Dynamic adjusting and optimizing method supporting source-grid-load-storage integrated coordination of micro-grid

Abstract

The invention discloses a dynamic adjusting and optimizing method supporting source-grid-load-storage integrated coordination of a micro-grid, and relates to the technical field of source-grid-load-storage of the micro-grid, and the method comprises the steps: 1, obtaining the power generation data of the micro-grid and the power utilization data of a power receiving unit, processing the power generation data and the power utilization data, and carrying out the distributed aggregation modeling, constructing a dynamic factor library based on external factor influence; 2, calling data in the dynamic factor library, and determining use scenes under different preconditions in combination with a user factor, a power consumption time period factor, a power supply load factor and an energy storage level factor; step 3, combining a plurality of use scenes and establishing a source network load storage scheduling scheme; 4, inputting different use scenes for multiple times, carrying out iterative optimization on the source network load storage scheduling scheme, and determining a source network load storage panoramic view; and step 5, based on the established source network load storage panoramic view, scheduling the micro-grid power by taking the highest tuning efficiency as a target. According to the invention, the operation efficiency of the source network load storage of the micro-grid is improved.

Description

Technical Field

[0001] This invention relates to the field of microgrid power generation, grid, load and energy storage technology, and in particular to a dynamic optimization method that supports integrated coordination of power generation, grid, load and energy storage in microgrids. Background Technology

[0002] In modern society, with the continuous increase in electricity demand and the requirements of environmental protection, microgrids, as small-scale power systems capable of self-control and self-management, have received widespread attention. Microgrids typically consist of distributed power sources, energy storage systems, and loads, enabling self-generation and self-consumption of electricity while exchanging energy with the main power grid. Integrated source-grid-load-storage coordinated control is an important technology in microgrids, aiming to improve the operational efficiency and economic benefits of the microgrid's source, grid, load, and storage systems by coordinating their operation.

[0003] Existing integrated control technologies for microgrid power generation, grid, load, and energy storage primarily involve real-time monitoring and management of the microgrid's operational status, followed by scheduling and control based on real-time data. These technologies typically employ a centralized control approach, where all control decisions are made by a single central controller. Additionally, some technologies utilize a distributed control approach, where each component has its own control authority, achieving overall optimized control through mutual coordination. However, existing integrated control technologies for microgrid power generation, grid, load, and energy storage have several limitations.

[0004] First, existing technologies are typically based on real-time data and cannot predict future operating conditions, thus hindering advance scheduling and control and impacting the operational efficiency of microgrid power generation, grid, load, and energy storage systems. Second, existing technologies are usually based on centralized control methods, which are prone to single points of failure and are ill-suited for large-scale microgrid systems. Furthermore, when considering the operational status of microgrids, existing technologies typically only consider the operating status of the power source and grid, neglecting the operational status of the energy storage system, thereby limiting further improvements in the operational efficiency of power generation, grid, load, and energy storage systems. Summary of the Invention

[0005] This invention is achieved through the following technical solution:

[0006] A dynamic optimization method supporting integrated coordination of power generation, grid, load, and energy storage in microgrids includes the following steps:

[0007] Step 1: Obtain microgrid power generation data and power consumption data of receiving units, process the power generation data and power consumption data and perform distributed aggregation modeling to build a dynamic factor library based on the influence of external factors;

[0008] Step 2: Retrieve data from the dynamic factor library and combine it with user factors, electricity consumption time factors, power load factors, and energy storage level factors to determine the usage scenarios under different preconditions;

[0009] Step 3: Combine multiple usage scenarios and establish a source-grid-load-storage scheduling scheme, which can be used for scenario display, operation tracking, and usage evaluation;

[0010] Step 4: Input different usage scenarios multiple times and iteratively optimize the source-grid-load-storage scheduling scheme to determine the panoramic view of source-grid-load-storage;

[0011] Step 5: Based on the established panoramic view of source, grid, load and storage, the microgrid power is dispatched with the goal of maximizing optimization efficiency.

[0012] Further settings include: microgrid power generation data includes data collected from the power generation, transmission, transformation, distribution, and consumption stages of the power system.

[0013] Further settings include: power consumption data of the receiving unit, including collected user information, real-time power consumption data, power quality data, and time-related data.

[0014] Further settings include: performing noise reduction processing on the acquired data.

[0015] Further settings include: in step two, user factors include user type and user behavior habits; electricity consumption time factors include peak hours, off-peak hours, and off-peak hours; power load factors include power type and load characteristics; and energy storage factors include energy storage capacity and energy storage status.

[0016] Further steps include: in step four, using a neural network algorithm to iteratively optimize the source-grid-load-storage scheduling scheme. Specific steps include: cleaning and normalizing the collected data; using the existing scheduling method or a randomly generated initial source-grid-load-storage scheduling scheme as the starting point for neural network optimization; training the model on the processed data using a convolutional neural network; and finally, optimizing the source-grid-load-storage scheduling scheme.

[0017] Further configuration: In step five, an emergency response module is established, with a threshold set within the module to enable crisis early warning.

[0018] Further settings include: noise reduction methods such as outlier detection and removal, missing value imputation, and data smoothing.

[0019] In summary, the beneficial technical effects of the present invention are as follows:

[0020] (1) Constructing a dynamic factor database based on external factors: By acquiring microgrid generation data and power consumption data from power-receiving units, the data is processed and distributed aggregation modeling is performed to construct a dynamic factor database based on external factors. This allows for prediction of future operating conditions, enabling advance scheduling and control, and improving the operating efficiency of the microgrid's power generation, grid, load, and storage systems. (2) Determine the usage scenarios under different preconditions: Retrieve data from the dynamic factor database and combine it with user factors, electricity consumption time factors, power load factors, and energy storage level factors to determine the usage scenarios under different preconditions. This can fully consider the operating status of the power source, power grid, and energy storage system, thereby improving the operating efficiency of the microgrid's source-grid-load-storage system.

[0021] (3) Establish a source-grid-load-storage scheduling scheme: Combine various usage scenarios to establish a source-grid-load-storage scheduling scheme, and enable scenario display, operation tracking, and usage evaluation. This enables centralized control of the microgrid, avoids single-point failure problems, and can adapt to large-scale microgrid systems.

[0022] (4) Iterative optimization of the source-grid-load-storage scheduling scheme: Input different usage scenarios multiple times and iteratively optimize the source-grid-load-storage scheduling scheme to determine a panoramic view of the source-grid-load-storage system. This can continuously optimize the operating status of the microgrid and further improve the operating efficiency of the microgrid's source-grid-load-storage system.

[0023] (5) Power dispatching of the microgrid based on the established panoramic view of the power generation, grid, load, and storage: Power dispatching of the microgrid is carried out with the goal of maximizing the optimization efficiency. This enables distributed control of the microgrid and improves the operating efficiency of the power generation, grid, load, and storage of the microgrid. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating the present invention. Detailed Implementation

[0025] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0026] Reference Figure 1 This invention discloses a dynamic optimization method for supporting integrated coordination of power generation, grid, load, and energy storage in microgrids. The method includes the following steps:

[0027] Step 1: Obtain microgrid power generation data and power consumption data of receiving units, process the power generation data and power consumption data and perform distributed aggregation modeling to build a dynamic factor library based on the influence of external factors.

[0028] Microgrid generation data includes data collected from all stages of the power system, including generation, transmission, transformation, distribution, and consumption. Power consumption data from receiving units includes user information, real-time power consumption data, power quality data, and time-related data.

[0029] The system acquires microgrid power generation data and power consumption data from receiving units, and performs comprehensive data noise reduction processing on both data, including but not limited to outlier detection and removal, missing value imputation, and data smoothing. It also performs distributed aggregation modeling to construct a dynamic factor library based on the influence of external factors. Simultaneously, advanced data encryption technology is employed to ensure data security and privacy.

[0030] Step 2: Retrieve data from the dynamic factor library and combine it with user factors, electricity consumption time factors, power load factors, and energy storage level factors to determine the usage scenarios under different preconditions.

[0031] User factors include user type and user behavior habits; electricity consumption time factors include peak hours, off-peak hours, and off-peak hours; power load factors include power type and load characteristics; and energy storage factors include energy storage capacity and energy storage status. In determining usage scenarios, intelligent data analysis algorithms are used to deeply mine and correlate various factors to improve the accuracy and relevance of scenario determination.

[0032] Step 3: Combine various usage scenarios to establish a source-grid-load-storage scheduling scheme, which should include scenario demonstration, operation tracking, and usage evaluation. The scheduling scheme should fully consider factors such as system reliability, stability, and economy, while providing a visual scenario display interface for users to intuitively understand the system's operating status. Operation tracking should be real-time and accurate, enabling timely problem detection and appropriate action. Usage evaluation should include, but is not limited to, assessments of the scheduling scheme's effectiveness and user satisfaction surveys.

[0033] Step 4: Input different usage scenarios multiple times and iteratively optimize the source-grid-load-storage scheduling scheme to determine the panoramic view of source-grid-load-storage.

[0034] The source-grid-load-storage scheduling scheme is iteratively optimized using a neural network algorithm. The specific steps include: cleaning and normalizing the collected data; using the existing scheduling method or a randomly generated initial source-grid-load-storage scheduling scheme as the starting point for neural network optimization; training the model on the processed data using a convolutional neural network; and finally, optimizing the source-grid-load-storage scheduling scheme.

[0035] Step 5: Based on the established panoramic view of source, grid, load and storage, the microgrid power is dispatched with the goal of maximizing optimization efficiency.

[0036] The dispatching process should be intelligent and automated, capable of dynamic adjustments based on real-time power demand and supply. Simultaneously, an emergency response module should be established, with built-in thresholds to provide early warning of crises, enabling rapid action in the event of emergencies to ensure the safe and stable operation of the system.

[0037] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape, and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A dynamic optimization method supporting integrated coordination of microgrid generation, grid, load, and storage, characterized in that, The steps are as follows: Step 1: Obtain microgrid power generation data and power consumption data of receiving units, process the power generation data and power consumption data and perform distributed aggregation modeling to build a dynamic factor library based on the influence of external factors; Step 2: Retrieve data from the dynamic factor library and combine it with user factors, electricity consumption time factors, power load factors, and energy storage level factors to determine the usage scenarios under different preconditions; Step 3: Combine multiple usage scenarios and establish a source-grid-load-storage scheduling scheme, which can be used for scenario display, operation tracking, and usage evaluation; Step 4: Input different usage scenarios multiple times and iteratively optimize the source-grid-load-storage scheduling scheme to determine the panoramic view of source-grid-load-storage; Step 5: Based on the established panoramic view of source, grid, load and storage, the microgrid power is dispatched with the goal of maximizing optimization efficiency.

2. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 1, characterized in that: Microgrid power generation data includes data collected from all stages of the power system, including power generation, transmission, transformation, distribution, and consumption.

3. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 1, characterized in that: The electricity consumption data of the receiving unit includes user information, real-time electricity consumption data, power quality data, and time-related data.

4. A dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 2 or 3, characterized in that: The acquired data is subjected to noise reduction processing.

5. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 1, characterized in that: In step two, user factors include user type and user behavior habits; electricity consumption time factors include peak hours, off-peak hours, and off-peak hours; power load factors include power type and load characteristics; and energy storage factors include energy storage capacity and energy storage status.

6. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 1, characterized in that: In step four, a neural network algorithm is used to iteratively optimize the source-grid-load-storage scheduling scheme. The specific steps include: cleaning and normalizing the collected data; using the existing scheduling method or a randomly generated initial source-grid-load-storage scheduling scheme as the starting point for neural network optimization; training the model on the processed data using a convolutional neural network; and finally, optimizing the source-grid-load-storage scheduling scheme.

7. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 1, characterized in that: In step five, an emergency response module is established, with thresholds set within the module to enable crisis early warning.

8. The dynamic optimization method for supporting integrated coordination of microgrid generation, grid, load, and storage as described in claim 4, characterized in that: Noise reduction methods include outlier detection and removal, missing value imputation, and data smoothing.

Images