New energy system collaborative management method and system

Abstract

The invention relates to the field of new energy technology and energy management, and particularly provides a new energy system collaborative management method and system, and the method comprises the following steps: S1, carrying out the global perception and data fusion; s2, an intelligent regulation and control core algorithm; s3, distributed cooperative control is carried out; and S4, carrying out cloud-edge-end collaborative architecture. Compared with the prior art, the method has the advantages that the new energy consumption rate can be increased, the wind curtailment and light curtailment rate can be reduced, dynamic peak load shifting can be realized, the power grid standby capacity requirement can be reduced, multi-objective optimization balance of carbon emission, economy and equipment service life can be realized, and the anti-disturbance capability of the system can be improved.

Description

Technical Field

[0001] The present invention relates to the fields of new energy technologies and energy management, and particularly provides a method and system for collaborative management of a new energy system. Background Art

[0002] New energy sources (such as photovoltaic and wind power) are characterized by volatility and intermittency, making it difficult for traditional regulation methods to achieve multi-energy collaborative optimization. There are "data islands" in the energy system, and there is a lack of dynamic response capabilities between devices, resulting in low energy utilization efficiency and high rates of wind and light abandonment. Existing regulation models are mostly single-objective optimizations (such as only economic), lacking comprehensive consideration of multi-dimensional objectives such as carbon emissions and equipment lifespan.

[0003] In existing technologies, the rule-based control strategies lack flexibility and cannot adapt to complex environmental changes (such as sudden weather changes and electricity price fluctuations). The traditional centralized optimization architecture has a slow response speed and is difficult to meet the real-time regulation requirements of new energy systems. Summary of the Invention

[0004] In view of the above deficiencies of the existing technologies, the present invention provides a practical method for collaborative management of a new energy system.

[0005] A further technical task of the present invention is to provide a new energy system collaborative management system with reasonable design, safety, and applicability.

[0006] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0007] A method for collaborative management of a new energy system includes the following steps:

[0008] S1, Global perception and data fusion;

[0009] S2, Intelligent regulation core algorithm;

[0010] S3, Distributed collaborative control;

[0011] S4, Cloud-edge-end collaborative architecture.

[0012] Further, in step S1, multi-source sensors are deployed to construct a digital twin model of the new energy system, and heterogeneous data is cleaned and feature-extracted in real time through edge computing nodes.

[0013] Further, in step S2, it includes a multi-time scale optimization model and multi-objective collaborative optimization. The multi-time scale optimization model includes long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning; the short-term regulation is to dynamically adjust the energy storage charging and discharging strategy and the grid connection / off-grid switching of the microgrid using reinforcement learning;

[0014] The multi-objective collaborative optimization constructs the objective function Cmin, and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

[0015] Further, in step S3, source-network-load-storage flexible interaction is realized in the microgrid. The photovoltaic inverter and the energy storage system cooperate in frequency regulation, and the electric vehicle charging pile participates in demand response to support V2G.

[0016] Further, in step S4, at the cloud side, global optimization and strategy generation; at the edge layer, local real-time regulation; at the terminal, device-level fast response.

[0017] A new energy system collaborative management system. First, global perception and data fusion are carried out. Then, the intelligent regulation core algorithm and distributed collaborative control are carried out. Finally, the cloud-edge-terminal collaborative architecture is carried out.

[0018] Further, in global perception and data fusion, multi-source sensors are deployed to construct a digital twin model of the new energy system, and heterogeneous data is cleaned and feature-extracted in real time through edge computing nodes.

[0019] Further, the intelligent regulation core algorithm includes a multi-time scale optimization model and multi-objective collaborative optimization. The multi-time scale optimization model includes long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning; the short-term regulation is to dynamically adjust the energy storage charge and discharge strategy and the microgrid grid-connected / off-grid switching using reinforcement learning;

[0020] The multi-objective collaborative optimization constructs the objective function Cmin, and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

[0021] Further, in distributed collaborative control, source-network-load-storage flexible interaction is realized in the microgrid. The photovoltaic inverter and the energy storage system cooperate in frequency regulation, and the electric vehicle charging pile participates in demand response to support V2G.

[0022] Further, in the cloud-edge-terminal collaborative architecture, at the cloud side, global optimization and strategy generation; at the edge layer, local real-time regulation; at the terminal, device-level fast response.

[0023] Compared with the prior art, a new energy system collaborative management method and system of the present invention has the following outstanding beneficial effects:

[0024] The present invention improves the new energy consumption rate by 10% - 20%, reduces the wind and light curtailment rate, reduces the demand for grid reserve capacity through dynamic peak shaving and valley filling, realizes the multi-objective optimization balance of carbon emissions, economy, and equipment life, supports second-level real-time regulation, and improves the system's anti-disturbance ability. Description of the Drawings

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0026] Appendix Figure 1 is a framework schematic diagram of a new energy system collaborative management method;

[0027] Appendix Figure 2 is a flowchart of the intelligent control core algorithm in a new energy system collaborative management method. Specific Embodiments

[0028] To enable those skilled in the art of this technology to better understand the solution of the present invention, the following will further elaborate on the present invention in combination with specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0029] The following gives a best embodiment:

[0030] As Figure 1-2 shown, a new energy system collaborative management method in this embodiment has the following steps:

[0031] S1, Global perception and data fusion;

[0032] Deploy multi-source sensors (light, wind speed, battery SOC, load power, etc.) to build a digital twin model of the new energy system. Through edge computing nodes, real-time cleaning and feature extraction of heterogeneous data (electricity, heat, environment) are performed.

[0033] S2, Intelligent control core algorithm;

[0034] Includes multi-time scale optimization models and multi-objective collaborative optimization. The multi-time scale optimization models include long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning (such as LSTM network); the short-term regulation is to dynamically adjust the energy storage charging and discharging strategy and the grid connection / off-grid switching of the microgrid using reinforcement learning (RL);

[0035] The multi-objective collaborative optimization constructs an objective function Cmin (energy consumption cost + carbon emissions + equipment loss), and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

[0036] S3, Distributed collaborative control;

[0037] Realize the flexible interaction of "source-grid-load-storage" in the microgrid, the photovoltaic inverter and the energy storage system cooperate to frequency regulate, and the electric vehicle (EV) charging pile participates in demand response to support V2G (vehicle-grid interaction).

[0038] S4. Cloud-edge-terminal collaborative architecture;

[0039] Cloud: Global optimization and strategy generation (such as the day-ahead scheduling plan based on weather prediction);

[0040] Edge layer: Local real-time regulation (such as energy storage SOC balance, voltage over-limit correction);

[0041] Terminal: Device-level fast response (such as photovoltaic MPPT control, wind turbine pitch angle adjustment).

[0042] Take the photovoltaic-energy storage-microgrid system as an example:

[0043] S1. Data acquisition;

[0044] Deploy light intensity sensors, battery management systems (BMS), and smart meters to collect data such as photovoltaic output, energy storage SOC, and load power in real time.

[0045] S2. Demand prediction and optimal scheduling;

[0046] The cloud predicts the next day's photovoltaic power generation and load curve through LSTM, generates the energy storage charge and discharge plan, and the edge node dynamically adjusts the energy storage charge and discharge power according to the real-time electricity price and SOC (such as charging at low electricity prices).

[0047] S3. Abnormal condition handling;

[0048] If a sudden drop in photovoltaic output is detected (such as rainy weather), the edge controller starts the standby energy storage power supply and triggers a demand response signal to reduce the power of non-critical loads.

[0049] Take the wind power-hydrogen energy coupling system as an example:

[0050] Use the abandoned wind power to electrolyze water to produce hydrogen, and optimize the start-stop strategy of the hydrogen production equipment through reinforcement learning;

[0051] Combine the hydrogen fuel cell and the energy storage system to suppress the impact of wind power fluctuations on the power grid.

[0052] Based on the above method, in a new energy system collaborative management system in this embodiment, first, perform global perception and data fusion, then, perform intelligent control core algorithms and distributed collaborative control, and finally, perform cloud-edge-terminal collaborative architecture.

[0053] Among them, in global perception and data fusion, multi-source sensors are deployed to build a digital twin model of the new energy system, and heterogeneous data is cleaned and feature-extracted in real time by edge computing nodes.

[0054] The energy regulation core algorithms include multi-time scale optimization models and multi-objective collaborative optimization. The multi-time scale optimization model includes long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning; the short-term regulation is to dynamically adjust the energy storage charge and discharge strategy and the grid-connected / off-grid switching of the microgrid using reinforcement learning.

[0055] Multi-objective collaborative optimization constructs the objective function Cmin and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

[0056] In distributed collaborative control, flexible interaction of source-network-load-storage is realized in the microgrid. The photovoltaic inverter and the energy storage system cooperate in frequency modulation, and the electric vehicle charging pile participates in demand response to support V2G.

[0057] In the cloud-edge-terminal collaborative architecture, in the cloud, there is global optimization and policy generation; in the edge layer, there is local real-time regulation; at the terminal, there is fast device-level response.

[0058] The above specific embodiments are only specific cases of the present invention. The patent protection scope of the present invention includes but is not limited to the above specific embodiments. Any technical solution that conforms to the technical solutions described in the above specific embodiments of the present invention and any appropriate changes or substitutions made by those of ordinary skill in the art shall fall within the patent protection scope of the present invention.

[0059] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A collaborative management method for a new energy system, characterized in that, It has the following steps: S1, Global perception and data fusion; S2, Intelligent regulation core algorithm; S3, Distributed collaborative control; S4, Cloud-edge-terminal collaborative architecture.

2. The collaborative management method of a new energy system according to claim 1, wherein In step S1, multi-source sensors are deployed to build a digital twin model of the new energy system, and heterogeneous data is cleaned and feature-extracted in real time through edge computing nodes.

3. A method for collaborative management of a new energy system according to claim 2, characterized in that, In step S2, it includes a multi-time scale optimization model and multi-objective collaborative optimization. The multi-time scale optimization model includes long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning; the short-term regulation is to dynamically adjust the energy storage charge and discharge strategy and the grid-connected / off-grid switching of the microgrid using reinforcement learning; The multi-objective collaborative optimization constructs an objective function Cmin and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

4. A method for collaborative management of a new energy system according to claim 3, characterized in that, In step S3, flexible interaction between the source, grid, load, and energy storage is achieved in the microgrid. The photovoltaic inverter and the energy storage system cooperate in frequency modulation, and the electric vehicle charging pile participates in demand response to support V2G.

5. A collaborative management method for a new energy system according to claim 4, characterized in that, In step S4, at the cloud, global optimization and strategy generation; at the edge layer, local real-time regulation; at the terminal, device-level fast response.

6. A collaborative management system for a new energy system, characterized in that, First, global perception and data fusion are carried out, then, the intelligent regulation core algorithm and distributed collaborative control are carried out, and finally, the cloud-edge-terminal collaborative architecture is carried out.

7. The collaborative management system of a new energy system according to claim 6, characterized in that, In global perception and data fusion, multi-source sensors are deployed to build a digital twin model of the new energy system, and heterogeneous data is cleaned and feature-extracted in real time through edge computing nodes.

8. The collaborative management system for a new energy system according to claim 7, characterized in that, The intelligent regulation core algorithm includes a multi-time scale optimization model and multi-objective collaborative optimization. The multi-time scale optimization model includes long-term strategies and short-term regulation. The long-term strategy is to predict new energy output and load demand based on deep learning; the short-term regulation is to dynamically adjust the energy storage charge and discharge strategy and the grid-connected / off-grid switching of the microgrid using reinforcement learning; The multi-objective collaborative optimization constructs an objective function Cmin and uses the NSGA-II algorithm to solve the Pareto optimal solution set.

9. The collaborative management system of a new energy system according to claim 8, wherein In distributed collaborative control, flexible interaction between the source, grid, load, and energy storage is achieved in the microgrid. The photovoltaic inverter and the energy storage system cooperate in frequency modulation, and the electric vehicle charging pile participates in demand response to support V2G.

10. The collaborative management system of a new energy system according to claim 9, characterized in that, In the cloud-edge-terminal collaborative architecture, at the cloud, global optimization and strategy generation; at the edge layer, local real-time regulation; at the terminal, device-level fast response.

Images