Quantum deep Q learning reconstruction method and system for new energy access power distribution network

Abstract

The invention belongs to the technical field of power grid optimization, and particularly relates to a quantum deep Q learning reconstruction method and system for a new energy access power distribution network, and the method comprises the steps: S1, constructing a power distribution network model based on a neural network; s2, constructing a quantum depth Q learning reconstruction method; and S3, training quantum depth Q learning. By accurately controlling the switching operation in the power distribution network, the utilization rate of new energy can be maximized on the basis of ensuring stable operation of the power grid, and unnecessary energy loss is reduced; through combination of quantum calculation and deep learning, the method can enable the power distribution network to automatically optimize the reconstruction strategy when facing new energy access and load change, and improves the adaptability and intelligent management level of the power distribution network.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid optimization, and in particular relates to a quantum deep Q learning reconstruction method and system for accessing a new energy distribution network. Background Art

[0002] In the field of distribution network management and optimization, traditional optimization methods usually rely on accurate mathematical models to describe the operating status of the distribution network and the access of renewable energy. This approach may be effective when dealing with simple or static systems, but when faced with actual distribution networks, especially considering the dynamics and uncertainty of renewable energy access, it becomes extremely difficult or even impossible to build an accurate and comprehensive model. This is because the power generation of renewable energy is affected by a variety of unpredictable factors, such as the direct impact of weather conditions on solar and wind energy, which makes the operating environment of the distribution network highly nonlinear and dynamic, which is difficult to accurately capture through traditional static models.

[0003] In addition, even if a relatively accurate model can be established, traditional optimization algorithms face problems such as large amount of calculation and slow solution speed when solving such complex problems, and it is difficult to meet the needs of real-time or near real-time optimization. This not only affects the operating efficiency of the distribution network, but also limits the flexibility and efficiency of new energy access, thus hindering the wider application of renewable energy in the power grid.

[0004] Correspondingly, reinforcement learning, as a model-free method, provides a new solution. It does not require the establishment of an accurate mathematical model of the distribution network in advance, but automatically discovers the optimal strategy through interactive learning with the environment. This method is particularly suitable for dealing with complex and dynamically changing systems such as distribution networks. Reinforcement learning can learn directly from the operating data of the distribution network and adaptively adjust the strategy to cope with the changes brought about by the access of new energy, thereby achieving more efficient and flexible distribution network optimization and management.

[0005] However, despite the advantages of reinforcement learning, when faced with practical applications, especially as quantum computing continues to mature, how to effectively use quantum computing to accelerate the learning process of reinforcement learning and improve learning efficiency and strategy quality has become a problem worth exploring. Quantum deep Q learning, as an emerging technology that combines the advantages of quantum computing and deep learning, provides a possible solution to the computational bottleneck of traditional reinforcement learning when dealing with high-dimensional and complex systems. By leveraging the parallelism and efficiency of quantum computing, quantum deep Q learning can maintain or even enhance the quality of learning strategies while increasing computing speed, which is of great significance for achieving efficient and intelligent distribution network management.

[0006] Through the above analysis, the problems and defects of the existing technology are as follows: Traditional optimization methods face challenges such as large amount of calculation and slow solution speed, which are difficult to meet the needs of real-time optimization. These limit the flexibility and efficiency of new energy access and hinder the widespread application of renewable energy in the power grid. Although reinforcement learning provides a model-free solution, its network structure is usually large and requires large storage memory, which puts higher requirements on computing devices in actual complex scenarios. Summary of the invention

[0007] In view of the problems existing in the prior art, the present invention provides a quantum deep Q learning reconstruction method and system for the access of new energy to the distribution network, aiming to realize the optimization reconstruction strategy for the access of new energy to the distribution network through quantum deep Q learning (QDQL) technology. In the context of large-scale access of new energy, the distribution network is facing major changes in structure and operation mode. The present invention constructs an advanced learning model to quickly and effectively optimize the structure of the distribution network, reduce power loss, and improve the overall efficiency of the system.

[0008] The present invention is implemented as follows: a quantum deep Q learning reconstruction method for renewable energy access to a distribution network, comprising:

[0009] S1: Construct a distribution network model based on neural network;

[0010] S2: Construct a quantum deep Q-learning reconstruction method;

[0011] S3: Training quantum deep Q-learning.

[0012] Furthermore, S1 specifically includes: constructing a mathematical model of a distribution network, which includes a detailed description of distribution network nodes, section switches, tie switches and new energy access points, mainly including node power balance constraints:

[0013]

[0014] Among them, n represents the total number of nodes in the distribution network system, P gen,i is the power generated by the generator at the i-th node, and is 0 if there is no generator at the node; P load,i is the load power at the i-th node; P renew_energy,i is the power generation of renewable energy at the i-th node; P loss,lines Expressed as the power loss on different transmission lines.

[0015] Furthermore, S1 also includes:

[0016] Voltage Constraints:

[0017] V i,min ≤V i |≤V i,max

[0018] Among them, V i,min and V i,max Represent the minimum and maximum voltage limits of node i, V i It is represented as the voltage at node i.

[0019] Current Constraint:

[0020] |I ij |≤I ij,max

[0021] Among them, I ij,max Indicates the maximum current carrying capacity of the line between nodes i and j.

[0022] Ohm's law constraints:

[0023] ΔV ij =I ij ·Z ij

[0024]

[0025] Among them, I ij is the current in the line between nodes i and j, Z ij is the impedance of the line between nodes i and j, R ij is the resistance of the line between nodes i and j, ΔV ij is the voltage drop of the line between nodes i and j, P loss,ij is the power loss in the line between nodes i and j.

[0026] Power generation constraints:

[0027] P renew_energy,min,i ≤P renew_energy,i ≤P renew_energy,max,i

[0028] P gen,min,i ≤P gen,i ≤P gen,max,i

[0029] Among them, P renew_energy,min,i and P renew_energy,max,i Respectively represent the minimum and maximum power generation limits of the i-th renewable energy power generation unit; P gen,min,i and P gen,max,i Represent the minimum and maximum power generation limits of the i-th traditional power generation unit respectively;

[0030] Integrating the above constraints into the optimal power flow problem, the overall mathematical model includes the objective function, power balance constraints, voltage constraints, current constraints, power generation constraints and Ohm's law constraints. The objective function is the total power loss:

[0031] Minimize∑P loss,lines

[0032] Based on the model established above, data of different switch actions under different loads are collected to construct the optimal power flow data set of the model.

[0033] Furthermore, a fully connected neural network is constructed to learn the dataset. The training process can be completed by minimizing the difference between the predicted output and the actual distribution network state:

[0034] L=∑(P pred -∑P loss,lines ) 2

[0035] Among them, L is the loss function, P pred is the sum of the power loss in the distribution network predicted by the neural network (i.e., the objective function of the model just constructed).

[0036] Furthermore, S2 specifically includes: after the distribution network model learning is completed, the neural network model can be used as quantum deep Q learning. Next, the encoder is used to encode the state of the distribution network, so as to compress and encode the state information of the environment output into a data size acceptable to quantum bits; the encoded state is then input into the PQC, and the PQC processes these quantum states and outputs the quantum measurement results of the action value; the output of the quantum deep Q learning model, that is, the switching operation strategy of the distribution network, is then decoded through a traditional neural network and mapped to the specific distribution network switching action.

[0037] Further, S3 specifically includes: After completing the encoding of the distribution network state and establishing the parameterized quantum circuit, the next step is to use the quantum deep Q learning framework to train the model. The training process includes the following key parts:

[0038] (1) Initialization parameters: Initialize the parameters θ in PQC, as well as the weights and biases of the encoder and decoder networks;

[0039] (2) Environmental interaction: Encode the current distribution network state S as S encoded , PQC according to S encoded The quantum measurement result of the output action value is then converted by the decoder into a specific switch operation A action , execute A action After that, the environment returns the new state S' and reward R, and the array of interactions (S, A action ,R,S') are stored in the replay pool;

[0040] (3) Update and optimization: Based on the data in the replay pool, the mean square error loss function is used to measure the difference between the predicted Q value and the target Q value, and the time difference method is used to calculate the loss function.

[0041] Another object of the present invention is to provide a quantum deep Q learning reconstruction system for renewable energy access distribution network that implements the quantum deep Q learning reconstruction method for renewable energy access distribution network, including:

[0042] Distribution network model building module: used to build a distribution network model based on neural network;

[0043] Quantum deep Q learning reconstruction method building module: used to build quantum deep Q learning reconstruction method;

[0044] Quantum Deep Q Learning Training Module: used to train quantum deep Q learning.

[0045] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the quantum deep Q learning reconstruction method for the access of new energy to the distribution network.

[0046] Another object of the present invention is to provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the quantum deep Q learning reconstruction method for the access of new energy to the distribution network.

[0047] Another object of the present invention is to provide an information data processing terminal, which is used to implement the quantum deep Q learning reconstruction system for new energy access to the distribution network.

[0048] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0049] First, in view of the technical problems existing in the above-mentioned prior art, some creative technical effects are brought about after solving the problems. The specific description is as follows:

[0050] 1. By accurately controlling the switch operation in the distribution network, the present invention can maximize the utilization rate of new energy and reduce unnecessary energy loss on the basis of ensuring the stable operation of the power grid;

[0051] 2. By combining quantum computing and deep learning, the present invention enables the distribution network to automatically optimize the reconstruction strategy when facing the access of new energy sources and load changes, thereby enhancing the adaptability and intelligent management level of the distribution network;

[0052] 3. Taking into account the characteristics of current quantum computers as noisy intermediate-scale quantum (NISQ) devices, the present invention ensures the application of quantum computing in distribution network management through efficient encoding and decoding strategies even when the number of quantum bits is limited, providing a new way for the application of quantum technology in actual power grid systems.

[0053] Second, the present invention proposes an innovative solution combining quantum computing and deep learning technology, which is specially designed for the access of new energy to the distribution network, aiming to improve the operating efficiency and intelligent management level of the distribution network. Through the carefully designed quantum deep Q learning (QDQL) framework, the present invention can efficiently optimize and reconstruct the distribution network. The specific technical effects and advantages are summarized as follows:

[0054] Efficient energy utilization and reduced losses: This technical solution can accurately control the switch operation in the distribution network and optimize the access and utilization of new energy sources such as solar energy and wind energy. Through intelligent management, the utilization rate of new energy can be maximized, while reducing energy losses during transmission and conversion, achieving a more environmentally friendly and economical grid operation mode.

[0055] Adaptive optimization reconstruction strategy: Combining the efficient processing power of quantum computing with the intelligent decision-making ability of deep learning, the present invention can respond to changes in the state of the distribution network in real time and automatically optimize and adjust the reconstruction strategy. This not only enhances the adaptability of the distribution network to the access of new energy sources and load fluctuations, but also improves the stability and reliability of the power grid.

[0056] Breaking through the application limitations of quantum computing: Taking into account the physical limitations and noise characteristics of current quantum computers, this invention overcomes the challenge of the limited number of qubits by designing efficient state encoding and decoding strategies. This makes it possible to apply quantum deep Q learning in distribution network management even under the current quantum computing technology conditions, demonstrating the potential for widespread application of quantum technology in the energy field.

[0057] Improve the level of intelligent management of power grids: By realizing intelligent optimization and management of distribution networks, the present invention provides powerful technical support for power grid operation and maintenance. This includes but is not limited to real-time monitoring of power grid status, prediction and response to load changes, automatic adjustment of power grid structure, etc., thereby improving the operation efficiency and service quality of the power grid.

[0058] Promote the integration of new energy and traditional energy: This invention not only optimizes the access and utilization of new energy, but also takes into account the coordination with traditional energy generation methods, and ensures the efficient operation of the power grid and the stability of energy supply through intelligent strategy adjustment. This provides important technical support for achieving the green transformation of energy structure and sustainable development goals.

[0059] Through its innovative technical solution, the present invention not only ensures the stable operation of the power grid, but also improves the utilization rate of new energy and the intelligent management level of the power grid, demonstrates the prospect of the application of quantum computing technology in the energy field, and provides new ideas and technical paths for the development of future power grids.

[0060] Third, the expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0061] This invention provides an optimized reconstruction solution for the access of new energy to the distribution network by efficiently integrating quantum computing and deep learning technologies. This not only improves the energy efficiency and operating efficiency of the distribution network, but also significantly reduces energy loss, thereby reducing operating costs. From a commercial perspective, this optimization can promote the widespread use of new energy and support the development of the green energy industry, and has huge market potential and commercial value. In addition, with the advancement of quantum technology, this invention is also expected to lead a new round of technological innovation and industrial upgrading, creating new growth points for enterprises and investors.

[0062] The technical solution of the present invention fills the technical gap in the industry at home and abroad: combining quantum computing with deep learning, the optimization and reconstruction of the access of new energy to the distribution network is a new field. At present, the application of quantum computing in energy management and optimization is still in its infancy. The present invention not only realizes the specific application of this concept, but also successfully demonstrates the application potential of quantum technology in actual energy systems, filling the technical gap in this field at home and abroad.

[0063] The technical solution of the present invention solves a technical problem that people have always been eager to solve but have never succeeded in solving: efficient access to new energy and intelligent optimization management of distribution networks have always been technical problems that the energy field seeks to solve. Especially in the context of large-scale access to new energy, how to efficiently and stably integrate these energy sources has become a challenge. The present invention provides an effective solution that not only improves the utilization rate of new energy, but also ensures the stability and reliability of the power grid, solving long-standing technical problems.

[0064] The technical solution of the present invention overcomes technical prejudice: before quantum computing is applied to actual industrial and energy management fields, there is a view that quantum computing technology is not yet mature and difficult to be applied to the optimization and management of complex systems in the short term. The present invention successfully applies quantum deep Q learning to the optimization and reconstruction of distribution networks by designing efficient encoding and decoding strategies, which not only proves the feasibility of applying quantum technology in the energy field, but also overcomes the technical prejudice about the scope of application of quantum computing, and opens up a new path for the application of quantum technology in the industrial and energy fields.

[0065] Fourth, the quantum deep Q learning reconstruction method for the access of new energy to the distribution network proposed in the present invention has made significant technical progress in solving the problems of the prior art. The following are the technical problems solved by the invention and the significant technical progress achieved in industrial applications:

[0066] Technical issues solved:

[0067] 1. Dealing with the complexity of distribution network model: Traditional distribution network management often relies on simple mathematical models and rules, which makes it difficult to deal with the complexity and uncertainty brought by the access of new energy. This invention can more accurately describe the dynamic characteristics of the distribution network and the impact of the access of new energy by constructing a distribution network model based on a neural network.

[0068] 2. Optimization of high-dimensional state space: With the expansion of the distribution network and the increase of new energy access points, the dimension of the state space has increased dramatically, which is difficult to handle with traditional optimization methods. This invention uses the parallelism and exponential state space processing capabilities of quantum computing to achieve optimization of high-dimensional state space through quantum deep Q learning.

[0069] 3. Real-time decision-making and adaptive adjustment: After the new energy is connected to the distribution network, the switch operation needs to be adjusted in real time to optimize the operation of the distribution network. The present invention realizes the real-time perception of the distribution network status and the adaptive adjustment of the switch operation strategy through quantum deep Q learning.

[0070] Significant technological advances in industrial applications:

[0071] 1. Improve energy utilization efficiency: By precisely controlling the switching operation of the distribution network, optimize the access and utilization of new energy, reduce energy loss, and improve energy utilization efficiency.

[0072] 2. Enhance the stability of the distribution network: The present invention can sense the state of the distribution network in real time and adjust the switch operation according to the state, thereby effectively avoiding problems such as overload and voltage fluctuation, and enhancing the stability of the distribution network.

[0073] 3. Reduce operation and maintenance costs: Through automated and intelligent distribution network management, reduce manual intervention and operation and maintenance costs, and improve the operating efficiency and economy of the distribution network.

[0074] 4. Promote the application of quantum computing in the industrial field: This invention combines quantum computing with distribution network management, provides new ideas and directions for the application of quantum computing in the industrial field, and promotes the practical application and industrialization of quantum computing technology.

[0075] The present invention achieves optimized management of the access of new energy to the distribution network by constructing a distribution network model based on a neural network and combining it with a quantum deep Q learning reconstruction method, solves the problems existing in the prior art, and achieves significant technological progress in industrial applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0077] Figure 1 It is a schematic diagram of a quantum deep Q learning reconstruction method for accessing a new energy distribution network provided by an embodiment of the present invention;

[0078] Figure 2 is a diagram of a quantum deep Q learning structure provided by an embodiment of the present invention;

[0079] Figure 3 This is a structure diagram of a quantum deep Q learning reconstruction system for accessing a new energy distribution network provided by an embodiment of the present invention;

[0080] Figure 4 is a schematic diagram of the IEEE 33-node power distribution network structure provided by an embodiment of the present invention;

[0081] Figure 5 It is a schematic diagram of the training effects of traditional neural networks and quantum deep Q learning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0083] In view of the problems existing in the prior art, the present invention provides a quantum deep Q learning reconstruction method and system for the access of new energy to the distribution network. The present invention is described in detail below with reference to the accompanying drawings.

[0084] like Figure 1 As shown, the quantum deep Q learning reconstruction method for accessing a new energy distribution network provided by an embodiment of the present invention includes:

[0085] S1: Construct a distribution network model based on neural network;

[0086] S2: Construct a quantum deep Q-learning reconstruction method;

[0087] S3: Training quantum deep Q-learning.

[0088] S1 specifically includes: constructing a mathematical model of a distribution network, which includes a detailed description of distribution network nodes, section switches, tie switches and new energy access points, mainly including node power balance constraints:

[0089]

[0090] Among them, n represents the total number of nodes in the distribution network system, P gen,i is the power generated by the generator at the i-th node, and is 0 if there is no generator at the node; P load,i is the load power at the i-th node; P renew_energy,i is the power generation of renewable energy at the i-th node; P loss,lines is the power loss on different transmission lines.

[0091] S1 also includes:

[0092] Voltage Constraints:

[0093] V i,min ≤|V i |≤V i,max

[0094] Among them, V i,min and V i,max Represent the minimum and maximum voltage limits of node i respectively.

[0095] Current Constraint:

[0096] |I ij |≤I ij,max

[0097] Among them, I ij,max Indicates the maximum current carrying capacity of the line.

[0098] Ohm's law constraints:

[0099] ΔV ij =I ij ·Z ij

[0100]

[0101] Among them, I ij is the current in the line between nodes i and j, Z ij is the impedance of the line between nodes i and j, R ij is the resistance of the line between nodes i and j, ΔV ij is the voltage drop of the line between nodes i and j, P loss,ij is the power loss in the line between nodes i and j.

[0102] Power generation constraints:

[0103] P renew_energy,min,i ≤P renew_energy,i ≤P renew_energy,max,i

[0104] P gen,min,i ≤P gen,i ≤P gen,max,i

[0105] Among them, P renew_energy,min,i and P renew_energy,max,i Respectively represent the minimum and maximum power generation limits of the i-th renewable energy power generation unit; P gen,min,i and P gen,max,i Represent the minimum and maximum power generation limits of the i-th traditional power generation unit respectively;

[0106] Integrating the above constraints into the optimal power flow problem, the overall mathematical model includes the objective function, power balance constraints, voltage constraints, current constraints, power generation constraints and Ohm's law constraints. The objective function is the total power loss:

[0107] Minimize∑P loss,lines

[0108] Based on the model established above, data of different switch actions under different loads are collected to construct the optimal power flow data set of the model.

[0109] A fully connected neural network is constructed to learn the dataset. The training process can be completed by minimizing the difference between the predicted output and the actual distribution network state:

[0110] L=∑(P pred -∑P loss,lines ) 2

[0111] Among them, L is the loss function, P pred is the sum of the power loss in the distribution network predicted by the neural network (i.e., the objective function of the model just constructed).

[0112] S2 specifically includes: after the distribution network model is learned, the neural network model can be used as quantum deep Q learning. Next, the encoder is used to encode the state of the distribution network, so as to compress and encode the state information of the environment output into a data size acceptable to quantum bits; the encoded state is then input into the PQC, which processes these quantum states and outputs the quantum measurement results of the action value; the output of the quantum deep Q learning model, that is, the switching operation strategy of the distribution network, is then decoded through a traditional neural network and mapped to the specific switching action of the distribution network.

[0113] S3 specifically includes: After completing the encoding of the distribution network state and establishing the parameterized quantum circuit, the next step is to use the quantum deep Q learning framework to train the model. The training process includes the following key parts:

[0114] (1) Initialization parameters: Initialize the parameters θ in PQC, as well as the weights and biases of the encoder and decoder networks;

[0115] (2) Environmental interaction: Encode the current distribution network state S as S encoded , PQC according to S encoded The quantum measurement result of the output action value is then converted by the decoder into a specific switch operation A action , execute A action After that, the environment returns the new state S' and reward R, and the array of interactions (S, A action ,R,S') are stored in the replay pool;

[0116] (3) Update and optimization: Based on the data in the replay pool, the mean square error loss function is used to measure the difference between the predicted Q value and the target Q value, and the time difference method is used to calculate the loss function.

[0117] like Figure 3 As shown, the quantum deep Q learning reconstruction system for accessing a new energy distribution network provided by an embodiment of the present invention includes:

[0118] Distribution network model building module: used to build a distribution network model based on neural network;

[0119] Quantum deep Q learning reconstruction method building module: used to build quantum deep Q learning reconstruction method;

[0120] Quantum Deep Q Learning Training Module: used to train quantum deep Q learning.

[0121] An application embodiment of the present invention provides a computer device, which includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of a quantum deep Q learning reconstruction method for accessing new energy to a distribution network.

[0122] An application embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of a quantum deep Q learning reconstruction method for accessing new energy to a distribution network.

[0123] An application embodiment of the present invention provides an information data processing terminal, which is used to implement a quantum deep Q learning reconstruction system for new energy access to a distribution network.

[0124] 2. Application Examples: In order to prove the creativity and technical value of the technical solution of the present invention, this section provides application examples of the technical solution of the claims on specific products or related technologies.

[0125] In order to fully verify the creativity and technical value of the technical solution of the present invention, the present invention takes the IEEE 33-node power distribution network as an example to demonstrate the application and implementation of the technology in specific products and technologies. Figure 4 As shown, the IEEE 33-node distribution network includes three generators and a photovoltaic power station. The maximum power generation of each generator is 0.7 megawatts (MW), and the maximum power generation of the photovoltaic power station is 0.2 megawatts (MW). In this network framework, the present invention designs the quantum deep Q learning (QDQL) network into 4 qubits, and the output side is equipped with a 4*52 action decoder. The decoder is responsible for converting the output of the quantum deep Q learning network into a specific distribution network switch operation strategy.

[0126] The input data of this embodiment is the total load demand power and total power generation of the distribution network, which is used as a quantitative representation of the network state. The quantum deep Q learning network uses this input information to optimize the structural reconstruction of the distribution network and minimize losses through the parallel processing of quantum computing and the pattern recognition ability of deep learning.

[0127] The implementation of the present invention adopts an efficient coding strategy to handle the quantitative representation of the distribution network state to adapt to the reality of limited number of qubits. This strategy covers the key parameters of the power grid state, such as node voltage, line current, etc., so that even with limited qubits, the real-time state of the power grid can be accurately reflected.

[0128] The use of a 4-qubit quantum deep Q learning network can ensure that the algorithm runs under limited quantum resources while maintaining algorithm performance and computational efficiency. The 4*52 action decoder on the output side maps the output of the quantum deep Q learning network to 52 specific possible distribution network switch actions, thereby providing decision support for the optimized operation of the distribution network.

[0129] Through the application of this embodiment, the present invention has proved its effectiveness in the actual power grid system, including improving the energy utilization efficiency of the power grid, optimizing the power grid operation structure, and realizing intelligent management. The present invention creatively integrates quantum computing and deep learning technology into the existing distribution network technology, provides an innovative optimization strategy for the access of new energy to the distribution network, and fully demonstrates its feasibility and technical value of commercial application.

[0130] The embodiments of the present invention have achieved remarkable positive results during the development and testing process, especially in the task of optimizing and reconfiguring the distribution network. Figure 5As shown in the figure, by comparing the training effects of traditional neural networks and quantum deep Q learning (QDQL), the following conclusions were drawn:

[0131] In the traditional neural network, when the number of neurons in the hidden layer is set to 4 and 9, the performance of the system is reflected in the red and blue lines in the figure respectively. Figure 5 It can be seen that quantum deep Q learning shows better performance and faster convergence speed throughout the training process, and its robustness and optimization effect are better than traditional neural networks. In the final test, the optimal action selection rate of quantum deep Q learning reached 100%, significantly higher than the 55.21% and 71.88% of traditional neural networks. This comparison not only highlights the significant advantages of quantum deep Q learning in action decision-making accuracy, but also verifies its practical application value in power grid optimization.

[0132] These test results prove that the present invention has a significant performance improvement in the optimization and reconstruction of distribution networks compared to the prior art. It not only improves the operating efficiency of the power grid, but also enhances the management capabilities of new energy access. Through the combined use of quantum computing and deep learning, the embodiments of the present invention overcome the limitations of traditional algorithms in dealing with complex power grid structures and dynamic changes, and provide strong technical support for the intelligent management and sustainable development of distribution networks.

[0133] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. A person of ordinary skill in the art will appreciate that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0134] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A quantum deep Q learning reconstruction method for renewable energy access to distribution networks, characterized in that: include: S1: Construct a distribution network model based on neural network; S2: Construct a quantum deep Q-learning reconstruction method; S3: Training quantum deep Q-learning.

2. The quantum deep Q learning reconstruction method for accessing new energy to the distribution network as claimed in claim 1 is characterized in that: S1 specifically includes: constructing a mathematical model of a distribution network, which includes a detailed description of distribution network nodes, section switches, tie switches and new energy access points, mainly including node power balance constraints: Among them, n represents the total number of nodes in the distribution network system, P gen,i is the power generated by the generator at the i-th node, and is 0 if there is no generator at the node; P load,i is the load power at the i-th node; P renew_energy,i is the power generation of renewable energy at the i-th node; P loss,lines is the power loss on different transmission lines.

3. The quantum deep Q learning reconstruction method for accessing new energy to the distribution network as claimed in claim 1 is characterized in that: S1 also includes: Voltage Constraints: V i,min ≤|V i |≤V i,max Among them, V i,min and V i,max Represent the minimum and maximum voltage limits of node i respectively. Current Constraint: I ij |≤I ij,max Among them, I ij,max Indicates the maximum current carrying capacity of the line. Ohm's law constraints: ΔV ij =I ij ·Z ij Among them, I ij is the current in the line between nodes i and j, Z ij is the impedance of the line between nodes i and j, R ij is the resistance of the line between nodes i and j, ΔV ij is the voltage drop of the line between nodes i and j, P loss,ij is the power loss in the line between nodes i and j. Power generation constraints: P renew_energy,min,i ≤P renew_energy,i ≤P renew_energy,max,i P gen,min,i ≤P gen,i ≤P gen,max,i Among them, P renew_energy,min,i and P renew_energy,max,i Respectively represent the minimum and maximum power generation limits of the i-th renewable energy power generation unit; P gen,min,i and P gen,max,i Represent the minimum and maximum power generation limits of the i-th traditional power generation unit respectively; Integrating the above constraints into the optimal power flow problem, the overall mathematical model includes the objective function, power balance constraints, voltage constraints, current constraints, power generation constraints and Ohm's law constraints. The objective function is the total power loss: MinimizeΣP loss,lines Based on the model established above, data of different switch actions under different loads are collected to construct the optimal power flow data set of the model.

4. The quantum deep Q learning reconstruction method for accessing new energy to the distribution network as claimed in claim 1 is characterized in that: A fully connected neural network is constructed to learn the dataset. The training process can be completed by minimizing the difference between the predicted output and the actual distribution network state: L=∑(P pred -∑P loss,lines ) 2 Among them, L is the loss function, P pred It is the sum of the power loss in the distribution network predicted by the neural network.

5. The quantum deep Q learning reconstruction method for accessing new energy to the distribution network as claimed in claim 1 is characterized in that: S2 specifically includes: after the distribution network model is learned, the neural network model can be used as quantum deep Q learning. Next, the encoder is used to encode the state of the distribution network, so as to compress and encode the state information of the environment output into a data size acceptable to quantum bits; the encoded state is then input into the PQC, which processes these quantum states and outputs the quantum measurement results of the action value; the output of the quantum deep Q learning model, that is, the switching operation strategy of the distribution network, is then decoded through a traditional neural network and mapped to the specific distribution network switching action.

6. The quantum deep Q learning reconstruction method for accessing new energy to the distribution network as claimed in claim 1 is characterized in that: S3 specifically includes: After completing the encoding of the distribution network state and establishing the parameterized quantum circuit, the next step is to use the quantum deep Q learning framework to train the model. The training process includes the following key parts: (1) Initialization parameters: Initialize the parameters θ in PQC, as well as the weights and biases of the encoder and decoder networks; (2) Environmental interaction: Encode the current distribution network state S as S encoded , PQC according to S encoded The quantum measurement result of the output action value is then converted by the decoder into a specific switch operation A action , execute A action After that, the environment returns the new state S' and reward R, and the array of interactions (S, A action ,R,S') are stored in the replay pool; (3) Update and optimization: Based on the data in the replay pool, the mean square error loss function is used to measure the difference between the predicted Q value and the target Q value, and the time difference method is used to calculate the loss function.

7. A quantum deep Q learning reconstruction system for a new energy access distribution network that implements the quantum deep Q learning reconstruction method for a new energy access distribution network as described in any one of claims 1 to 6, characterized in that: include: Distribution network model building module: used to build a distribution network model based on neural network; Quantum deep Q learning reconstruction method building module: used to build quantum deep Q learning reconstruction method; Quantum Deep Q Learning Training Module: used to train quantum deep Q learning.

8. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the quantum deep Q learning reconstruction method for the access of new energy to the distribution network as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the quantum deep Q learning reconstruction method for the access of new energy to the distribution network as described in any one of claims 1 to 6.

10. An information data processing terminal, which is used to implement the quantum deep Q learning reconstruction system for new energy access to the distribution network as described in claim 7.

Images