a biogas power generation control virtual power plant is characterized in that: The load prediction formula in the load prediction step is: L t+k =β0+β1x1+β2x2+β3x3+β4x4+…+β m x m in: L t+k The load forecast value at a certain moment in the future; β0,β1,β2,β3,…β m is the regression coefficient to be sought; x 1, x2,x3,…,x m is the characteristic variable that affects the load.

5. According to claim 2, a biogas power generation control virtual power plant peak and valley value intelligent allocation method is characterized in that: Electricity demand forecast calculation formula in, is the predicted value at time t, and Y is the historical electricity demand data; The efficiency of biogas power generation can be calculated using the following formula: Where η is the efficiency, P 出 is the electric power output by the power generation equipment, P 入 is the input energy; Genetic Algorithm Optimization Algorithm: The basic steps of genetic algorithms include selection, crossover and mutation. The fitness function can be calculated using the benefits: Among them, P i is the power generation, C i is the electricity price, F j It is the running cost.

6. According to claim 2, a biogas power generation control virtual power plant peak and valley value intelligent allocation method is characterized in that: In the deployment strategy generation step, the deployment strategy formula is: Let x i For the load distribution of each device, the supply and demand satisfy the following relationship: where D is the predicted total load demand, Objective function: Minimize the total cost: where c i, is the unit load cost of equipment i.

7. According to claim 6, a biogas power generation control virtual power plant peak and valley value intelligent allocation method is characterized in that: In the deployment strategy generation step, the specific calculation process is as follows: Input demand: load demand D obtained by load forecasting algorithm; Get equipment information: Get the unit cost c of all available equipment i and maximum / minimum load capacity; Construct a linear programming model: Use the above formulas and constraints to build a linear programming model; Solution: Use the linear programming solver to solve the optimization problem and obtain the load distribution x of each device. i ; Through load forecasting and efficient resource allocation, the system's operating efficiency and resource utilization can be effectively improved.

Images