An energy-saving safety box-type substation

Abstract

This invention discloses an energy-saving and safe prefabricated substation, relating to the field of power systems. It includes: a power demand forecasting module: predicting future power demand and adjusting transformer operating parameters based on this demand; a quantum communication configuration module: selecting a quantum key distribution protocol based on the transformer operating parameters, deploying quantum communication equipment, connecting smart sensors installed at various nodes, establishing an energy management panel, and collecting operational intelligent data through the smart sensors; an intelligent sensor network deployment module: receiving and preprocessing the operational intelligent data collected by the sensors through the energy management panel, deploying smart nodes within the substation to form a distributed sensing network; and a local data analysis and decision-making module: completing the operational intelligent data analysis and decision-making process locally through the distributed sensing network. This invention, through its power demand forecasting module, achieves accurate prediction of future power demand.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to an energy-saving and safe prefabricated substation. Background Technology

[0002] In the power system field, with the development of smart grids and the increasing emphasis on energy efficiency, the intelligent assembly of substations has become a research hotspot. Traditional substations mainly rely on static configuration and manual operation, making it difficult to adapt to the dynamic needs of modern power systems. In recent years, by introducing machine learning algorithms for power demand forecasting and combining them with automatic control technology to adjust transformer operating parameters, power distribution has become more efficient and flexible.

[0003] Most existing power demand forecasting models are based on centralized processing, failing to fully utilize the advantages of distributed sensing networks, resulting in slow response times and insufficient data transmission security. Furthermore, traditional communication methods are susceptible to interference, making it difficult to guarantee the secure transmission of critical data and limiting the application of smart substations in complex environments. Summary of the Invention

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

[0005] Therefore, this invention provides an energy-saving and safe box-type substation to solve the problems of inaccurate power demand forecasting, slow response speed, and insufficient communication security in the intelligent assembly of existing substations.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides an energy-saving and safe prefabricated substation, comprising,

[0008] Power demand forecasting module: Predicts future power demand and adjusts transformer operating parameters based on future power demand;

[0009] Quantum communication configuration module: Selects the quantum key distribution protocol through the transformer's operating parameters, deploys quantum communication equipment, connects the smart sensors installed on each node, establishes an energy management panel, and collects operational smart data through the smart sensors;

[0010] Intelligent sensor network deployment module: Receives and preprocesses operational intelligent data collected by sensors through the energy management panel, and deploys intelligent nodes within the substation to form a distributed sensing network;

[0011] Local data analysis and decision-making module: It completes the operational intelligent data analysis and decision-making process locally through a distributed sensing network, initiates encrypted communication, and generates a shared key;

[0012] Encrypted Communication and Key Management Module: After quantum encryption, the operational intelligent data analysis and decision-making process is sent to the central management.

[0013] Central Management and Overall Optimization Module: The central management module receives operational intelligent data analysis and decision-making processes, further processes and analyzes them, and optimizes the operation of the overall system.

[0014] As a preferred embodiment of the energy-saving and safe prefabricated substation described in this invention, the following steps are included: predicting future power demand and adjusting the transformer's operating parameters according to the future power demand:

[0015] Machine learning algorithms are used to analyze historical electricity usage data, weather forecasts, and user behavior patterns to generate future electricity demand forecasting models.

[0016] Based on a future electricity demand forecasting model, future electricity demand is obtained, and the operating parameters of the transformer are automatically adjusted according to the future electricity demand.

[0017] As a preferred embodiment of the energy-saving and safe prefabricated substation described in this invention, the following steps are included: selecting a quantum key distribution protocol based on the transformer's operating parameters and deploying quantum communication equipment:

[0018] Based on the adjusted transformer operating parameters, assess the required level of communication security;

[0019] Based on the communication security level, the BB84 quantum key distribution protocol is selected, and the architecture of quantum communication is designed, along with the physical location of the equipment and the wiring path.

[0020] As a preferred embodiment of the energy-saving and safety-oriented box-type substation described in this invention, the following steps are included: connecting the intelligent sensors installed at each node to establish an energy management panel, and collecting operational intelligent data through the intelligent sensors:

[0021] Intelligent nodes with local processing capabilities are deployed throughout the substation. Intelligent sensors are installed on the intelligent nodes and connected wirelessly. An energy management panel is installed in the central control room and connected to the intelligent nodes and sensors.

[0022] Configure the data acquisition frequency and format, enable the data acquisition function, and start collecting data from various smart sensors in real time to obtain operational intelligent data.

[0023] As a preferred embodiment of the energy-saving and safety-oriented box-type substation described in this invention, the following steps are included: receiving and preprocessing operational intelligent data collected by sensors through an energy management panel:

[0024] Install the database management and data analysis platform in the energy management panel, set the initial parameters, use network testing tools to verify the stability and latency of data transmission, define the transmission format of sensor data, and configure the data acquisition frequency and storage strategy.

[0025] Enable the data receiving function of the energy management panel to start collecting operational smart data from various smart sensors in real time. Clean the received data, convert the sensor data into a unified format, and standardize the numerical range.

[0026] Useful features are extracted from the cleaned data, frequency domain features are extracted using signal processing techniques, and the frequency domain feature data is labeled.

[0027] As a preferred embodiment of the energy-saving and safe box-type substation described in this invention, the deployment of intelligent nodes includes data analysis tasks, real-time monitoring and alarms;

[0028] The data analysis tasks include predictive maintenance, electricity demand forecasting, energy efficiency optimization, security assessment, comprehensive decision support, and long-term performance evaluation.

[0029] The real-time monitoring and alarm system continuously monitors the operating status of transformers and circuit breakers, including temperature, current, and voltage, promptly detects potential faults or abnormal operations, and triggers alarm mechanisms.

[0030] As a preferred embodiment of the energy-saving and safety-oriented prefabricated substation described in this invention, the process of intelligent operational data analysis and decision-making is completed locally through a distributed sensing network, including the following steps:

[0031] Based on the characteristics of frequency domain feature data and analysis objectives, an AI algorithm is selected, historical data is used to train the AI ​​model, model parameters are adjusted to improve prediction accuracy and generalization ability, and model performance is optimized through cross-validation and hyperparameter tuning methods.

[0032] Based on the analysis results, make real-time decisions locally, set automatic response rules, execute decision instructions, feed back the decision results to the central management system, and establish a two-way communication mechanism to share information with intelligent nodes, optimize local decision-making, and improve overall performance.

[0033] As a preferred embodiment of the energy-saving and safe prefabricated substation described in this invention, the process of initiating encrypted communication and generating a shared key includes the following steps:

[0034] The QKD device is started, and the two devices begin to work synchronously. According to the BB84 protocol, the parameters and options are configured, and an initial connection is established through the classical communication channel. The transmitting end generates a single photon according to the BB84 protocol rules and sends it to the receiving end through the quantum channel. The transmitting end and the receiving end disclose part of the measurement results, compare the basis vectors of both parties, retain the measurement results under the same basis vectors, and form an initial key sequence.

[0035] The error correction algorithm is executed using a classic communication channel to correct errors that occur during transmission. The privacy amplification algorithm is applied to reduce the risk of information leakage and to convert the initial key sequence into the final encryption and decryption keys.

[0036] The generated shared key is stored in an encrypted storage medium, the key's validity period is defined, and the key is updated periodically to achieve an automated key rotation mechanism.

[0037] As a preferred embodiment of the energy-saving and safe box-type substation described in this invention, the process of sending operational intelligent data analysis and decision-making processes after quantum encryption, and then sending the operational intelligent data analysis and decision-making processes to the central management, includes the following steps:

[0038] The data analysis and decision results are encrypted using the acquired encryption key and then sent to the central management via a quantum communication channel. The central management receives the encrypted data analysis and decision results and checks their integrity and security.

[0039] Use the corresponding decryption key to decrypt the encrypted data, restore the original data analysis and decision results, and verify the decrypted data analysis and decision results.

[0040] As a preferred embodiment of the energy-saving and safe prefabricated substation described in this invention, the central management receives and analyzes operational intelligent data and makes decisions, further processes and analyzes the data, and optimizes the overall system operation, including the following steps:

[0041] The central management receives data analysis and decision-making results, performs preliminary cleaning on the received data analysis and decision-making results to remove redundant information, missing values, and outliers, and converts the data analysis and decision-making results into a unified standard format to standardize the numerical range.

[0042] Machine learning algorithms are used to analyze potential safety risks in substations, assess equipment health, predict possible failure points, and develop maintenance plans.

[0043] Analyze the energy loss during power transmission, identify high-energy-consuming links, optimize power allocation schemes through intelligent scheduling algorithms, and provide scientific and reasonable decision-making suggestions for the central management system based on the comprehensive analysis results;

[0044] The processing results are fed back to the intelligent nodes to guide them in making local decisions and responding instantly. The system also receives new data and updates from the intelligent nodes through a two-way communication mechanism.

[0045] Establish a data warehouse to centrally store and manage all data analysis and decision-making results.

[0046] The beneficial effects of this invention are as follows: through the power demand forecasting module, accurate prediction of future power demand is achieved; through the quantum communication configuration module, a suitable quantum key distribution protocol is selected based on the transformer operating parameters; through the intelligent sensor network deployment module, data collected by sensors is received and preprocessed on the energy management panel; through the local data analysis and decision-making module, data analysis and decision-making processes are completed in a distributed sensing network; and through the encrypted communication and key management module, the preprocessed data analysis and decision-making results are quantum encrypted and sent to the central management. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the energy-saving safety box-type substation in Example 1.

[0049] Figure 2 This is a flowchart of receiving sensor data via the energy management panel in Example 1. Detailed Implementation

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0051] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides an energy-saving and safe prefabricated substation, including the following steps:

[0052] S1. Predict future electricity demand and adjust the transformer's operating parameters accordingly. The specific steps are as follows:

[0053] We obtain hourly electricity consumption records from power companies and substation management over the past year, and acquire data on temperature, humidity, and wind speed over the past year from weather stations and third-party APIs. We also collect user electricity consumption habits, such as peak hours, off-peak hours, and frequency of use of specific devices, through smart meters and sensors.

[0054] Set up automated scripts, install database software, regularly scrape data from various data sources and store it in the database. For some data that cannot be automatically retrieved, assign a dedicated person to manually enter it and ensure the accuracy and completeness of the data.

[0055] Identify and remove obviously erroneous data points from the collected data, including but not limited to values ​​that are out of reasonable range or missing values, and fill in the missing data points using interpolation, K-nearest neighbor algorithm and time series prediction methods;

[0056] Transforming all data to the same scale using Z-score normalization helps improve the convergence speed and performance of machine learning models, ensuring that all data uses consistent units, including but not limited to converting all temperature data to degrees Celsius and all electricity data to kilowatt-hours.

[0057] Extract periodic, trend, and fluctuation features from time series data, calculate basic statistics, including but not limited to mean, standard deviation, maximum, and minimum values, to describe the basic characteristics of the data, apply signal processing techniques to extract frequency domain features, and use principal component analysis for dimensionality reduction to retain the most representative features.

[0058] Choose an appropriate machine learning algorithm based on the prediction target and data characteristics. Considering the needs of time series prediction, you can choose support vector regression, random forest, gradient boosting tree and long short-term memory network in deep learning. Use cross-validation to evaluate the performance of different algorithms and select the algorithm with the best performance as the final model.

[0059] The preprocessed data is divided into training and test sets, typically in a ratio of 80% training set and 20% test set. Model parameters are adjusted using grid search to improve prediction accuracy. The selected machine learning model is trained using the training set data to ensure that the model can fully learn the patterns and rules in the data. The model's prediction performance is evaluated using the test set data, including but not limited to mean squared error and mean absolute error metrics, to ensure that the model has good generalization ability.

[0060] By using machine learning models to analyze historical electricity usage data, weather forecasts, and user behavior patterns, a future electricity demand forecasting model can be generated.

[0061] Based on a future electricity demand forecasting model, future electricity demand is obtained. The transformer's operating parameters are then automatically adjusted according to this future demand, as expressed below.

[0062]

[0063] Where P(t) is the predicted future electricity demand at time t, where t is the predicted time point, representing the specific future time point, D(τ) is historical electricity usage data, reflecting past electricity consumption patterns, W(τ) is weather forecast data, representing meteorological conditions at the past time point τ, and U(τ) is user behavior pattern, reflecting users' electricity consumption habits. W(τ) and U(τ) are functions reflecting the factors influencing electricity demand. τ is the integration variable used to iterate through historical data during integration. T is the time window length of the historical data considered, representing the time range of the most recent historical data for prediction. -α(T-τ) It is an exponential decay function used to weight closer data points, where i is the feature index variable used to iterate through all selected features or factors, and β... i It is the importance weight of the i-th feature, reflecting the importance of each feature in the prediction, g i (D(t-Δt i ) is an information filtering function used to extract a specific time delay Δt from historical electricity usage data. i Relevant information at the location, Δt i Γ(γ) represents the time delay corresponding to the i-th feature, indicating the location of the historical data point that needs to be referenced when predicting this feature. N is the number of selected features, used to represent the number of selected features. i +1) is the gamma function, used as a normalization factor, γ i These are shape parameters associated with each feature, used for calculating the gamma function.

[0064] S2. Select the quantum key distribution protocol through the transformer's operating parameters, deploy quantum communication equipment, connect the smart sensors installed on each node, establish an energy management panel, and collect operational smart data through the smart sensors. The specific steps are as follows:

[0065] Collect and analyze the adjusted transformer operating parameters, including but not limited to output power, load conditions, and operating temperature, assess the impact of these parameters on the stability and security of the power system, and determine which parameters are highly sensitive and require the highest level of communication security.

[0066] Identify potential security threats, including but not limited to data tampering, man-in-the-middle attacks, and unauthorized access; and define communication security requirements based on risk assessment results, including but not limited to data confidentiality, integrity, and availability requirements.

[0067] Based on international and industry standards, communication security requirements are divided into different security levels. Transformer operating parameters are matched with security levels to determine the minimum communication security level required for each parameter.

[0068] Evaluate existing quantum key distribution protocols, including but not limited to BB84 and E91, select the protocol most suitable for the current application scenario, compare the performance of different protocols in terms of security, transmission rate, distance limitation, etc., and select the optimal solution;

[0069] Given the maturity and widespread application of the BB84 protocol, especially in power systems, BB84 was chosen as the quantum key distribution protocol. The BB84 protocol uses single-photon states to transmit qubits and achieves secure key distribution through the selection of two non-orthogonal basis vectors.

[0070] Design the topology of the quantum communication network to ensure that the communication paths between all key nodes are clear and unambiguous, and introduce redundant paths and backup devices to ensure that communication continuity can still be maintained when the main communication path fails.

[0071] Select appropriate quantum communication equipment, including but not limited to quantum key distributors, single-photon detectors, and fiber amplifiers, and configure necessary classical communication equipment, including but not limited to routers and switches, to assist in information transmission and control signal transmission.

[0072] Choose a suitable location to install quantum communication equipment, ensure that the equipment is in a safe and stable environment, avoid the influence of electromagnetic interference and other environmental factors, optimize the spatial layout of the equipment, and ensure that there is sufficient heat dissipation space and maintenance channels between the equipment;

[0073] Plan the fiber optic cabling path to minimize bends and connectors, ensure signal transmission quality, and adopt appropriate protection measures, including but not limited to duct laying and armored cables, to prevent physical damage to the fiber optic cable.

[0074] Based on the specific needs of the substation, select intelligent node devices with sufficient computing power and storage space, such as edge computing servers. Plan the physical location of intelligent nodes within the substation to ensure coverage of key areas, such as transformers and switch cabinets. Consider heat dissipation, ventilation, and ease of maintenance. Use appropriate brackets or racks to fix the intelligent nodes in the predetermined positions to ensure that the equipment is stable and not easily affected by the external environment.

[0075] The parameters to be monitored include, but are not limited to, temperature, humidity, current, and voltage. Select appropriate smart sensors and connect them to the corresponding smart nodes via wired or wireless interfaces to ensure stable and reliable communication. Calibrate and perform preliminary testing on each sensor to ensure that it works properly and outputs accurate data.

[0076] Design the topology of the wireless network to ensure effective communication between all intelligent nodes. Select a suitable wireless frequency band based on the electromagnetic environment of the substation to avoid interference. Configure the security settings of the wireless network, including but not limited to encryption protocols and access control lists, to ensure communication security.

[0077] Install wireless access points in appropriate locations to ensure signal coverage of the entire substation area. Connect each smart node to the wireless network wirelessly to ensure that they can communicate with each other and upload data to the central control. Adjust wireless network parameters according to the actual environment, including but not limited to transmission power and channel allocation, to optimize network performance.

[0078] A dedicated space is planned within the central control room for installing energy management panels, ensuring that the central control room has sufficient power supply, air conditioning system, and lightning protection measures to protect the safe operation of the equipment;

[0079] Select an energy management panel with high reliability and scalability that supports multiple communication protocols. Connect the energy management panel to each smart node via wired and wireless means to ensure stable data transmission. Debug the energy management panel to verify whether its communication with the smart node is normal and conduct preliminary tests.

[0080] Configure the data acquisition frequency according to specific needs, such as per minute, per hour, or trigger on demand. For key parameters, a higher acquisition frequency can be set to ensure timely response. Define the data acquisition format, including timestamps, sensor identifiers, and measured values, to ensure that the data is easy to parse and process. Configure data storage strategies to ensure that the data is not lost due to network problems.

[0081] Complete the initial setup on the smart node and energy management panel to ensure all devices are in normal working order, then officially enable the data acquisition function and begin collecting data from various smart sensors in real time.

[0082] S3. Receive and preprocess operational intelligent data collected by sensors through the energy management panel, and deploy intelligent nodes within the substation to form a distributed sensing network. The specific steps are as follows:

[0083] Select a suitable database management system according to your needs, install the selected database management system on the energy management panel, ensure that it can run stably, and configure the necessary security settings.

[0084] Choose a suitable data analytics platform and integrate it with the database management system to ensure seamless communication between the two and support real-time data stream processing and batch data processing.

[0085] Set the initial parameters for the operating system and related software, including but not limited to time synchronization, user permissions, and communication protocols; create the necessary database table structure; set indexes and constraints; and ensure efficient data storage.

[0086] Select appropriate network testing tools and use them to test the stability of data transmission between smart nodes and energy management panels. Record key indicators such as latency and packet loss rate, analyze the test results, identify potential network problems, and take corresponding measures to optimize network configuration, including but not limited to adjusting wireless frequency bands and adding access points.

[0087] Choose a suitable communication protocol and define the data transmission format, including but not limited to timestamps, sensor identifiers, and measurement values, to ensure that the data is easy to parse and process;

[0088] Configure the data collection frequency according to actual needs, such as every minute, every hour, or trigger on demand. For critical parameters, a higher collection frequency can be set to ensure timely response. Configure a local data caching mechanism to prevent data loss due to network failure.

[0089] Configure a local data caching mechanism to prevent data loss due to network failures, and set up regular data synchronization to remote servers or cloud storage to ensure secure data backup;

[0090] Enable the data reception function on the energy management panel to ensure that it can receive data from various smart sensors in real time. Perform preliminary testing on the received data to verify whether the data reception is normal. Identify and remove obviously erroneous data points and use interpolation to fill in the missing data points.

[0091] Transform all data to the same scale, ensure that all data use consistent units, extract periodic features, trend features and fluctuation features from time series data, and calculate basic statistics, including but not limited to mean, standard deviation, maximum and minimum values, to describe the basic characteristics of the data;

[0092] Signal processing techniques are applied to extract frequency domain features, identify periodic and non-periodic components in the data, and label the extracted frequency domain feature data to facilitate subsequent analysis and model training.

[0093] Further deployment of intelligent nodes includes data analysis tasks, real-time monitoring and alerts;

[0094] The data analysis tasks include predictive maintenance, electricity demand forecasting, energy efficiency optimization, security assessment, comprehensive decision support, and long-term performance evaluation.

[0095] The real-time monitoring and alarm system continuously monitors the operating status of transformers and circuit breakers, including temperature, current, and voltage, promptly detects potential faults or abnormal operations, and triggers alarm mechanisms.

[0096] Assess the characteristics of frequency domain data, such as periodicity, harmonic components, and noise levels, and clarify the specific objectives of the analysis, such as predicting power demand, fault detection, and anomaly identification.

[0097] S4. The operational intelligent data analysis and decision-making process is completed locally through a distributed sensing network, encrypted communication is initiated, and a shared key is generated. The specific steps are as follows:

[0098] Select an appropriate AI algorithm based on the characteristics of the frequency domain feature data and the analysis objectives;

[0099] Collect sufficient historical data, including frequency domain feature data and their corresponding labels or output values, and divide the data into training set, validation set and test set, with a general ratio of 70% training set, 15% validation set and 15% test set.

[0100] The selected AI model is initially trained using the training set data to ensure that the model can learn the patterns in the data. The model performance is evaluated using the validation set data, and the model parameters are adjusted to improve prediction accuracy and generalization ability.

[0101] The K-fold cross-validation method is adopted to divide the training set into multiple subsets, which are used as the validation set in turn for multiple training and validations to ensure the stability and reliability of the model. The results of each validation are recorded, the average performance index is calculated, and the overall performance of the model is evaluated.

[0102] The model uses a grid search to traverse possible combinations of hyperparameters to find the optimal parameter configuration. Then, it uses a Bayesian optimization method to dynamically adjust the hyperparameters to further improve the model performance. Finally, it uses test set data to evaluate the model performance and ensure that it has good generalization ability.

[0103] Based on the analysis results, automatic response rules are set up to define the actions to be taken in different situations, including but not limited to starting the cooling system, issuing alarms, and adjusting transformer parameters. Automated scripts and programs are developed to ensure that decision-making instructions can be executed quickly locally and to reduce response delays.

[0104] The decision-making results are fed back to the central management system in real time, ensuring that the central system can understand the status and decision-making of each node in a timely manner. A two-way communication mechanism is established to allow the central management system and intelligent nodes to exchange information and achieve collaborative work.

[0105] Regularly synchronize data between the central management system and intelligent nodes to ensure that all nodes have the latest information, optimize local decisions from a global perspective, adjust response rules or update model parameters to adapt to changing environmental conditions;

[0106] Regularly evaluate the system's performance, compare the situation before and after improvements, summarize experiences, and continuously train and optimize machine learning models based on the latest collected data to maintain the system's advanced nature and competitiveness;

[0107] Confirm that both the sending and receiving QKD devices are correctly installed and connected to power. Start the QKD devices and perform a system self-test to ensure that all hardware components are working properly.

[0108] In the device management interface, select the BB84 protocol as the quantum key distribution protocol and configure the necessary parameters, including but not limited to photon source intensity, detector sensitivity, and synchronization clock frequency, to ensure that they meet the experimental requirements.

[0109] Synchronization signals are sent through the classic communication channel to enable the sending and receiving devices to enter a synchronized working state, monitor the device status in real time, and ensure that the two devices can work stably and synchronously.

[0110] An initial connection is established between the sender and receiver through a classical communication channel. A handshake protocol is executed to verify the identities of both ends and ensure communication security. According to the BB84 protocol rules, the sender randomly selects one of two non-orthogonal basis vectors, generates a single photon and encodes it into a qubit. The single photon is then sent to the receiver through a quantum channel. The receiver also randomly selects a basis vector for measurement and records the measurement result.

[0111] Through a classic communication channel, the sender and receiver disclose the basis selection of some measurement results, compare the basis selections of both parties, retain the measurement results with the same basis, remove potentially interfered data points from the retained measurement results with the same basis, form a preliminary key sequence, and perform statistical analysis on the preliminary key sequence to evaluate its quality and security.

[0112] Select an appropriate error correction algorithm, execute the error correction algorithm through a classic communication channel to correct possible bit errors during transmission, ensure the accuracy of the key, apply a privacy amplification algorithm to further compress the initial key sequence, reduce the potential risk of information leakage, and convert the processed key sequence into the final encryption key and decryption key;

[0113] Store the generated shared key in a highly secure encrypted storage medium, set strict access control policies to ensure that only authorized personnel or systems can access the key, define the key's validity period (e.g., one week) to ensure that the key is not exposed for a long time, and set up an automated key rotation mechanism to generate new keys regularly and automatically replace old keys to maintain the continuous security of the system.

[0114] S5. After quantum encryption, the operational intelligent data analysis and decision-making process is sent to central management. The specific steps are as follows:

[0115] Collect the data analysis and decision results that need to be transmitted from intelligent nodes or local data analysis platforms, ensuring that the data format is consistent and facilitates subsequent processing and transmission;

[0116] Securely retrieve the encryption key from the encrypted storage medium, verify the key's validity, and ensure it has not expired or been tampered with. Select a suitable encryption algorithm to ensure data security during transmission. Use the obtained encryption key to encrypt the data analysis and decision results, generate an encrypted data packet, and add an integrity check code to the encrypted data packet to ensure it has not been tampered with during data transmission.

[0117] Ensure that the quantum communication channel has been established and is in working order. Send the encrypted data analysis and decision-making results to the central management system through the quantum communication channel, monitor the transmission process in real time, and ensure that there is no data packet loss or error.

[0118] The central management system receives data packets from the quantum communication channel and confirms successful reception. It checks the format and integrity of the data packets to ensure they meet expectations, extracts the integrity check code from the data packets, and compares it with the calculated hash value. If the check code does not match, it records the abnormal situation and takes corresponding measures, such as requesting data retransmission.

[0119] Verify that the key used for decryption is valid and has not been tampered with, verify the security of the data transmission path, ensure there are no man-in-the-middle attacks or other security risks, securely retrieve the key used for decryption from the encrypted storage medium, verify the validity of the key, and ensure that it matches the key used for encryption.

[0120] Choose the same decryption algorithm as when encrypting to ensure that the original data can be correctly recovered. Use the obtained decryption key to decrypt the encrypted data and recover the original data analysis and decision results.

[0121] Verify the completeness and accuracy of the decrypted data analysis and decision-making results, ensuring consistency with the original data. Perform logical checks on the decrypted data to ensure its rationality and usability. Record the decryption and verification process and results for subsequent auditing and problem tracking.

[0122] S6. The central management receives operational intelligent data analysis and decision-making processes, further processes and analyzes them, and optimizes the overall system operation. The specific steps are as follows:

[0123] The central management system receives the encrypted data analysis and decision results, confirms successful reception, decrypts the encrypted data using the corresponding decryption key, restores the original content, and verifies the integrity of the decrypted data.

[0124] Identify and remove duplicate or unnecessary data items to ensure the dataset is concise and clear; fill in missing data points using interpolation, mean imputation, or time series forecasting methods; identify and remove obviously erroneous data points; convert all data analysis and decision-making results into a unified standard format to ensure the data is easy to parse and process; and convert all values ​​to the same scale to ensure consistent numerical ranges.

[0125] By analyzing potential safety risks in substations using machine learning algorithms, and based on the prediction results, detailed maintenance plans are developed, and regular inspections and preventative maintenance are arranged to reduce the probability of failures.

[0126] Collect energy loss data at each node during power transmission, analyze the data, identify links with high energy loss, find the main energy consumption points, and select appropriate intelligent scheduling algorithms.

[0127] Based on the algorithm output, an optimized power distribution scheme is generated to ensure maximum energy utilization efficiency. Combined with the results of safety risk analysis, equipment health assessment and energy loss analysis, scientific and reasonable decision-making suggestions are provided, and a detailed analysis report is generated for the central management system to refer to and make decisions. Based on the comprehensive analysis results, specific decision instructions are generated, such as adjusting transformer parameters and starting the cooling system.

[0128] Decision-making instructions are sent to intelligent nodes via quantum communication channels or other secure communication methods to guide them in making local decisions and responding instantly. A two-way communication mechanism is established to regularly synchronize data between the central management system and intelligent nodes to ensure information sharing. New data and updates are received from intelligent nodes to adjust analysis models and decision-making strategies in a timely manner.

[0129] Design the overall architecture of the data warehouse, including but not limited to data storage, indexing, and querying; select appropriate data warehouse technologies; import all data analysis and decision-making results into the data warehouse; ensure centralized storage and management of data; implement strict data governance measures; and ensure data quality, security, and accessibility.

[0130] Regularly back up data, clean up expired or no longer needed data, ensure the efficient operation of the data warehouse, continuously monitor the performance of the data warehouse, and optimize query speed and storage efficiency.

[0131] This embodiment also provides an image communication digital media system, including: a power demand forecasting module, a quantum communication configuration module, an intelligent sensor network deployment module, a local data analysis and decision-making module, an encrypted communication and key management module, and a central management and global optimization module.

[0132] The system comprises the following modules: Power Demand Forecasting Module: Forecasts future power demand and adjusts transformer operating parameters accordingly; Quantum Communication Configuration Module: Selects a quantum key distribution protocol based on transformer operating parameters, deploys quantum communication equipment, connects smart sensors installed at various nodes, establishes an energy management panel, and collects operational intelligent data through the smart sensors; Smart Sensor Network Deployment Module: Receives and preprocesses the operational intelligent data collected by sensors through the energy management panel, deploys smart nodes within the substation, and forms a distributed sensing network; Local Data Analysis and Decision-Making Module: Performs operational intelligent data analysis and decision-making locally through the distributed sensing network, initiates encrypted communication, and generates a shared key; Encrypted Communication and Key Management Module: Sends the operational intelligent data analysis and decision-making process after quantum encryption, and then sends it to central management; Central Management and Global Optimization Module: The central management receives the operational intelligent data analysis and decision-making process, further processes and analyzes it, and optimizes the overall system operation.

[0133] In summary, this invention achieves accurate prediction of future electricity demand through an electricity demand forecasting module, selects a suitable quantum key distribution protocol based on transformer operating parameters through a quantum communication configuration module, receives and preprocesses sensor data on the energy management panel through an intelligent sensor network deployment module, completes data analysis and decision-making processes in a distributed sensing network through a local data analysis and decision-making module, and sends the preprocessed data analysis and decision-making results to central management after quantum encryption through an encrypted communication and key management module.

[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An energy-saving, safety-type prefabricated substation intelligent assembly system, characterized in that: include, Electricity Demand Forecasting Module: This module forecasts future electricity demand and adjusts transformer operating parameters accordingly. Specifically, it uses a future electricity demand forecasting model to obtain future electricity demand data and automatically adjusts the transformer's operating parameters based on this demand. ； in, It is in time The future electricity demand forecast, It refers to the predicted point in time, used to indicate a specific point in the future. It is historical electricity usage data, used to reflect past electricity consumption patterns. It is weather forecast data, used to represent past points in time. The local weather conditions, It is a user behavior pattern used to reflect users' electricity consumption habits. It is a function that reflects the factors influencing electricity demand, and is used to reflect these factors. Specifically, it means based on historical electricity usage data. Weather forecast data and user behavior patterns The prediction model is obtained by training with machine learning algorithms. It is an integration variable used to iterate through historical data during the integration process. It refers to the length of the historical data time window considered, which is the time range of the most recent historical data used for prediction. It is an exponential decay function used to weight more recent data points. It is a feature index variable used to iterate through all selected features or factors. It is the first The importance weights of each feature reflect the importance of each feature in the prediction. This is an information filtering function used to extract specific time delays from historical electricity usage data. Relevant information at the location, It is the first The time delay corresponding to each feature indicates the location of the historical data points that need to be referenced when predicting that feature. It represents the number of selected features. It is the gamma function, used as a normalization factor. These are the shape parameters associated with each feature, used for calculating the gamma function; Quantum communication configuration module: Selects the quantum key distribution protocol through the transformer's operating parameters, deploys quantum communication equipment, connects the smart sensors installed on each node, establishes an energy management panel, and collects operational smart data through the smart sensors; Intelligent sensor network deployment module: Receives and preprocesses operational intelligent data collected by sensors through the energy management panel, and deploys intelligent nodes within the substation to form a distributed sensing network; Local data analysis and decision-making module: It completes the operational intelligent data analysis and decision-making process locally through a distributed sensing network, initiates encrypted communication, and generates a shared key; Encrypted Communication and Key Management Module: After quantum encryption, the operational intelligent data analysis and decision-making process is sent to the central management. Central Management and Overall Optimization Module: The central management module receives operational intelligent data analysis and decision-making processes, further processes and analyzes them, and optimizes the operation of the overall system. The connection of smart sensors installed at each node establishes an energy management panel, which collects operational smart data through the smart sensors, including the following steps: Intelligent nodes with local processing capabilities are deployed throughout the substation. Intelligent sensors are installed on the intelligent nodes and connected wirelessly. An energy management panel is installed in the central control room and connected to the intelligent nodes and sensors. Configure the data acquisition frequency and format, enable the data acquisition function, and start collecting data from various smart sensors in real time to obtain operational smart data. The process of receiving and preprocessing operational intelligence data collected by sensors through the energy management panel includes the following steps: Install the database management and data analysis platform in the energy management panel, set the initial parameters, use network testing tools to verify the stability and latency of data transmission, define the transmission format of sensor data, and configure the data acquisition frequency and storage strategy. Enable the data receiving function of the energy management panel to start collecting operational smart data from various smart sensors in real time. Clean the received data, convert the sensor data into a unified format, and standardize the numerical range. Useful features are extracted from the cleaned data, frequency domain features are extracted using signal processing techniques, and the frequency domain feature data is labeled.

2. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 1, characterized in that: The process of predicting future electricity demand and adjusting the transformer's operating parameters based on that demand includes the following steps: Machine learning algorithms are used to analyze historical electricity usage data, weather forecasts, and user behavior patterns to generate future electricity demand forecasting models. Based on a future electricity demand forecasting model, future electricity demand is obtained, and the operating parameters of the transformer are automatically adjusted according to the future electricity demand.

3. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 2, characterized in that: The process of selecting a quantum key distribution protocol through the operating parameters of a transformer and deploying quantum communication equipment includes the following steps: Based on the adjusted transformer operating parameters, assess the required level of communication security; Based on the communication security level, the BB84 quantum key distribution protocol is selected, and the architecture of quantum communication is designed, along with the physical location of the equipment and the wiring path.

4. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 1, characterized in that: The deployed intelligent nodes include data analysis tasks, real-time monitoring, and alarms; The data analysis tasks include predictive maintenance, electricity demand forecasting, energy efficiency optimization, security assessment, comprehensive decision support, and long-term performance evaluation. The real-time monitoring and alarm system continuously monitors the operating status of transformers and circuit breakers, including temperature, current, and voltage, promptly detects potential faults or abnormal operations, and triggers alarm mechanisms.

5. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 4, characterized in that: The process of completing operational intelligent data analysis and decision-making locally through a distributed sensing network includes the following steps: Based on the characteristics of frequency domain feature data and analysis objectives, an AI algorithm is selected, historical data is used to train the AI ​​model, model parameters are adjusted to improve prediction accuracy and generalization ability, and model performance is optimized through cross-validation and hyperparameter tuning methods. Based on the analysis results, make real-time decisions locally, set automatic response rules, execute decision instructions, feed back the decision results to the central management system, and establish a two-way communication mechanism to share information with intelligent nodes, optimize local decision-making, and improve overall performance.

6. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 5, characterized in that: The process of initiating encrypted communication and generating a shared key includes the following steps: The QKD device is started, and the two devices begin to work synchronously. According to the BB84 protocol, the parameters and options are configured, and an initial connection is established through the classical communication channel. The transmitting end generates a single photon according to the BB84 protocol rules and sends it to the receiving end through the quantum channel. The transmitting end and the receiving end disclose part of the measurement results, compare the basis vectors of both parties, retain the measurement results under the same basis vectors, and form an initial key sequence. The error correction algorithm is executed using a classic communication channel to correct errors that occur during transmission. The privacy amplification algorithm is applied to reduce the risk of information leakage and to convert the initial key sequence into the final encryption and decryption keys. The generated shared key is stored in an encrypted storage medium, the key's validity period is defined, and the key is updated periodically to achieve an automated key rotation mechanism.

7. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 6, characterized in that: The quantum encryption process is then used to send operational intelligent data analysis and decision-making processes to central management, including the following steps: The data analysis and decision results are encrypted using the acquired encryption key and then sent to the central management via a quantum communication channel. The central management receives the encrypted data analysis and decision results and checks their integrity and security. Use the corresponding decryption key to decrypt the encrypted data, restore the original data analysis and decision results, and verify the decrypted data analysis and decision results.

8. The energy-saving and safety-oriented intelligent assembly system for prefabricated substations as described in claim 7, characterized in that: The central management receives operational intelligent data analysis and decision-making processes, further processes and analyzes them, and optimizes the overall system operation, including the following steps: The central management receives data analysis and decision-making results, performs preliminary cleaning on the received data analysis and decision-making results to remove redundant information, missing values, and outliers, and converts the data analysis and decision-making results into a unified standard format to standardize the numerical range. Based on data analysis and decision-making results, machine learning algorithms are used to analyze potential safety risks in substations, assess equipment health, predict possible failure points, and develop maintenance plans. Analyze the energy loss during power transmission, identify high-energy-consuming links, optimize power allocation schemes through intelligent scheduling algorithms, and provide scientific and reasonable decision-making suggestions for the central management system based on the comprehensive analysis results; The processing results are fed back to the intelligent nodes to guide them in making local decisions and responding instantly. The system also receives new data and updates from the intelligent nodes through a two-way communication mechanism. Establish a data warehouse to centrally store and manage all data analysis and decision-making results.

Images