Energy aggregation and scheduling optimization method based on Internet of Things and AI

Abstract

The invention discloses an energy scheduling method applying the Internet of Things and artificial intelligence. The method comprises the steps of S1, collecting operation data of different distributed energy devices in a region in real time through an Internet of Things system; s2, processing the operation data of each energy device through an artificial intelligence model, constructing a standardized operation model of each energy device, and aggregating the standardized operation model into a schedulable virtual unit; s3, collecting real-time price information of the electricity market, and generating a scheduling strategy through a rolling optimization algorithm in combination with new energy actual power generation power prediction, load demand prediction and electricity price prediction; and S4, controlling corresponding energy equipment to work through a multi-level control system according to a scheduling instruction of the scheduling strategy, and feeding back execution data, thereby realizing source network load storage collaborative optimization, improving resource utilization rate and scheduling flexibility, and improving competitiveness and income level of a virtual power plant in an electric power market.

Description

[Technical Field]

[0001] This invention relates to the fields of new energy management and smart grid technology, and in particular to a method for energy aggregation and scheduling optimization based on the Internet of Things and AI. [Background Technology]

[0002] With the rapid growth of my country's installed capacity of new energy sources, the proportion of renewable energy such as wind power and photovoltaics in the power system continues to increase. However, the output of new energy sources is highly volatile and uncontrollable, posing challenges to the safe and stable operation of the power grid. A large number of dispersed distributed energy resources lack effective aggregation and coordination mechanisms, making it difficult to realize their flexible adjustment potential.

[0003] Existing energy management systems are mostly limited to single-device monitoring or localized energy management, lacking unified dispatch capabilities across devices and regions. Especially under the backdrop of power market reform, how to achieve dynamic response of distributed resources to electricity price signals, participate in electricity trading, and obtain diversified benefits has become a pressing technical challenge. Traditional dispatch methods rely on manual experience or static rules, making them ill-suited to the complex operating environment under high-proportion renewable energy integration. [Summary of the Invention]

[0004] This invention overcomes the shortcomings of existing technologies and provides a method for energy aggregation and scheduling optimization based on the Internet of Things and AI.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for energy aggregation and scheduling optimization based on the Internet of Things and AI, characterized by: including...

[0007] S1. Real-time collection of operational data from different distributed energy devices within the region via an Internet of Things (IoT) system;

[0008] S2. Process the operating data of each energy device through an artificial intelligence model, construct a standardized operating model for each energy device, and aggregate them into a schedulable virtual machine group;

[0009] S3. Collect real-time price information from the electricity market and combine it with forecasts of actual power generation from new energy sources, load demand, and electricity prices to generate scheduling strategies through a rolling optimization algorithm.

[0010] S4. Based on the scheduling instructions of the scheduling strategy, the corresponding energy equipment is controlled through a multi-level control system, and the execution data is fed back to achieve coordinated optimization of source, grid, load and storage.

[0011] The energy aggregation and scheduling optimization method based on the Internet of Things and AI described above is characterized in that: the distributed energy equipment in S1 includes photovoltaic power stations, energy storage systems, charging piles and adjustable load equipment.

[0012] The energy aggregation and scheduling optimization method based on the Internet of Things and AI described above is characterized in that: the artificial intelligence model in S2 includes an LSTM neural network or a Transformer model.

[0013] The energy aggregation and scheduling optimization method based on the Internet of Things and AI described above is characterized in that: the virtual machine group in S2 includes a power generation virtual machine group and a load virtual machine group.

[0014] The energy aggregation and scheduling optimization method based on the Internet of Things and AI, as described above, is characterized in that: the power generation virtual machine group includes distributed photovoltaic and energy storage discharge modes; the load virtual machine group includes charging pile charging load, interruptible industrial load and controllable commercial load.

[0015] The energy aggregation and scheduling optimization method based on IoT and AI described above is characterized in that: the rolling optimization algorithm in S3 is a model predictive control optimization algorithm that performs multi-stage optimization on three time scales: day-ahead, intraday, and real-time.

[0016] The energy aggregation and scheduling optimization method based on the Internet of Things and AI, as described above, is characterized in that: the multi-level control system in S4 includes a cloud scheduling platform and an edge gateway.

[0017] The energy aggregation and scheduling optimization method based on the Internet of Things and AI, as described above, is characterized by: further including storing the adjustment behavior and revenue distribution information during the scheduling execution process through blockchain technology.

[0018] The energy aggregation and scheduling optimization method based on the Internet of Things and AI described above is characterized in that: the scheduling strategy in S3 comprehensively considers carbon emission factors, prioritizes the scheduling of low-carbon resources, and supports the linkage between green electricity trading and the carbon market.

[0019] The beneficial effects of this invention are:

[0020] This invention collects operational data from various distributed energy devices through an Internet of Things (IoT) system, transforms this data into a standardized operational model using an artificial intelligence (AI) model, and aggregates it into a schedulable virtual machine group. A rolling optimization algorithm generates a scheduling strategy to schedule the corresponding distributed energy devices, achieving coordinated optimization of power generation, grid, load, and storage. By unifying the dispersed and heterogeneous distributed energy devices into a schedulable virtual machine group through the AI ​​model, resource utilization and scheduling flexibility are significantly improved. Furthermore, by combining AI model prediction with the rolling optimization algorithm, dynamic responses to electricity market price fluctuations are achieved, enhancing the competitiveness and profitability of virtual power plants in the electricity market. [Image Description]

[0021] Figure 1This is a schematic diagram of the invention. [Detailed Implementation]

[0022] The technical solutions in the embodiments of the present invention will now be clearly and completely described in conjunction with the accompanying drawings.

[0023] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of the components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. Furthermore, descriptions involving "preferred," "second-best," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "preferred" or "second-best" may explicitly or implicitly include at least one of those features.

[0024] like Figure 1 As shown, an energy aggregation and scheduling optimization method based on the Internet of Things and AI includes:

[0025] S1. Real-time collection of operational data from different distributed energy devices within the region via an Internet of Things (IoT) system;

[0026] Specifically, distributed energy devices include photovoltaic power plants, energy storage systems, charging piles, and adjustable load devices, and all distributed energy devices are connected via the MQTT protocol.

[0027] S2. Process the operating data of each energy device through an artificial intelligence model, construct a standardized operating model for each energy device, and aggregate them into a schedulable virtual machine group;

[0028] Specifically, the artificial intelligence model employs deep learning algorithms, including LSTM neural networks or Transformer models, to dynamically assess and classify the output capacity, response potential, and health status of distributed energy devices. The virtual machine groups include power generation virtual machine groups and load virtual machine groups. The power generation group includes distributed photovoltaic and energy storage discharge modes, while the load group includes charging pile loads, interruptible industrial loads, and controllable commercial loads.

[0029] S3. Collect real-time price information from the electricity market and combine it with forecasts of actual power generation from new energy sources, load demand, and electricity prices to generate scheduling strategies through a rolling optimization algorithm.

[0030] Specifically, the rolling optimization algorithm is a model predictive control optimization algorithm that performs multi-stage optimization on three time scales: day-ahead, intraday, and real-time, in order to maximize the comprehensive benefits of the virtual power plant in the electricity market and ancillary services market.

[0031] S4. Based on the scheduling instructions of the scheduling strategy, the corresponding energy equipment is controlled through a multi-level control system, and the execution data is fed back to achieve coordinated optimization of source, grid, load and storage.

[0032] Specifically, the multi-level control system includes a cloud-based dispatching platform and an edge gateway, realizing a collaborative control architecture between the cloud-based dispatching platform, the edge gateway, and distributed energy devices. In conjunction with a closed-loop feedback mechanism, it ensures the safe and rapid execution of dispatching commands.

[0033] This case also includes using blockchain technology to store information on adjustment behaviors and revenue distribution during the scheduling and execution process, ensuring that the data is traceable and tamper-proof, and enhancing market participation transparency and trust.

[0034] In this case, the dispatch strategy comprehensively considers carbon emission factors, prioritizes the dispatch of low-carbon resources, and supports the linkage between green electricity trading and the carbon market, thereby achieving dual optimization of economic and environmental benefits and promoting the transformation of the energy system towards low-carbon and intelligentization.

[0035] This case can be applied to regional virtual power plant systems, supporting the off-grid electricity sales model, promoting the local consumption of renewable energy, and improving the rate of return on distributed energy assets.

[0036] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. All equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct or indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for energy aggregation and scheduling optimization based on the Internet of Things and AI, characterized in that: Including S1. Real-time collection of operational data from different distributed energy devices within the region via an Internet of Things (IoT) system; S2. Process the operating data of each energy device through an artificial intelligence model, construct a standardized operating model for each energy device, and aggregate them into a schedulable virtual machine group; S3. Collect real-time price information from the electricity market and combine it with forecasts of actual power generation from new energy sources, load demand, and electricity prices to generate scheduling strategies through a rolling optimization algorithm. S4. Based on the scheduling instructions of the scheduling strategy, the corresponding energy equipment is controlled through a multi-level control system, and the execution data is fed back to achieve coordinated optimization of source, grid, load and storage.

2. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: Distributed energy equipment in S1 includes photovoltaic power plants, energy storage systems, charging piles, and adjustable load equipment.

3. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: The artificial intelligence models in S2 include LSTM neural networks or Transformer models.

4. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: The virtual machine groups in S2 include power generation virtual machine groups and load virtual machine groups.

5. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 4, characterized in that: The power generation virtual machine group includes distributed photovoltaic and energy storage discharge modes; the load virtual machine group includes charging pile charging load, interruptible industrial load and controllable commercial load.

6. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: The rolling optimization algorithm in S3 is an optimization algorithm for model predictive control that performs multi-stage optimization at three time scales: day-ahead, intraday, and real-time.

7. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: The multi-level control system in S4 includes a cloud-based scheduling platform and an edge gateway.

8. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: It also includes storing information on adjustment behaviors and revenue distribution during the scheduling and execution process using blockchain technology.

9. The energy aggregation and scheduling optimization method based on the Internet of Things and AI according to claim 1, characterized in that: The S3 scheduling strategy comprehensively considers carbon emission factors, prioritizes the scheduling of low-carbon resources, and supports the linkage between green electricity trading and the carbon market.

Images