An adaptive switching system and method for power supply and distribution

Abstract

The application discloses a kind of adaptive switching system and method of power supply and distribution, it is related to smart grid technical field, including, quantum algorithm library and power grid operation data are loaded to quantum computing platform, utilize quantum algorithm to carry out parallel processing to power grid operation data, analyze the abnormal situation in current power grid, according to analysis result, generate power grid state report, use quantum algorithm to calculate the optimal solution of power generation equipment to load point, obtain optimal power supply path and switching strategy, the application realizes the optimization of the best path and switching strategy of power generation equipment to load point, and quantum algorithm can quickly find optimal solution when processing large-scale complex power grid, effectively reduce the transmission loss of transmission line and power generation equipment, and improve the power supply efficiency of power grid.In addition, by introducing time attenuation factor and priority weight, the switching strategy is further optimized, and the efficient operation of the power grid and the reasonable allocation of the load are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to an adaptive switching system and method for power supply and distribution. Background Art

[0002] With the continuous expansion of power grids and advancements in technology, conventional power supply and distribution networks are gradually moving towards intelligentization. Early power supply and distribution networks relied primarily on manual operations and simple automated equipment. While these devices were capable of providing basic power supply functions, they struggled to cope with complex and changing load demands and detect anomalies.

[0003] The existing power supply and distribution network still has many shortcomings in terms of intelligence. For load demand forecasting, existing methods lack the ability to efficiently process real-time data, making it difficult to accurately predict future load demand changes and limiting the grid's adaptive scheduling capabilities. Furthermore, for anomaly detection, existing methods are unable to effectively address complex failure modes within the grid, prone to false positives and missed detections, impacting the grid's safe operation. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an adaptive switching method for power supply and distribution to solve the problems of inaccurate grid load demand prediction and poor reliability of anomaly detection.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for adaptive switching of power supply and distribution, comprising collecting grid operation data and load demand data;

[0008] Design and train corresponding quantum algorithms based on the scale and complexity of the power grid to form a quantum algorithm library;

[0009] Load the quantum algorithm library and power grid operation data onto the quantum computing platform, use quantum algorithms to parallel process the power grid operation data, analyze abnormal conditions in the current power grid, and generate a power grid status report based on the analysis results;

[0010] Inputting grid status reports and load demand data into the quantum computing platform, the quantum algorithm is used to calculate the optimal solution from the power generation equipment to the load point, and the optimal power supply path and switching strategy are obtained;

[0011] The optimal power supply path and switching strategy are sent to the central control center, and anomaly detection models are used to monitor power grid status changes and generate protection action recommendations.

[0012] As a preferred scheme of the adaptive switching method of power supply and distribution of the application, wherein: the optimal power supply path and switching strategy are sent to the central control center, and the state change of the power grid is monitored using an anomaly detection model to generate a protection action suggestion, including the following steps,

[0013] The optimal power supply path and switching strategy are converted into JSON format, and the converted optimal power supply path and switching strategy are sent to the central control center using the HTTPS communication protocol;

[0014] The central control center analyzes the converted optimal power supply path and switching strategy to generate control instructions for switching time points, switching actions, and load distribution ratios;

[0015] The Autoencoder is selected as the anomaly detection model;

[0016] The control instructions are input into the anomaly detection model to obtain a reconstruction error value;

[0017] The power grid state error threshold is set, and whether the current power grid state is normal is determined according to the interval in which the reconstruction error value is located within the power grid state error threshold;

[0018] According to the judgment result, a protection action suggestion is generated.

[0019] In a second aspect, the application provides an adaptive switching system for power supply and distribution, which includes a data acquisition module that acquires power grid operation data and load demand data;

[0020] An algorithm design and training module designs and trains corresponding quantum algorithms according to the size and complexity of the power grid to form a quantum algorithm library;

[0021] A power grid state report generation module loads the quantum algorithm library and power grid operation data onto a quantum computing platform, uses quantum algorithms to perform parallel processing on the power grid operation data, analyzes the abnormal conditions in the current power grid, and generates a power grid state report according to the analysis results;

[0022] A scheme planning module inputs the power grid state report and load demand data into the quantum computing platform, uses quantum algorithms to find the optimal solution from the power generation equipment to the load point, and obtains the optimal power supply path and switching strategy;

[0023] A protection action suggestion module sends the optimal power supply path and switching strategy to the central control center and uses an anomaly detection model to monitor the state change of the power grid to generate a protection action suggestion.

[0024] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the computer program, when executed by the processor, implements any step of the adaptive switching method for power supply and distribution of the first aspect of the present application.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the adaptive switching method for power supply and distribution of the first aspect of the present application.

[0026] The present application has the following beneficial effects: The power grid state report and load demand data are input into a quantum computing platform, and a quantum algorithm is used to calculate the optimal solution from the power generation equipment to the load point, to obtain the optimal power supply path and switching strategy, thereby optimizing the best path and switching strategy from the power generation equipment to the load point. The quantum algorithm can quickly find the optimal solution when processing large-scale complex power grids, thereby effectively reducing the transmission loss of power transmission lines and power generation equipment, and improving the power supply efficiency of the power grid. In addition, by introducing a time decay factor and a priority weight, the switching strategy is further optimized to ensure efficient operation of the power grid and reasonable allocation of loads. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0028] Figure 1 Flowchart of the adaptive switching method for power supply and distribution in Example 1.

[0029] Figure 2 Determination diagram for determining whether the current power grid state is normal in Example 1. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0031] Example 1, refer to Figure 1 and Figure 2 , the first embodiment of the present application provides an adaptive switching method for power supply and distribution, comprising the following steps:

[0032] S1. The grid operation data includes voltage, current, grid frequency (i.e., the number of changes per second of alternating current, usually measured in hertz, Hz), temperature, and transmission line parameters (i.e., resistance, reactance, capacitance, used for subsequent calculation of transmission losses of power transmission lines) of power generation equipment;

[0033] The load demand data includes load growth rate, peak load, total load demand, time-of-use load demand, and user classification load demand (i.e., according to different types of users, such as industry, commerce, and residents, to divide their respective load demands).

[0034] S2. Design a corresponding quantum algorithm according to the grid scale and grid complexity.

[0035] including the following steps,

[0036] Obtain the grid scale of the grid using the SCADA grid management program;

[0037] Open the client of SCADA, query a certain area (such as area A) and its corresponding grid facilities (such as the number of power stations is 5, the number of substations is 8), use the export function to organize the queried area and grid facilities into Excel format, name it as area A_grid scale.xlsx, and get the grid scale of the grid;

[0038] The grid scale of the grid includes the number of power stations, the number of substations, the number of transformers, the number of circuit breakers, the number of relays, and the length of the transmission line;

[0039] Based on the grid scale, select QAOA as the quantum algorithm, define a unique identifier for each node in the grid, and identify the connection relationship between each node;

[0040] Assign a unique prefix to each type of node (such as G for power station, S for substation, and L for load point), and assign a number to each node in order of size (i.e., G1, G2, S1, S2, L1, L2). After the assignment is completed, generate a unique identifier based on the current geographic coordinates of the node, such as G_40.7128_74.0060 representing a power station located in a certain city;

[0041] Use an adjacency list (a data structure used to store nodes and their adjacent nodes in a graph) to create an empty list for each node in the grid, and add each node's adjacent nodes to the corresponding list, for example, if node S1 is connected to nodes L1 and L2, add L1 and L2 to S1's list, and also add S1 to L1 and L2's lists;

[0042] The node state of the connection relationship between each node is represented by using a Pauli-Z matrix as a binary decision variable (a mathematical tool for representing whether a certain condition is true or not, the binary decision variable usually takes values of 0 or 1, representing no and yes respectively), which is divided into a connected state and an unconnected state, and the +1 eigenvalue and the -1 eigenvalue of the Pauli-Z matrix are used to represent the node state, that is, +1 represents the connected state and -1 represents the unconnected state;

[0043] The current parameter and the resistance parameter of the power transmission line are extracted from the power grid database, and the transmission loss of the power transmission line is calculated, and the expression is:

[0044] Z = I 2 × R;

[0045] Wherein, Z represents the transmission loss of the power transmission line, I represents the current parameter value of the power transmission line, and R represents the resistance parameter value of the power transmission line;

[0046] Suppose that the current and resistance of a power transmission line are 100 A and 0.05 Ω respectively, and the transmission loss of the power transmission line is calculated to be 500 W (watt) by using this formula;

[0047] According to the definition of the interaction of the node state of the power transmission line (i.e. the transmission loss generated when the nodes are connected through the power transmission line), the weighted sum is formed, and the cost function is converted into the form of quantum Hamiltonian, and the cost Hamiltonian is obtained;

[0048] The formation process of the cost function is as follows: first, a pair of nodes is selected, such as (x, y), and (x, y) is substituted into the formula of the transmission loss of the power transmission line, the transmission loss (i.e. Z') generated when the nodes are connected through the power transmission line is calculated and the weighted sum is performed, and finally the node connection state (O) between x and y is defined by using the Pauli-Z matrix, and the cost function C is represented as:

[0049] C = ∑ x<y Z' × O;

[0050] Converting the cost function into the form of quantum Hamiltonian means that the node connection state O xy Between x and y is replaced by a form suitable for quantum calculation;

[0051] Based on the cost Hamiltonian, aluminum is selected as a superconducting material to design a superconducting circuit, and a Josephson junction (a structure composed of two layers of superconductor sandwiching an insulating layer) is introduced into the superconducting circuit to form a superconducting quantum bit;

[0052] The reason for choosing aluminum is that aluminum has a low resistivity and a high ductility, which is convenient for processing into a complex circuit structure;

[0053] Coating photoresist on the support material using photolithography technology, and forming the required circuit shape pattern through mask exposure, based on the circuit shape pattern, using electron beam evaporation method to deposit aluminum on the support material, etching and separating out the material other than aluminum, forming the final superconducting circuit;

[0054] Integrating Josephson junction into the superconducting circuit, until the superconducting circuit is cooled to below its critical temperature (about 1200℃), using microwave pulses to apply a driving signal to each quantum bit of the superconducting circuit, and using a capacitive coupler to connect and combine each group of quantum bits (a group of 2) after applying the driving signal and changing the plate area of the capacitive coupler by the interaction force of the electric field (charged particles passing through the electric field), thereby adjusting the coupling capacitance value of the capacitor, forming a superconducting quantum bit;

[0055] Initializing the superconducting quantum bit to a uniform superposition state (i.e., the superconducting quantum bit is in an equal probability superposition state of all possible states), defining the driving term of each initialized superconducting quantum bit using the Pauli-X matrix (i.e., an external physical quantity that controls the evolution of the superconducting quantum bit state), obtaining the driving Hamiltonian;

[0056] Cooling the superconducting quantum bit to a temperature of 0.01K to form the ground state |0> with the lowest energy, using the Hadamard to emit a radio frequency signal to the superconducting quantum bit, converting the ground state |0> to a uniform superposition state

[0057] Performing a Pauli-X operation on the superconducting quantum bit in a uniform superposition state (i.e., a control pulse signal), flipping the probability amplitude of the superconducting quantum bit to |0> or |1>, and adding the driving term of the superconducting quantum bit and the probability amplitude of the superconducting quantum bit to obtain the driving Hamiltonian.

[0058] S3. Training the quantum algorithm to form a quantum algorithm library.

[0059] Comprising the following steps,

[0060] Using graph theory to identify the specific topology of the power grid (divided into tree structure, ring structure and mesh structure), obtaining the complexity of the power grid;

[0061] Using graph theory to list the connection relationship between power grid equipment and power grid nodes as nodes and edges of the power grid graph, using breadth-first search algorithm to create an access state array and a parent node array, selecting an arbitrary power grid node to join the queue (marked as visited), taking out a node from the queue as the current node and traversing all neighbor nodes of the current node until the queue is empty;

[0062] If any node's neighbor node has been visited and is not its parent node during the whole traversal process, it means that there is a loop in the graph (if it is one loop, the topology of the power grid is ring structure, if there are multiple loops, the topology of the power grid is mesh structure, if there is no loop, the topology of the power grid is tree structure);

[0063] Based on the complexity of the power grid, the P layer is selected as the number of layers of QAOA and the angle parameters of QAOA are initialized;

[0064] The P layer here is selected according to the complexity of the power grid, assuming that the power grid has 100 nodes and 200 edges, and multiple loops exist, then P is initially selected as 4;

[0065] P is 4 means that 4 layers of angle parameters need to be initialized, for each layer, a random number generator is used to generate two random numbers in the interval [0, 2π] (θ represents the angle parameter of the evolution time of the driving Hamiltonian, φ represents the angle parameter of the evolution time of the cost Hamiltonian), for example, in the first layer (P = 1), a value is randomly selected from the interval [0, 2π], for example, θ1 is 1.57 and φ1 is 3.04;

[0066] Based on the cost Hamiltonian and the driving Hamiltonian, the initialized angle parameters are iteratively adjusted using the COBYLA optimizer to obtain the optimal angle parameters;

[0067] The initialized angle parameters are input into the COBYLA optimizer and a target function is determined (its core is to reflect the specific goal of the optimization problem), in the first iteration, COBYLA will select a random direction as the initial trial direction to adjust the angle parameters (try to increase or decrease the value of the angle parameter, and observe which change is more beneficial to the target function), while recording the adjusted target function value, in the second iteration, if the target function value becomes better, record this direction as the effective direction (continue to adjust along this direction in the next iteration), otherwise mark it as an invalid direction (select the opposite direction of the invalid direction for small-scale random perturbation of the angle parameter), with the increase of the number of iterations, COBYLA will gradually reduce the adjustment range of the angle parameter, until the target function value becomes very small (i.e. ten to the power of minus six or smaller), the optimal angle parameters are obtained;

[0068] The optimal angle parameters are saved as a data file in a structured form (i.e. key-value pair form, the key is the name of the angle parameter, and the value is the corresponding angle parameter value), forming a quantum algorithm library;

[0069] The quantum algorithm library in this step can be used in different scenarios, such as testing new hardware and verifying algorithm performance, while the structured data file is easy to query and update, which helps to maintain the integrity and consistency of the quantum algorithm library in the long term.

[0070] S4. Load the quantum algorithm library and power grid operation data onto the quantum computing platform, use quantum algorithms to process the power grid operation data in parallel, analyze the abnormal situation in the current power grid, and generate a power grid state report according to the analysis results.

[0071] comprising the following steps,

[0072] Select IBMQuantum as the quantum computing platform, and load the quantum algorithm library and power grid operation data onto IBMQuantum;

[0073] The reason for choosing IBMQuantum is that it has multiple quantum processors of different sizes and performance, which can meet the needs from basic research to complex applications;

[0074] Log in to IBMQuantum, install the Qiskit library using the pip install qiskit command and obtain the API key, and load the quantum algorithm library and power grid operation data onto IBMQuantum;

[0075] Select the voltage level, current intensity of the power generation equipment, and frequency stability of the power grid as the operation indicators of the power grid nodes;

[0076] The reason for choosing these three as the operation indicators of the power grid nodes is that the voltage level determines the output force of the power grid nodes and the synchronization ability with the power grid, by monitoring the current, the power demand of the nodes and whether there is an overload phenomenon can be understood, and many electrical equipment is very sensitive to the change of power grid frequency, frequency instability will lead to electrical equipment efficiency decline or failure;

[0077] According to the operation indicators of the power grid nodes, define the state categories of the power grid nodes and the specific number of quantum bits required, and formulate the corresponding mapping rules for each state category of the power grid nodes to map the state of the power grid nodes to quantum bit representation;

[0078] For each operation indicator (take voltage level as an example), divide it into several intervals according to actual needs (multiply each interval to get the number of state categories): normal (voltage lower limit ≤ voltage value ≤ voltage upper limit), low (voltage value < voltage lower limit), high (voltage value > voltage upper limit);

[0079] Combine the intervals of different operation indicators to form the state categories of the power grid nodes (such as voltage low, current high load, frequency slight fluctuation);

[0080] The number of qubits depends on the total number of state categories, if there are N state categories in total, the number of qubits q required satisfies that 2q is greater than or equal to N (for example, there are 3 operation indicators, each indicator is divided into 3 intervals, and the total number of state categories is 3*3*3 = 27, and the number of qubits required is 2^5 = 32);

[0081] Each state category is represented by a unique binary string, and each state category is one-to-one corresponding to a binary string (for example, voltage is low, current is high load, frequency is slightly fluctuating → 00010), and finally the binary string is directly mapped to the state representation of the quantum bit (00010 corresponds to the quantum bit state 00010 → |00010);

[0082] The state categories of the grid node include normal state, low load state and high load state;

[0083] The superposition and entanglement of quantum states are used to process the criticality and correlation of the mapped state of the grid node, and the quantum state of the grid node state is obtained;

[0084] Criticality processing: first determine which state categories belong to critical state (such as voltage is low, high, frequency is seriously fluctuating), use the probability amplitude to multiply the critical state and the normal state respectively and add them up to get a quantum comprehensive state (representing the possibility distribution between normal state and critical state), if the possibility of critical state of quantum comprehensive state is high, increase the value of probability amplitude, otherwise decrease the value of probability amplitude, and adjust the quantum comprehensive state as the result of criticality processing;

[0085] Correlation processing: first identify the strong correlation between the grid nodes (such as two nodes sharing the same transmission line or the frequency fluctuation of one node affecting the voltage level of another node), use quantum entangled state to represent the correlation between the grid nodes, assume that there are two nodes, the states of which are a and b respectively, use a1 to multiply b1 and add a2 to multiply b2 (a1, a2, b1, b2 represent a certain state category of the grid node, such as low load and high load of current), and finally multiply by root 2 / 1 to get the final quantum entangled state, and the quantum entangled state is taken as the result of correlation processing;

[0086] Select the initial state of the quantum state of the grid node state (for |0 state, if 3 qubits are required, the initial state is |000);

[0087] Use the Ry parameterized rotation gate to adjust the initial state of the grid node state to the superposition state, and use the Rz parameterized rotation gate to rotate around the z axis to adjust the phase of the initial state of the grid node state;

[0088] The initial state of the grid node state is changed in the latitude position on the globe by using the Ry parameterized rotation gate (if the initial state is located at the North Pole |0, after rotating along the y-axis by an angle of θ, the initial state of the grid node state will move to the vicinity of the equator, or even close to the South Pole |1, which is the adjusted superposition state), and the Rz parameterized rotation gate changes the initial state of the grid node state in the longitude position on the globe (if the initial state of the grid node state is originally located at the prime meridian 0° longitude, after rotating along the z-axis by an angle of θ, its longitude position will move to 90° longitude, which is the phase of the adjusted initial state of the grid node state);

[0089] The adjusted superposition state and phase of the grid node state are combined to form a QAOA circuit using the Qiskit computing framework;

[0090] The adjusted superposition state and phase of the grid node state are combined to form a QAOA circuit using the Qiskit computing framework;

[0091] The adjusted superposition state and phase of the grid node state are combined to form a QAOA circuit using the Qiskit computing framework;

[0092]

[0093] where Q i represents the quantum state of the i-th grid node after adjustment, P(Q i ) represents the state probability distribution of the quantum state of the i-th grid node after adjustment, ψ() represents the quantum state function, ψ(Q i ) represents the quantum state function of the i-th grid node after adjustment, which describes the complete quantum characteristics of Q i , d represents the operator for integrating the quantum state of the i-th grid node after adjustment, and the integration function is to summarize the probability density of the quantum state in the whole space to ensure the total probability is 1 (normalization condition);

[0094] The state probability distribution of the adjusted grid node is analyzed using Pandas to find out the abnormal situations existing in the current grid (including low or high voltage level, large or unstable frequency fluctuation, and high current load);

[0095] The state probability distribution of the adjusted power grid nodes is arranged in descending order using the data frame in Pandas, and a pie chart is used to visually display the probability distribution of different power grid nodes. Through this visualization, it can be quickly found out which states occupy a larger proportion and which states are rare.

[0096] Based on the analysis results, a power grid state report is generated (including power grid operation profile, summary of abnormal situations, and visual charts of pie charts).

[0097] S5. Input the power grid state report and load demand data into the quantum computing platform, and use quantum algorithms to calculate the optimal solution from power generation equipment to load points to obtain the optimal power supply path and switching strategy.

[0098] comprising the steps of,

[0099] The load demand data is normalized and a smoothing function is used to calculate the load demand prediction value for a future period of time, expressed as:

[0100]

[0101] where L(s) represents the load demand prediction value for a future period of time, s represents a future period of time, n represents the time window size of the load demand data, k represents the discrete time point index, a represents the smoothing degree of the load demand prediction value for a future period of time s, a larger a value will make the load demand prediction value more smooth, and a smaller a value will retain the fluctuations of the load demand prediction value, and B represents the normalized load demand data.

[0102] The input and output power of the power generation equipment under different load conditions (such as 50% load, 70% load) is obtained using the SCADA power grid management program, and a device efficiency model is established by plotting the input-output efficiency versus load condition graph;

[0103] The power generation equipment efficiency is determined (using the output power divided by the input power to obtain the efficiency of the power generation equipment), and the input-output efficiency versus load condition graph is plotted (the horizontal axis represents the load condition, and the vertical axis represents the power generation equipment efficiency), the trend between input-output efficiency and load condition is observed, and the highest efficiency load range is found (usually, the efficiency of the power generation equipment will first increase and then decrease with the increase of the load, showing a hump-shaped curve, and the highest efficiency load range is the highest point of the hump);

[0104] The mathematical model using the piecewise linear function divides the most efficient load range into several intervals, and in each interval, a straight line equation y=kx+b is used to represent the relationship between efficiency and load, and the slope and intercept of the hump curve are measured to obtain the fitting parameters, based on which a normal distribution of device efficiency is defined for each load condition (μ,σ 2 )(μ represents the fitting parameter, and σ represents the standard deviation of the load point, which can be estimated using historical device load data), forming a complete device efficiency model;

[0105] The transmission loss ratio of each power generation device (defined as 1 minus the efficiency of the power generation device) is calculated using the device efficiency model and summed up to obtain the total transmission loss of the power generation device (the transmission loss of a power generation device is obtained by multiplying its output power by its transmission loss ratio, assuming there are three devices, then the transmission loss of each is calculated and added to obtain the total transmission loss);

[0106] The grid state report and load demand prediction value for a future period of time are input into the quantum computing platform, combined with the total transmission loss of the power generation device and the connection relationship between each grid node, and a quantum algorithm is used to calculate the path optimization index of each power supply path, expressed as:

[0107]

[0108] Where G V represents the path optimization index of the Vth power supply path, m represents the number of grid nodes, H j represents the total transmission loss of the jth power generation device, β represents the influence factor of the total transmission loss of the power generation device, a larger β value will make the transmission loss of the power generation device more significant, and vice versa, max(B) represents the maximum value of the normalized load demand data;

[0109] The power supply path with the highest path optimization index is selected as the optimal power supply path;

[0110] Assuming there are three power supply paths (a, b, c), the transmission losses of a, b, and c are 5, 8, and 6 respectively, and the normalized load demand data of a, b, and c are 0.8, 0.6, and 0.7 respectively, the above data is substituted into the path optimization index formula to calculate the path optimization index of the three power supply paths a, b, and c, which are 0.235, 0.137, and 0.181 respectively, then the path optimization index of the power supply path a is the highest, and a is selected as the optimal power supply path;

[0111] An initial time point and a priority weight of the grid node are set (the initial time point is set according to a specific event and a periodically operated device, the specific event including a sudden increase in current load, access of new energy, etc., and the priority weight is set according to stability and peak demand of different grid nodes, for example, a node for power supply of a hospital or a data center should be given a higher weight), a time decay factor is introduced, and an optimal switching time point of the grid node is calculated, and the expression is:

[0112]

[0113] wherein T i represents the optimal switching time point of the i th grid node, t represents the current time point of the grid node, W i represents the priority weight of the i th grid node, t 0 represents the initial time point of the grid node, and γ represents the time decay factor, which functions to reduce the influence of an early state as time elapses, so that the calculation pays more attention to recent changes.

[0114] Based on the optimal switching time point of the grid node, a corresponding switching action is performed.

[0115] The switching action includes power switching, load transfer, and device start-stop.

[0116] Power switching: when the main power supply fails or the load demand exceeds its capacity, the state (such as voltage and power output) of the current power supply is detected, and the connection of the current power supply is disconnected and the standby power supply is enabled at the optimal switching time point.

[0117] Load transfer: when a line or device approaches full load or overload, the topological structure of the grid (such as tree-shaped or mesh-shaped) is identified, the target node or line to which the load can be transferred is determined, and the current path is redistributed and the switch state of the circuit breaker is disconnected at the optimal switching time point.

[0118] Device start-stop: when the load demand increases and the standby device is started, it is first necessary to ensure that the device start-stop process meets the safety specifications (such as preheating and cooling time), the device is started at the optimal switching time point, the output power is gradually increased to avoid impact, and when the device is stopped, the output power is gradually reduced to ensure smooth transition of the device state.

[0119] The corresponding switching action is a switching strategy.

[0120] S6. The optimal power supply path and the switching strategy are sent to the central control center, and the state change of the grid is monitored using an anomaly detection model to generate a protection action suggestion.

[0121] comprising the steps of,

[0122] The optimal power supply path and switching strategy are converted into JSON format and sent to the central control center using the HTTPS communication protocol;

[0123] The JSON format of the optimal power supply path and switching strategy in this step is more concise than other formats such as XML, reducing the volume of data transmission. The use of HTTPS ensures the security and integrity of data transmission, reducing the potential risks caused by data leakage or tampering;

[0124] The central control center parses the converted optimal power supply path and switching strategy, generates switching time points (e.g., the best switching time for a certain node is 2025-02-11 15:00:00, then generates the instruction: node_1:{switchTime:2025-02-11 15:00:00}), switching actions (taking the start and stop of a device as an example, the generated instruction is: node_3:{action:startDevice,deviceID:generator_1}) and control instructions for load distribution ratio (assuming the load distribution ratio of a certain node is 60%, then the generated instruction is node_1:{loadDistribution:60%});

[0125] Autoencoder is selected as the anomaly detection model (the reason for selection is that Autoencoder can effectively extract important features from high-dimensional data and learn complex nonlinear relationships in data);

[0126] The application of Autoencoder in the detection of abnormal state of power grid is not a simple scene migration, but through targeted calculation and detection. Autoencoder can capture minor abnormal signals and calculate reconstruction error values by inputting control instructions. According to the reconstruction error value and the set threshold, the abnormality degree of the power grid is quantified, and the accuracy of the power grid state is realized, thus greatly improving the sensitivity of Autoencoder detection;

[0127] The control instruction is input into the anomaly detection model to obtain the reconstruction error value;

[0128] After inputting the anomaly detection model, the input control instruction is compressed into a low-dimensional feature representation by the encoder, and the compressed low-dimensional feature representation is decoded into the initial control instruction by the decoder. The difference square between the low-dimensional feature representation and the initial control instruction is calculated using the mean square error, and finally the average value of the difference square is obtained to obtain the reconstruction error value;

[0129] Setting a grid state error threshold (set according to the reconstruction error distribution characteristics, calculated by mean ± 3 times standard deviation, 0.02-0.08), according to the interval in which the reconstruction error value is located within the grid state error threshold to determine whether the current grid state is normal;

[0130] When the reconstruction error value is less than or equal to 0.05 and greater than or equal to 0.02, the current grid state is normal, and when the reconstruction error value is greater than 0.05 and less than or equal to 0.08, the current grid state is abnormal;

[0131] According to the judgment result, a protection action suggestion is generated;

[0132] When the current grid state is abnormal, the protection action suggestion is as follows: a red warning prompt is popped up on the monitoring interface of the central control center, and the abnormal grid node or area is highlighted, the warning prompt is sent to the operation and maintenance personnel through SMS, the operation and maintenance personnel locate the affected line (for example, the current of a certain line suddenly fluctuates greatly, then the switch equipment of the line is checked) according to the grid topology structure and the specific location of the abnormal grid node or area, and automatically trigger the circuit breaker or relay to disconnect the fault line; for the key load area, find the specific reason (such as insulation aging, load overlimit, etc.) and switch to the standby power supply to ensure the continuous operation of important equipment.

[0133] The embodiment also provides an adaptive switching system for power supply and distribution, comprising:

[0134] A data acquisition module acquires grid operation data and load demand data;

[0135] An algorithm design and training module designs and trains corresponding quantum algorithms according to the grid scale and grid complexity to form a quantum algorithm library;

[0136] A grid state report generation module loads the quantum algorithm library and the grid operation data onto a quantum computing platform, uses quantum algorithms to perform parallel processing on the grid operation data, analyzes the abnormal conditions in the current grid, and generates a grid state report according to the analysis result;

[0137] A scheme planning module inputs the grid state report and the load demand data into the quantum computing platform, uses quantum algorithms to find the optimal solution from the power generation equipment to the load point, and obtains the optimal power supply path and switching strategy;

[0138] A protection action suggestion module sends the optimal power supply path and switching strategy to the central control center, and uses an abnormality detection model to monitor the state change of the grid to generate a protection action suggestion.

[0139] The embodiment also provides a computer device suitable for the adaptive switching method of power supply and distribution, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the adaptive switching method of power supply and distribution proposed in the above embodiment.

[0140] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, a trackball or a touchpad arranged on the shell of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0141] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to realize the adaptive switching method of power supply and distribution proposed in the above embodiment. The storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0142] To sum up, the application realizes the optimization of the optimal path and switching strategy from the power generation equipment to the load point by inputting the power grid state report and load demand data into the quantum computing platform, using quantum algorithm to calculate the optimal solution from the power generation equipment to the load point, and obtaining the optimal power supply path and switching strategy. The quantum algorithm can quickly find the optimal solution when processing large-scale complex power grids, thereby effectively reducing the transmission loss of the power transmission line and the power generation equipment, and improving the power supply efficiency of the power grid. In addition, by introducing the time decay factor and the priority weight, the switching strategy is further optimized, ensuring the efficient operation of the power grid and the reasonable allocation of the load.

[0143] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. An adaptive switching method for power supply and distribution, characterized by: include, Collect grid operation data and load demand data; Design and train corresponding quantum algorithms based on the scale and complexity of the power grid to form a quantum algorithm library; Load the quantum algorithm library and power grid operation data onto the quantum computing platform, use quantum algorithms to parallel process the power grid operation data, analyze abnormal conditions in the current power grid, and generate a power grid status report based on the analysis results; Input the grid status report and load demand data into the quantum computing platform, use the quantum algorithm to calculate the optimal solution from the power generation equipment to the load point, and obtain the optimal power supply path and switching strategy. The steps are as follows: Normalize the load demand data and use the smoothing function to calculate the load demand forecast value for a period of time in the future; Use the SCADA grid management program to obtain the input and output power of power generation equipment under different load conditions, and establish an equipment efficiency model by plotting the relationship between input and output efficiency and load conditions; Use the equipment efficiency model to calculate the transmission loss ratio of each power generation equipment and sum them up to obtain the total transmission loss of the power generation equipment; The grid status report and the load demand forecast for the next period of time are input into the quantum computing platform. Combined with the total transmission loss of the power generation equipment and the connection relationship between each grid node, the quantum algorithm is used to calculate the path optimization index of each power supply path; Select the power supply path with the highest path optimization index as the optimal power supply path; Set the initial time point and priority weight of the grid node, introduce the time decay factor, and calculate the optimal switching time point of the grid node; Based on the optimal switching time point of the grid node, the corresponding switching action is executed; The corresponding switching action is a switching strategy; The optimal power supply path and switching strategy are sent to the central control center, and anomaly detection models are used to monitor power grid status changes and generate protection action recommendations.

2. The adaptive switching method for power supply and distribution according to claim 1, wherein: The grid operation data includes voltage, current, grid frequency, temperature and transmission line parameters of power generation equipment; The load demand data includes load growth rate, peak load, total load demand, time-sharing load demand and user classification load demand.

3. The adaptive switching method for power supply and distribution according to claim 2, wherein: Designing a corresponding quantum algorithm based on the scale and complexity of the power grid includes the following steps: Use SCADA grid management program to obtain grid size of the power grid; The grid scale of the power grid includes the number of power stations, substations, transformers, circuit breakers, relays and the length of transmission lines in the power grid; Based on the scale of the power grid, QAOA is selected as the quantum algorithm to define a unique identifier for each node in the power grid and identify the connection relationship between each node; Use the Pauli-Z matrix as a binary decision variable to represent the node status of the connection relationship between each node; Extract the current and resistance parameters of the transmission line from the power grid database and calculate the transmission loss of the transmission line; The interaction of node states is defined according to the transmission loss of the transmission line and weighted summed to form a cost function. The cost function is then converted into the form of quantum Hamiltonian to obtain the cost Hamiltonian. Based on the cost Hamiltonian, aluminum is selected as the superconducting material to design a superconducting circuit, and a Josephson junction is introduced into the superconducting circuit to form a superconducting quantum bit; The superconducting qubit is initialized to a uniform superposition state, and the Pauli-X matrix is ​​used to define the driving term of each initialized superconducting qubit to obtain the driving Hamiltonian.

4. The adaptive switching method for power supply and distribution according to claim 3, wherein: Training the quantum algorithm to form a quantum algorithm library includes the following steps: Use graph theory to identify the specific topology of the power grid and obtain the complexity of the power grid; Based on the complexity of the power grid, P layers are selected as the number of layers of QAOA and the angle parameters of QAOA are initialized; Based on the cost Hamiltonian and the driving Hamiltonian, the COBYLA optimizer is used to iteratively adjust the initialized angle parameters to obtain the optimal angle parameters; The optimal angle parameters are saved as structured data files to form a quantum algorithm library.

5. The adaptive switching method for power supply and distribution according to claim 4, wherein: Load the quantum algorithm library and power grid operation data onto the quantum computing platform, use the quantum algorithm to process the power grid operation data in parallel, analyze the abnormal conditions in the current power grid, and generate a power grid status report based on the analysis results, including the following steps: Select IBM Quantum as the quantum computing platform and load the quantum algorithm library and power grid operation data onto IBM Quantum; The voltage level and current intensity of power generation equipment and the frequency stability of the power grid are selected as the operation indicators of the power grid nodes; Based on the operating indicators of the grid nodes, the state categories of the grid nodes and the specific number of qubits required are defined. At the same time, corresponding mapping rules are formulated for each state category of the grid nodes to map the state of the grid nodes into qubit representations. The state categories of the power grid nodes include normal state, low load state and high load state; Use the superposition and entanglement of quantum states to perform criticality and correlation processing on the states of the mapped power grid nodes to obtain the quantum state of the power grid nodes; Selecting the initial state of the quantum state of the grid node; The Ry parameterized revolving gate is used to adjust the initial state of the power grid node state to a superposition state, and the Rz parameterized revolving gate is used to rotate around the z axis to adjust the phase of the initial state of the power grid node state; The superposition state and phase of the adjusted grid node states are combined using the Qiskit computation framework to form a QAOA circuit. The QAOA circuit is run on a quantum computing platform using the Aer simulator, and the state probability distribution of the adjusted grid nodes is calculated using quantum state functions. Use Pandas to analyze the state probability distribution of the adjusted grid nodes and identify any abnormalities in the current grid. Based on the analysis results, a power grid status report is generated.

6. The adaptive switching method for power supply and distribution according to claim 5, wherein: The optimal power supply path and switching strategy are sent to the central control center, and the anomaly detection model is used to monitor the state changes of the power grid and generate protection action suggestions, including the following steps: Convert the optimal power supply path and switching strategy into JSON format and send the converted optimal power supply path and switching strategy to the central control center using the HTTPS communication protocol; The central control center analyzes the optimal power supply path and switching strategy after format conversion, and generates control instructions for switching time points, switching actions, and load distribution ratios; Select Autoencoder as the anomaly detection model; Input the control instruction into the anomaly detection model to obtain the reconstruction error value; Set a grid state error threshold, and determine whether the current grid state is normal based on whether the reconstruction error value is within the grid state error threshold; Generate protection action suggestions based on the judgment results.

7. An adaptive switching system for power supply and distribution, based on the adaptive switching method for power supply and distribution according to any one of claims 1 to 6, characterized in that: include, Data acquisition module, collecting power grid operation data and load demand data; Algorithm design and training module: Design and train corresponding quantum algorithms based on the scale and complexity of the power grid to form a quantum algorithm library; The power grid status report generation module loads the quantum algorithm library and power grid operation data onto the quantum computing platform, uses quantum algorithms to parallel process the power grid operation data, analyzes abnormal conditions in the current power grid, and generates a power grid status report based on the analysis results; The solution planning module inputs grid status reports and load demand data into the quantum computing platform, uses quantum algorithms to find the optimal solution from power generation equipment to load points, and obtains the optimal power supply path and switching strategy; The protection action recommendation module sends the optimal power supply path and switching strategy to the central control center, and uses the anomaly detection model to monitor the state changes of the power grid and generate protection action recommendations.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the adaptive switching method for power supply and distribution according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the adaptive switching method for power supply and distribution according to any one of claims 1 to 6 are implemented.

Images