Solution derivation method and solution derivation device for volage control systems

Abstract

The present invention relates to a solution derivation device for deriving an optimal solution for a voltage control system that controls the voltage of a power system, comprising: a collection unit that collects real-time power consumption data and control data from the voltage control system; a simulation unit that configures a digital twin-based virtual system based on the real-time power consumption and control data to simulate the power system and performs a simulation of the virtual system; and a derivation unit that derives a set of optimal scenarios to be transmitted to the voltage control system based on the simulation results from the simulation unit. Through this, real-time power measurement values ​​of major system facilities are collected to simulate the power flow and voltage status of the entire power system, and based on the results, not only is the voltage impact at the level of all facilities precisely predicted, but an optimal solution for the voltage control system is also derived, thereby simultaneously securing the energy efficiency and stability of the power system.

Description

Technology Field

[0001] The present invention relates to a method for deriving a solution and a device for deriving a solution for a voltage control system, and more specifically, to a method for deriving a solution and a device for deriving a solution for deriving an optimal solution for a voltage control system that controls the voltage of a power system. Background Technology

[0002] In power systems, various power facilities such as transformers, voltage regulators, distribution lines, and terminal loads are organically connected to supply power, and it is essential to maintain the system voltage within a certain range for the stable operation of such a system.

[0003] In particular, voltage fluctuations are intensifying due to increased loads or the expansion of variable power sources such as renewable energy, which can lead to deterioration of power quality, shortened equipment lifespans, and, in the worst case, serious accidents such as blackouts.

[0004] Conventional voltage control has primarily relied on local devices such as tap regulators and capacitor bank controllers at the substation level. Since this control method performs control based on limited information without reflecting the voltage distribution of the entire system, it leads to problems such as excessive voltage regulation or unnecessary power consumption. Furthermore, as it does not consider the interaction between multiple facilities, adverse effects frequently occur where voltage improvement in one area leads to voltage instability in another.

[0005] Recently, with the advancement of smart meters, measurement infrastructure, and communication networks, it has become possible to collect real-time power measurement values ​​from various facilities. Consequently, there is a growing demand for voltage prediction and optimized control technologies based on high-precision simulations that utilize these values. However, the commercialization of global simulation-based control systems for voltage changes at individual facility levels remains insufficient. Prior art literature

[0006] Korean Registered Patent Publication No. 10-1505472 The problem to be solved

[0007] The present invention has been devised to solve the above-mentioned problems, and the objective of the present invention is to provide a method for deriving a solution for a voltage control system and a device for deriving a solution, which collect real-time power measurement values ​​of major system facilities to simulate the power flow and voltage status of the entire power system, and based on the results, not only accurately predict the voltage impact at the level of all facilities but also derive an optimal solution for the corresponding voltage control system, thereby simultaneously securing energy efficiency and stability of the power system. means of solving the problem

[0008] A solution derivation device according to an embodiment of the present invention for achieving the above objective comprises: a collection unit for collecting real-time power consumption data and control data from the voltage control system; a simulation unit for configuring a digital twin-based virtual system based on the real-time power consumption and control data to simulate the power system and performing a simulation of the virtual system; and a derivation unit for deriving an optimal scenario set to be transmitted to the voltage control system based on the simulation results from the simulation unit, wherein the optimal scenario set includes at least one of an allowable voltage range, a control reference value, priority information, and a control instruction condition calculated according to a pre-set optimization goal.

[0009] And the above derivation unit can derive the set of optimal scenarios including the allowable voltage range of the power system according to the optimization goal, which includes at least one of the risk of blackout of the voltage control system, minimization of power consumption, and improvement of power quality.

[0010] In addition, the derivation unit may compare the sets of optimal scenarios derived for each voltage control system located in a geographically adjacent area among voltage control systems having the same optimization goal, and if the comparison result satisfies a pre-set correction condition, at least one of the sets of optimal scenarios derived may be corrected.

[0011] And the above derivation unit can dynamically reset the allowable voltage range based on multidimensional data including external environment data including at least one of temperature, humidity, time zone and seasonal information and load characteristics, evaluate one of a plurality of optimal scenario sets based on the reset allowable voltage range, and dynamically calculate the priority for each scenario set according to the multidimensional data, and transmit the scenario set with the highest priority to the voltage control system.

[0012] In addition, the above derivation unit can select an optimal scenario set that gradually lowers the voltage applied to the voltage control system or readjusts the application time period in combination with the load characteristics at that time when the external environment data exceeds a preset threshold temperature and threshold humidity.

[0013] And the above derivation unit evaluates the power efficiency of the voltage control system, and if it is determined that the power efficiency has decreased, it may preferentially select an optimal scenario set corresponding to load redistribution or dynamic idle mode switching to minimize power loss.

[0014] Meanwhile, a solution derivation method according to an embodiment of the present invention for achieving the above objective is a solution derivation method in a solution derivation device for deriving an optimal solution for a voltage control system that controls the voltage of a power system, comprising: a step of collecting real-time power consumption data and control data from the voltage control system; a step of configuring a digital twin-based virtual system based on the real-time power consumption and control data to simulate the power system and performing a simulation of the virtual system; and a step of deriving an optimal scenario set to be transmitted to the voltage control system based on the simulation results, wherein the optimal scenario set includes at least one of an allowable voltage range, a control reference value, priority information, and a control instruction condition calculated according to a pre-set optimization goal.

[0015] And the step of deriving the set of optimal scenarios may be a step of deriving the set of optimal scenarios including an allowable voltage range of the power system according to the optimization goal, which includes at least one of the risk of blackout of the voltage control system, minimization of power consumption, and improvement of power quality.

[0016] In addition, the step of deriving the optimal scenario may further include the step of comparing the sets of optimal scenarios derived for each voltage control system located in a geographically adjacent area among voltage control systems having the same optimization goal, and if the comparison result satisfies a pre-set correction condition, correcting at least one of the sets of optimal scenarios derived.

[0017] And the step of deriving the optimal scenario may further include: a step of dynamically resetting the allowable voltage range based on external environment data including at least one of temperature, humidity, time zone and seasonal information and multidimensional data including load characteristics; and a step of evaluating one of a plurality of optimal scenario sets based on the reset allowable voltage range, dynamically calculating a priority for each scenario set according to the multidimensional data, and selecting the scenario set with the highest priority.

[0018] In addition, in the step of selecting the set of scenarios with the highest priority, if the external environment data exceeds a preset threshold temperature and threshold humidity, an optimal set of scenarios can be selected that gradually lowers the voltage applied to the voltage control system or readjusts the application time period in combination with the load characteristics at that time.

[0019] And the step of deriving the optimal scenario may further include the step of evaluating the power efficiency of the voltage control system and, if it is determined that the power efficiency has decreased, prioritizing the selection of a set of optimal scenarios corresponding to load redistribution or dynamic idle mode switching to minimize power loss. Effects of the invention

[0020] According to one aspect of the present invention described above, by providing a method for deriving a solution for a voltage control system and a device for deriving a solution, it is possible to collect real-time power measurement values ​​of major system facilities to simulate the power flow and voltage status of the entire power system, and based on the results, not only to accurately predict the voltage impact at the level of all facilities but also to derive an optimal solution for the voltage control system, thereby simultaneously securing energy efficiency and stability of the power system. Brief explanation of the drawing

[0021] FIG. 1 is a drawing illustrating a solution derivation device according to an embodiment of the present invention being linked with a voltage control system. FIG. 2 is a block diagram for explaining a solution derivation device according to an embodiment of the present invention, and, FIG. 3 is a flowchart illustrating a method for deriving a solution according to an embodiment of the present invention. Specific details for implementing the invention

[0022] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in relation to one embodiment. It should also be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the invention is limited only by the appended claims, including all equivalents to those claimed therein, provided appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects.

[0023] The components according to the present invention are defined by functional distinction rather than physical distinction, and can be defined by the functions each performs. Each component may be implemented as hardware or as program code and processing units that perform each function, and the functions of two or more components may be included and implemented in a single component. Therefore, it should be noted that the names assigned to the components in the following embodiments are not intended to physically distinguish each component but are assigned to imply the representative function performed by each component, and that the technical concept of the present invention is not limited by the names of the components.

[0024] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0025] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform a desired characteristic (or objective) are created by a basic artificial intelligence model being trained using a number of training data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0026] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained by the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.

[0027] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that enables a machine to learn by mimicking human biological neurons. Methodologies of artificial intelligence can be classified according to the learning method into supervised learning, where input and output data are provided together as training data and the solution (output data) to the problem (input data) is predetermined; unsupervised learning, where only input data is provided without output data and the solution (output data) to the problem (input data) is not predetermined; and reinforcement learning, where a reward is given from an external environment whenever an action is taken from the current state, and learning proceeds in a direction that maximizes such reward. In addition, artificial intelligence methodologies can be classified according to the architecture, which is the structure of the learning model. The architectures of widely used deep learning technologies can be classified into Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Transformers, and Generative Adversarial Networks (GAN).

[0028] The device and system may include an artificial intelligence model. The artificial intelligence model may be a single model or may be implemented as multiple models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms in machine learning and cognitive science that mimic biological neurons. A neural network may refer to a model that possesses problem-solving capabilities by having artificial neurons (nodes) that form a network through synaptic connections and change the strength of synaptic connections through learning. The neurons of a neural network may include combinations of weights or biases. A neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a result (output) to be predicted from an arbitrary input by changing the weights of the neurons through learning.

[0029] The processor can create neural networks, train or learn neural networks, perform computations based on received input data, generate information signals based on the results of the computation, or retrain neural networks. Neural network models may include, but are not limited to, various types of models such as Convolutional Neural Networks (CNN), Region with Convolutional Neural Networks (R-CNN), Region Proposal Networks (RPN), Recurrent Neural Networks (RNN), Stacking-based Deep Neural Networks (S-DNN), State-Space Dynamic Neural Networks (S-SDNN), Deconvolution Networks, Deep Belief Networks (DBN), Restructured Boltzmann Machines (RBM), Fully Convolutional Networks, Long Short-Term Memory Networks (LSTM), and Classification Networks, such as GoogleNet, AlexNet, and VGG Network. The processor may include one or more processors to perform computations according to neural network models. For example, a neural network is a deep neural network It may include a (Deep Neural Network).

[0030] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo It will be understood by a person skilled in the art that any neural network may be included, but is not limited to, State Network, Deep Residual Network, Differential Neural Computer, Neural Turning Machine, Capsule Network, Kohonen Network, and Attention Network.

[0031] According to an exemplary embodiment of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as recommendation and data creation, may be used, but are not limited thereto.

[0032] Preferred embodiments of the present invention will be described in more detail below with reference to the drawings.

[0033] FIG. 1 is a diagram showing a solution derivation device (100) according to one embodiment of the present invention connected to a voltage control system (1), and FIG. 2 is a block diagram for explaining a solution derivation device (100) according to one embodiment of the present invention.

[0034] The solution derivation device (100, hereinafter the device) according to the present embodiment may be provided to derive an optimal solution for a voltage control system (1) that controls the voltage of a power system.

[0035] The voltage control system (1) illustrated in FIG. 1 is provided to control the voltage of a power system and may include a high-voltage and low-voltage automatic voltage regulator, a local server that controls the low-voltage automatic voltage regulator, and a global server that controls the high-voltage automatic voltage regulator. This voltage control system (1) may include an artificial intelligence model that predicts the power of a load based on real-time power data collected from a meter connected to some of the end loads.

[0036] And the voltage control system (1) can transmit real-time power consumption data collected from the measuring instrument to the device (100). Here, real-time power consumption data may refer to quantitative power consumption information accumulated along a time axis or aggregated by interval.

[0037] For example, real-time power consumption data may include active power (kW), reactive power (kVar), energy consumption per hour (kWh), tap position change history, and load distribution information by transformer or phase.

[0038] Additionally, the voltage control system (1) can transmit control data generated to control the voltage of the power system to the device (100). Here, the control data may refer to data for generating control commands for the high-voltage and low-voltage automatic voltage regulators of the voltage control system (1).

[0039] For example, control data may include items that directly affect power quality diagnosis and adjustment judgment, such as voltage (V), current (A), power factor (PF), total harmonic distortion (THD), frequency (Hz), switching event log (e.g., OLTC operation history), and the imbalance ratio of inter-phase current.

[0040] Additionally, the voltage control system (1) can receive a set of optimal scenarios from the device (100) and control the voltage based on the set of optimal scenarios.

[0041] Meanwhile, the device (100) according to the present embodiment may be provided in conjunction with the voltage control system (1) described above to derive an optimal solution for the voltage control system (1).

[0042] In FIG. 1, the voltage control system (1) is shown as being provided as a single unit, but this is an exemplary case for convenience of explanation, and the solution derivation device according to the present embodiment may be linked with a plurality of voltage control systems (1) to derive an optimal solution for each voltage control system (1).

[0043] To this end, the device (100) according to the present embodiment may include a collection unit (110), a simulation unit (130), and a derivation unit (150). In addition, software (application) for performing a solution derivation method may be installed and executed on the device (100), and the collection unit (110), the simulation unit (130), and the derivation unit (150) may be controlled by the software (application) for performing the solution derivation method.

[0044] At this time, the device (100) may be a separate terminal or a part module of the terminal. Additionally, the configuration of the collection unit (110), the simulation unit (130), and the derivation unit (150) may be formed as an integrated module or composed of one or more modules. However, conversely, each configuration may be composed of a separate module.

[0045] Additionally, the device (100) may be mobile or fixed. This device (100) may be in the form of a server or an engine and may be referred to by other terms such as device, apparatus, terminal, UE (user equipment), MS (mobile station), wireless device, or handheld device. Furthermore, the device (100) may execute or create various software based on an operating system (OS), that is, a system. Here, the operating system is a system program that enables software to use the device's hardware, and may include all mobile computer operating systems such as Android OS, iOS, Windows Mobile OS, Bada OS, Symbian OS, BlackBerry OS, etc., as well as computer operating systems such as Windows family, Linux family, Unix family, MAC, AIX, HP-UX, etc.

[0046] And the device (100) may further include a storage unit in which a program for performing a solution derivation method is recorded, although not shown in the drawing. Such a storage unit temporarily or permanently stores data processed by the collection unit (110), the simulation unit (130), and the derivation unit (150), and may include a volatile storage medium or a non-volatile storage medium, but the scope of the present invention is not limited thereto.

[0047] Meanwhile, the collection unit (110) can collect real-time power amount data and control data from the voltage control system (1).

[0048] Additionally, the collection unit (110) may collect external environment data and load characteristics including at least one of temperature, humidity, time zone, and seasonal information from various types of sensors provided inside or outside the voltage control system (1) or the voltage control system (1).

[0049] Meanwhile, the simulation unit (130) according to the present embodiment can configure a digital twin-based virtual system based on real-time power consumption and control data to simulate a power system and perform a simulation of the virtual system.

[0050] The simulation unit (130) according to the present embodiment can simulate power system operations under various operating conditions on a digital twin-based virtual system. Specifically, the digital twin is composed of virtual objects that model the components of an actual power system, such as transmission nodes, transformers, branch circuits, terminal loads, and high-voltage automatic voltage regulators, and each object can dynamically update its state by reflecting power consumption data and control command data collected in real time.

[0051] This digital twin-based virtual system is configured to precisely simulate physical phenomena such as various operating conditions and load distribution that may occur in the actual system, and can also include data synchronization and omission correction functions for real-time state estimation.

[0052] Accordingly, the simulation unit (130) can analyze indicators such as the current state of the system voltage distribution, current flow, load rate per node, voltage fluctuation rate, voltage drop, and system loss based on this digital twin.

[0053] And the simulation performed by the simulation unit (130) is performed for various scenarios according to pre-set optimization goals. Here, the optimization goals may include preventing blackouts, minimizing power consumption, and improving voltage quality. Accordingly, the simulation unit (130) may apply a scenario for changing the tap position of an automatic voltage regulator to a virtual system by reflecting, for example, the load prediction results of a specific time period, and evaluate whether the system voltage stability is improved as a result, or transmit information that can be evaluated to the derivation unit (150).

[0054] Additionally, the simulation unit (130) executes scenarios that reflect external environmental data such as temperature, humidity, season, and time of day, and can evaluate whether the voltage exceeds the allowable range, control delay time, control stability, etc. for each scenario. The simulation results performed by the simulation unit (130) can be transmitted to the derivation unit (150).

[0055] And the simulation unit (130) can perform simulations using static analysis and dynamic time series analysis methods, and by analyzing voltage change trends, load increase patterns, power loss changes, etc. along the time axis, it can make time-based optimal control judgments possible.

[0056] In addition, the simulation unit (130) according to the present embodiment can correct real-time power data that is missing or contains noise by utilizing a state estimation technique, and can improve the consistency of the digital twin model. To this end, it may be configured to increase the accuracy of load prediction by combining a machine learning-based prediction module and to support the automation of simulation condition settings.

[0057] Meanwhile, the derivation unit (150) according to the present embodiment can derive an optimal scenario set to be transmitted to the voltage control system (1) based on the simulation results from the simulation unit (130).

[0058] And the optimal scenario set derived by the derivation unit (150) may include at least one of an allowable voltage range, a control reference value, priority information, and a control instruction condition calculated according to a pre-set optimization goal.

[0059] The optimization goal for deriving an optimal scenario set may include at least one of preventing blackout of the voltage control system (1), minimizing power consumption, and improving power quality. Accordingly, the derivation unit (150) according to the present embodiment can derive an optimal scenario set including an allowable voltage range of the power system according to these optimization goals.

[0060] In addition, the derivation unit (150) can compare the sets of optimal scenarios derived for each of the voltage control systems (1) located in geographically adjacent regions among the voltage control systems (1) having the same optimization goal.

[0061] Accordingly, the derivation unit (150) can correct at least one of the derived optimal scenario sets when the result of comparing each optimal scenario set of the voltage control system (1) satisfies a pre-set correction condition. That is, the derivation unit (150) according to the present embodiment can perform verification on the derived optimal scenario sets under the same optimization goal. Here, the pre-set correction condition may be when the difference between the optimal scenario sets is excessively large, such as when the upper or lower limit value of the allowable voltage range between the plurality of voltage control systems (1) exceeds a predetermined threshold deviation (e.g., 5V), when the difference between tap settings widens excessively to a set step (e.g., 2 steps or more), or when the difference in the expected power loss or power consumption amount according to each optimal scenario set exceeds a set standard (e.g., 10% or more), or when there is a possibility that the control operation between adjacent voltage control systems (1) may cause mutual interference or overcontrol. Of course, this is merely an exemplary matter for the convenience of explanation and is not necessarily limited thereto.

[0062] Hereinafter, a specific embodiment will be described for correcting at least one of the sets of optimal scenarios when the derived sets of optimal scenarios satisfy the correction conditions, even though there are multiple voltage control systems (1) having the same optimization goal.

[0063] For example, in the case where the optimization goal of the first voltage control system and the second voltage control system, which are voltage control systems (1) provided in regions A and B respectively, which are geographically adjacent, have similar external environments such as temperature and humidity, and have similar load types centered on industrial loads, is to minimize power consumption, the derivation unit (150) may derive each set of optimal scenarios.

[0064] And it is assumed that the derivation unit (150) derives "allowable voltage range 215~230V, tap position of high voltage regulator 3rd stage, no load control" as the optimal scenario set (first scenario) for the first voltage control system, and derives "allowable voltage range 210~225V, tap position of high voltage regulator 1st stage, non-essential load 10% cutoff" as the optimal scenario set (second scenario) for the second voltage control system.

[0065] Accordingly, the derivation unit (150) can determine that the pre-set correction conditions are satisfied because, as a result of comparing the first scenario and the second scenario, there is a difference of more than 5V in the allowable voltage range despite the same environmental conditions, and the tap settings are excessively different, so there is a possibility of a chain reaction such as a decrease in power factor or overvoltage in the adjacent B region due to the voltage rise in region A.

[0066] Accordingly, the derivation unit (150) can correct the first scenario, such as by lowering the allowable voltage range to 210~225V and changing the tap position to 1 stage. At this time, if the derivation unit (150) confirms that the first voltage control system includes some loads sensitive to high voltage, the corrected first scenario may additionally include a control instruction condition of “exclude tap operation in sensitive load section”.

[0067] And in order to correct the optimal scenario set in this way, the derivation unit (150) may create a new corrected optimal scenario set by aligning the voltage control system with lower power loss among the voltage control systems being compared, and modifying at least one of the allowable voltage range, control reference value, or control instruction condition of the other optimal scenario set based on the optimal scenario set that provides a relatively more efficient or stable reference.

[0068] In addition, the derivation unit (150) according to the present embodiment can dynamically reset the allowable voltage range based on multidimensional data including external environment data and load characteristics, including at least one of temperature, humidity, time zone and seasonal information.

[0069] And the derivation unit (150) evaluates one of a plurality of optimal scenario sets based on the reset allowable voltage range and dynamically calculates the priority for each scenario set according to multidimensional data, and can transmit the scenario set with the highest priority to the voltage control system (1).

[0070] For example, it can be assumed that multidimensional data is input, such as when a voltage control system (1) equipped in a specific area is operating during the summer peak hours (2 PM to 5 PM), the current temperature is 36 degrees, which is higher than the critical temperature of 33 degrees, the current humidity is 88%, which is higher than the critical humidity of 85%, sensitive loads including precision electronic equipment are present, the ratio of non-essential loads is 25%, and the predicted load rate is 92%.

[0071] In this case, the output unit (150) can dynamically reset the basic ±5% allowable voltage range to ensure the quality of the terminal voltage. Specifically, the allowable voltage range for the sensitive load section can be set to ±3 (213.4V to 226.6V), and the existing ±5% can be maintained for the general load section.

[0072] Subsequently, the derivation unit (150) can evaluate a plurality of optimal scenario sets pre-generated in the simulation unit (130). For example, the plurality of optimal scenario sets pre-generated are assumed to be: pre-scenario 1 is "Tap 1 step increase, no load control", pre-scenario 2 is "Tap fixed, 10% control of non-essential load", pre-scenario 3 is "Tap 2 step increase, no load control", and pre-scenario 4 is "Tap fixed, 20% control of non-essential load".

[0073] In this case, the derivation unit (150) according to the present embodiment analyzes whether the voltage is maintained within the range in each preliminary scenario based on the condition of the allowable voltage range reset in the above description, and based on this, can filter only suitable preliminary scenarios as evaluation targets. When the evaluation results show that the expected loss amounts in preliminary scenarios 1 to 4 are 5.5kW, 5.9kW, 5.0kW, and 6.1kW, respectively, and the terminal voltage ranges are 212~230V, 215~225V, 210~223V, and 217~223V, respectively, the derivation unit (150) determines that in the case of preliminary scenarios 1 and 3, the voltage at some nodes exceeds the upper or lower limit and excludes them, and only preliminary scenarios 2 and 4 can be maintained as scenarios that satisfy the criteria.

[0074] And the derivation unit (150) can apply a multidimensional data-based priority calculation logic to prior scenarios 2 and 4. Here, the priority calculation criteria may include voltage stability, which is an item determining whether the terminal voltage exists stably within the allowable voltage range; loss amount, which is an item determining whether the expected power loss amount is low; and the cutoff load rate, which determines whether the load cutoff ratio is low, and the importance of these priority criteria may be in the order of voltage stability > loss amount > cutoff load rate.

[0075] Based on these criteria, the derivation unit (150) determines that preliminary scenario 2 shows the most balanced results in terms of voltage stability, amount of loss, and degree of load control, and selects preliminary scenario 2 as the final optimal scenario set and can transmit it to the corresponding voltage control system (1).

[0076] Accordingly, the derivation unit (150) according to the present embodiment can automatically select a scenario optimized for operating conditions through dynamic adjustment of the allowable voltage range reflecting external environment and load conditions and quantitative priority evaluation of a plurality of scenario sets.

[0077] In addition, the derivation unit (150) according to the present embodiment may select an optimal scenario set that gradually lowers the voltage applied to the voltage control system or readjusts the application time period in combination with the load characteristics at that time when external environment data exceeds a preset threshold temperature and threshold humidity.

[0078] For example, it can be assumed that multidimensional data is input, such as when a voltage control system (1) equipped in a specific area is operating during the summer peak hours (2 PM to 5 PM), the current temperature is 37 degrees, which is higher than the critical temperature of 33 degrees, the current humidity is 90%, which is higher than the critical humidity of 85%, there are sensitive loads including precision electronic equipment, the ratio of non-essential loads is 30%, and the predicted load rate is 94%.

[0079] In this case, the derivation unit (150) according to the present embodiment can determine that external environment data has exceeded a threshold value and evaluate an optimal scenario set in combination with the load characteristics at that time to gradually lower the voltage applied to the voltage control system (1) or readjust the application time period.

[0080] For example, under conditions where the ambient temperature exceeds 35 degrees and the load rate exceeds 90%, preliminary scenario A may include the condition that "the tap is gradually lowered by up to 2 stages at 15-minute intervals, and the section where sensitive loads are connected is adjusted within ±2%," and preliminary scenario B may include the condition that "the existing authorized time period for non-essential loads is readjusted from 14:00 to 18:00 to the night time period of 20:00 to 24:00."

[0081] In this case, the derivation unit (150) can receive a simulation result from the simulation unit (130) for pre-scenario A in which the terminal voltage range due to the tap downward adjustment is maintained at 215~225V, the transformer load rate is reduced to 92%, and the power consumption is reduced by about 3.8%.

[0082] Additionally, for pre-scenario B, the derivation unit (150) can receive simulation results from the simulation unit (130) such that the load rate during peak hours drops from 94% to 87%, and by distributing the applied power of some air conditioning loads to night, the total power consumption is reduced by about 7% and the terminal voltage is maintained in the range of 217~223V.

[0083] Subsequently, the derivation unit (150) can determine the priority for preliminary scenarios A and B based on external conditions, power saving effects, and the degree of voltage quality assurance.

[0084] For example, priority criteria may include voltage stability, power consumption reduction rate, and load operation flexibility, and the order of importance may be voltage stability > energy saving effect > load flexibility.

[0085] Based on these criteria, the derivation unit (150) can determine that preliminary scenario A secures power saving effects while maintaining the terminal voltage stably through stepwise voltage adjustment, and accordingly, can select scenario A as the final optimal scenario set and transmit it to the corresponding voltage control system (1).

[0086] In addition, the derivation unit (150) according to the present embodiment evaluates the power efficiency of the voltage control system (1), and if it is determined that the power efficiency has decreased, it may preferentially select an optimal scenario set corresponding to load redistribution or dynamic idle mode switching to minimize power loss.

[0087] For example, a voltage control system (1) installed in a specific industrial complex monitors power efficiency in real time, and the power efficiency is defined as the ratio of active power to transformer output, and if the average value over a certain period falls below a preset standard (e.g., 85%), it can be determined that the power efficiency has decreased.

[0088] For example, if the transformer output is 1200 kVA, the active power is 810 kW, and the reactive power is 600 kVar, the calculated power efficiency is approximately 80%, and the derivation unit (150) can determine that the power efficiency is reduced. In this case, the derivation unit (150) can consider multiple preliminary scenarios to evaluate a set of optimal scenarios for minimizing power loss.

[0089] At this time, preliminary scenario A may include a condition of "redistributing the 15kW cooling load of building A, which has a high load concentration among two buildings in the industrial complex, to building B, which has a low load state, to balance the load," and the simulation unit (130) can perform a system simulation for this scenario and derive a simulation result in which the power factor of building A is improved from 0.85 to 0.91, the total system loss is reduced by about 4.2%, and the transformer load rate is stabilized.

[0090] Additionally, preliminary scenario B may include a condition of "automatically switching three pieces of equipment that are currently in standby state and whose power consumption is detected to idle mode to suppress reactive power," and the simulation unit (130) can derive a result in which the total power consumption is reduced by about 75kW, the terminal voltage quality is improved, and the reactive power burden on the system is reduced.

[0091] Subsequently, the derivation unit (150) can determine the priority for preliminary scenarios A and B based on criteria such as power loss reduction effect, possibility of load interference, and voltage stability. For example, the importance of loss reduction > load interference minimization > voltage stability can be considered. Based on these criteria, the derivation unit (150) can determine that preliminary scenario B has a greater power loss suppression effect and no load interference, and accordingly, can select preliminary scenario B as the final optimal scenario set and transmit it to the corresponding voltage control system (1).

[0092] According to the above configuration, the device (100) according to the present embodiment collects real-time power measurement values ​​of major system facilities to simulate the power flow and voltage status of the entire power system, and based on the results, not only accurately predicts the voltage impact at the level of all facilities but also derives an optimal solution for the voltage control system to simultaneously secure energy efficiency and stability of the power system.

[0094] Meanwhile, FIG. 3 is a flowchart for explaining a solution derivation method according to an embodiment of the present invention. Since the solution derivation method according to an embodiment of the present invention proceeds on a configuration substantially identical to that of the device (100) shown in FIG. 1 and FIG. 2, the same reference numerals are assigned to components identical to those of the device (100) in FIG. 1 and FIG. 2, and repetitive descriptions are omitted.

[0095] The solution derivation method according to the present embodiment is provided to derive an optimal solution for a voltage control system (1) that controls the voltage of a power system.

[0096] To this end, the solution derivation method according to the present embodiment includes the step of collecting data (S110), the step of performing a simulation (S130), and the step of deriving an optimal scenario set (S150).

[0097] The step of collecting data (S110) is a step in which the collection unit (110) collects real-time power amount data and control data from the voltage control system (1).

[0098] Meanwhile, the step of performing a simulation according to the present embodiment (S130) is a step in which the simulation unit (130) configures a digital twin-based virtual system based on real-time power consumption and control data to simulate a power system, and performs a simulation of the virtual system.

[0099] The step of deriving an optimal scenario set according to the present embodiment (S150) is a step in which the derivation unit (150) derives an optimal scenario set to be transmitted to the voltage control system (1) based on the simulation results.

[0100] Here, the optimal scenario set may include at least one of an allowable voltage range, control reference value, priority information, and control instruction conditions calculated according to a pre-set optimization goal.

[0101] And the step (S150) of deriving an optimal scenario set according to the present embodiment may be a step in which the derivation unit (150) derives an optimal scenario set including an allowable voltage range of the power system according to an optimization goal that includes at least one of the risk of blackout occurrence of the voltage control system (1), minimization of power consumption, and improvement of power quality.

[0102] In addition, the step (S150) of deriving an optimal scenario set according to the present embodiment may include comparing the derived optimal scenario sets for each of the voltage control systems (1) located in geographically adjacent areas among the voltage control systems (1) having the same optimization goal, and if the comparison result satisfies a pre-set correction condition, correcting at least one of the derived optimal scenario sets.

[0103] And the step of deriving an optimal scenario set (S150) may further include the step of dynamically resetting an allowable voltage range based on external environment data including at least one of temperature, humidity, time zone and seasonal information, and multidimensional data including load characteristics.

[0104] Additionally, the step of deriving an optimal scenario set (S150) may further include the step of evaluating one of a plurality of optimal scenario sets based on a reset allowable voltage range, dynamically calculating the priority for each scenario set according to multidimensional data, and selecting the scenario set with the highest priority.

[0105] In the step of selecting the set of scenarios with the highest priority, if the external environment data exceeds the preset threshold temperature and threshold humidity, the optimal set of scenarios can be selected to gradually lower the voltage applied to the voltage control system (1) or readjust the application time period in combination with the load characteristics at that time.

[0106] And the step of deriving an optimal scenario set (S150) may further include the step of evaluating the power efficiency of the voltage control system (1), and if it is determined that the power efficiency has decreased, prioritizing the selection of an optimal scenario set corresponding to load redistribution or dynamic idle mode switching to minimize power loss.

[0107] The solution derivation method of the present invention as described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination.

[0108] The program instructions recorded on the above-mentioned computer-readable recording medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software.

[0109] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

[0110] Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

[0112] Although various embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention. Explanation of the symbols

[0113] 1 : Voltage Control System 100 : Solution Derivation Device 110 : Collection Unit 130 : Simulation Unit 150 : Derivative part

Claims

Claim 1 A solution derivation device for deriving an optimal solution for a voltage control system that controls the voltage of a power system, comprising: a collection unit that collects real-time power consumption data and control data from the voltage control system; a simulation unit that configures a digital twin-based virtual system based on the real-time power consumption and control data to simulate the power system and performs a simulation of the virtual system; and a derivation unit that derives an optimal scenario set to be transmitted to the voltage control system based on the simulation results from the simulation unit, wherein the optimal scenario set includes at least one of an allowable voltage range, a control reference value, priority information, and a control instruction condition calculated according to a pre-set optimization goal, and the derivation unit compares the derived optimal scenario set for each voltage control system located in a geographically adjacent area among voltage control systems having the same optimization goal, and if the comparison result satisfies a pre-set correction condition, corrects at least one of the derived optimal scenario set, wherein the pre-set correction condition is when the difference between the control reference value or control instruction condition between the optimal scenario sets exceeds a critical deviation, or when there is a possibility that the control operation between adjacent voltage control systems may cause mutual interference or overcontrol. Claim 2 In claim 1, the derivation unit derives the set of optimal scenarios including the allowable voltage range of the power system according to the optimization goal, which includes at least one of preventing blackout of the voltage control system, minimizing power consumption, and improving power quality. Claim 3 delete Claim 4 In paragraph 2, the solution derivation device comprises: the derivation unit dynamically resetting the allowable voltage range based on external environment data including at least one of temperature, humidity, time zone and seasonal information and multidimensional data including load characteristics; evaluating one of a plurality of optimal scenario sets based on the reset allowable voltage range; dynamically calculating the priority for each scenario set according to the multidimensional data; and transmitting the scenario set with the highest priority to the voltage control system. Claim 5 In claim 4, the derivation unit is a solution derivation device that selects an optimal scenario set for gradually lowering the voltage applied to the voltage control system or readjusting the application time period in combination with the load characteristics at the corresponding time when the external environment data exceeds a preset critical temperature and critical humidity. Claim 6 In paragraph 2, the solution derivation device, wherein the derivation unit evaluates the power efficiency of the voltage control system and, if it is determined that the power efficiency has decreased, preferentially selects a set of optimal scenarios corresponding to load redistribution or dynamic idle mode switching to minimize power loss. Claim 7 A method for deriving a solution in a solution derivation device for deriving an optimal solution for a voltage control system that controls the voltage of a power system, comprising: a step of collecting real-time power consumption data and control data from the voltage control system; a step of configuring a digital twin-based virtual system based on the real-time power consumption and control data to simulate the power system and performing a simulation of the virtual system; and a step of deriving an optimal scenario set to be transmitted to the voltage control system based on the simulation results, wherein the optimal scenario set comprises at least one of an allowable voltage range, a control reference value, priority information, and a control instruction condition calculated according to a pre-set optimization goal, and the step of deriving the optimal scenario set comprises comparing the optimal scenario sets derived for each voltage control system located in a geographically adjacent area among voltage control systems having the same optimization goal, and if the comparison result satisfies a pre-set correction condition, correcting at least one of the derived optimal scenario sets, wherein the pre-set correction condition is when the difference between the control reference value or control instruction condition between the optimal scenario sets exceeds a critical deviation, or when there is a possibility that the control operation between adjacent voltage control systems may cause mutual interference or overcontrol. Claim 8 A solution derivation method according to claim 7, wherein the step of deriving the optimal scenario set is a step of deriving the optimal scenario set including an allowable voltage range of the power system according to the optimization goal including at least one of preventing blackout of the voltage control system, minimizing power consumption, and improving power quality. Claim 9 delete Claim 10 A method for deriving a solution according to claim 8, wherein the step of deriving the optimal scenario set further comprises: a step of dynamically resetting the allowable voltage range based on external environment data including at least one of temperature, humidity, time zone and seasonal information and multidimensional data including load characteristics; and a step of evaluating one of a plurality of optimal scenario sets based on the reset allowable voltage range, dynamically calculating a priority for each scenario set according to the multidimensional data, and selecting the scenario set with the highest priority. Claim 11 A method for deriving a solution according to claim 10, wherein in the step of selecting the set of scenarios with the highest priority, when the external environment data exceeds a preset threshold temperature and threshold humidity, the optimal set of scenarios is selected to gradually lower the voltage applied to the voltage control system or readjust the application time period in combination with the load characteristics at that time. Claim 12 A method for deriving a solution according to claim 8, wherein the step of deriving the optimal scenario set further comprises the step of evaluating the power efficiency of the voltage control system and, if it is determined that the power efficiency has decreased, preferentially selecting the optimal scenario set corresponding to load redistribution or dynamic idle mode switching to minimize power loss.

Images