Virtual oscillator power grid stabilization system and method based on intelligent control

Abstract

The invention relates to the technical field of intelligent control power grids, in particular to a virtual oscillator power grid stabilization system and method based on intelligent control, and the system comprises an intelligent control unit which automatically adjusts control parameters, optimizes a control strategy, and predicts a future operation state; when the method is used, power grid operation can be optimized in real time, power grid robustness can be improved, power grid energy utilization efficiency can be improved through reasonable load distribution and voltage adjustment, energy waste can be reduced, local fault spreading can be avoided, the overall fault risk of a power grid can be reduced, and through an information sharing and updating mechanism, the power grid energy utilization efficiency can be improved. Power grid state data can be shared in real time among areas, it is ensured that control strategies of all agents are always kept consistent, the anti-interference capacity of a power grid on external environment factors is improved, a simulation model and a prediction algorithm of the power grid are adjusted according to real-time data, and the method has high adaptability and is suitable for power grids of different scales and types.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control power grid, and in particular to a virtual oscillator power grid stabilization system and method based on intelligent control. Background Art

[0002] The intelligently controlled virtual oscillator grid stabilization system simulates the characteristics of traditional synchronous generators, enabling distributed energy resources and energy storage systems to better participate in the frequency and voltage regulation of the grid, thereby improving the stability and reliability of the entire grid.

[0003] The patent application number is CN202110904801.0, which states in the specification that "the embodiment of the present invention discloses an intelligent stabilization system and method, which includes: a setting module, through which the safe operation threshold of each sub-module in the power grid is set; a data acquisition module, which is used to collect the actual operation data of each sub-module in the power grid, and convert all the collected data into a unified standard format; a push module, the data converted by the data acquisition module is transmitted to the screening module through the push module; the screening module, according to the setting conditions of the screening module, screens and judges the data pushed in the push module, and transmits the qualified data to the processing module; the processing module establishes a corresponding stability evaluation model, analyzes the received operation data of each sub-module, and then judges the stability of the power grid. The present invention provides an intelligent stabilization system and method to solve the problem that the prior art cannot effectively supervise the abnormal data of electronic devices before problems occur in the power grid." The above-mentioned technology is affected by the external environment and sensor accuracy when collecting data, and incomplete or inaccurate data collection may occur. In addition, the above-mentioned technology will be affected by various external environmental factors during operation, so that the normal monitoring and early warning of the system will be interfered with by external environmental factors.

[0004] In summary, developing a virtual oscillator grid stabilization system and method based on intelligent control is still a key issue that needs to be urgently solved in the field of intelligent control grid technology. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that the above-mentioned technology is affected by the external environment and sensor accuracy when collecting data, resulting in incomplete or inaccurate data collection. In addition, the above-mentioned technology will be affected by various external environmental factors during operation, thereby interfering with the normal monitoring and early warning of the system due to external environmental factors. The present invention provides a virtual oscillator power grid stabilization system and method based on intelligent control.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention provides a virtual oscillator grid stabilization system based on intelligent control, comprising: an intelligent control unit, which automatically adjusts control parameters and optimizes control strategies, and predicts future operating states;

[0008] an assisting distribution unit, performing multi-area assisting control according to the future operating state, and monitoring the grid state in real time and performing load distribution;

[0009] an oscillation simulation unit, which simulates the oscillation behavior in the power grid according to the load distribution, predicts the subsequent dynamics of the power grid, and generates a dynamic regulation benchmark;

[0010] The automated execution unit couples and adjusts the frequency and voltage control according to the dynamic adjustment benchmark to guide the power grid to restore dynamic balance.

[0011] Furthermore, the intelligent control unit comprises:

[0012] Dynamic dispatch module dynamically adjusts control parameters according to the real-time grid operation status, and automatically optimizes control strategies under grid load, grid topology changes and environmental conditions;

[0013] A prediction control module, based on the real-time operation status of the power grid, predicts the future operation status of each submodule of the power grid;

[0014] Assistance distribution units include:

[0015] The collaborative interconnection module adopts a multi-agent collaborative control method, allowing controllers or smart devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control;

[0016] The fault-tolerant control module automatically adjusts the operating status of the remaining normal devices and the load distribution of the power grid when individual devices fail, based on the future operating status, shared information and real-time monitoring data obtained by real-time monitoring of the power grid.

[0017] 3. The virtual oscillator grid stabilization system based on intelligent control according to claim 2, characterized in that the oscillation simulation unit comprises:

[0018] A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time;

[0019] A response module monitors the operation status of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation or instability in advance, and generating a reference signal as a dynamic adjustment benchmark for equipment in the power grid;

[0020] The automation execution unit includes:

[0021] An associated control module, for synchronously monitoring the frequency and voltage fluctuations of the power grid, combining the dynamic adjustment benchmark, and adjusting the control strategy of the frequency and voltage according to their common changes;

[0022] The switch system, based on the oscillation mode and the control strategy, can quickly identify the source of the fault and adjust other areas of the power grid when the power grid encounters a transient fault.

[0023] 4. The virtual oscillator grid stabilization system based on intelligent control according to claim 3, characterized in that the working process of the intelligent control unit includes:

[0024] The dynamic dispatch module obtains real-time grid status data through sensors, and dynamically monitors the current and voltage parameters of each node based on the changes in the grid topology and load. According to the real-time data and changes, it uses the reinforcement learning algorithm formula and the optimal control law formula to dynamically adjust the control parameters, outputs the results according to the voltage adjustment formula and the load distribution formula, and adjusts the operating parameters of each grid equipment in real time. The reinforcement learning algorithm formula is: Where X(z′, d′) is the state action value, W(z) is the immediate reward, α is the discount factor, and the optimal control law formula is: Where C(w) is the cost function, t(s) is the system state, w(s) is the control input, U and V are weight matrices, N is the time interval, Ls is the differential element of the integral, which represents the integration of the time variable s. The voltage adjustment formula is: V j (s) = V j (s-1)+ΔV j (s), where V j (s) is the current node voltage, ΔV j (s) is the adjustment amount, load distribution formula: F ld (s) = F ld (s-1)+ΔF ld (s), where F ld (s) is the current load, ΔF ld (s) is the adjusted load, F ld (s-1) is the load power at the previous moment;

[0025] The predictive control model pre-processes the collected data based on the real-time operation status of the power grid to ensure the consistency of the data format, and uses the long short-term memory formula and the current prediction formula to perform time series prediction and predict the future power grid status. The long short-term memory formula is: Q s =β(E Q Q s-1 +E r ·r s +d), where Qs is the current state, β is the activation function, E Q , E r is the weight matrix, r s is the input data, d is the bias, and the current prediction formula is: I(s+1)=y[I(s), W(s), V(s)], where I(s+1) is the predicted current, W(s) is the electric power, V(s) is the voltage, I(s) is the state of the power grid or equipment at the moment, and y is a differential equation that can comprehensively consider the impact of the current power grid state, load and voltage changes on the system state at future moments.

[0026] 5. The virtual oscillator grid stabilization system based on intelligent control according to claim 4, characterized in that the working process of the assisting distribution unit comprises:

[0027] The collaborative interconnection module uses the regional control collaborative formula and the distributed optimal control formula based on the shared information of the intelligent agent and the future operating state to achieve inter-regional coordination. At the same time, it adjusts the local control strategy based on the information sharing update formula and the multi-agent collaborative communication constraint formula. The regional control collaborative formula is: Among them, QM gl (s) is the global control target, QM local (s) is the local control target, T is the number of agents, and the information sharing update formula is: ZN j (s)=ZN j (s-1)+χ·[ZN k (s)-ZN j (s-1)], where ZN j (s) is the current information of the jth agent, ZN j (s-1) is the state information of the agent at the previous moment, χ is the learning rate, ZN k (s) is the information of other agents, and the distributed optimal control formula is: where z j (s) is the local state of the jth agent, k j (s) is its control input, z gbl (s) is the global power grid state, θ is the weighted coefficient indicating the degree of coordination between local and global states, and the multi-agent collaborative communication constraint formula is: Among them ZN j (t) and ZN k (t) is the state information between two agents, ∈ is the maximum tolerable error;

[0028] The fault-tolerant control module uses a fault detection formula method to determine whether there is a device failure based on the future operating state, shared information, and real-time monitoring data obtained by real-time monitoring of the power grid. If there is a failure, the fault type is determined, and the load adjustment formula is used to automatically adjust the load distribution of the remaining devices when the faulty device is detected. The fault detection formula is: in is the voltage deviation of the jth device, V nom is the rated voltage of the equipment, ω is the deviation threshold, and the load adjustment formula is: where F aud (s) is the adjusted load, g fail is the load of the faulty equipment, g total is the total load of the power grid.

[0029] 6. A virtual oscillator grid stabilization system based on intelligent control according to claim 5, characterized in that the working process of the oscillation simulation unit includes:

[0030] The virtual oscillation model simulates the oscillation behavior in the power grid based on the load distribution, and then uses the oscillation frequency formula and the oscillation amplitude formula to simulate the frequency and voltage oscillation mode in the power grid. After the oscillation data is obtained, it is used to feedback the current stability of the power grid and evaluate whether it is in a stable range. The oscillation frequency formula is: Where z(s) is the oscillation frequency, d is the system stiffness, n is the system mass, and the oscillation amplitude formula is: Where B(s) is the oscillation amplitude, B 0 is the initial amplitude, γ is the damping coefficient, η z is the damped oscillation frequency, is the initial phase;

[0031] The response module predicts whether the system will oscillate or become unstable according to the vibration data and the real-time operation status of the power grid, and generates a reference signal as a dynamic adjustment benchmark based on the prediction result and the reference signal generation formula, which is used to adjust the working status of the power grid equipment. The reference signal generation formula is: huf (s) = B (s) sin (2π f (s) s), where P huf (s) is the reference signal, B(s) is the oscillation amplitude, f(s) is the oscillation frequency, and s is the time variable of signal generation.

[0032] 7. The virtual oscillator grid stabilization system based on intelligent control according to claim 6, characterized in that the workflow of the automation execution unit includes:

[0033] The associated control module uses the frequency and voltage association formula to simultaneously monitor the frequency and voltage fluctuations of the power grid, and dynamically adjusts the frequency and voltage control strategy of the power grid based on the common changes of frequency and voltage and the dynamic adjustment benchmark. The frequency and voltage association formula is: G fq-ve (s)=U 1 y(s)+U 2 V(s), where G fq-ve (s) is the control power of frequency and voltage, y(s) is the frequency, V(s) is the voltage, U 1 is a constant coefficient indicating the contribution of frequency change to the control power, U 2 is a constant coefficient that indicates the contribution of voltage change to the control power;

[0034] The switch system identifies the fault source in the power grid based on the oscillation mode and the control strategy, and then automatically adjusts the switch in the fault area of ​​the power grid using the fault source identification and switch adjustment formula, the fault source identification and switch adjustment formula is: Among them G fault (s) is the power of the fault area, G j (s) is the power of the jth device, 1 {j∈Y(s)} is the indicator function, and Y(s) is the fault area.

[0035] On the other hand, the present invention also provides a virtual oscillator grid stabilization method based on intelligent control, which comprises the following steps:

[0036] S1, automatically adjust control parameters and optimize control strategies to predict future operating conditions;

[0037] S2. Perform multi-region assistive control according to the future operating status, monitor the grid status in real time and perform load distribution;

[0038] S3, simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating a dynamic regulation benchmark;

[0039] S4. According to the dynamic adjustment benchmark, frequency and voltage control are coupled and adjusted to guide the power grid to restore dynamic balance;

[0040] Furthermore, in step S1, the method of automatically adjusting the control parameters and optimizing the control strategy to predict the future operating state is:

[0041] Dynamically adjust control parameters according to real-time grid operation status, and automatically optimize control strategies under grid load, grid topology changes and environmental conditions;

[0042] Based on the real-time operating status of the power grid, predict the future operating status of each submodule of the power grid;

[0043] In step S2, the method of performing multi-area assistive control according to the future operating state, monitoring the power grid state in real time and performing load distribution is as follows:

[0044] A multi-agent collaborative control method is adopted to allow controllers or intelligent devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control;

[0045] Based on the future operating status, shared information and real-time monitoring data obtained by real-time monitoring of the power grid, the operating status of the remaining normal equipment and the load distribution of the power grid are automatically adjusted when individual equipment fails.

[0046] Further, in step S3, the method of simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating the dynamic regulation benchmark is:

[0047] A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time;

[0048] Monitoring the operating state of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation or instability in advance, and generating a reference signal as a dynamic regulation benchmark for equipment in the power grid;

[0049] In step S4, according to the dynamic adjustment reference, the frequency and voltage control are coupled and adjusted to guide the power grid to restore dynamic balance.

[0050] Used to synchronously monitor the frequency and voltage fluctuations of the power grid, and adjust the control strategy of frequency and voltage according to their common changes in combination with the dynamic regulation benchmark;

[0051] Based on the oscillation mode and the control strategy, when the power grid encounters a transient fault, the fault source is quickly identified and other areas of the power grid are adjusted.

[0052] Beneficial Effects

[0053] Compared with the known public technology, the technical solution provided by the present invention has the following advantages:

[0054] Beneficial effects:

[0055] When the present invention is in use, it is beneficial to optimize the operation of the power grid in real time and improve the robustness of the power grid. At the same time, through reasonable load distribution and voltage adjustment, it can improve the energy utilization efficiency of the power grid, reduce energy waste, and help avoid the spread of local faults and reduce the overall failure risk of the power grid. At the same time, through the information sharing and updating mechanism, the power grid status data can be shared in real time between regions to ensure that the control strategy of each intelligent body is always consistent, which is beneficial to improving the power grid's ability to resist interference from external environmental factors, and adjust its simulation model and prediction algorithm according to real-time data to make it have strong adaptability and suitable for power grids of different sizes and types. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A system diagram of a virtual oscillator power grid stabilization system based on intelligent control according to the present invention;

[0057] Figure 2 The present invention is a flow chart of a virtual oscillator power grid stabilization method based on intelligent control. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0059] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0060] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0061] Embodiment 1:

[0062] like Figure 1As shown, the present invention provides a virtual oscillator power grid stabilization system based on intelligent control, including: an intelligent control unit, which automatically adjusts control parameters and optimizes control strategies, and predicts future operating states;

[0063] The intelligent control unit includes:

[0064] Dynamic dispatch module dynamically adjusts control parameters according to the real-time grid operation status, and automatically optimizes control strategies under grid load, grid topology changes and environmental conditions;

[0065] A prediction control module, based on the real-time operation status of the power grid, predicts the future operation status of each submodule of the power grid;

[0066] The workflow of the intelligent control unit includes:

[0067] The dynamic dispatch module obtains real-time grid status data through sensors, and dynamically monitors the current and voltage parameters of each node based on the changes in the grid topology and load. According to the real-time data and changes, it uses the reinforcement learning algorithm formula and the optimal control law formula to dynamically adjust the control parameters, outputs the results according to the voltage adjustment formula and the load distribution formula, and adjusts the operating parameters of each grid equipment in real time. The reinforcement learning algorithm formula is:

[0068] Where X(z′, d′) is the state action value, W(z) is the immediate reward, α is the discount factor, and the optimal control law formula is: Where C(w) is the cost function, t(s) is the system state, w(s) is the control input, U and V are weight matrices, N is the time interval, Ls is the differential element of the integral, which represents the integration of the time variable s. The voltage adjustment formula is: V j (s) = V j (s-1)+ΔV j (s), where V j (s) is the current node voltage, ΔV j (s) is the adjustment amount, load distribution formula: F ld (s) = F ld (s-1)+ΔF ld (s), where F ld (s) is the current load, ΔF ld (s) is the adjusted load, F ld (s-1) is the load power at the previous moment;

[0069] The predictive control model pre-processes the collected data based on the real-time operation status of the power grid to ensure the consistency of the data format, and uses the long short-term memory formula and the current prediction formula to perform time series prediction and predict the future power grid status. The long short-term memory formula is: Q s=β(E Q Q s-1 +E r ·r s +d), where Q s is the current state, β is the activation function, E Q , E r is the weight matrix, r s is the input data, d is the bias, and the current prediction formula is: I(s+1)=y[I(s), W(s), V(s)], where I(s+1) is the predicted current, W(s) is the electric power, V(s) is the voltage, I(s) is the state of the power grid or equipment at the time, and y is a differential equation that can comprehensively consider the impact of the current power grid state, load and voltage changes on the system state at the future time;

[0070] Specifically, there will be multiple sub-modules in the power grid. The working status of each sub-module needs to be monitored in real time by sensors and fed back to the intelligent control unit. When the load on a certain node increases, the dynamic scheduling module will automatically adjust the voltage and load distribution of the surrounding nodes to avoid overload. At the same time, the predictive control model can be used to predict load fluctuations in the next few hours and adjust the operating parameters of related equipment in advance to prevent failures caused by sudden load changes. This is conducive to real-time optimization of power grid operation and improving the robustness of the power grid. At the same time, through reasonable load distribution and voltage adjustment, the energy utilization efficiency of the power grid can be improved and energy waste can be reduced.

[0071] Assist the distribution unit, assist in multi-area control, share data, monitor the grid status in real time and distribute the load;

[0072] Assistance distribution units include:

[0073] The collaborative interconnection module adopts a multi-agent collaborative control method, allowing controllers and smart devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control;

[0074] A fault-tolerant control module, based on the future operating state, shared information and real-time monitoring data obtained by real-time monitoring of the power grid, so as to automatically adjust the operating state of the remaining normal equipment and the load distribution of the power grid when an individual equipment fails;

[0075] The workflow of the Assistance Distribution Unit includes:

[0076] The collaborative interconnection module uses the regional control collaborative formula and the distributed optimal control formula based on the shared information of the intelligent agent and the future operating state to achieve inter-regional coordination. At the same time, it adjusts the local control strategy based on the information sharing update formula and the multi-agent collaborative communication constraint formula. The regional control collaborative formula is: Among them, QM gl (s) is the global control target, QM local (s) is the local control target, T is the number of agents, and the information sharing update formula is: ZN j (s)=ZN j (s-1)+χ·[ZN k (s)-ZN j (s-1)], where ZN j (s) is the current information of the jth agent, ZN j (s-1) is the state information of the agent at the previous moment, χ is the learning rate, ZN k (s) is the information of other agents, and the distributed optimal control formula is: where z j (s) is the local state of the jth agent, k j (s) is its control input, z gbl (s) is the global power grid state, θ is the weighted coefficient indicating the degree of coordination between local and global states, and the multi-agent collaborative communication constraint formula is: Among them ZN j (t) and ZN k (t) is the state information between two agents, ∈ is the maximum tolerable error;

[0077] The fault-tolerant control module uses a fault detection formula method to determine whether there is a device failure based on the future operating state, shared information, and real-time monitoring data obtained by real-time monitoring of the power grid. If there is a failure, the fault type is determined, and the load adjustment formula is used to automatically adjust the load distribution of the remaining devices when the faulty device is detected. The fault detection formula is: in is the voltage deviation of the jth device, V nom is the rated voltage of the equipment, ω is the deviation threshold, and the load adjustment formula is: where F aud (s) is the adjusted load, g fail is the load of the faulty equipment, g total is the total load of the power grid;

[0078] Specifically, by assisting the distribution unit, the intelligent agent in each area can independently monitor and control the power grid status according to local real-time data. When the load in one area suddenly increases, the load distribution of other areas can be coordinated and adjusted through the collaborative interconnection module to ensure the stable operation of the entire power grid. When a generator in a certain area fails, the fault-tolerant control module can detect the fault in time and adjust the load distribution of the remaining areas to prevent large-scale failures in the power grid, which is conducive to avoiding the spread of local faults and reducing the overall failure risk of the power grid. At the same time, through the information sharing and updating mechanism, the power grid status data can be shared in real time between regions to ensure that the control strategies of each intelligent agent are always consistent.

[0079] Oscillation simulation unit, which simulates the oscillation behavior in the power grid, predicts the subsequent dynamics of the power grid, and generates a dynamic regulation benchmark;

[0080] The oscillation simulation unit includes:

[0081] A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time;

[0082] A response module monitors the operation status of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation and instability in advance, and generating a reference signal as a dynamic adjustment benchmark for the equipment in the power grid;

[0083] The workflow of the oscillation simulation unit includes:

[0084] The virtual oscillation model simulates the oscillation behavior in the power grid based on the load distribution, and then uses the oscillation frequency formula and the oscillation amplitude formula to simulate the frequency and voltage oscillation mode in the power grid. After the oscillation data is obtained, it is used to feedback the current stability of the power grid and evaluate whether it is in a stable range. The oscillation frequency formula is: Where z(s) is the oscillation frequency, d is the system stiffness, n is the system mass, and the oscillation amplitude formula is: Where B(s) is the oscillation amplitude, B 0 is the initial amplitude, γ is the damping coefficient, η z is the damped oscillation frequency, is the initial phase;

[0085] The response module predicts whether the system will oscillate or become unstable according to the vibration data and the real-time operation status of the power grid, and generates a reference signal as a dynamic adjustment benchmark based on the prediction result and the reference signal generation formula, which is used to adjust the working status of the power grid equipment. The reference signal generation formula is: huf (s) = B (s) sin (2π f (s) s), where P huf(s) is the reference signal, B(s) is the oscillation amplitude, f(s) is the oscillation frequency, and s is the time variable of signal generation;

[0086] Specifically, during the operation of the power grid system, changes in grid frequency and voltage fluctuations are detected, and the current grid oscillation frequency and amplitude are calculated through a virtual oscillation model to identify grid instability. At the same time, the response module generates a corresponding reference signal based on the current oscillation amplitude and frequency, and adjusts the working state of the equipment in real time to suppress the further development of the oscillation. This is conducive to taking preventive measures in advance to prevent large-scale failures and power outages in the power grid, avoid equipment damage and large-scale failures caused by excessive frequency and voltage fluctuations, and enhance the power grid's ability to resist interference from external environmental factors. The simulation model and prediction algorithm are adjusted according to real-time data to make it highly adaptable and suitable for power grids of different sizes and types.

[0087] The automated execution unit couples the frequency and voltage control to guide the grid to restore dynamic balance;

[0088] The automation execution unit includes:

[0089] An associated control module, for synchronously monitoring the frequency and voltage fluctuations of the power grid, combining the dynamic adjustment benchmark, and adjusting the control strategy of the frequency and voltage according to their common changes;

[0090] The switch system, based on the oscillation mode and the control strategy, quickly identifies the source of the fault and adjusts other areas of the power grid when the power grid encounters a transient fault;

[0091] The workflow of the automated execution unit includes:

[0092] The associated control module uses the frequency and voltage association formula to simultaneously monitor the frequency and voltage fluctuations of the power grid, and dynamically adjusts the frequency and voltage control strategy of the power grid based on the common changes of frequency and voltage and the dynamic adjustment benchmark. The frequency and voltage association formula is: G fq-ve (s)=U 1 y(s)+U 2 V(s), where G fq-ve (s) is the control power of frequency and voltage, y(s) is the frequency, V(s) is the voltage, U 1 is a constant coefficient indicating the contribution of frequency change to the control power, U 2 is a constant coefficient that indicates the contribution of voltage change to the control power;

[0093] The switch system identifies the fault source in the power grid based on the oscillation mode and the control strategy, and then automatically adjusts the switch in the fault area of ​​the power grid using the fault source identification and switch adjustment formula, the fault source identification and switch adjustment formula is: Among them G fault (s) is the power of the fault area, G j (s) is the power of the jth device, 1 {j∈Y(s)} is the indicator function, Y(s) is the fault area;

[0094] Specifically, the frequency and voltage fluctuations of the power grid are monitored synchronously through the associated control modules, and the control strategy of the power grid is dynamically adjusted according to the common changes of frequency and voltage, so that the changes of the two are kept synchronized, avoiding system instability caused by the separate adjustment of frequency and voltage. When the power grid encounters a transient fault, the switching system determines the location of the fault source and automatically switches the switch state of the fault area to restore the dynamic balance of the power grid, which is conducive to reducing the impact of the fault on the overall stability of the power grid, reducing the risk of power grid collapse and large-scale power outages, and improving the continuity and reliability of power supply.

[0095] Embodiment 2:

[0096] like Figure 2 As shown, embodiment 2 provides a virtual oscillator grid stabilization method based on intelligent control, which includes the following steps:

[0097] S1, automatically adjust control parameters and optimize control strategies to predict future operating conditions;

[0098] S2. Perform multi-region assistive control according to the future operating status, monitor the grid status in real time and perform load distribution;

[0099] S3, simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating a dynamic regulation benchmark;

[0100] S4. According to the dynamic adjustment benchmark, frequency and voltage control are coupled and adjusted to guide the power grid to restore dynamic balance;

[0101] Furthermore, in step S1, the method of automatically adjusting the control parameters and optimizing the control strategy to predict the future operating state is:

[0102] Dynamically adjust control parameters according to real-time grid operation status, and automatically optimize control strategies under grid load, grid topology changes and environmental conditions;

[0103] Based on the real-time operating status of the power grid, predict the future operating status of each submodule of the power grid;

[0104] In step S2, the method of performing multi-area assistive control according to the future operating state, monitoring the power grid state in real time and performing load distribution is as follows:

[0105] A multi-agent collaborative control method is adopted to allow controllers and intelligent devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control;

[0106] Based on the future operating status, shared information and real-time monitoring data obtained by real-time monitoring of the power grid, the operating status of the remaining normal equipment and the load distribution of the power grid are automatically adjusted when individual equipment fails.

[0107] Further, in step S3, the method of simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating the dynamic regulation benchmark is:

[0108] A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time;

[0109] Monitoring the operating state of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation and instability in advance, and generating a reference signal as a dynamic regulation benchmark for equipment in the power grid;

[0110] In step S4, according to the dynamic adjustment reference, the frequency and voltage control are coupled and adjusted to guide the power grid to restore dynamic balance.

[0111] Used to synchronously monitor the frequency and voltage fluctuations of the power grid, and adjust the control strategy of frequency and voltage according to their common changes in combination with the dynamic regulation benchmark;

[0112] Based on the oscillation mode and the control strategy, when the power grid encounters a transient fault, the fault source is quickly identified and other areas of the power grid are adjusted.

[0113] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A virtual oscillator power grid stabilization system based on intelligent control, characterized in that: include: Intelligent control unit, automatically adjusts control parameters and optimizes control strategies, and predicts future operating status; an assisting distribution unit, performing multi-area assisting control according to the future operating state, and monitoring the grid state in real time and performing load distribution; an oscillation simulation unit, which simulates the oscillation behavior in the power grid according to the load distribution, predicts the subsequent dynamics of the power grid, and generates a dynamic regulation benchmark; The automated execution unit couples and adjusts the frequency and voltage control according to the dynamic adjustment benchmark to guide the power grid to restore dynamic balance.

2. The virtual oscillator grid stabilization system based on intelligent control according to claim 1, characterized in that: The intelligent control unit includes: Dynamic dispatch module dynamically adjusts control parameters according to the real-time grid operation status, and automatically optimizes control strategies under grid load, grid topology changes and environmental conditions; A prediction control module, based on the real-time operation status of the power grid, predicts the future operation status of each submodule of the power grid; Assistance distribution units include: The collaborative interconnection module adopts a multi-agent collaborative control method, allowing controllers or smart devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control; The fault-tolerant control module automatically adjusts the operating status of the remaining normal devices and the load distribution of the power grid when individual devices fail, based on the future operating status, shared information and real-time monitoring data obtained by real-time monitoring of the power grid.

3. The virtual oscillator grid stabilization system based on intelligent control according to claim 2, characterized in that: The oscillation simulation unit includes: A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time; A response module monitors the operation status of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation or instability in advance, and generating a reference signal as a dynamic adjustment benchmark for equipment in the power grid; The automation execution unit includes: An associated control module, for synchronously monitoring the frequency and voltage fluctuations of the power grid, combining the dynamic adjustment benchmark, and adjusting the control strategy of the frequency and voltage according to their common changes; The switch system, based on the oscillation mode and the control strategy, can quickly identify the source of the fault and adjust other areas of the power grid when the power grid encounters a transient fault.

4. The virtual oscillator grid stabilization system based on intelligent control according to claim 3, characterized in that: The workflow of the intelligent control unit includes: The dynamic dispatch module obtains real-time grid status data through sensors, and dynamically monitors the current and voltage parameters of each node based on the changes in the grid topology and load. According to the real-time data and changes, it uses the reinforcement learning algorithm formula and the optimal control law formula to dynamically adjust the control parameters, outputs the results according to the voltage adjustment formula and the load distribution formula, and adjusts the operating parameters of each grid equipment in real time. The reinforcement learning algorithm formula is: X(z, d) = W(z) + αm d a ′ xX(z′, d′), where X(z′, d′) is the state action value, W(z) is the immediate reward, α is the discount factor, and the optimal control law formula is: Where C(w) is the cost function, t(s) is the system state, w(s) is the control input, U and V are weight matrices, N is the time interval, Ls is the differential element of the integral, which represents the integration of the time variable s. The voltage adjustment formula is: V j (s) = V j (s-1)+ΔV j (s), where V j (s) is the current node voltage, ΔV j (s) is the adjustment amount, load distribution formula: F ld (s) = F ld (s-1)+ΔF ld (s), where F ld (s) is the current load, ΔF ld (s) is the adjusted load, F ld (s-1) is the load power at the previous moment; The predictive control model pre-processes the collected data based on the real-time operation status of the power grid to ensure the consistency of the data format, and uses the long short-term memory formula and the current prediction formula to perform time series prediction and predict the future power grid status. The long short-term memory formula is: Q s =β(E Q Q s-1 +E r ·r s +d), where Q s is the current state, β is the activation function, E Q , E r is the weight matrix, r s is the input data, d is the bias, and the current prediction formula is: I(s+1)=y[I(s), W(s), V(s)], where I(s+1) is the predicted current, W(s) is the electric power, V(s) is the voltage, I(s) is the state of the power grid or equipment at the moment, and y is a differential equation that can comprehensively consider the impact of the current power grid state, load and voltage changes on the system state at future moments.

5. The virtual oscillator grid stabilization system based on intelligent control according to claim 4, characterized in that: The workflow of the Assistance Distribution Unit includes: The collaborative interconnection module uses the regional control collaborative formula and the distributed optimal control formula based on the shared information of the intelligent agent and the future operating state to achieve inter-regional coordination. At the same time, it adjusts the local control strategy based on the information sharing update formula and the multi-agent collaborative communication constraint formula. The regional control collaborative formula is: Among them, QM gl (s) is the global control target, QM local (s) is the local control target, T is the number of agents, and the information sharing update formula is: ZN j (s)=ZN j (s-1)+χ·[ZN k (s)-ZN j (s-1)], where ZN j (s) is the current information of the jth agent, ZN j (s-1) is the state information of the agent at the previous moment, χ is the learning rate, ZN k (s) is the information of other agents, and the distributed optimal control formula is: where z j (s) is the local state of the jth agent, k j (s) is its control input, z gbl (s) is the global power grid state, θ is the weighted coefficient indicating the degree of coordination between local and global states, and the multi-agent collaborative communication constraint formula is: Among them ZN j (t) and ZN k (t) is the state information between two agents, ∈ is the maximum tolerable error; The fault-tolerant control module uses a fault detection formula method to determine whether there is a device failure based on the future operating state, shared information, and real-time monitoring data obtained by real-time monitoring of the power grid. If there is a failure, the fault type is determined, and the load adjustment formula is used to automatically adjust the load distribution of the remaining devices when the faulty device is detected. The fault detection formula is: in is the voltage deviation of the jth device, V nom is the rated voltage of the equipment, ω is the deviation threshold, and the load adjustment formula is: where F aud (s) is the adjusted load, g fail is the load of the faulty equipment, g total is the total load of the power grid.

6. A virtual oscillator grid stabilization system based on intelligent control according to claim 5, characterized in that: The workflow of the oscillation simulation unit includes: The virtual oscillation model simulates the oscillation behavior in the power grid based on the load distribution, and then uses the oscillation frequency formula and the oscillation amplitude formula to simulate the frequency and voltage oscillation mode in the power grid. After the oscillation data is obtained, it is used to feedback the current stability of the power grid and evaluate whether it is in a stable range. The oscillation frequency formula is: Where z(s) is the oscillation frequency, d is the system stiffness, n is the system mass, and the oscillation amplitude formula is: Where B(s) is the oscillation amplitude, B0 is the initial amplitude, γ is the damping coefficient, η z is the damped oscillation frequency, is the initial phase; The response module predicts whether the system will oscillate or become unstable according to the vibration data and the real-time operation status of the power grid, and generates a reference signal as a dynamic adjustment benchmark based on the prediction result and the reference signal generation formula, which is used to adjust the working status of the power grid equipment. The reference signal generation formula is: huf (s) = B (s) sin (2π f (s) s), where P huf (s) is the reference signal, B(s) is the oscillation amplitude, f(s) is the oscillation frequency, and s is the time variable of signal generation.

7. A virtual oscillator grid stabilization system based on intelligent control according to claim 6, characterized in that: The workflow of the automated execution unit includes: The associated control module uses the frequency and voltage association formula to simultaneously monitor the frequency and voltage fluctuations of the power grid, and dynamically adjusts the frequency and voltage control strategy of the power grid based on the common changes of frequency and voltage and the dynamic adjustment benchmark. The frequency and voltage association formula is: G fq-ve (s)=U1·y(s)+U2·V(s), where G fq-ve (s) is the control power of frequency and voltage, y(s) is the frequency, V(s) is the voltage, U1 is a constant coefficient indicating the contribution of frequency change to the control power, and U2 is a constant coefficient indicating the contribution of voltage change to the control power; The switch system identifies the fault source in the power grid based on the oscillation mode and the control strategy, and then automatically adjusts the switch in the fault area of ​​the power grid using the fault source identification and switch adjustment formula, the fault source identification and switch adjustment formula is: Among them G fault (s) is the power of the fault area, G j (s) is the power of the jth device, 1 {j∈Y(s)} is the indicator function, and Y(s) is the fault area.

8. A virtual oscillator grid stabilization method based on intelligent control, based on a virtual oscillator grid stabilization system based on intelligent control according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1, automatically adjust control parameters and optimize control strategies to predict future operating conditions; S2. Perform multi-region assistive control according to the future operating status, monitor the grid status in real time and perform load distribution; S3, simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating a dynamic regulation benchmark; S4. According to the dynamic adjustment benchmark, frequency and voltage control are coupled and adjusted to guide the power grid to restore dynamic balance.

9. A virtual oscillator grid stabilization method based on intelligent control according to claim 8, characterized in that: In step S1, the method of automatically adjusting control parameters and optimizing control strategies and predicting future operating states is as follows: Dynamically adjust control parameters according to real-time grid operation status, and automatically optimize control strategies under grid load, grid topology changes and environmental conditions; Based on the real-time operating status of the power grid, predict the future operating status of each submodule of the power grid; In step S2, the method of performing multi-area assistive control according to the future operating state, monitoring the power grid state in real time and performing load distribution is as follows: A multi-agent collaborative control method is adopted to allow controllers or intelligent devices in different areas to cooperate with each other. Each agent independently senses and controls the power grid status in its own area, and shares information with other agents, combined with the future operating status, to coordinate global control; Based on the future operating status, shared information and real-time monitoring data obtained by real-time monitoring of the power grid, the operating status of the remaining normal equipment and the load distribution of the power grid are automatically adjusted when individual equipment fails.

10. A virtual oscillator grid stabilization method based on intelligent control according to claim 9, characterized in that: In step S3, the method of simulating the oscillation behavior in the power grid according to the load distribution, predicting the subsequent dynamics of the power grid, and generating a dynamic regulation benchmark is as follows: A virtual oscillation model is used to simulate the oscillation behavior in the power grid based on the load distribution, and monitor and feedback the oscillation mode of the power grid to evaluate the stability of the power grid in real time; Monitoring the operating state of the power grid according to the oscillation mode, thereby predicting the upcoming oscillation or instability in advance, and generating a reference signal as a dynamic regulation benchmark for equipment in the power grid; In step S4, the method of coupling and adjusting the frequency and voltage control according to the dynamic adjustment reference to guide the power grid to restore the dynamic balance is: Used to synchronously monitor the frequency and voltage fluctuations of the power grid, and in combination with the dynamic regulation benchmark, adjust the control strategy of frequency and voltage according to their common changes; Based on the oscillation mode and the control strategy, when the power grid encounters a transient fault, the fault source is quickly identified and other areas of the power grid are adjusted.

Images