Smart park comprehensive energy optimization management and control system and management and control method

Abstract

The invention relates to the technical field of energy management, in particular to a smart park comprehensive energy optimization management and control system and method, and the method comprises the following steps: collecting the energy data of electric power, heating power and natural gas in real time, and employing the algorithm based on a long-short-term memory network, support vector regression and random forest regression; modeling is carried out on demand characteristics of electric power, thermal power and natural gas, and future demands are predicted; the method comprises the steps of establishing an optimization objective function, optimizing park energy configuration by adopting a particle swarm optimization algorithm based on the established optimization objective function, determining an optimal energy scheduling scheme, and finally applying the optimized energy scheduling scheme to a park energy management system to realize dynamic scheduling and real-time control of energy. According to the invention, the energy waste of the park can be effectively reduced, the energy use efficiency is improved, and intelligent and refined management of energy is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and particularly to an integrated energy optimization control system and control method for an intelligent park. Background Art

[0002] With the construction and development of intelligent parks, the energy consumption in the parks has gradually increased. Traditional park energy management usually relies on manual or simple scheduling systems, which are difficult to monitor and adjust energy demand in real time, resulting in problems of energy waste and insufficient supply.

[0003] Currently, although some parks have introduced energy management systems based on information technology, the existing technologies often have the following problems: First, most systems lack comprehensive consideration of multiple energy sources, resulting in inefficient cross - energy optimization scheduling. Second, the existing energy management systems rely mostly on static models or simple algorithms for energy demand prediction and scheduling adjustment, and fail to make full use of real - time data for dynamic prediction and scheduling, thus unable to cope with the complex and changeable energy demands in the park. Summary of the Invention

[0004] The present invention provides an integrated energy optimization control system and control method for an intelligent park.

[0005] An integrated energy optimization control method for an intelligent park includes the following steps: S1. Obtain energy data in the intelligent park, where the energy data includes electric energy data, thermal energy data, and natural gas energy data; S2. Based on the collected energy data, establish a mathematical model according to the demand characteristics of various types of energy; S3. Based on the real - time energy data and the mathematical model, conduct real - time monitoring and prediction of various types of energy in the park; S4. Analyze the energy usage demand and establish an optimization objective function; S5. Optimize the energy configuration through an intelligent optimization algorithm to determine the best energy scheduling plan; S6. Apply the energy scheduling plan to the energy management system of the park for dynamic scheduling and real - time control of energy.

[0006] Optionally, the S1 includes: S11. Install electric sensors in the park, and the electric sensors collect real - time electric energy data of the park, including voltage, current, and power; S12. Install temperature, pressure, and flow sensors in the thermal pipeline network in the park to collect real - time thermal energy data of the park, including the flow, temperature, and pressure data of hot water or steam; S13. Install gas flow meters, pressure sensors, and temperature sensors in the natural gas pipelines within the park to collect real-time natural gas energy data, including the flow rate, pressure, and temperature data of natural gas. S14. Preprocess the collected energy data. The preprocessing process includes data cleaning, denoising, and standardization to ensure data quality and accuracy. S15. Upload the preprocessed energy data to the energy management system of the smart park for subsequent analysis and optimization.

[0007] Optionally, S2 includes: S21. Analysis of electricity energy demand characteristics: Analyze the variation patterns of electricity demand in different periods within the park, including peak periods during the day and low periods at night. Through historical electricity energy data, identify the periodic and non-periodic fluctuation characteristics of electricity consumption, and quantitatively describe the electricity demand based on these characteristics.

[0008] S22. Electricity energy modeling: Based on the collected electricity energy data, use the long short-term memory network algorithm to construct an electricity energy mathematical model. S23. Training of the electricity model: Use historical electricity energy data to train the electricity energy mathematical model.

[0009] Optionally, S2 further includes: S25. Analysis of thermal energy demand characteristics: Analyze the thermal energy demand characteristics within the park, including concentrated demand during the heating season and low demand during the non-heating season. Through historical thermal consumption data, identify the seasonal fluctuation of thermal energy demand. S26. Thermal energy modeling: Based on the collected thermal energy data, use the support vector regression algorithm to construct a thermal energy mathematical model. S27. Training of the thermal energy mathematical model: Use historical thermal energy data to train the thermal energy mathematical model.

[0010] Optionally, S2 further includes: Analysis of natural gas energy demand characteristics: Analyze the demand characteristics of natural gas within the park, including demand during winter heating and summer demand, and identify the seasonal change characteristics of natural gas demand.

[0011] Natural gas energy modeling: Based on the collected natural gas energy data, use the random forest regression algorithm to establish a natural gas energy mathematical model. Model training: Use historical natural gas demand data to train the natural gas energy mathematical model.

[0012] Optionally, S3 includes: S31, Electric energy prediction: Based on the real-time collected electric energy data, output the future change trend of electric power demand through the trained electric energy mathematical model; S32, Thermal energy prediction: Based on the real-time collected thermal energy data, output the future change trend of thermal demand through the trained thermal energy mathematical model; S33, Natural gas energy prediction: Based on the real-time collected natural gas energy data, output the future change trend of natural gas demand through the trained natural gas energy mathematical model; S34, Demand comparison: Compare the predicted energy demand results with the actual demand to generate an energy demand prediction report, providing a reference basis for subsequent energy optimization scheduling and real-time control.

[0013] Optionally, the S4 includes: S41, Energy demand analysis: Based on the established mathematical models of electric power, thermal energy and natural gas energy, analyze the energy demand in the park and determine the demand curves of various types of energy; S42, Objective function establishment: According to the demand curves of various types of energy, combined with the existing energy supply capacity and energy cost in the park, establish an optimization objective function.

[0014] Optionally, the S5 includes: S51, Energy optimization: According to the established optimization objective function, use the particle swarm optimization algorithm to optimize the configuration of electric power, thermal energy and natural gas energy in the park; S52, Scheduling plan generation: Based on the optimization results, determine the best scheduling plan for each type of energy in different time periods.

[0015] Optionally, the S6 includes: S61, Plan application: Import the obtained best energy scheduling plan into the energy management system of the park; S62, Energy distribution: The energy management system dynamically adjusts the energy distribution and scheduling according to the best energy scheduling plan; S63, Based on the real-time energy data, conduct real-time control on the usage of electric power, thermal energy and natural gas through the energy management system.

[0016] An integrated energy optimization and control system for an intelligent park, used to implement the above-mentioned integrated energy optimization and control method for an intelligent park, including the following modules: Data acquisition module: Real-time obtain the energy data in the intelligent park through the sensor network, and the energy data includes electric energy data, thermal energy data and natural gas energy data; Energy modeling module: Based on the collected energy data, establish a mathematical model according to the demand characteristics of various types of energy; Prediction Analysis Module: Based on real-time energy data and mathematical models, it monitors and predicts various types of energy in the park in real time; Demand Analysis Module: Analyzes the energy usage demand and establishes an optimization objective function; Energy Optimization Module: Optimizes the energy configuration through intelligent optimization algorithms to determine the best energy scheduling plan; Scheme Application Module: Applies the energy scheduling plan to the energy management system of the park for dynamic scheduling and real-time control of energy.

[0017] Advantages of the present invention: In the present invention, through the real-time monitoring and prediction of three types of energy, namely electricity, heat, and natural gas, in the smart park, accurate mathematical models are constructed using long short-term memory networks, support vector regression, and random forest regression algorithms, enabling accurate grasp of the demand changes and seasonal fluctuations of the park's energy. Through the real-time prediction of these models, the energy supply plan can be adjusted in a timely manner, thereby significantly improving the energy utilization efficiency and reducing energy waste.

[0018] In the present invention, the particle swarm optimization algorithm is combined to optimize the energy configuration based on real-time data and model prediction. Through intelligent optimization algorithms, the present invention can accurately schedule the best usage plans for electricity, heat, and natural gas according to the demand fluctuations in different time periods. This optimization process can effectively reduce the energy cost in the park, avoid over-purchasing and waste of energy, and achieve refined and economical energy management in the park. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic flowchart of the method according to the embodiment of the present invention; Figure 2 It is a schematic flowchart of the system according to the embodiment of the present invention. Detailed Embodiments

[0021] The present invention will be described in detail below in combination with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawing part is only for more specific description of the embodiments, and is not intended to specifically limit the present invention.

[0022] It should be noted that in the specification, the mention of "an embodiment", "embodiment", "exemplary embodiment", "some embodiments", etc. indicates that the described embodiments may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. Additionally, when combining an embodiment to describe a specific feature, structure or characteristic, implementing such feature, structure or characteristic in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0023] Generally, terms can be understood at least in part from their use in the context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but instead, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0024] As Figure 1 shown, an integrated energy optimization control method for an intelligent park includes the following steps: S1. Obtain the energy data in the intelligent park, where the energy data includes electric energy data, thermal energy data, and natural gas energy data; S2. Based on the collected energy data, establish a mathematical model according to the demand characteristics of various types of energy; S3. Based on the real-time energy data and the mathematical model, conduct real-time monitoring and prediction of various types of energy in the park; S4. Analyze the energy usage demand and establish an optimization objective function; S5. Optimize the energy configuration through an intelligent optimization algorithm to determine the best energy scheduling plan; S6. Apply the energy scheduling plan to the energy management system of the park for dynamic scheduling and real-time control of energy.

[0025] S1 includes: S11. Deploy electric sensors in the park, and the electric sensors collect the electric energy data of the park in real time, including voltage, current, and power; S12. Deploy temperature, pressure, and flow sensors in the thermal pipeline network in the park for collecting the thermal energy data of the park in real time, including the flow rate, temperature, and pressure data of hot water or steam; S13. Deploy gas flow meters, pressure sensors, and temperature sensors in the natural gas pipelines in the park for collecting the natural gas energy data in real time, including the flow rate, pressure, and temperature data of natural gas; S14. Preprocess the collected energy data. The preprocessing process includes data cleaning, denoising, and standardization to ensure data quality and accuracy. S15. Upload the preprocessed energy data to the energy management system of the smart park for subsequent analysis and optimization.

[0026] S2 includes: S21. Analysis of the characteristics of electricity energy demand: Analyze the variation rules of electricity demand in different periods within the park, including the peak period during the day and the low period at night. Through historical electricity energy data, identify the periodic and non-periodic fluctuation characteristics of electricity consumption, and quantitatively describe the electricity demand based on these characteristics.

[0027] S22. Electricity energy modeling: Based on the collected electricity energy data, use the long short-term memory network algorithm to construct a mathematical model of electricity energy. The specific steps include: Feature selection and extraction: Extract relevant feature variables from the collected electricity energy data, including voltage, current, and power. Model construction: Use the long short-term memory network algorithm to construct a mathematical model of electricity energy. The model includes: Input layer: It contains multiple feature input units and inputs time series feature data (such as voltage, current, and power).

[0028] Hidden layer: Set multiple long short-term memory network units to learn the time dependence of the input data.

[0029] Output layer: Output the predicted value of future electricity demand through the long short-term memory network units.

[0030] The basic formula of the LSTM model is: ; Where, is the long short-term memory network, is the input data, and are the weights and bias terms, is the hidden state at the current moment, is the cell state at the previous moment; The model prediction formula is: ; Where, is the predicted electricity demand value, and are the weights and bias of the output layer; The mathematical model of electricity energy can effectively capture the time dependence and long-term trend of electricity demand, and adapt to factors such as seasonality and holiday changes within the park; S23, Power model training: Use historical power energy data to train the power energy mathematical model.

[0031] S2 also includes: S25, Thermal energy demand characteristic analysis: Analyze the thermal demand characteristics in the park, including the concentrated demand in the heating season and the low demand in the non - heating season. Identify the seasonal fluctuations of thermal demand through historical thermal consumption data; S26, Thermal energy modeling: Based on the collected thermal energy data, use the support vector regression algorithm to construct a thermal energy mathematical model, specifically including: According to the seasonal fluctuation characteristics of thermal demand, extract the main features affecting thermal demand from historical thermal energy data, such as time factors (season, month, time period within a day) and pressure, flow rate, etc.; Use the support vector regression algorithm to construct a thermal energy mathematical model to predict thermal demand in different time periods and seasons. The model expression is: ; Among them, represents the input features (such as time, temperature, etc.), is the weight of the support vector, is the kernel function, is the bias term; S27, Thermal energy mathematical model training: Use historical thermal energy data to train the thermal energy mathematical model.

[0032] S2 further includes: Natural gas energy demand characteristic analysis: Analyze the demand characteristics of natural gas in the park, including the demand in winter heating and summer demand, and identify the seasonal change characteristics of natural gas demand.

[0033] Natural gas energy modeling: Based on the collected natural gas energy data, use the random forest regression algorithm to establish a natural gas energy mathematical model, specifically including: Feature selection: Extract the key features affecting natural gas demand from historical natural gas energy data, such as timestamps (including year, month, day, hour), temperature, pressure, etc.; Model construction: Use the random forest regression algorithm to model natural gas demand through multiple decision trees. Each decision tree will be trained based on different feature combinations, and finally a more robust prediction result will be obtained through ensemble learning; Let the natural gas demand be , the feature vector be , where are the respective features, and the model is expressed as: ; Among them, is the output of the k-th decision tree, is the weight of the tree. By integrating the prediction results of all decision trees, the final natural gas demand prediction value is obtained; Model training: Use historical natural gas demand data to train the natural gas energy mathematical model.

[0034] S3 includes: S31, Electric energy prediction: Based on the real-time collected electric energy data, output the future change trend of the electric demand through the trained electric energy mathematical model; S32, Thermal energy prediction: Based on the real-time collected thermal energy data, output the future change trend of the thermal demand through the trained thermal energy mathematical model; S33, Natural gas energy prediction: Based on the real-time collected natural gas energy data, output the future change trend of the natural gas demand through the trained natural gas energy mathematical model; S34, Demand comparison: Compare the predicted energy demand results with the actual demand, generate an energy demand prediction report, and provide a reference basis for subsequent energy optimization scheduling and real-time control.

[0035] S4 includes: S41, Energy demand analysis: Based on the established mathematical models of electric, thermal and natural gas energy, analyze the energy demand in the park and determine the demand curves of various types of energy; S42, Objective function establishment: According to the demand curves of various types of energy, combined with the existing energy supply capacity and energy cost in the park, establish an optimization objective function, expressed as: Objective function ; where, is the electricity operation cost at time , is the thermal operation cost at time , is the natural gas operation cost at time . And by optimizing the supply of electricity, heat and natural gas at time , the overall cost is minimized to ensure the balanced supply and efficient use of energy.

[0036] S5 includes: S51, Energy optimization: According to the established optimization objective function, use the particle swarm optimization algorithm to optimize the electricity, heat and natural gas energy configuration in the park, specifically including: Initialize the particle swarm, each particle represents an energy configuration plan, and set the initial position and velocity of the particle according to historical data and current demand; By iteratively updating the velocities and positions of the particles, the particle swarm gradually approaches the optimal energy allocation solution. In each iteration, the objective function value is calculated, and the best position of the particle is updated according to the objective function value; In each iteration of the particle swarm, the supply-demand balance and operating costs of various types of energy are considered to ensure the minimum energy waste and maximum energy utilization efficiency during the optimization process; S52, Generation of scheduling plan: Based on the optimization results, determine the optimal scheduling plan for each type of energy in different time periods, specifically including: According to the optimized energy allocation results, establish a time period scheduling plan for energy to ensure that the supply of each type of energy meets the park's demand during different load periods (such as peak periods, off-peak periods, etc.); Monitor the energy usage in real time and dynamically adjust the scheduling plan according to the energy demand fluctuations to maintain the stability and optimal economy of energy supply; According to the actual operating conditions, further adjust the scheduling plan to ensure the coordinated operation of electricity, heat, and natural gas and optimize the energy utilization efficiency in the park.

[0037] S6 includes: S61, Application of the plan: Import the obtained optimal energy scheduling plan into the park's energy management system; S62, Energy allocation: The energy management system dynamically adjusts the energy allocation and scheduling according to the optimal energy scheduling plan; S63, Based on real-time energy data, the energy management system performs real-time control on the usage of electricity, heat, and natural gas.

[0038] As Figure 2 shown, an integrated energy optimization and control system for a smart park, used to implement the above-mentioned integrated energy optimization and control method for a smart park, includes the following modules: Data acquisition module: Real-time obtain energy data in the smart park through a sensor network. The energy data includes electricity energy data, heat energy data, and natural gas energy data; Energy modeling module: Based on the collected energy data, establish a mathematical model according to the demand characteristics of various types of energy; Prediction and analysis module: Based on real-time energy data and the mathematical model, perform real-time monitoring and prediction on various types of energy in the park; Demand analysis module: Analyze the energy usage demand and establish an optimization objective function; Energy optimization module: Optimize the energy allocation through intelligent optimization algorithms to determine the optimal energy scheduling plan; Plan application module: Apply the energy scheduling plan to the park's energy management system for dynamic scheduling and real-time control of energy.

[0039] The present invention covers any alternatives, modifications, equivalent methods and solutions made to the essence and scope of the present invention. For the purpose of enabling the public to thoroughly understand the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention even without the description of these details. In addition, well-known methods, processes, procedures, components and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0040] The above description is only a preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A comprehensive energy optimization management and control method for a smart park, characterized in that: The following steps are involved: S1, obtain energy data in the smart park, including electric energy data, thermal energy data and natural gas energy data; S2, based on the collected energy data, a mathematical model is established according to the demand characteristics of various energy sources; S3, based on real-time energy data and mathematical models, conducts real-time monitoring and prediction of various energy sources in the park; S4, analyzing the energy usage demand and establishing the optimization objective function; S5, optimizes energy configuration through intelligent optimization algorithm and determines the best energy scheduling plan; S6, applies the energy scheduling solution to the park’s energy management system to perform dynamic scheduling and real-time control of energy.

2. A smart park comprehensive energy optimization management and control method according to claim 1, characterized in that: The S1 includes: S11, deploying power sensors in the park, wherein the power sensors collect power energy data of the park in real time, including voltage, current and power; S12, deploying temperature, pressure and flow sensors in the thermal pipe network in the park to collect real-time thermal energy data of the park, including flow, temperature and pressure data of hot water or steam; S13, gas flow meters, pressure sensors and temperature sensors are installed in the natural gas pipelines in the park to collect natural gas energy data in real time, including natural gas flow, pressure and temperature data; S14, preprocessing the collected energy data, the preprocessing process includes data cleaning, denoising and standardization; S15, uploading the pre-processed energy data to the energy management system of the smart park.

3. A smart park comprehensive energy optimization management and control method according to claim 2, characterized in that: The S2 includes: S21, analysis of power energy demand characteristics: Analyze the changing patterns of power demand in the park at different time periods, including the daytime peak period and the nighttime trough period, and identify the periodic and non-periodic fluctuation characteristics of power consumption through historical power energy data; S22, power energy modeling: Based on the collected power energy data, a long short-term memory network algorithm is used to construct a power energy mathematical model; S23, power model training: use historical power energy data to train the power energy mathematical model.

4. A smart park comprehensive energy optimization management and control method according to claim 3, characterized in that: The S2 further includes: S25, Analysis of thermal energy demand characteristics: Analyze the thermal demand characteristics within the park, including concentrated demand during the heating season and low demand during the non-heating season, and identify seasonal fluctuations in thermal demand through historical thermal consumption data; S26, Thermal Energy Modeling: Based on the collected thermal energy data, a thermal energy mathematical model is constructed using the support vector regression algorithm; S27, thermal energy mathematical model training: use historical thermal energy data to train the thermal energy mathematical model.

5. A smart park comprehensive energy optimization management and control method according to claim 4, characterized in that: The S2 further comprises: Analysis of natural gas energy demand characteristics: Analyze the natural gas demand characteristics in the park, including winter heating demand and summer demand, and identify the seasonal variation characteristics of natural gas demand; Natural gas energy modeling: Based on the collected natural gas energy data, a natural gas energy mathematical model is established using the random forest regression algorithm; Model training: Use historical natural gas demand data to train the natural gas energy mathematical model.

6. A smart park comprehensive energy optimization management and control method according to claim 5, characterized in that: The S3 includes: S31, power energy forecast: Based on the real-time collected power energy data, the future trend of power demand is output through the trained power energy mathematical model; S32, thermal energy forecast: Based on the real-time collected thermal energy data, the future trend of thermal demand is output through the trained thermal energy mathematical model; S33, natural gas energy forecast: Based on the real-time collected natural gas energy data, the future trend of natural gas demand is output through the trained natural gas energy mathematical model; S34, demand comparison: compare the predicted energy demand results with the actual demand and generate an energy demand forecast report.

7. A smart park comprehensive energy optimization management and control method according to claim 6, characterized in that: The S4 includes: S41, Energy demand analysis: Based on the established mathematical models of electricity, heat and natural gas energy, analyze the energy demand in the park and determine the demand curves of various energy sources; S42, objective function establishment: According to the demand curves of various energy sources, combined with the existing energy supply capacity and energy costs in the park, an optimization objective function is established.

8. A smart park comprehensive energy optimization management and control method according to claim 7, characterized in that: The S5 includes: S51, Energy Optimization: Based on the established optimization objective function, the particle swarm optimization algorithm is used to optimize the power, heat and natural gas energy configuration in the park; S52, generation of scheduling plan: based on the optimization results, determine the best scheduling plan for each energy source in different time periods.

9. A smart park comprehensive energy optimization management and control method according to claim 8, characterized in that: The S6 includes: S61, solution application: import the obtained optimal energy scheduling solution into the energy management system of the park; S62, Energy Allocation: The energy management system dynamically adjusts energy allocation and scheduling according to the optimal energy scheduling plan; S63, based on real-time energy data, controls the use of electricity, heat and natural gas in real time through the energy management system.

10. A smart park comprehensive energy optimization management and control system, used to implement a smart park comprehensive energy optimization management and control method as described in any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: obtains energy data in the smart park in real time through the sensor network. The energy data includes electric energy data, thermal energy data and natural gas energy data; Energy modeling module: Based on the collected energy data, a mathematical model is established according to the demand characteristics of various energy sources; Prediction and analysis module: Based on real-time energy data and mathematical models, it conducts real-time monitoring and prediction of various energy sources in the park; Demand analysis module: Analyze energy usage demand and establish optimization objective function; Energy optimization module: optimizes energy configuration through intelligent optimization algorithms to determine the best energy scheduling plan; Solution application module: Apply the energy scheduling solution to the park's energy management system to perform dynamic scheduling and real-time control of energy.

Images