Energy management and control prediction method based on quantum deep learning

Abstract

The invention relates to an energy management and control prediction method based on quantum deep learning. Accurate prediction and efficient management and control of a closed space energy system are realized. Comprising the following steps: constructing a quantum mechanical model and a virtual reality model of the closed space energy system; establishing a quantum deep learning platform comprising a quantum mechanics model, a virtual reality model and knowledge graph cooperation; the quantum deep learning platform collects and integrates data of the Internet of Things of the energy system in the confined space; calculating the physical structure, the fluid and the particle state of the closed space according to the knowledge graph and the data of the internet of things; the safety and energy consumption of the closed space are predicted and analyzed according to the calculation result; according to the prediction result, making a control strategy and establishing an updated knowledge graph; integrating the management and control strategy, the updated knowledge graph and the quantum deep learning platform into a closed space energy management system; and optimizing the closed space energy management system.

Description

Technical Field

[0001] The present invention relates to the field of energy management, and in particular to an energy management and control prediction method based on quantum deep learning. Through quantum deep learning, energy data is efficiently and accurately predicted, providing a scientific basis and decision-making support for energy management and control. Background Art

[0002] Traditional energy forecasting methods are mainly based on statistical analysis and machine learning techniques, but when dealing with large-scale, high-dimensional, nonlinear and time-series energy data, there are problems such as low computational efficiency and insufficient prediction accuracy.

[0003] This invention proposes an energy management and control prediction method based on quantum deep learning, aiming to achieve accurate prediction and efficient control of confined space energy systems. This method combines the high efficiency of quantum computing with the automatic feature extraction capability of deep learning. By constructing a quantum neural network (QNN) and a quantum recurrent neural network (QRNN), key features are extracted from historical and real-time collected data, capturing long-term dependencies in time series, and thus accurately predicting the safety and future energy consumption of confined space energy systems. In addition, the invention also introduces a quantum optimization algorithm to optimize the model parameters, thereby improving the accuracy and robustness of the prediction model.

[0004] The present invention constructs a quantum deep learning platform and utilizes structures such as space-time hybrid models, state time-varying equations, energy spectrum analysis, particle positions, quantum neural networks, and quantum recurrent neural networks to process complex nonlinear relationships and timing dependencies in energy data. This method not only takes into account the movement and interaction of microscopic particles in the energy system, but also combines real-time operation data to achieve high-precision prediction of the operating status of the energy system. The application of the present invention will promote the innovation of energy management and control technology, and provide new technical means and solutions for the safe, intelligent, and efficient operation of energy systems in confined spaces such as buildings, railway carriages, aircraft cabins, and clean workshops, which has important practical theoretical significance and application value. Summary of the invention

[0005] Technical problems to be solved: It solves the problem that traditional energy prediction methods are mainly based on statistical analysis and machine learning technology, but have low computational efficiency and low prediction accuracy when processing large-scale, high-dimensional, nonlinear and time-series energy data. A method for energy management and control prediction based on quantum deep learning can achieve accurate prediction of energy data and provide more scientific and efficient decision-making support for confined space energy management.

[0006] Technical solution: The present invention provides a photovoltaic power generation prediction method based on machine vision prediction body, comprising the following steps: Step 1: Establish a quantum mechanical model and virtual reality model of the confined space energy system; the energy system includes the power system, heating system, ventilation and air conditioning system. The quantum mechanical model contains all the key components of the energy system and their interactions, as well as the quantum mechanical parameters that describe these components and relationships; the quantum mechanical model is established and analyzed through quantum mechanical calculation software or algorithms.

[0007] Step 2: Establish a quantum deep learning platform that includes quantum mechanics models, virtual reality models and knowledge graphs. The quantum deep learning platform includes a computer program that is stored in the processor, and when the computer program is executed, it implements an energy management prediction method based on quantum deep learning. The construction of the quantum deep learning platform also includes designing the architecture of the quantum neural network, the number of quantum neurons in the input layer, hidden layer and output layer, and the connection method. The weight update and activation function calculation between quantum neurons are realized by using quantum algorithms, quantum Fourier transform and quantum phase estimation. The quantum neural network is combined with the deep learning algorithm to improve the accuracy of model prediction. The knowledge graph includes a knowledge base of computational fluid dynamics models. A knowledge base of semantic networks is constructed for the entities, data and mutual connections of the confined space energy system, and hidden risks and energy consumption are predicted. The prediction results are visualized, such as drawing energy demand forecast curves and energy consumption distribution maps. According to the visualization results, the energy management strategy is further optimized and adjusted.

[0008] Step 3: The quantum deep learning platform collects and integrates the IoT data of the confined space energy system; the operating data of the confined space energy system collected through the IoT is input into the quantum deep learning platform for real-time prediction and analysis, and the energy management and control strategy is dynamically adjusted according to the prediction results.

[0009] Step 4: Calculate the physical structure, fluid and particle state of the confined space based on the knowledge graph and IoT data.

[0010] Step 5: Predict and analyze the safety and energy consumption of confined spaces based on the calculation results; use the quantum deep learning platform to diagnose and warn of hidden risks in confined space energy systems to improve system reliability.

[0011] Step 6: Based on the prediction results, formulate management and control strategies and establish an updated knowledge graph.

[0012] Step 7: Integrate the control strategy, updated knowledge graph and quantum deep learning platform into the confined space energy management system.

[0013] Step 8: Optimize the confined space energy management system; Optimize to optimize the operating efficiency of the confined space energy system, reduce energy consumption and improve safety. Optimizing the confined space energy management system includes training the model using the quantum gradient descent algorithm or the quantum stochastic gradient descent algorithm to minimize the prediction error; using the advantages of quantum parallel computing to accelerate the model training process; and evaluating the generalization ability of the model through methods such as quantum cross-validation to avoid overfitting.

[0014] Beneficial effects: The present invention constructs a quantum deep learning platform and uses structures such as space-time hybrid models, state time-varying equations, energy spectrum analysis, particle positions, quantum neural networks, and quantum recurrent neural networks to process complex nonlinear relationships and time-series dependencies in energy data. This method not only takes into account the movement and interaction of microscopic particles in the energy system, but also combines real-time operation data to achieve intelligent control and high-precision prediction of the operating status of the confined space energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0016] The present invention is described in detail below with reference to the accompanying drawings.

[0017] like Figure 1 As shown, the present invention provides an energy management and control prediction method based on quantum deep learning, comprising the following steps: Step 1: Establish a quantum mechanical model and virtual reality model of the confined space energy system, which includes the power system, heating system, ventilation and air conditioning system. The quantum mechanical model contains all the key components of the energy system and their interactions, as well as the quantum mechanical parameters that describe these components and relationships; the quantum mechanical model is established and analyzed using quantum mechanical calculation software and algorithms.

[0018] Construct a quantum mechanical model of the confined space energy system, identify and parameterize system components: identify all key components of the energy system, and assign corresponding quantum mechanical parameters to each component based on quantum mechanics theory, such as wave function, energy level, transition probability, etc., to accurately describe their physical properties and interactions.

[0019] Based on the identified components and their parameters, a quantum mechanical model is constructed, and the Schrödinger equation is used to describe the movement and energy distribution of microscopic particles in the energy system, reflecting the overall operating status of the system.

[0020] A virtual reality model of a confined space energy system is established. Based on the model prediction results and online comparison and analysis with historical and measured data, the hidden risks of the fluid in the physical model are predicted and fault location is performed, achieving "faults can be warned and accidents can be predicted", thereby improving the refined management of the entire life cycle of the energy system. A management and control method for the entire process of confined space energy systems is established, and the standards for mapping interaction, algorithm prediction and optimized control structure are defined. Through comparison with physical entities and real-time analysis, it is constantly revised to become a model that is synchronized with physical entities and can be managed. It has a self-learning function, and real-time data updates the virtual reality model.

[0021] Step 2: Establish a quantum deep learning platform that includes quantum mechanics models, virtual reality models, and knowledge graphs. The quantum deep learning platform includes the design of a quantum neural network architecture, an input layer, a hidden layer, and an output layer. The input layer receives preprocessed energy data, the hidden layer uses quantum neurons, and uses the superposition and entanglement characteristics of quantum states to achieve nonlinear transformation and feature extraction of data. The output layer outputs the prediction results. The hidden layer uses quantum neurons, and uses the superposition and entanglement characteristics of quantum states to achieve nonlinear transformation and feature extraction of data. Including quantum recurrent neural networks (QRNN) or quantum long short-term memory networks (QLSTM), better handle the temporal dependencies in energy data, realize parallel processing of time series data, and improve the prediction ability of the model.

[0022] Quantum algorithms such as quantum Fourier transform (QFT) and quantum phase estimation are used to optimize model parameters, accelerate the training process, and improve the model's training efficiency and prediction accuracy.

[0023] The quantum deep learning platform includes quantum neural network (QNN) as the core model, which uses the parallelism and efficiency of quantum computing to process large-scale, high-dimensional energy data. It is combined with quantum machine learning algorithms, quantum support vector machine (QSVM) and quantum random forest (QRF) to enhance the model's predictive ability.

[0024] Utilize the automatic feature extraction capability of the quantum deep learning platform to extract key features from historical data, use the quantum approximate optimization algorithm (QAOA) to optimize model parameters, and improve the model's learning efficiency and prediction accuracy.

[0025] Time series prediction and long-term dependency capture introduce quantum recurrent neural network (QRNN) or quantum long short-term memory network (QLSTM) to capture long-term dependencies in time series. Using characteristics such as quantum entanglement and superposition, the model's sensitivity to time series changes and prediction accuracy are improved.

[0026] The quantum deep learning platform includes a computer program that stores energy management prediction methods based on quantum deep learning when executed by the processor. The program develops energy management prediction software based on quantum mechanics to achieve functions such as model construction, quantum state analysis, and prediction result output. The system center database adopts NoSQL database, business database, and subject database application models. Among them, the NoSQL database uses the distributed database MongoDB, and the business database and subject database use the relational database Oracle. Spark is compatible with Hadoop's distributed file system (such as HDFS) and processes a wider range of data and application scenarios by expanding the Hadoop ecosystem. Spark uses Hadoop as the underlying storage system and uses Hadoop's resources for more efficient parallel computing.

[0027] The construction of the quantum deep learning platform also includes designing the architecture of the quantum neural network, the number of quantum neurons in the input layer, hidden layer and output layer, and the connection method; using quantum algorithms, quantum Fourier transform, and quantum phase estimation to achieve weight updates and activation function calculations between quantum neurons; combining quantum neural networks with deep learning algorithms to improve the accuracy of model predictions.

[0028] Using quantum mechanics models, we calculate the energy spectrum of the energy system and the distribution of all possible energy levels in the system. By analyzing the time-varying equations of the quantum state, we predict the evolution trend of the energy system over time, including the changes in physical quantities such as the position, velocity, and acceleration of microscopic particles in the system, as well as their interactions. Using the transition probability theory in quantum mechanics, we predict the possibility of particle transitions between energy levels in the energy system and evaluate the stability and reliability of the system under different working conditions.

[0029] Construct a knowledge graph: Generate corresponding classes for equipment, sensors, etc. in the confined space heating and air-conditioning system; connect them using object attributes according to the equipment organization structure in the system; map the collected real-time data to the corresponding classes through data attributes; define the domain ontology, including the construction of classes and attributes, which are used to describe the equipment, sensors and their relationships in the system; define anomaly detection rules, which are used to detect operational abnormalities such as excessive air supply temperature of air handling units; use the constructed knowledge graph to run anomaly detection semantic rules; when the semantic rules are activated, output the corresponding conclusions, including relevant information about the abnormal components and the type of abnormal problem; and predict and diagnose the safety of confined space power, heating, ventilation and air-conditioning systems.

[0030] The knowledge graph includes the knowledge base of computational fluid dynamics models; constructs a knowledge base of semantic networks for entities, data and interrelationships of confined space energy systems, and predicts hidden risks and energy consumption; visualizes the prediction results, such as drawing energy demand prediction curves and energy consumption distribution maps; and further optimizes and adjusts energy management strategies based on the visualization results; Step 3: The quantum deep learning platform collects and integrates the IoT data of the confined space energy system; collects and integrates the IoT operation data of the confined space energy system, inputs the operation data into the quantum deep learning platform, performs real-time prediction and analysis, and dynamically adjusts the energy management and control strategy according to the real-time prediction results.

[0031] Data collection and preprocessing: Clean IoT operation data, remove outliers and duplicate data, and perform data normalization and standardization to improve data quality and prediction accuracy. Convert data into a form suitable for model training.

[0032] Step 4: Calculate the physical structure, fluid and particle state of the confined space based on the knowledge graph and IoT data; use the CNN-LSTM-SVM spatiotemporal hybrid model algorithm to establish a model standard framework, improve the computing power of the prediction and control function of the confined space energy system on Huawei Cloud, reduce the model training time, and improve the technical optimization level and efficiency. Through the trained CNN-LSTM-SVM network, it can automatically extract local features in the effective area and inter-regional sequence features, enhance the prediction effect, and improve the prediction accuracy. First, the CNN model is used to extract the spatial features of the data, and the LSTM model is used to extract the temporal features of the data. Then, based on the trained CNN-LSTM network, the SVM classifier is updated. Based on the trained CNN-LSTM network and the new SVM classifier, a trained CNN-LSTM-SVM prediction network is constructed.

[0033] Based on the equipment information and historical energy consumption data in the knowledge graph, a hidden risk and energy consumption prediction model is constructed. Using graph database technology, the collected data and defined ontology are converted into a knowledge graph. The nodes in the graph represent entities, and the edges represent the relationship between entities. The ontology definition includes the equipment class, which describes the various equipment in the heating and air-conditioning system; the sensor class, which describes the various sensors installed in the system; the location class, which describes the physical location of the equipment and sensors in the system; the data point class, which describes the data collection point; and the safety and energy efficiency problem class, which describes the energy efficiency problems and anomalies in the system.

[0034] Step 5: Predict and analyze the safety and energy consumption of the confined space based on the calculation results. Safety is to use the quantum deep learning platform to diagnose and warn the hidden risks of the confined space energy system to improve the reliability of the system. In the knowledge graph, define and apply anomaly detection rules, such as detecting that the air supply temperature of the air handling unit is too high and the sensor data is abnormal. Based on the anomaly detection results, conduct a risk assessment on the safety of the system and predict possible failures or safety issues.

[0035] Energy consumption prediction: Draw the actual operating capacity diagram of the unit based on the basic parameters of the unit's terminal fan disk; obtain the fixed model fan disk capacity diagram in the preset database; determine whether the deviation between the unit's actual operating capacity diagram and the fixed model fan disk capacity diagram meets the convergence conditions, and the convergence conditions include stable unit operation and reasonable motor efficiency; if the convergence conditions are met, output the hourly energy consumption prediction results of the air-conditioning system based on the unit's actual operating capacity diagram; realize accurate prediction of energy consumption in confined spaces and energy-saving analysis.

[0036] Step 6: Based on the prediction results, formulate management and control strategies and establish an updated knowledge graph. Collect energy system operation data in real time through the Internet of Things and transmit it to the quantum deep learning platform for correction and prediction. Use the quantum gradient descent algorithm to train the model and use the parallelism of quantum computing to accelerate the gradient calculation process.

[0037] The generalization ability of the model is evaluated by using the quantum cross-validation method. The data set is divided into multiple subsets for training and validation respectively to evaluate the performance of the model on different data sets, avoid overfitting, and improve the generalization ability of the model. According to the results of quantum cross-validation, the architecture and parameters of the model are adjusted, such as the number of quantum neurons, connection mode, activation function, etc., to optimize the model performance. According to the evaluation results, the model architecture and parameters are adjusted to optimize the model performance. According to the feedback results, the energy management strategy is dynamically adjusted to adapt to system changes.

[0038] Step 7: Integrate the control strategy, updated knowledge graph and quantum deep learning platform into the confined space energy management system. This includes detailed data on fluid flow in the confined space, the distribution of physical quantities such as velocity, temperature, humidity and harmful substance concentration, whether the air flow is uniform, whether there is local overheating or overcooling, whether the concentration of harmful substances exceeds the standard, and whether there are air flow short circuits, vortices, dead corners and other phenomena that are not conducive to air circulation and temperature distribution uniformity. At the same time, evaluate whether the concentration of harmful substances exceeds the safety standard to ensure that the indoor air quality meets health requirements. Integrate the prediction model based on quantum deep learning into the energy management system to achieve intelligent control.

[0039] Step 8: Optimize the operating efficiency, reduce energy consumption and improve safety of the confined space energy management system, including fluid momentum, heat and mass equations, changes in fluid temperature or density and flow rate settings; fluid properties, density, viscosity, boundary conditions, inlet velocity, temperature, pressure, distribution of heat and cold sources, etc. At the same time, according to the actual use of the confined space, set different working conditions, such as indoor temperature setting value, personnel activity intensity, outdoor climate conditions, etc.; optimize the confined space energy management system, including using quantum gradient descent algorithm or quantum random gradient descent algorithm to train the model to minimize the prediction error; use the advantages of quantum parallel computing to accelerate the model training process; evaluate the generalization ability of the model through quantum cross-validation and other methods to avoid overfitting, adjust system parameters and improve airflow organization design, etc.

[0040] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims of this application.

Claims

1. An energy management and control prediction method based on quantum deep learning, characterized in that: The following steps are involved: Step 1: Construct a quantum mechanics model and a virtual reality model of the confined space energy system; Step 2: Establish a quantum deep learning platform that includes quantum mechanics models, virtual reality models and knowledge graphs; Step 3: The quantum deep learning platform collects and integrates IoT data of the confined space energy system; Step 4: Calculate the physical structure, fluid and particle state of the confined space based on the knowledge graph and IoT data; Step 5: Predict and analyze the safety and energy consumption of the confined space based on the calculation results; Step 6: Based on the prediction results, formulate management and control strategies and establish a new knowledge graph; Step 7: Integrate the management and control strategies, new knowledge graphs and quantum deep learning platforms into the confined space energy management system; Step 8: Optimize the confined space energy management system.

2. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The quantum mechanical model contains all the key components of the energy system and their interactions, as well as the quantum mechanical parameters that describe these components and relationships.

3. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The energy system includes an electric power system, a heating system, and a ventilation and air conditioning system.

4. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The quantum mechanics model is established and analyzed by quantum mechanics calculation software and algorithms.

5. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The aforementioned collection and integration of the IoT operation data of the confined space energy system is to input the confined space energy system operation data collected through the IoT into the aforementioned quantum deep learning platform for real-time prediction and analysis, and dynamically adjust the energy management and control strategy based on the prediction results.

6. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The knowledge graph includes a knowledge base of computational fluid dynamics models, constructs a knowledge base of semantic networks for entities, data and mutual connections of confined space energy systems, and predicts hidden risks and energy consumption; visualizes the prediction results, draws energy demand prediction curves and energy consumption distribution maps; and further optimizes and adjusts energy management strategies based on the visualization results.

7. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The quantum deep learning platform includes a stored computer program, which, when executed by a processor, can implement the energy management and prediction method based on quantum deep learning described in any one of claims 1 to 6.

8. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The safety mentioned above is to use the quantum deep learning platform to diagnose and warn of hidden risks in confined space energy systems, thereby improving the reliability of the system.

9. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The quantum deep learning platform includes designing the architecture of the quantum neural network, the number of quantum neurons in the input layer, hidden layer and output layer, and the connection method; using quantum algorithms, quantum Fourier transforms, and quantum phase estimation to achieve weight updates and activation function calculations between quantum neurons; combining quantum neural networks with deep learning algorithms to improve the accuracy of model predictions.

10. The energy management and control prediction method based on quantum deep learning according to claim 1 is characterized in that: The optimization of the confined space energy management system is to optimize the operating efficiency of the confined space energy system, reduce energy consumption and improve safety, including using a quantum gradient descent algorithm or a quantum stochastic gradient descent algorithm to train the model to minimize prediction errors; using the advantages of quantum parallel computing to accelerate the model training process; and evaluating the generalization ability of the model through quantum cross-validation to avoid overfitting.

Images