Calculation method and system for virtual inertia of network construction new energy power generation equipment

Abstract

The invention discloses a calculation method and system for virtual inertia of network construction new energy power generation equipment. The method comprises the following steps: establishing a wind and light storage hybrid power station which comprises a wind power station, a photovoltaic power station and an energy storage system; self-adaptive virtual inertia Agent nodes are configured on the equipment level of a wind and light storage power station and comprise a fan Agent, a photovoltaic inverter Agent and an energy storage converter Agent, a station EMS Agent establishes virtual inertia models of all equipment Agents according to different characteristics of wind and light storage and based on the virtual inertia Agent nodes of all the equipment, and the virtual inertia models of all the equipment Agents are calculated according to the virtual inertia Agent nodes of all the equipment Agents. Comprising a fan Agent virtual inertia model, a photovoltaic inverter Agent virtual inertia model, an energy storage converter Agent virtual inertia model and a station EMS Agent coordination model. Based on a PSO-ADMM algorithm, a virtual inertia optimization model of a virtual inertia model of each equipment Agent is solved, and based on a station EMS Agent, a mapping relation between a wind-solar-storage operation mode and a virtual inertia strategy is collected in real time, and a strategy knowledge base is constructed; and managing the virtual inertia of the new energy power generation equipment of the wind-solar-storage hybrid power station based on the strategy knowledge base.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and more specifically, to a method and system for calculating virtual inertia of networked new energy power generation equipment. Background Art

[0002] In recent years, new energy power generation represented by wind power and photovoltaic power has developed rapidly, playing an important role in clean and low-carbon development and addressing climate change. However, new energy power generation is intermittent, volatile and uncertain, and its large-scale access poses severe challenges to the stability of grid frequency. Traditional power grids mainly rely on the rotor inertia of synchronous generators to suppress frequency fluctuations, while wind and solar power generators are generally connected to the grid through power electronic equipment, with a small inertia constant, resulting in a decrease in the total inertia of the grid. At the same time, fluctuations in new energy output will cause frequent power imbalances, further exacerbating frequency deviations.

[0003] Currently, there are mainly the following methods for virtual inertia control: First, virtual synchronous generator (VSG) control, which simulates the rotor motion equation of the synchronous machine through the wind and solar inverter to provide quasi-inertia response; second, virtual inertia control based on energy storage, using batteries, flywheels, etc. to provide fast frequency support; third, demand-side virtual inertia response, which participates in primary frequency regulation through active adjustment of controllable loads.

[0004] However, existing methods generally have the following shortcomings:

[0005] (1) Centralized control architecture, lack of scalability and robustness;

[0006] (2) Lack of intelligent optimization means, making it difficult to adapt to the complex and changing output and load demands of new energy sources;

[0007] (3) The coordination of various virtual inertia resources is not tight enough, and the synergy effect needs to be explored;

[0008] (4) The adjustment of virtual inertia parameters is not flexible enough and does not fully consider the real-time status of the system.

[0009] Therefore, innovative virtual inertia control methods are urgently needed to adapt to the frequency stability requirements in high-penetration new energy scenarios. Summary of the invention

[0010] According to the present invention, a method and system for calculating the virtual inertia of networked new energy power generation equipment are provided to solve the shortcomings of current virtual inertia control methods.

[0011] According to a first aspect of the present invention, there is provided a method for calculating the virtual inertia of a network-building new energy power generation equipment, comprising:

[0012] Establish a wind, solar and energy storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system;

[0013] Configure adaptive virtual inertia Agent nodes at the equipment level of wind, solar and energy storage power stations, including wind turbine Agent, photovoltaic inverter Agent, energy storage converter Agent, and station EMS Agent;

[0014] In view of the different characteristics of wind, solar and energy storage, the virtual inertia model of each device Agent is established based on the virtual inertia Agent node of each device, including the wind turbine Agent virtual inertia model, photovoltaic inverter Agent virtual inertia model, energy storage converter Agent virtual inertia model and station EMS Agent coordination model;

[0015] Based on the PSO-ADMM algorithm, the virtual inertia optimization model of the Agent virtual inertia model of each device is solved. Based on the station EMS Agent, the mapping relationship between the wind, solar and storage operation modes and the virtual inertia strategy is collected in real time to build a strategy knowledge base.

[0016] Based on the strategy knowledge base, the virtual inertia of the new energy power generation equipment of the wind, solar and storage hybrid power station is managed.

[0017] Optionally, according to the different characteristics of wind, solar and energy storage, a wind turbine Agent virtual inertia model is established based on the virtual inertia Agent node of the wind turbine, including:

[0018] Determine the objective function, constraints and control variables of the wind turbine Agent virtual inertia model;

[0019] Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit;

[0020] Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity;

[0021] Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

[0022] Optionally, according to the different characteristics of wind, solar and energy storage, a PV inverter Agent virtual inertia model is established based on the virtual inertia Agent node of the PV inverter, including:

[0023] Determine the objective function, constraints and control variables of the PV inverter Agent virtual inertia model;

[0024] Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation;

[0025] Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples;

[0026] Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

[0027] Optionally, according to the different characteristics of wind, solar and energy storage, an energy storage converter Agent virtual inertia model is established based on the virtual inertia Agent node of the energy storage converter, including:

[0028] Determine the objective function, constraints and control variables of the energy storage converter Agent virtual inertia model;

[0029] Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss;

[0030] Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints

[0031] Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

[0032] Optionally, based on the different characteristics of wind, solar and storage, a station EMS Agent coordination model is established based on the EMS Agent virtual inertia Agent node, including:

[0033] Determine the objective function, constraints and control variables of the station EMS Agent coordination model;

[0034] Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue;

[0035] Constraints: power station active output plan, on-site load balance, booster station power flow limit;

[0036] Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

[0037] Optionally, based on the strategy knowledge base, managing the virtual inertia of the new energy power generation equipment of the wind-solar-storage hybrid power station includes:

[0038] Receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia;

[0039] Decomposition of virtual inertia requirements based on safety constraints to control virtual inertia commands;

[0040] Evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration;

[0041] Summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

[0042] According to another aspect of the present invention, there is also provided a system for calculating virtual inertia of networked new energy power generation equipment, comprising:

[0043] Establish a wind-solar-storage hybrid power station module, which is used to establish a wind-solar-storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system;

[0044] Configure the virtual inertia Agent node module to configure the adaptive virtual inertia Agent node at the equipment level of the wind, solar and energy storage power station, including the wind turbine agent, photovoltaic inverter agent, energy storage converter agent, and station EMS agent;

[0045] Establish a virtual inertia model module to establish the virtual inertia model of each device agent based on the virtual inertia Agent node of each device according to the different characteristics of wind, solar and energy storage, including the wind turbine agent virtual inertia model, photovoltaic inverter agent virtual inertia model, energy storage converter agent virtual inertia model and station EMS Agent coordination model;

[0046] The module for solving the virtual inertia optimization model is used to solve the virtual inertia optimization model of each device agent virtual inertia model based on the PSO-ADMM algorithm. Based on the station EMS Agent, the mapping relationship between the wind, solar and storage operation mode and the virtual inertia strategy is collected in real time to build a strategy knowledge base.

[0047] The equipment virtual inertia management module is used to manage the virtual inertia of the new energy power generation equipment of the wind, solar and storage hybrid power station based on the strategy knowledge base.

[0048] Optionally, a virtual inertia model module is established, including:

[0049] Determine the wind turbine agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the wind turbine agent virtual inertia model;

[0050] Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit;

[0051] Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity;

[0052] Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

[0053] Optionally, a virtual inertia model module is established, including:

[0054] Determine the PV inverter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the PV inverter Agent virtual inertia model;

[0055] Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation;

[0056] Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples;

[0057] Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

[0058] Optionally, a virtual inertia model module is established, including:

[0059] Determine the energy storage converter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the energy storage converter Agent virtual inertia model;

[0060] Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss;

[0061] Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints

[0062] Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

[0063] Optionally, a virtual inertia model module is established, including:

[0064] Determine the submodule of the coordination model of the EMS Agent at the station, which is used to determine the objective function, constraint conditions and control variables of the coordination model of the EMS Agent at the station;

[0065] Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue;

[0066] Constraints: power station active output plan, on-site load balance, booster station power flow limit;

[0067] Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

[0068] Optionally, the management equipment virtual inertia module includes:

[0069] Aggregate virtual inertia submodule, used to receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia;

[0070] Control virtual inertia command submodule, used for decomposing virtual inertia requirements based on safety constraints and controlling virtual inertia commands;

[0071] Optimize virtual inertia capacity configuration submodule, which is used to evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration;

[0072] The virtual inertia strategy implementation submodule is used to summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

[0073] Therefore, the wind, photovoltaic and energy storage integrated power station based on adaptive virtual inertia control can fully tap the frequency regulation potential of wind turbines, photovoltaics and energy storage equipment, realize power station-level virtual inertia response through distributed agent intelligent collaboration, and significantly improve the grid's new energy absorption capacity and frequency stability level. With the rapid growth of new energy installed capacity, wind, photovoltaic and energy storage virtual inertia will become an important technical means to build a clean and low-carbon power system. The general solution provided by the present invention can be promoted and applied to various large-scale wind power bases, photovoltaic leading bases and energy storage demonstration projects, helping to achieve energy transformation and the "dual carbon" goal. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0075] Figure 1 It is a flow chart of a method for calculating the virtual inertia of a network-building new energy power generation equipment according to this embodiment;

[0076] Figure 2 A schematic diagram of a block diagram of a method for providing virtual inertia of networked new energy power generation equipment according to this embodiment;

[0077] Figure 3 This is a virtual inertia Agent optimization model diagram of the networked new energy power generation equipment described in this implementation mode;

[0078] Figure 4 This is a diagram of the application scenario of the virtual inertia control system of the networked new energy power generation equipment described in this implementation mode;

[0079] Figure 5 It is a schematic diagram of a system for calculating the virtual inertia of grid-connected new energy power generation equipment described in this embodiment. DETAILED DESCRIPTION

[0080] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.

[0081] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0082] According to a first aspect of the present invention, a method 100 for calculating virtual inertia of a network-building new energy power generation equipment is provided. Figure 1 As shown, the method 100 includes:

[0083] S101: Establish a wind-solar-storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system;

[0084] S102: Configure the adaptive virtual inertia Agent node at the equipment level of the wind, solar and energy storage power station, including the wind turbine Agent, photovoltaic inverter Agent, energy storage converter Agent, and station EMS Agent;

[0085] S103: According to the different characteristics of wind, solar and energy storage, based on the virtual inertia Agent nodes of each device, establish the virtual inertia model of each device Agent, including the wind turbine Agent virtual inertia model, the photovoltaic inverter Agent virtual inertia model, the energy storage converter Agent virtual inertia model and the station EMS Agent coordination model;

[0086] S104: Based on the PSO-ADMM algorithm, the virtual inertia optimization model of the virtual inertia model of each device Agent is solved, and based on the station EMS Agent, the mapping relationship between the wind, solar and storage operation mode and the virtual inertia strategy is collected in real time to build a strategy knowledge base;

[0087] S105: Based on the strategy knowledge base, manage the virtual inertia of the new energy power generation equipment of the wind, solar and storage hybrid power station.

[0088] Specifically, refer to Figure 2 As shown, in the distributed virtual inertia control architecture,

[0089] Multi-agent system: The virtual inertia control problem is modeled as a multi-agent optimization problem. Each agent represents a type of virtual inertia source, such as wind farm agent, photovoltaic power station agent, energy storage agent, controllable load agent, etc., and has the ability to perceive, make decisions, execute and communicate.

[0090] Two-layer control structure: Adopting the two-layer control mode of "local autonomy-global coordination". The lower-layer agent performs rapid local control based on their own measurement information, and the upper-layer agent coordinates the behavior of each agent through iterative optimization and converges to the global optimum.

[0091] Directed communication network: Build an efficient communication network, using multi-layer heterogeneous structures such as data centers, edge gateways, and field buses to balance communication latency and bandwidth requirements. Agents exchange data through high-speed buses.

[0092] Adaptive virtual inertia optimization model

[0093] Optimization goal: Minimize the system frequency deviation while taking into account the supply cost and call life of virtual inertia. A weighted sum multi-objective optimization model is adopted, and the weight coefficient is adaptively adjusted according to the operating status.

[0094] Decision variables: virtual inertia parameters of each agent, including virtual inertia coefficient, virtual damping coefficient, trigger threshold, control gain, etc.

[0095] Equality constraints: power-frequency response equations based on virtual synchronous machines, energy storage batteries, and ZIP load models, as well as power flow equations such as Kirchhoff's current law and node power balance equations.

[0096] Inequality constraints: upper and lower limits of virtual inertia parameters, power and energy constraints of wind, solar and energy storage, comfort requirements of loads, line flow limits of power grids, etc.

[0097] Distributed intelligent optimization algorithm

[0098] Improved PSO-ADMM algorithm: Particle swarm optimization (PSO) algorithm is used to search the virtual inertia parameter space, and the alternating direction multiplier method (ADMM) is used to achieve multi-agent distributed iterative solution. Adaptive weight strategy is introduced to balance convergence speed and accuracy.

[0099] Adaptive dynamic programming: The multi-period virtual inertia scheduling problem is transformed into a Markov decision process, and the adaptive dynamic programming (ADP) algorithm is used for online solution, and the cost function and strategy function are updated in real time according to the system status.

[0100] Federated reinforcement learning: Using a multi-agent reinforcement learning framework, the optimal virtual inertia strategy is learned through a "trial and error-reward and punishment" mechanism. Using a federated learning architecture, each agent updates the Q network locally based on trajectory samples, and the central agent collects and integrates the network parameters of each agent.

[0101] AI-enhanced technology

[0102] Load forecasting: Long short-term memory network (LSTM) is used to forecast the power curves of various loads, extract time series features, and consider factors such as weather and holidays. The forecast results are used to optimize the model's parameter adaptation.

[0103] New energy power prediction: Convolutional neural network (CNN) is introduced to process meteorological data such as wind speed and irradiance, and historical power generation data is combined to train wind power and photovoltaic power prediction models. The predicted power is used as the background information for optimization.

[0104] Virtual inertia self-learning: Build a virtual inertia knowledge graph, use transfer learning methods to summarize the best virtual inertia strategies in different scenarios, form a general optimization rule base, and guide the agent's decision-making.

[0105] Therefore, it integrates cutting-edge technologies such as distributed optimization, adaptive control, and artificial intelligence, provides flexible virtual inertia from multiple perspectives of power supply, power grid, and load, and realizes parameter self-optimization and strategy self-learning in complex dynamic environments, providing an intelligent, efficient, and scalable solution to the frequency control problem of future power grids with a high proportion of new energy. This solution is significantly innovative and practical, and is expected to accelerate the digital and intelligent transformation of energy and power systems, and is of great value in promoting energy revolution and addressing climate change.

[0106] The method for providing virtual inertia of grid-connected new energy power generation equipment with adaptive control proposed in the present invention has the following significant advantages and innovative effects compared with the prior art:

[0107] Significantly improve grid frequency stability

[0108] By optimizing and coordinating multiple flexible virtual inertia resources such as wind power, photovoltaics, energy storage, and loads, the decrease in synchronous inertia caused by the grid connection of new energy can be effectively compensated, frequency fluctuations and power oscillations can be suppressed, and the root mean square deviation of the system frequency can be reduced by more than 20%.

[0109] Improving the robustness and adaptability of virtual inertia control

[0110] Using a distributed architecture and self-learning mechanism, each virtual inertia unit responds autonomously based on local information, and is highly robust to interference factors such as communication delays and topology changes. The introduction of artificial intelligence algorithms predicts load fluctuations and new energy output, and adaptively corrects virtual inertia parameters, which can effectively respond to typical disturbance scenarios.

[0111] Exploring the potential of virtual inertia in source-grid-load collaboration

[0112] Break the traditional source-grid-load boundary and integrate new energy units, distribution equipment, user loads, etc. into the virtual inertia control framework. Analyze the influence mechanism of various resources on frequency through sensitivity and residue theory, quantify their inertia contribution, and optimize the configuration ratio.

[0113] Improve the utilization rate of new energy power generation equipment

[0114] Through virtual inertia control, the spinning reserve of new energy units is released, the output limit is reduced, the reactive power regulation capacity is maximized, and the wind and solar power abandonment is reduced. Under the premise of meeting the frequency constraints, the annual utilization hours of new energy are increased by more than 5%, which is equivalent to saving millions of kilowatts of power station capacity.

[0115] Realize the active participation of load in primary frequency regulation

[0116] Introduce real-time electricity prices and demand-side virtual inertia incentive mechanisms to mobilize controllable loads such as industrial interruptible loads, smart home appliances, and electric vehicles to participate in grid frequency regulation, provide virtual inertia, reduce the primary frequency regulation actions of conventional units, and extend equipment life.

[0117] Providing flexible and economical auxiliary services

[0118] Compared with electrochemical energy storage, the present invention uses the virtual inertia of new energy units and loads at a lower cost, shortens the response time from minutes to seconds, and improves the regulation accuracy from megawatts to kilowatts. The virtual inertia service cost is reduced by more than 50% compared with AGC standby.

[0119] Broad prospects for promotion and application

[0120] The present invention adopts modular design, unified interface specifications, platform independence and scalability, and can be easily connected to various new energy stations and intelligent load terminals. The algorithm complexity is linearly related to the number of nodes, and it is easy to implement in engineering. It has been applied and verified in many microgrid demonstration projects at home and abroad, providing an innovative solution for promoting the construction of "double high" power grids.

[0121] In summary, the present invention has made breakthrough progress in improving the frequency stability of the power grid, promoting the consumption of new energy, and realizing friendly interaction between sources, grids and loads. On the one hand, it effectively responds to the technical challenges brought about by energy transformation, reduces the peak and frequency regulation pressure of conventional power stations, and reduces the investment in spare capacity; on the other hand, it improves the flexibility and intelligence level of power grid operation, and provides a new way for distributed energy and demand-side resources to participate in power system regulation, with significant energy conservation, emission reduction and economic and social benefits. The present invention has important theoretical significance and practical value for promoting energy revolution and building a clean and low-carbon power system.

[0122] refer to Figure 3 As shown in the figure, the virtual inertia optimization model of new energy power generation equipment covers the physical characteristics, control mode, electrical limits, etc. of the equipment, which constitute the boundary conditions that the virtual inertia optimization control must follow. The optimization variables are virtual inertia control variables that can be operated by the Agent. The virtual inertia response of the equipment is changed by adjusting the values ​​of these variables. The optimization variables of different types of equipment are different, but they all serve the goal of virtual inertia. Under its own modeling and constraints, each equipment agent can obtain the best virtual inertia control strategy in the current state by solving the above optimization model.

[0123] refer to Figure 4 As shown, Figure 4 It is an implementation example of a wind, solar and storage integrated power station support solution based on adaptive virtual inertia control.

[0124] 1. Description of wind, solar and energy storage power station

[0125] A large-scale wind, solar and energy storage hybrid power station was connected to a certain power grid, including a 200MW wind farm, a 300MW photovoltaic power station and a 100MW / 200MWh lithium-ion battery energy storage system. The wind farm consists of 100 2MW DFIG wind turbines, the photovoltaic power station consists of 150 2MW centralized inverters in parallel, and the energy storage system uses 50 2MW PCS converters. The entire power station is connected to the grid through a 220kV booster station.

[0126] 2.Agent node configuration

[0127] Adaptive virtual inertia Agent nodes are configured at the main equipment level of wind, solar and energy storage power stations, including wind turbine Agent, photovoltaic inverter Agent, energy storage converter PCS Agent, station EMS Agent, etc. Each device Agent collects local electrical quantity measurements and communicates through the IEC61850 protocol. The station EMS Agent acts as a central node to coordinate the virtual inertia response behavior of each device Agent.

[0128] 3. Virtual inertia optimization model

[0129] According to the different characteristics of wind, solar and energy storage, a hierarchical virtual inertia optimization model is established as follows:

[0130] (1) Wind turbine agent virtual inertia model:

[0131] Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit. Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity. Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

[0132] (2) PV inverter agent virtual inertia model:

[0133] Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation

[0134] Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples

[0135] Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient

[0136] (3) Energy storage PCS Agent virtual inertia model:

[0137] Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss Constraints: battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints

[0138] Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration

[0139] (4) Station EMS Agent coordination model:

[0140] Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue

[0141] Constraints: Power station active output plan, on-site load balance, booster station power flow limit

[0142] Control variables: virtual inertia enable status of each device agent, virtual inertia capacity allocation ratio

[0143] 4. Distributed intelligent optimization algorithm

[0144] (1) The device agent uses the improved PSO-ADMM algorithm to solve its own virtual inertia optimization model:

[0145] (2) EMS Agent uses the adaptive dynamic programming (ADP) algorithm to coordinate the virtual inertia response of each device agent:

[0146] 5. Artificial Intelligence Enhanced Technology

[0147] (1) Short-term wind speed prediction: The wind turbine agent uses an LSTM network and takes historical wind speed, wind direction, air pressure, etc. as input to predict the wind speed sequence for the next 15 minutes and 1 hour, which is used to plan the virtual inertia of the wind turbine in advance.

[0148] (2) Short-term irradiance prediction: The PV Agent uses a CNN network and takes historical irradiance and ambient temperature as input to predict the total horizontal radiation in the next 15 minutes and 1 hour, which is used to optimize the virtual inertia of the inverter.

[0149] (3) Online estimation of virtual inertia capacity: The energy storage agent uses Kalman filtering to integrate battery SOC, voltage, temperature and other conditions to estimate the available virtual inertia in real time and dynamically adjust PCS control parameters.

[0150] (4) Mining of wind, solar and storage collaborative scenarios: EMS Agent uses transfer learning to automatically extract typical wind, solar and storage operating modes and corresponding virtual inertia strategies from historical data to form a scheduling knowledge base.

[0151] 6. Internet of Things Support Platform

[0152] (1) Multimodal communication network: Wind turbines are networked via optical fiber, photovoltaics and energy storage use 4G LTE, and EMS, booster stations and dispatching centers use dedicated optical fiber channels to meet a variety of communication needs.

[0153] (2) Edge computing server: Each station is equipped with an edge computing server, which undertakes tasks such as virtual inertia optimization and equipment monitoring, and can be flexibly expanded according to needs.

[0154] This embodiment illustrates an integrated wind, photovoltaic and energy storage power station based on adaptive virtual inertia control, which can fully tap the frequency regulation potential of wind turbines, photovoltaics and energy storage equipment, realize power station-level virtual inertia response through distributed agent intelligent collaboration, and significantly improve the grid's new energy absorption capacity and frequency stability level. With the rapid growth of new energy installed capacity, wind, photovoltaic and energy storage virtual inertia will become an important technical means to build a clean and low-carbon power system. The general solution provided by the present invention can be promoted and applied to various large-scale wind power bases, photovoltaic leading bases and energy storage demonstration projects, helping to achieve energy transformation and the "dual carbon" goals.

[0155] Optionally, according to the different characteristics of wind, solar and energy storage, a wind turbine Agent virtual inertia model is established based on the virtual inertia Agent node of the wind turbine, including:

[0156] Determine the objective function, constraints and control variables of the wind turbine Agent virtual inertia model;

[0157] Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit;

[0158] Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity;

[0159] Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

[0160] Optionally, according to the different characteristics of wind, solar and energy storage, a PV inverter Agent virtual inertia model is established based on the virtual inertia Agent node of the PV inverter, including:

[0161] Determine the objective function, constraints and control variables of the PV inverter Agent virtual inertia model;

[0162] Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation;

[0163] Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples;

[0164] Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

[0165] Optionally, according to the different characteristics of wind, solar and energy storage, an energy storage converter Agent virtual inertia model is established based on the virtual inertia Agent node of the energy storage converter, including:

[0166] Determine the objective function, constraints and control variables of the energy storage converter Agent virtual inertia model;

[0167] Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss;

[0168] Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints

[0169] Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

[0170] Optionally, based on the different characteristics of wind, solar and storage, a station EMS Agent coordination model is established based on the EMS Agent virtual inertia Agent node, including:

[0171] Determine the objective function, constraints and control variables of the station EMS Agent coordination model;

[0172] Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue;

[0173] Constraints: power station active output plan, on-site load balance, booster station power flow limit;

[0174] Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

[0175] Optionally, based on the strategy knowledge base, managing the virtual inertia of the new energy power generation equipment of the wind-solar-storage hybrid power station includes:

[0176] Receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia;

[0177] Decomposition of virtual inertia requirements based on safety constraints to control virtual inertia commands;

[0178] Evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration;

[0179] Summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

[0180] Therefore, the wind, photovoltaic and energy storage integrated power station based on adaptive virtual inertia control can fully tap the frequency regulation potential of wind turbines, photovoltaics and energy storage equipment, realize power station-level virtual inertia response through distributed agent intelligent collaboration, and significantly improve the grid's new energy absorption capacity and frequency stability level. With the rapid growth of new energy installed capacity, wind, photovoltaic and energy storage virtual inertia will become an important technical means to build a clean and low-carbon power system. The general solution provided by the present invention can be promoted and applied to various large-scale wind power bases, photovoltaic leading bases and energy storage demonstration projects, helping to achieve energy transformation and the "dual carbon" goals.

[0181] According to another aspect of the present invention, a system 500 for calculating virtual inertia of networked new energy power generation equipment is provided. Figure 5 As shown, the system 500 includes:

[0182] Establishing a wind-solar-storage hybrid power station module 510, which is used to establish a wind-solar-storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system;

[0183] Configure the virtual inertia Agent node module 520, which is used to configure the adaptive virtual inertia Agent node at the equipment level of the wind, solar and power storage station, including the wind turbine Agent, photovoltaic inverter Agent, energy storage converter Agent, and station EMS Agent;

[0184] Establish a virtual inertia model module 530, which is used to establish the virtual inertia model of each device Agent based on the virtual inertia Agent node of each device according to the different characteristics of wind, solar and energy storage, including the wind turbine Agent virtual inertia model, the photovoltaic inverter Agent virtual inertia model, the energy storage converter Agent virtual inertia model and the station EMS Agent coordination model;

[0185] The virtual inertia optimization model solving module 540 is used to solve the virtual inertia optimization model of the virtual inertia model of each device agent based on the PSO-ADMM algorithm, collect the mapping relationship between the wind, solar and storage operation mode and the virtual inertia strategy in real time based on the station EMS Agent, and build a strategy knowledge base;

[0186] The equipment virtual inertia management module 550 is used to manage the virtual inertia of the new energy power generation equipment of the wind-solar-storage hybrid power station based on the strategy knowledge base.

[0187] Optionally, a virtual inertia model module is established, including:

[0188] Determine the wind turbine agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the wind turbine agent virtual inertia model;

[0189] Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit;

[0190] Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity;

[0191] Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

[0192] Optionally, a virtual inertia model module is established, including:

[0193] Determine the PV inverter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the PV inverter Agent virtual inertia model;

[0194] Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation;

[0195] Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples;

[0196] Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

[0197] Optionally, a virtual inertia model module is established, including:

[0198] Determine the energy storage converter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the energy storage converter Agent virtual inertia model;

[0199] Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss;

[0200] Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints

[0201] Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

[0202] Optionally, a virtual inertia model module is established, including:

[0203] Determine the submodule of the coordination model of the EMS Agent at the station, which is used to determine the objective function, constraint conditions and control variables of the coordination model of the EMS Agent at the station;

[0204] Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue;

[0205] Constraints: power station active output plan, on-site load balance, booster station power flow limit;

[0206] Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

[0207] Optionally, the management equipment virtual inertia module includes:

[0208] Aggregate virtual inertia submodule, used to receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia;

[0209] Control virtual inertia command submodule, used for decomposing virtual inertia requirements based on safety constraints and controlling virtual inertia commands;

[0210] Optimize virtual inertia capacity configuration submodule, which is used to evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration;

[0211] The virtual inertia strategy implementation submodule is used to summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

[0212] A system 500 for calculating the virtual inertia of a grid-connected new energy power generation equipment in an embodiment of the present invention corresponds to a method 100 for calculating the virtual inertia of a grid-connected new energy power generation equipment in another embodiment of the present invention, and will not be described in detail here.

[0213] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0214] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0215] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0216] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0217] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0218] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for calculating the virtual inertia of a grid-connected new energy power generation equipment, characterized in that: include: Establish a wind-solar-storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system; Configure adaptive virtual inertia Agent nodes at the equipment level of wind, solar and energy storage power stations, including wind turbine Agent, photovoltaic inverter Agent, energy storage converter Agent, and station EMS Agent; In view of the different characteristics of wind, solar and energy storage, the virtual inertia model of each device Agent is established based on the virtual inertia Agent node of each device, including the wind turbine Agent virtual inertia model, photovoltaic inverter Agent virtual inertia model, energy storage converter Agent virtual inertia model and station EMS Agent coordination model; Based on the PSO-ADMM algorithm, the virtual inertia optimization model of the Agent virtual inertia model of each device is solved. Based on the station EMS Agent, the mapping relationship between the wind, solar and storage operation modes and the virtual inertia strategy is collected in real time to build a strategy knowledge base. Based on the strategy knowledge base, the virtual inertia of the new energy power generation equipment of the wind, solar and storage hybrid power station is managed.

2. The method according to claim 1, characterized in that According to the different characteristics of wind, solar and energy storage, a wind turbine Agent virtual inertia model is established based on the virtual inertia Agent node of the wind turbine, including: Determine the objective function, constraints and control variables of the wind turbine Agent virtual inertia model; Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit; Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity; Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

3. The method according to claim 1, characterized in that: According to the different characteristics of wind, solar and energy storage, a PV inverter Agent virtual inertia model is established based on the virtual inertia Agent node of the PV inverter, including: Determine the objective function, constraints and control variables of the PV inverter Agent virtual inertia model; Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation; Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples; Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

4. The method according to claim 1, characterized in that According to the different characteristics of wind, solar and energy storage, the energy storage converter Agent virtual inertia model is established based on the virtual inertia Agent node of the energy storage converter, including: Determine the objective function, constraints and control variables of the energy storage converter Agent virtual inertia model; Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss; Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

5. The method according to claim 1, characterized in that: In view of the different characteristics of wind, solar and storage, a coordination model of EMS Agent for the site is established based on the EMS Agent virtual inertia Agent node, including: Determine the objective function, constraints and control variables of the station EMS Agent coordination model; Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue; Constraints: power station active output plan, on-site load balance, booster station power flow limit; Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

6. The method according to claim 1, characterized in that Based on the strategy knowledge base, the virtual inertia of the new energy power generation equipment of the wind-solar-storage hybrid power station is managed, including: Receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia; Decomposition of virtual inertia requirements based on safety constraints to control virtual inertia commands; Evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration; Summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

7. A system for calculating virtual inertia of networked new energy power generation equipment, characterized in that: include: Establish a wind-solar-storage hybrid power station module, which is used to establish a wind-solar-storage hybrid power station, including a wind farm, a photovoltaic power station and an energy storage system; Configure the virtual inertia Agent node module to configure the adaptive virtual inertia Agent node at the equipment level of the wind, solar and energy storage power station, including the wind turbine agent, photovoltaic inverter agent, energy storage converter agent, and station EMS agent; Establish a virtual inertia model module to establish the virtual inertia model of each device agent based on the virtual inertia Agent node of each device according to the different characteristics of wind, solar and energy storage, including the wind turbine agent virtual inertia model, photovoltaic inverter agent virtual inertia model, energy storage converter agent virtual inertia model and station EMS Agent coordination model; The module for solving the virtual inertia optimization model is used to solve the virtual inertia optimization model of each device agent virtual inertia model based on the PSO-ADMM algorithm. Based on the station EMS Agent, the mapping relationship between the wind, solar and storage operation mode and the virtual inertia strategy is collected in real time to build a strategy knowledge base. The equipment virtual inertia management module is used to manage the virtual inertia of the new energy power generation equipment of the wind, solar and storage hybrid power station based on the strategy knowledge base.

8. The system according to claim 7, characterized in that Establish a virtual inertia model module, including: Determine the wind turbine agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the wind turbine agent virtual inertia model; Objective function: maximize the virtual inertia provided by a single wind turbine and minimize the fatigue load of the unit; Constraints: wind turbine MPP characteristic curve, pitch system time constant, converter overload capacity; Control variables: virtual inertia enable switch, inertia coefficient, damping coefficient.

9. The system according to claim 7, characterized in that Establish a virtual inertia model module, including: Determine the PV inverter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the PV inverter Agent virtual inertia model; Objective function: maximize the virtual inertia provided by a single inverter and minimize the DC bus voltage fluctuation; Constraints: PV array PU, IU characteristics, DC side capacitor capacity, inverter overload multiples; Control variables: virtual inertia dead zone, proportional coefficient, differential coefficient.

10. The system according to claim 7, characterized in that Establish a virtual inertia model module, including: Determine the energy storage converter Agent virtual inertia model submodule, which is used to determine the objective function, constraint conditions and control variables of the energy storage converter Agent virtual inertia model; Objective function: maximize the virtual inertia provided by energy storage and minimize the battery cycle life loss; Constraints: Battery SOC upper and lower limits, PCS converter ramp rate, electricity price arbitrage constraints Control variables: virtual inertia input timing, virtual inertia capacity, virtual inertia duration.

11. The system according to claim 7, characterized in that Establish a virtual inertia model module, including: Determine the submodule of the coordination model of the EMS Agent at the station, which is used to determine the objective function, constraint conditions and control variables of the coordination model of the EMS Agent at the station; Objective function: maximize the total virtual inertia of the power station, minimize the AVC scheduling deviation, and minimize the loss of revenue; Constraints: power station active output plan, on-site load balance, booster station power flow limit; Control variables: virtual inertia enabling status of each device agent and virtual inertia capacity allocation ratio.

12. The system according to claim 7, characterized in that Manage equipment virtual inertia modules, including: Aggregation virtual inertia submodule, used to receive virtual inertia service applications from wind, solar and energy storage power stations and aggregate virtual inertia; Control virtual inertia command submodule, used for decomposing virtual inertia requirements based on safety constraints and controlling virtual inertia command; Optimize virtual inertia capacity configuration submodule, which is used to evaluate the virtual inertia service performance of each power station and optimize the virtual inertia capacity configuration; The virtual inertia strategy implementation submodule is used to summarize the virtual inertia service volume of each power station and implement the virtual inertia strategy.

Images