Distributed energy consumption scheme generation method
Through the generation method of distributed energy consumption scheme, energy demand prediction and planning algorithms are used, combined with system design, construction and control algorithms, the impact of distributed power generation on the previous power grid is solved, and efficient energy consumption and stability are achieved run.
Patent Information
- Application Number
- CN202411558973.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-04
- Publication Date
- 2025-02-14
AI Technical Summary
The existing distributed power generation is difficult to effectively manage the power quality and fault detection of distributed energy for the previous power grid under high permeability, resulting in energy waste.
Provide a distributed energy consumption scheme generation method, by collecting energy demand data, using energy demand prediction algorithms and energy planning algorithms to generate energy planning schemes, and through system design and construction algorithms and control algorithm optimization schemes, output practical consumption plan.
It realizes efficient consumption of distributed energy, improves energy utilization efficiency and stability, and avoids energy waste.
Smart Images
Figure CN119443685A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power grid systems, and in particular to a method for generating a consumption plan for distributed energy. Background Art
[0002] Energy is the foundation for the survival and development of modern society. In order to cope with the energy crisis, countries are actively researching new energy technologies, especially renewable energy such as solar energy, wind energy, and bioenergy. Renewable energy is inexhaustible, clean and environmentally friendly, and is highly valued by countries around the world. Renewable energy has the characteristics of geographical dispersion, discontinuous production, randomness, volatility and uncontrollability. The centralized and unified management method of traditional power networks is difficult to adapt to the requirements of large-scale utilization of renewable energy. The effective way to utilize renewable energy is distributed "on-site collection, on-site storage, and on-site use".
[0003] However, the existing distributed power generation grid connection cannot fundamentally change the impact of distributed power generation on the power quality, fault detection, and fault isolation of the upper-level power grid under high penetration conditions. The output characteristics of existing distributed energy sources (such as solar energy, wind energy, etc.) are different, and their power generation and power generation time distribution are also different. As a result, it is difficult to combine regional energy demand and distributed energy characteristics for energy planning and use, which easily leads to energy waste. Therefore, this application proposes a method for generating a distributed energy consumption plan. Summary of the invention
[0004] The purpose of the present invention is to provide a method for generating a distributed energy consumption plan, which solves the problem that the output characteristics of existing distributed energy sources are different, making it difficult to combine regional energy demand and distributed energy characteristics for energy planning and use, which easily leads to energy waste.
[0005] To achieve the above-mentioned purpose, the present invention provides a method for generating a distributed energy consumption plan for consuming energy in an energy system, the method comprising: step S1, collecting and analyzing energy demand data to obtain ideal future demand data; step S2, generating an energy planning plan based on the ideal future demand data; step S3, optimizing the energy planning plan to obtain an optimized planning plan; step S4, introducing a control algorithm for controlling the energy system into the optimized planning plan, and outputting a practical consumption plan.
[0006] Preferably, in step S1, an energy demand prediction algorithm is used to analyze the energy demand data; the energy demand prediction algorithm includes time series analysis, neural network analysis and support vector machine analysis.
[0007] Preferably, the time series analysis includes: moving average analysis, calculating the average value of energy demand data within a certain period to smooth the data, thereby revealing potential trends; exponential smoothing analysis, assigning different weights to energy demand data at different time points to reflect the speed of change of energy demand data, and then making predictions; ARIMA model analysis, putting energy demand data into the model to capture trends, seasonality and random fluctuations in energy demand data.
[0008] Preferably, the neural network analysis includes: multi-layer perceptron analysis, which processes the energy demand data and outputs the corresponding data at a certain time point in the future; recurrent neural network analysis, which captures the dependency relationship between the energy demand data at different time points and predicts the corresponding data at the next moment by memorizing the energy demand data at the previous moment; long short-term memory network analysis, which can retain long-term dependency information through memory cells and capture the long-term trend of energy consumption; bidirectional LSTM analysis, which improves the prediction accuracy by considering past and future time information at the same time.
[0009] Preferably, the support vector machine analyzes and processes the nonlinear relationship in the energy demand data, and finds the optimal prediction model by optimizing the objective function.
[0010] Preferably, in step S2, an energy planning algorithm is used to generate an energy planning solution based on ideal future demand data.
[0011] Preferably, the energy planning algorithm includes: linear programming, which solves the maximum and minimum values of the linear objective function under the constraints of given linear equations and inequalities, so as to determine the optimal strategy for energy production, distribution and conversion; integer programming, which is an optimization problem in which variables must take integer values based on linear programming, and is used to determine the capacity, quantity and location of equipment in the energy system to meet specific constraints; dynamic programming, which is used to solve optimization problems with overlapping sub-problems, and is used to formulate long-term energy production plans, storage strategies and conversion plans to cope with the uncertainty of energy demand.
[0012] Preferably, in step S3, a system design and construction algorithm is used to optimize the energy planning scheme, and the system design and construction algorithm includes a genetic algorithm and a particle swarm optimization; the genetic algorithm is used to determine the optimal equipment selection, layout and parameter setting in the energy system; various configuration parameters in the energy system are encoded as chromosomes, and a fitness function is defined to evaluate the performance of different configurations, so as to obtain the optimal solution; the particle swarm optimization is also used to determine the optimal equipment selection, layout and parameter setting in the energy system, and the particle swarm optimization encodes the configuration parameters of the energy system as particles, and searches for the optimal solution by continuously updating the position and speed of the particles.
[0013] Preferably, in step S4, the control algorithm includes but is not limited to a PID control algorithm, a fuzzy control algorithm, and an adaptive control algorithm; the PID control algorithm achieves precise control of the energy system by adjusting three parameters: proportional, integral, and differential; the fuzzy control algorithm processes some links that are difficult to accurately model, thereby achieving more flexible and stable control of the energy system; the adaptive control algorithm is used to cope with the uncertainty of energy demand and changes in weather conditions to ensure stable operation and efficient output of the energy system.
[0014] Preferably, the energy system is maintained and serviced regularly to ensure the long-term stable operation of the energy system.
[0015] In summary, compared with the prior art, the method for generating a distributed energy consumption plan provided by the present invention has the following beneficial effects:
[0016] First, the present invention can obtain practical consumption solutions, optimize the energy system, and improve energy utilization efficiency and stability.
[0017] Second, the present invention proposes to use a control algorithm to adjust the energy production, storage and distribution process to achieve efficient energy utilization and stable operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the attached embodiment of the present invention Figure 1 , the technical solutions, structural features, objectives achieved and effects in the embodiments of the present invention are described in detail.
[0020] It should be noted that the drawings are in a very simplified form and use non-precise proportions. They are only used to conveniently and clearly assist in explaining the embodiments of the present invention, and are not used to limit the conditions for the implementation of the present invention. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical content disclosed by the present invention.
[0021] It should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only the elements explicitly listed, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0022] The present invention provides a method for generating a distributed energy consumption plan for consuming energy in an energy system; so-called energy consumption means making the energy basically in a "generated and used" state; for example, the electricity generated by a power plant is digested and absorbed so that the electricity generated by the power plant and the electricity consumed by the load end can achieve real-time dynamic balance in the entire power system.
[0023] like Figure 1 As shown, the method includes:
[0024] Step S1, collecting and analyzing energy demand data to obtain ideal future demand data;
[0025] Among them, taking the power system as an example; the energy demand data includes but is not limited to the power consumption, power consumption time, power load characteristics (the law that the active power and reactive power absorbed by the power load from the power system changes with the voltage at the load end and the system frequency) in the historical situation; the ideal future demand data is a kind of data such as power consumption, power consumption time and power load characteristics in the predicted situation, and the only difference between it and the energy demand data is that one is the existing data and the other is the predicted data;
[0026] In the process of analyzing and obtaining the ideal data of future demand, multiple factors such as the user's energy preference, economic conditions, environmental protection requirements, energy production goals, and energy use constraints need to be considered.
[0027] Step S2, generating an energy planning scheme based on ideal future demand data;
[0028] The energy planning scheme includes but is not limited to strategies for energy production, storage, conversion and distribution; as well as optimal technical solutions and equipment configuration solutions generated by considering the availability, cost and environmental impact factors of energy resources.
[0029] Step S3, optimizing the energy planning scheme to obtain an optimized planning scheme;
[0030] Because the energy planning scheme generated above is only a prototype, in the process of implementing the energy planning scheme; for example, energy system design and construction, operating equipment selection, layout design, network connection, system integration and other aspects need to be designed in detail.
[0031] Step S4, introducing a control algorithm for controlling the energy system into the optimization planning scheme, and outputting a practical consumption scheme;
[0032] Because after establishing an energy management system, it is necessary to monitor and control the operating status of the energy system in real time; at this time, it is necessary to introduce a control algorithm to control the energy system and improve energy utilization efficiency and stability.
[0033] In a specific embodiment, in step S1, an energy demand prediction algorithm is used to analyze energy demand data, and the energy demand prediction algorithm includes time series analysis, neural network analysis and support vector machine analysis. Specifically, based on energy demand data (such as historical data, weather forecast, user behavior pattern information), ideal future demand data is obtained through time series analysis / neural network analysis / support vector machine analysis.
[0034] In a specific embodiment, the time series analysis includes the following three analysis methods:
[0035] (1) Moving average analysis, which smoothes the data by calculating the average value of energy demand data over a certain period of time, thereby revealing potential trends.
[0036] (2) Exponential smoothing analysis assigns different weights to energy demand data at different time points to reflect the speed of change of energy demand data and make predictions.
[0037] (3) ARIMA model analysis (Autoregressive Integrated Moving Average model) incorporates energy demand data into the model to capture trends, seasonality, and random fluctuations in energy demand data.
[0038] In a specific embodiment, the neural network analysis includes the following four analysis methods:
[0039] (1) Multilayer Perceptron Analysis: The multilayer perceptron processes energy demand data, such as temperature, humidity, and historical energy consumption data, and outputs the corresponding data at a certain point in the future.
[0040] (2) Recurrent neural network analysis captures the dependency relationship between energy demand data at different time points and predicts the corresponding data at the next moment by memorizing the energy demand data at the previous moment.
[0041] (3) Long Short-Term Memory Network Analysis: Long Short-Term Memory Network can retain long-term dependency information through memory cells. For example, in energy consumption prediction, Long Short-Term Memory Network is used to capture the long-term trend of energy consumption.
[0042] (4) Bidirectional LSTM analysis (Long Short-Term Memory): Bidirectional LSTM analysis can combine historical consumption data and future information (such as weather forecasts and holidays) to make more accurate predictions. This type of analysis further improves the prediction accuracy by considering both past and future time information.
[0043] In a specific embodiment, the principle of the support vector machine analysis is that it can handle nonlinear relationships in energy demand data and find the optimal prediction model by optimizing the objective function.
[0044] In a specific embodiment, in step S2, an energy planning algorithm is used to generate an energy planning scheme, and the energy planning algorithm is specifically:
[0045] Based on the ideal data of future demand, the energy planning algorithm is used to determine the best energy production, storage and conversion strategy. The energy planning algorithm includes but is not limited to linear programming, integer programming and dynamic programming. In the process of energy planning algorithm operation, multiple factors such as cost, environmental impact and energy efficiency should be considered to achieve economy and sustainability.
[0046] Specifically, specific embodiments of linear programming, integer programming and dynamic programming will be introduced below:
[0047] (1) Linear programming
[0048] The principle of linear programming is to solve the maximum and minimum values of the linear objective function under the constraints of given linear equations and inequalities. Linear programming is used to determine the optimal strategy for energy production, distribution and conversion in order to minimize costs and maximize benefits.
[0049] (2) Integer Programming
[0050] The integer programming is an optimization problem based on linear programming, which requires variables to take integer values. In energy systems, integer programming is used to determine the capacity, quantity and location of energy facilities to meet specific constraints, such as energy demand and environmental standards.
[0051] (3) Dynamic programming
[0052] The dynamic programming is used to solve optimization problems with overlapping sub-problems. In energy systems, dynamic programming is used to formulate long-term energy production plans, storage strategies and conversion plans to cope with the uncertainty of energy demand.
[0053] In a specific embodiment, in step S3, a system design and construction algorithm is used to optimize the energy planning scheme. The principle of the system design and construction algorithm is to use simulation and modeling technology to design and optimize the various components of the distributed energy system. Specifically, the system design and construction algorithm includes but is not limited to genetic algorithms, particle swarm optimization, etc., and its core purpose is to determine the best equipment selection, layout and parameter settings; it will be introduced below.
[0054] (1) Genetic Algorithm
[0055] The genetic algorithm is used to determine the best equipment selection, layout and parameter settings in the energy system; the optimal solution is obtained by encoding various configuration parameters in the energy system as "chromosomes" and defining a fitness function to evaluate the performance of different configurations.
[0056] (2) Particle Swarm Optimization
[0057] The particle swarm optimization is also used to determine the best equipment selection, layout and parameter settings in the energy system. Particle swarm optimization encodes the configuration parameters of the energy system into "particles" and continuously updates the position and speed of the particles to find the optimal solution. The advantage of particle swarm optimization is that it converges quickly and is easy to implement and debug.
[0058] In a specific embodiment, step S4 uses a control algorithm to adjust the energy production, storage and distribution process to achieve efficient energy utilization and stable operation; the control algorithm includes but is not limited to a PID control algorithm (Proportional, Integral, Differential), a fuzzy control algorithm, and an adaptive control algorithm.
[0059] Specifically, specific embodiments of the PID control algorithm, the fuzzy control algorithm and the adaptive control algorithm will be introduced below.
[0060] (1) PID control algorithm
[0061] The PID control algorithm achieves precise control of the system by adjusting the three parameters of proportion, integration and differentiation. In the energy system, it is used to adjust the output power of the generator set and the charge and discharge rate of the energy storage system to ensure the stable output and efficient operation of the entire energy system.
[0062] (2) Fuzzy control algorithm
[0063] The fuzzy control algorithm is used in energy systems to process some links that are difficult to accurately model, so as to achieve more flexible and stable control.
[0064] (3) Adaptive control algorithm
[0065] Adaptive control algorithms are used in energy systems to cope with the uncertainty of energy demand and changes in weather conditions to ensure stable operation and efficient output of energy systems.
[0066] In addition to the above, the energy system also needs to be maintained and serviced regularly to ensure the long-term and stable operation of the energy system.
[0067] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.
Claims
1. A method for generating a distributed energy consumption plan, characterized in that: For consuming energy in an energy system, the method comprises: Step S1, collecting and analyzing energy demand data to obtain ideal future demand data; Step S2, generating an energy planning scheme based on ideal future demand data; Step S3, optimizing the energy planning scheme to obtain an optimized planning scheme; Step S4, introducing a control algorithm for controlling the energy system into the optimization planning scheme, and outputting a practical consumption scheme.
2. The method for generating a distributed energy consumption plan according to claim 1, characterized in that: In the step S1, an energy demand prediction algorithm is used to analyze the energy demand data; the energy demand prediction algorithm includes time series analysis, neural network analysis and support vector machine analysis.
3. The method for generating a distributed energy consumption plan according to claim 2, characterized in that: The time series analysis includes: Moving average analysis, which calculates the average of energy demand data over a certain period to smooth the data and reveal underlying trends; Exponential smoothing analysis assigns different weights to energy demand data at different time points to reflect the speed of change of energy demand data and make predictions; ARIMA model analysis,inputs energy demand data into the model to capture trends, seasonality and random fluctuations in energy demand data.
4. The method for generating a distributed energy consumption plan according to claim 3, characterized in that: The neural network analysis includes: Multi-layer perceptron analysis processes energy demand data and outputs corresponding data at a certain point in the future; Recurrent neural network analysis captures the dependency of energy demand data between different time points and predicts the corresponding data at the next moment by memorizing the energy demand data at the previous moment; Long short-term memory network analysis, which can retain long-term dependency information through memory cells and capture long-term trends in energy consumption; Bidirectional LSTM analysis improves the prediction accuracy by considering both past and future time information.
5. The method for generating a distributed energy consumption plan according to claim 4, characterized in that: The support vector machine analyzes and processes the nonlinear relationship in the energy demand data and finds the optimal prediction model by optimizing the objective function.
6. A method for generating a distributed energy consumption plan according to claim 5, characterized in that: In step S2, an energy planning algorithm is used to generate an energy planning solution based on ideal future demand data.
7. The method for generating a distributed energy consumption plan according to claim 6, characterized in that: The energy planning algorithm includes: Linear programming, which solves the maximum and minimum values of linear objective functions under given linear equations and inequality constraints to determine the optimal strategy for energy production, distribution and conversion; Integer programming, which is an optimization problem based on linear programming and requires that variables must take integer values. It is used to determine the capacity, quantity and location of equipment in the energy system to meet specific constraints; Dynamic programming is used to solve optimization problems with overlapping subproblems and to develop long-term energy production plans, storage strategies, and conversion schemes to cope with the uncertainty of energy demand.
8. The method for generating a distributed energy consumption plan according to claim 7, characterized in that: In step S3, the energy planning scheme is optimized by using a system design and construction algorithm, wherein the system design and construction algorithm includes a genetic algorithm and a particle swarm optimization; The genetic algorithm is used to determine the best equipment selection, layout and parameter settings in the energy system; the optimal solution is obtained by encoding various configuration parameters in the energy system into chromosomes and defining a fitness function to evaluate the performance of different configurations; The particle swarm optimization is also used to determine the best equipment selection, layout and parameter settings in the energy system. The particle swarm optimization encodes the configuration parameters of the energy system into particles and searches for the optimal solution by continuously updating the position and speed of the particles.
9. The method for generating a distributed energy consumption plan according to claim 8, characterized in that: In step S4, the control algorithm includes but is not limited to a PID control algorithm, a fuzzy control algorithm, and an adaptive control algorithm; The PID control algorithm achieves precise control of the energy system by adjusting the three parameters of proportion, integration and differentiation; The fuzzy control algorithm handles some links that are difficult to accurately model, achieving more flexible and stable control of the energy system; The adaptive control algorithm is used to cope with the uncertainty of energy demand and changes in weather conditions to ensure stable operation and efficient output of the energy system.
10. A method for generating a distributed energy consumption plan according to any one of claims 1 to 9, characterized in that: Regularly maintain and service the energy system to ensure its long-term stable operation.