Multi-energy dynamic regulation and control system and method based on electricity-heat-energy storage collaborative optimization
The multi-energy dynamic control system, which optimizes the synergy of electricity, heat and energy storage, solves the problems of low energy utilization, slow response and high energy consumption in multi-energy systems. It achieves efficient energy management and system stability and is suitable for microgrids, distributed energy systems, industrial parks and smart building complexes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-11
- Publication Date
- 2026-04-14
AI Technical Summary
Existing multi-energy systems suffer from low energy utilization, slow system response, high energy consumption, and lack of integrated optimization and dynamic control capabilities for electricity, heat, and energy storage, making it difficult to quickly respond to load fluctuations and unstable renewable energy output.
A multi-energy dynamic control system based on synergistic optimization of electricity, heat and energy storage is adopted. Through data acquisition, load and renewable energy forecasting, joint optimization control module of electricity, heat and energy storage and execution and feedback module, multi-energy synergistic control is achieved. Time series and machine learning models are used to improve prediction accuracy and response speed. Energy output and energy storage strategy are optimized by combining multi-objective optimization algorithm.
It achieves efficient coordinated control of multiple energy systems, reduces total system energy consumption, improves energy utilization, responds in real time to load and renewable energy fluctuations, and ensures stable system operation.
Smart Images
Figure CN121863549A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of energy system optimization and intelligent control, and in particular to a multi-energy dynamic regulation system based on the coordinated optimization of electricity, heat and energy storage, as well as a dynamic regulation method. Background Technology
[0002] In existing multi-energy systems, the output of energy sources such as wind power, photovoltaic power, waste heat from natural gas, and energy storage is volatile, and the load demand is complex and variable, leading to the following problems in the system.
[0003] 1. Low energy utilization: Single optimization strategies usually only consider electricity or heat, lacking energy storage and coordinated scheduling, resulting in some energy waste.
[0004] 2. Slow system response: Existing control methods lack dynamic adjustment capabilities and are unable to quickly respond to load fluctuations and unstable output from renewable energy sources.
[0005] 3. High energy consumption: Under traditional static scheduling, the system consumes a lot of energy, energy storage is not fully utilized, and heat recovery efficiency is low.
[0006] Therefore, there is a need for a control system and method that can achieve joint optimization, dynamic regulation, and real-time response to load and renewable energy fluctuations of electricity, heat and energy storage, so as to improve energy utilization and reduce system losses. Summary of the Invention
[0007] One of the objectives of this invention is to provide a multi-energy dynamic control system based on the coordinated optimization of electricity, heat and energy storage, in order to solve the problems of low energy utilization, large system losses, slow control response and underutilization of energy storage in existing multi-energy systems.
[0008] The technical solution adopted by this invention to solve its technical problem is: a multi-energy dynamic control system based on synergistic optimization of electricity, heat, and energy storage, including a data acquisition module, a load and renewable energy prediction module, an electricity-heat-energy storage joint optimization control module, and an execution and feedback module connected in sequence; multi-energy synergistic control is achieved through an electricity-heat-energy storage joint optimization algorithm: the data acquisition module collects in real time various energy outputs (electricity, heat), power load, heat load, energy storage status (SOC, temperature, etc.) and environmental information (temperature, irradiance, wind speed, etc.), providing a real-time data foundation for prediction and optimization control, and realizing... The system features dynamic regulation and control. The load and renewable energy prediction module predicts the power load, heat load, and renewable energy (wind and solar) output over a future period based on historical data and real-time monitoring data. The electricity-heat-energy storage joint optimization control module establishes a joint optimization model for electricity, heat, and energy storage, dynamically calculates the output of each energy source and the charging and discharging strategies of energy storage. The execution and feedback module converts the optimization calculation results into control commands, dynamically adjusts the output of each energy source and the charging and discharging of energy storage, and collects system feedback data in real time to form a closed-loop control, ensuring that the optimization strategy continuously adapts to load and energy fluctuations and achieves dynamic regulation and control.
[0009] Furthermore, the load and renewable energy forecasting module employs time series models (such as ARIMA), machine learning models (such as LSTM), or combined forecasting methods to improve forecast accuracy and response speed.
[0010] Furthermore, the joint optimization control module establishes an optimization model based on a multi-objective optimization algorithm. The optimization objective is to minimize the total energy loss of the system and ensure load stability. This includes minimizing the total energy loss of the system (including electrical energy, thermal energy, and energy storage loss), maximizing the utilization rate of renewable energy, and ensuring a stable supply of electrical and thermal loads. It also includes constraints on energy storage capacity, electrical-thermal balance, and system safety and stable operation. The solution method employs mixed integer programming (MIP), model predictive control (MPC), genetic algorithms, or combinatorial optimization algorithms.
[0011] The second objective of this invention is to provide a multi-energy dynamic control method based on the synergistic optimization of electricity, heat, and energy storage, the steps of which are as follows: The first step is data acquisition: real-time acquisition of various energy data and environmental parameters, including energy output including power output and heat output, as well as energy storage status information, load data and environmental information, etc. The sampling period is 1 to 10 minutes, which can be adjusted according to the system scale. The second step is load forecasting: based on historical data and real-time monitoring, forecasting the electricity load, heat load and renewable energy output for the next period. The third step is to establish a joint optimization model for electricity, heat, and energy storage: Define a multi-objective optimization function The constraints are set as energy storage capacity, electrical-thermal balance, load demand, and system safety. Set the optimization objective function ,in P grid For power input from the power grid, P loss For energy storage and power system losses, Q loss For heat energy system losses; The constraints include: energy storage capacity constraints. SOC min ≤ SOC(t) ≤ SOC max Electro-thermal balance constraint , And system safety constraints: voltage, current, and temperature are all within the allowable range; The fourth step is to solve the optimization problem: the control strategy is solved by a multi-objective optimization algorithm to obtain the optimal strategies for each energy output and energy storage charging and discharging, and the strategies for each energy output and energy storage charging and discharging are dynamically adjusted. The fifth step is execution control: the optimization strategy is converted into control commands, the control commands are sent to each energy device, the energy storage charging and discharging, the output of electricity and heat are dynamically adjusted, and the execution effect is collected in real time to form a closed-loop control. Step 6, Feedback Correction: Collect the control data executed in Step 5, update the prediction model and optimization parameters, and form a dynamic closed-loop control.
[0012] Furthermore, in the second step, the power load forecast is based on historical load data and uses an LSTM neural network to predict the load for the next hour; the heat load forecast combines weather data (temperature, humidity) and historical heat load and uses multivariate linear regression for prediction; the photovoltaic forecast in renewable energy uses short-term time series combined with irradiance correction for prediction; and the wind power forecast uses the ARIMA model.
[0013] The beneficial effects of this invention are as follows: This invention treats electricity, heat energy, and energy storage as a unified optimization object to achieve multi-energy coordinated regulation and improve the overall system efficiency; it significantly reduces the total energy consumption of the system through joint optimization strategies, including energy storage losses and heat energy waste, resulting in significant energy-saving effects; it can respond in real time to load fluctuations and changes in renewable energy output to achieve dynamic regulation and ensure stable system operation; and it is applicable to microgrids, distributed energy systems, industrial parks, and smart building complexes, and can be combined with cloud computing to achieve cross-regional collaborative optimization.
[0014] The method of this invention can effectively cope with the fluctuations in renewable energy and load changes, improve system stability and energy utilization efficiency, and is applicable to dynamic energy management in microgrids, distributed energy systems, industrial parks and smart building complexes. Attached Figure Description
[0015] Figure 1 This is a block diagram of the control system structure of the present invention; Figure 2 This is a flowchart of the joint optimization control method of the present invention (MPC optimization framework).
[0016] The attached diagrams are labeled as follows: 1—Data acquisition module, 2—Load and renewable energy forecasting module, 3—Joint optimization control module, 4—Execution and feedback module. Detailed Implementation
[0017] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.
[0018] This invention provides a multi-energy dynamic control system based on the synergistic optimization of electricity, heat, and energy storage to achieve the following objectives: dynamic synergistic control of electricity, heat, and energy storage to improve the overall utilization efficiency of the multi-energy system; significant reduction of total system energy consumption and heat waste through joint optimization algorithms; efficient charging and discharging management of the energy storage system to extend its lifespan and reduce energy loss; dynamic adaptation to load changes and renewable energy output fluctuations to ensure stable system operation; and applicability to microgrids, distributed energy systems, industrial parks, and smart building complexes to achieve intelligent energy management.
[0019] like Figure 1 As shown, the system includes a data acquisition module 1, a load and renewable energy prediction module 2, an electricity-heat-energy storage joint optimization control module 3, and an execution and feedback module 4, connected in sequence. It achieves multi-energy coordinated regulation through an electricity-heat-energy storage joint optimization algorithm. The energy storage module includes electrochemical energy storage and thermal energy storage, used for dynamically adjusting the energy supply and demand balance.
[0020] Data acquisition module 1 can collect various energy outputs (electrical energy, thermal energy), power load, heat load, energy storage status (SOC, temperature, etc.), and environmental information (temperature, irradiance, wind speed, etc.) in real time. This provides a real-time data foundation for prediction and optimization control, enabling dynamic system regulation.
[0021] The load and renewable energy forecasting module 2 can predict electricity load, heat load, and renewable energy (wind and solar) output over a future period based on historical data and real-time monitoring. It employs time series models (such as ARIMA), machine learning models (such as LSTM), or a combination of forecasting methods to improve forecast accuracy and response speed.
[0022] The joint optimization control module 3 for electricity, heat, and energy storage establishes a joint optimization model for these three components. It dynamically calculates the output of each energy source and the charging and discharging strategies for energy storage, and builds an optimization model based on a multi-objective optimization algorithm. Its optimization objectives include minimizing total system energy loss (including electrical, thermal, and energy storage losses), maximizing renewable energy utilization, and ensuring a stable supply of electricity and heat loads. It also incorporates constraints related to energy storage capacity, electricity-heat balance, and system safety and stability. The solution method can employ mixed-integer programming (MIP), model predictive control (MPC), genetic algorithms, or combinatorial optimization algorithms.
[0023] Joint optimization control can dynamically respond to load changes and renewable energy fluctuations, thereby maximizing energy utilization efficiency.
[0024] The execution and feedback module 4 can convert the optimization calculation results into control commands, dynamically adjust the output of each energy source and the charging and discharging of energy storage, and collect system feedback data in real time. This function can form a closed-loop control to ensure that the optimization strategy continuously adapts to load and energy fluctuations and achieves dynamic regulation.
[0025] The dynamic control system of this invention can be used for dynamic energy management in distributed energy systems, microgrids, industrial parks and smart building complexes. It aims to reduce system operating energy consumption, improve energy utilization, and achieve dynamic coordinated scheduling of electricity, heat and energy storage.
[0026] like Figure 2 As shown, the present invention discloses a multi-energy dynamic control method based on the synergistic optimization of electricity, heat and energy storage, the steps of which are as follows.
[0027] The first step is data collection.
[0028] It collects various energy data and environmental parameters in real time, including energy output such as power output and heat output, as well as energy storage status information, load data and environmental information. The sampling period is 1 to 10 minutes, which can be adjusted according to the system scale.
[0029] The second step is load forecasting.
[0030] Based on historical data and real-time monitoring, predictive models are used to calculate the electricity load, heat load, and renewable energy output for the next time period.
[0031] This method predicts the electricity load, heat load, and renewable energy output for the next time period. Electricity load forecasting can be based on historical load data, using an LSTM neural network to predict the load for the next hour. Heat load forecasting can combine weather data (temperature, humidity) and historical heat load data, employing multivariate linear regression. For renewable energy, photovoltaic forecasting can use short-term time series data combined with irradiance correction. Wind power forecasting can use an ARIMA model. This allows for the prediction of the electricity load for the next time period.P load Heat load Q load Renewable power output P renew .
[0032] The third step is to optimize the model: establish a joint optimization model of electricity, heat and energy storage.
[0033] Define a multi-objective optimization function The constraints are set as energy storage capacity, electric-thermal balance, load demand and system safety.
[0034] Set the optimization objective function ,in P grid For power input from the power grid, P loss For energy storage and power system losses, Q loss This refers to the loss of thermal energy in the system.
[0035] When optimizing the model, energy storage capacity constraints, electrical-thermal balance constraints, and system safety constraints should be considered.
[0036] The constraints are as follows: including energy storage capacity constraints. SOC min ≤ SOC(t) ≤ SOC max Electro-thermal balance constraint , System safety constraints: Voltage, current, and temperature are all within the allowable range.
[0037] The fourth step is optimization: the control strategy is solved by multi-objective optimization algorithm to obtain the optimal strategy for each energy output and energy storage charging and discharging, and the strategy for each energy output and energy storage charging and discharging is dynamically adjusted.
[0038] The optimal scheduling strategy is solved using mixed-integer programming (MIP), model predictive control (MPC), or genetic algorithms to predict the optimal scheduling strategy for the next hour. This yields power dispatch instructions, including: charging and discharging power of each energy storage unit, photovoltaic / wind power utilization ratio, grid input power, and thermal energy dispatch instructions, including: thermal energy storage charging and discharging power, and thermal load allocation strategy.
[0039] Step 5: Execution control.
[0040] The optimization strategy is transformed into control commands, which are then sent to each energy device to dynamically adjust the charging and discharging of energy storage, as well as the output of electricity and heat. The execution effect is collected in real time to form a closed-loop control.
[0041] Feedback data is used to revise the prediction model and optimize parameters for the next cycle, thereby improving the system's dynamic response capability.
[0042] Step 6: Feedback and correction.
[0043] The fifth step involves collecting control data, updating the prediction model and optimizing parameters to form a dynamic closed-loop control.
[0044] Those skilled in the art will readily understand that the above description is merely a preferred use case of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A multi-energy dynamic control system based on synergistic optimization of electricity, heat, and energy storage, characterized in that: The system includes a data acquisition module (1), a load and renewable energy prediction module (2), a joint optimization control module (3), and an execution and feedback module (4) connected in sequence. The data acquisition module (1) collects real-time data on various energy outputs, including electricity and heat, power load, heat load, energy storage status including SOC and temperature, and environmental information including temperature, irradiance, and wind speed, providing a real-time data basis for prediction and optimization control. The load and renewable energy prediction module (2) predicts power load, heat load, and renewable energy output including wind and photovoltaic power in the future based on historical data and data obtained from real-time monitoring. The joint optimization control module (3) establishes a joint optimization model for electricity, heat, and energy storage, dynamically calculates the output of each energy source and the charging and discharging strategy of energy storage. The execution and feedback module (4) converts the calculation results into control commands, dynamically adjusts the output of each energy source and the charging and discharging of energy storage, and collects system feedback data in real time to form a closed-loop control to achieve dynamic regulation.
2. The multi-energy dynamic control system based on synergistic optimization of electricity, heat, and energy storage as described in claim 1, characterized in that, The load and renewable energy forecasting module (2) uses time series models, machine learning models or combined forecasting methods to improve forecast accuracy and response speed.
3. The multi-energy dynamic control system based on synergistic optimization of electricity, heat, and energy storage as described in claim 1 or 2, characterized in that, The joint optimization control module (3) establishes an optimization model based on a multi-objective optimization algorithm. The optimization objectives include minimizing the total energy loss of the system, maximizing the utilization rate of renewable energy, ensuring the stable supply of power load and heat load, and having energy storage capacity, electric-heat balance and system safety and stable operation constraints. The solution method adopts mixed integer programming, model predictive control, genetic algorithm or combinatorial optimization algorithm.
4. A multi-energy dynamic control method based on synergistic optimization of electricity, heat, and energy storage, employing the control system described in claim 1, characterized in that: The steps are as follows: The first step is to collect real-time data on energy output, including power output and heat output, as well as energy storage status information, load data, and environmental information, with a sampling period of 1 to 10 minutes. The second step is to predict the electricity load, heat load, and renewable energy output for the next period based on historical data and real-time monitoring. The third step is to define the multi-objective optimization function. The constraints are set as energy storage capacity, electrical-thermal balance, load demand, and system safety. Set the optimization objective function ,in P grid For power input from the power grid, P loss For energy storage and power system losses, Q loss For heat energy system losses; The constraints include: energy storage capacity constraints. SOC min ≤ SOC(t) ≤ SOC max Electro-thermal balance constraint , And system safety constraints: voltage, current, and temperature are all within the allowable range; The fourth step is to solve the control strategy through a multi-objective optimization algorithm to obtain the optimal strategies for each energy output and energy storage charging and discharging, and then dynamically adjust the strategies for each energy output and energy storage charging and discharging. The fifth step is to convert the optimization strategy into control commands, send the control commands to each energy device, dynamically adjust the charging and discharging of energy storage, the output of electricity and heat, and collect the execution effect in real time to form a closed-loop control. Step 6, Feedback and Correction: Collect the execution control data from Step 5, update the prediction model and optimize the parameters.
5. The multi-energy dynamic control method based on synergistic optimization of electricity, heat, and energy storage as described in claim 4, characterized in that, In the second step, the power load forecast is based on historical load data and uses an LSTM neural network to predict the load for the next hour; the heat load forecast combines weather data including temperature and humidity with historical heat load and uses multivariate linear regression for prediction; the photovoltaic forecast for renewable energy uses short-term time series combined with irradiance correction for prediction; and the wind power forecast uses the ARIMA model.