A port energy dynamic optimization method and system based on digital twin

Abstract

This paper proposes a method and system for dynamic port energy optimization based on digital twins, relating to the technical field of port energy optimization. This method achieves full-link closed-loop control of port energy data by constructing a three-layer digital twin architecture: physical-edge-virtual. Through real-time data synchronization and multi-timescale optimization strategies, it improves renewable energy utilization and reduces carbon emissions. The combination of edge-layer preprocessing and virtual-layer physical constraint models addresses the disconnect between dynamic response delays and physical laws in traditional methods.

Description

Technical Field

[0001] The present invention relates to the technical field of port energy optimization, and in particular to a port energy dynamic optimization method and system based on digital twins. Background Art

[0002] The global maritime industry, as a core carrier of international trade, carries the brunt of global trade, yet its energy system is highly reliant on fossil fuels. Ports, as critical logistics nodes, face highly dynamic energy demand and require the coordination of multiple clean energy sources, including wind, solar, and hydrogen. Traditional energy management approaches suffer from significant flaws: First, static models are disconnected from dynamic demand: Existing systems rely on offline optimization and fixed models, making it difficult to respond in real time to fluctuations in renewable energy and sudden load changes caused by ship operations, resulting in energy waste. Second, carbon tracking mechanisms are lacking: Traditional approaches lack granular monitoring of carbon emissions and are unable to link ship operations, energy procurement, and carbon quotas. Third, multi-timescale control is disconnected: Millisecond-level power regulation (such as crane start-up and shutdown) and hourly energy scheduling (such as hydrogen storage) lack coordination, leading to grid frequency instability and reduced energy storage lifespan. Fourth, data heterogeneity hinders optimization: Data formats and sampling rates vary significantly across port energy devices (shore power, energy storage, and photovoltaics), and insufficient edge computing capabilities result in low cloud-based model prediction accuracy.

[0003] Although digital twin technology has been applied in the industrial field, it has not yet solved core problems such as multi-energy flow coupling optimization, real-time tracking of carbon flow, and cross-level control synchronization in port scenarios. Summary of the Invention

[0004] In response to the above-mentioned problems existing in the prior art, the first aspect of the present invention proposes a port energy dynamic optimization method based on digital twins, comprising:

[0005] Step S1: construct a multi-level digital twin model of the port energy system, which includes a physical layer, an edge layer, and a virtual layer;

[0006] Step S2: collecting real-time operating data of the port energy equipment through the sensor network in the physical layer, pre-processing the real-time operating data in the edge layer to generate a compressed dynamic data stream, and synchronizing the dynamic data stream to the virtual layer;

[0007] Step S3: In the virtual layer, a physical information neural network is trained based on dynamic data flows and preset physical constraint equations to generate a multi-energy flow prediction model. In combination with real-time carbon signal data, a quantum-inspired optimization algorithm is used to generate a multi-timescale energy scheduling strategy.

[0008] Step S4: Decompose the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmit them back to the energy router of the physical layer through the edge layer;

[0009] Step S5: The energy router executes the dynamic adjustment instruction to adjust the operating parameters of the port energy equipment, and allocates renewable energy and energy storage resources based on the periodic scheduling instruction.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, in step S3, the specific steps of training the physical information neural network include:

[0011] Step S31, extracting energy equipment state parameters from the dynamic data stream as input;

[0012] Step S32: converting the thermodynamic partial differential equations and the power network conservation equations in the physical constraint equations into residual terms, and performing weighted fusion with the output of the physical information neural network to generate a constrained optimization target;

[0013] Step S33: updating the weight parameters of the physical information neural network through the distributed nodes in the joint learning algorithm to minimize the constrained optimization target and generate a multi-energy flow prediction model.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, in step S3, the specific steps of generating the energy scheduling strategy include:

[0015] Step S34, inputting the energy demand forecast data and real-time carbon signal data output by the multi-energy flow forecasting model into the quantum-inspired optimization algorithm;

[0016] Step S35, decomposing the energy scheduling problem into discrete variable optimization subproblems and continuous variable optimization subproblems through a hybrid computing unit in a quantum-inspired optimization algorithm;

[0017] Step S36, using a quantum annealing algorithm to generate discrete decision parameters for the discrete variable optimization subproblem, and using a gradient descent algorithm to generate continuous decision parameters for the continuous variable optimization subproblem;

[0018] Step S37: Combine the discrete decision parameters and the continuous decision parameters to generate a multi-time-scale energy scheduling strategy.

[0019] In combination with the first aspect, in some implementations of the first aspect, the discrete variable optimization sub-problem includes the start and stop status of the energy storage device and the switching instructions of the energy router, and the continuous variable optimization sub-problem includes the energy storage charging and discharging rate and the energy purchase amount.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, step S4 includes:

[0021] Step S41, extracting voltage-frequency deviation and instantaneous power variation from the energy dispatch strategy and generating a dynamic adjustment instruction;

[0022] Step S42: extracting the carbon quota allocation plan and energy procurement plan from the energy scheduling strategy and generating a periodic scheduling instruction;

[0023] Step S43 , aligning the time bases of the dynamic adjustment instruction and the periodic scheduling instruction through the timestamp synchronization module, generating a time-consistent scheduling instruction set, and transmitting it back to the energy router of the physical layer through the edge layer.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, step S5 includes:

[0025] Step S51: Input the dynamic adjustment instruction into the power electronic interface of the energy router to generate a voltage regulation signal and an energy storage charge and discharge control signal;

[0026] Step S52: Input the periodic scheduling instructions into the blockchain verification module of the energy router to generate energy transaction records and carbon emission audit data;

[0027] In step S53, the energy transaction records are compared with the carbon emission audit data through the smart contract to generate energy allocation instructions, and renewable energy and energy storage resources are allocated based on the energy allocation instructions.

[0028] In combination with the first aspect, in some implementations of the first aspect, the blockchain verification module connects the port's internal energy ledger and the external carbon trading platform through a cross-chain protocol, and synchronizes energy trading records and carbon emission audit data to the external carbon trading platform.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, in step S2, the preprocessing includes:

[0030] Step S21, filtering the real-time operation data through the abnormality detection unit to generate a filtered data sequence;

[0031] Step S22: Synchronize the filtered data sequence with a preset clock source through a timestamp alignment module to generate a time-uniformed data stream;

[0032] Step S23: Perform feature extraction and dimensionality reduction on the time-uniform data stream through a lightweight convolutional network to generate a compressed dynamic data stream.

[0033] In combination with the first aspect, in some implementations of the first aspect, the real-time carbon signal data includes power grid carbon intensity data and ship emission characteristic data. The power grid carbon intensity data is acquired in real time through an external energy database, and the ship emission characteristic data is generated through analysis of a ship automatic identification system.

[0034] In a second aspect, the present invention provides a port energy dynamic optimization system based on digital twins, the system adopting the method provided in any of the above embodiments, and the system comprising:

[0035] A modeling module for building a multi-level digital twin model of the port energy system, which includes the physical layer, edge layer, and virtual layer;

[0036] The data acquisition module is deployed at the physical layer and collects real-time operating data of port energy equipment through a sensor network;

[0037] The preprocessing module is deployed at the edge layer and is used to filter, align timestamps, and reduce the dimension of features of real-time running data, generate compressed dynamic data streams, and synchronize the dynamic data streams to the virtual layer;

[0038] The model training module is deployed in the virtual layer and is used to train the physical information neural network based on dynamic data flow and preset physical constraint equations to generate a multi-energy flow prediction model;

[0039] The strategy generation module is deployed in the virtual layer and is used to combine multiple energy flow prediction models and real-time carbon signal data to generate multi-timescale energy scheduling strategies through quantum-inspired optimization algorithms;

[0040] The instruction decomposition module is deployed at the edge layer and is used to decompose the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmit them back to the energy router at the physical layer;

[0041] The execution module, deployed on the energy router, is used to execute dynamic adjustment instructions to adjust the operating parameters of the port energy equipment and allocate renewable energy and energy storage resources based on periodic scheduling instructions.

[0042] In a third aspect, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method provided in any of the above embodiments.

[0043] In a fourth aspect, the present invention provides an electronic device, the electronic device comprising:

[0044] processor;

[0045] a memory for storing processor-executable instructions;

[0046] The processor is used to execute the method provided in any of the above embodiments.

[0047] Compared with the existing technology, the beneficial effects of the present invention are as follows: Step S1 constructs a physical-edge-virtual three-layer digital twin model to provide a unified mapping framework for real-time data streams (such as millisecond-level voltage transients and hour-level energy storage temperature), breaking the limitations of isolated modeling of traditional subsystems; Step S2 completes data filtering, timestamp alignment and lightweight compression at the edge layer, which not only reduces transmission delay but also retains key dynamic features (such as crane motor harmonics) to provide high-quality input for the virtual layer; Step S3 embeds physical laws such as thermodynamic partial differential equations into model training through physical information neural network (PINN) Practice, constrain the rationality of data-driven prediction, and combine the quantum-inspired optimization algorithm to simultaneously solve millisecond-level frequency regulation and daily carbon quota allocation, avoiding policy conflicts caused by hierarchical optimization; step S4 decomposes the strategy into dynamic adjustment instructions (voltage / power transient response) and periodic scheduling instructions (carbon quota, procurement plan), and realizes the "prediction-decision-execution" closed loop through edge layer reverse control; step S5 relies on the power electronic interface and blockchain module of the energy router to correct the frequency deviation at the millisecond level while allocating clean energy according to the periodic scheduling instructions, and verifies the consistency of carbon data based on smart contracts.

[0048] The synergistic effect of steps S1 to S5 has the following beneficial effects: First, a data-model closed loop is formed: edge layer preprocessing ensures the quality of virtual layer model input, and the model output strategy reversely controls the physical equipment through the edge layer to form a bidirectional optimization link; second, cross-time scale coupling is achieved: the quantum optimization algorithm integrates transient response and long-term planning, and the timestamp synchronization module ensures the consistency of instruction timing to avoid overcharging / discharging of energy storage; third, carbon-energy synergy is achieved: real-time carbon signals (grid strength, ship emissions) are dynamically weighted to optimize the target, so that energy distribution can meet both economic efficiency and compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 The figure shows a flow chart of a port energy dynamic optimization method based on digital twins provided in one embodiment of the present invention.

[0051] Figure 2 Shown is a flow chart of a port energy dynamic optimization method based on digital twins provided in another embodiment of the present invention.

[0052] Figure 3Shown is a structural schematic diagram of a port energy dynamic optimization system based on digital twins provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0053] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0054] The specific embodiments of the present invention are described below.

[0055] Example 1

[0056] like Figure 1 and Figure 2 As shown, the present invention proposes a port energy dynamic optimization method based on digital twin, including:

[0057] Step S1: construct a multi-level digital twin model of the port energy system, which includes a physical layer, an edge layer, and a virtual layer;

[0058] Step S2: collecting real-time operating data of the port energy equipment through the sensor network in the physical layer, pre-processing the real-time operating data in the edge layer to generate a compressed dynamic data stream, and synchronizing the dynamic data stream to the virtual layer;

[0059] Step S3: In the virtual layer, a physical information neural network is trained based on dynamic data flows and preset physical constraint equations to generate a multi-energy flow prediction model. In combination with real-time carbon signal data, a quantum-inspired optimization algorithm is used to generate a multi-timescale energy scheduling strategy.

[0060] Step S4: Decompose the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmit them back to the energy router of the physical layer through the edge layer;

[0061] Step S5: The energy router executes the dynamic adjustment instruction to adjust the operating parameters of the port energy equipment, and allocates renewable energy and energy storage resources based on the periodic scheduling instruction.

[0062] This method achieves dynamic port energy optimization by constructing a multi-layered digital twin model comprising physical, edge, and virtual layers. At the physical layer, a sensor network is deployed at key nodes of port energy equipment (such as shore power systems, photovoltaic arrays, and energy storage devices) to collect real-time operational data, including voltage, current, temperature, and device status signals. The edge layer, comprised of distributed computing nodes, receives the physical layer data and performs preprocessing operations. First, a filtering algorithm is used to remove noise interference (such as abnormal fluctuations caused by electromagnetic interference). Then, a timestamp alignment module is used to synchronize data streams with different sampling frequencies (millisecond-level power parameters and minute-level temperature data) to a unified clock source. Finally, a lightweight convolutional network is used to extract core features (such as voltage harmonics and energy storage charge and discharge curves). This generates a compressed dynamic data stream and uploads it to the virtual layer. The virtual layer, deployed in the cloud, receives the dynamic data stream and models multiple energy flows using a physical information neural network. This network embeds thermodynamic partial differential equations (describing heat diffusion in energy storage systems) and power network conservation equations (such as Kirchhoff's laws) as residual terms in the training process to ensure that predictions conform to physical laws.

[0063] Simultaneously, a quantum-inspired optimization algorithm, combined with real-time carbon signal data (grid carbon emission intensity and ship emission characteristics), generates multi-timescale scheduling strategies, spanning milliseconds to daily levels. These strategies are decomposed at the edge layer into dynamic adjustment instructions (such as voltage and frequency regulation signals) and periodic scheduling instructions (such as carbon quota allocation plans), which are then transmitted back to the energy router at the physical layer. The energy router executes the dynamic adjustment instructions (such as adjusting the inverter switching frequency) through the power electronics interface and allocates renewable energy and energy storage resources (such as prioritizing photovoltaic power) based on the periodic scheduling instructions, ultimately achieving dynamic optimization of the energy system.

[0064] This approach achieves full-link closed-loop control of port energy data by building a three-layer digital twin architecture: physical-edge-virtual. Through real-time data synchronization and multi-timescale optimization strategies, it improves renewable energy utilization and reduces carbon emissions. The combination of edge-layer preprocessing and virtual-layer physical constraint models addresses the disconnect between dynamic response delays and physical laws in traditional approaches.

[0065] In conjunction with the first aspect, in some implementations of the first aspect, in step S3, the specific steps of training the physical information neural network include:

[0066] Step S31, extracting energy equipment state parameters from the dynamic data stream as input;

[0067] Step S32: converting the thermodynamic partial differential equations and the power network conservation equations in the physical constraint equations into residual terms, and performing weighted fusion with the output of the physical information neural network to generate a constrained optimization target;

[0068] Step S33: updating the weight parameters of the physical information neural network through the distributed nodes in the joint learning algorithm to minimize the constrained optimization target and generate a multi-energy flow prediction model.

[0069] In some embodiments, the training process of the physical information neural network is as follows: first, energy device state parameters, including the state of charge of the energy storage system, the output power of the photovoltaic array, and the shore power load curve, are extracted from the dynamic data stream as network input. Subsequently, the physical constraint equations are converted into residual terms: for example, the partial differential equations describing battery thermal management (such as the Fourier heat conduction equation) are discretized into residual form and weighted fused with the neural network output (predicted temperature field) to form a constrained optimization objective function. The joint learning algorithm collaboratively updates the network weights through distributed nodes (such as edge computing units): each node calculates the gradient based on local data and aggregates it to the global model in the cloud through a secure aggregation protocol to ensure data privacy. During the training process, the constrained optimization objective function drives the network to simultaneously meet data fitting accuracy and physical laws. For example, when predicting the energy storage temperature, it is forced to meet energy conservation to avoid physical contradictions that may occur in pure data-driven models.

[0070] Alternatively, the residual term fusion can adopt an adaptive weighting strategy (such as dynamically adjusting the physical constraint weight according to the prediction error) instead of fixed-ratio weighting.

[0071] Physical information neural networks constrain the training process by using residual terms in physical equations to ensure that predictions meet both data fitting and thermodynamic / electrical laws, avoiding the physical contradictions of purely data-driven models. Distributed federated learning ensures data privacy and model generalization, improving prediction accuracy and supporting cross-port scenario migration.

[0072] In conjunction with the first aspect, in some implementations of the first aspect, in step S3, the specific steps of generating the energy scheduling strategy include:

[0073] Step S34, inputting the energy demand forecast data and real-time carbon signal data output by the multi-energy flow forecasting model into the quantum-inspired optimization algorithm;

[0074] Step S35, decomposing the energy scheduling problem into discrete variable optimization subproblems and continuous variable optimization subproblems through a hybrid computing unit in a quantum-inspired optimization algorithm;

[0075] Step S36, using a quantum annealing algorithm to generate discrete decision parameters for the discrete variable optimization subproblem, and using a gradient descent algorithm to generate continuous decision parameters for the continuous variable optimization subproblem;

[0076] Step S37: Combine the discrete decision parameters and the continuous decision parameters to generate a multi-time-scale energy scheduling strategy.

[0077] In some embodiments, the energy scheduling strategy generation process includes the following steps: Demand forecast data (e.g., photovoltaic power generation for the next 24 hours, ship berthing energy consumption) output by a multi-energy flow forecasting model and real-time carbon signal data (e.g., current grid carbon intensity, ship emission factors) are fed into a quantum-inspired optimization algorithm. This algorithm, using a hybrid computing unit, decomposes the problem into discrete variable optimization subproblems (e.g., energy storage start / stop status, energy router switching instructions) and continuous variable optimization subproblems (e.g., energy storage charge / discharge rate, hydrogen procurement volume). The discrete subproblems are solved using a quantum annealing algorithm: The problem is mapped to an Ising model, and a quantum annealer is used to search for the optimal solution, for example, determining the start / stop status of energy storage equipment during peak electricity price periods. The continuous subproblems are iteratively solved using a gradient descent algorithm: for example, optimizing the energy storage charge / discharge rate to minimize battery loss. Finally, the two parameter types are combined to generate a multi-timescale strategy consisting of millisecond-level regulation instructions (e.g., frequency deviation compensation) and daily procurement plans.

[0078] Alternatively, discrete variable optimization can use a genetic algorithm, and continuous variable optimization can use a sequential quadratic programming method.

[0079] The quantum-inspired optimization algorithm decomposes the complex scheduling problem into discrete and continuous subproblems, efficiently solving them using quantum annealing and gradient descent, respectively, to balance millisecond-level control with daily planning requirements. The discrete-continuous variable separation strategy reduces computational dimensionality.

[0080] In combination with the first aspect, in some implementations of the first aspect, the discrete variable optimization sub-problem includes the start and stop status of the energy storage device and the switching instructions of the energy router, and the continuous variable optimization sub-problem includes the energy storage charging and discharging rate and the energy purchase amount.

[0081] In some embodiments, the discrete variable optimization subproblem focuses on device state decisions: the start and stop states of energy storage devices must balance instantaneous power demand with device life (e.g., frequent starts and stops accelerate battery aging), and the switching instructions of energy routers must coordinate multiple energy flow paths (e.g., switching to hydrogen power during a typhoon). The continuous variable optimization subproblem involves refined control: the energy storage charge and discharge rates must match the fluctuations of renewable energy (e.g., rapidly increasing the discharge rate when photovoltaic power drops sharply), and the energy procurement volume must be combined with market prices and carbon quotas (e.g., increasing local hydrogen production when carbon prices are high). By separating discrete and continuous variables, the problem dimension is reduced and the solution efficiency is improved, for example, avoiding the computational complexity of mixed-integer nonlinear programming.

[0082] This method clarifies the optimization boundaries of discrete variables (equipment start and stop / switch instructions) and continuous variables (charge and discharge rates / purchase volume), avoiding strategy conflicts caused by mixed optimization.

[0083] In conjunction with the first aspect, in some implementations of the first aspect, step S4 includes:

[0084] Step S41, extracting voltage-frequency deviation and instantaneous power variation from the energy dispatch strategy and generating a dynamic adjustment instruction;

[0085] Step S42: extracting the carbon quota allocation plan and energy procurement plan from the energy scheduling strategy and generating a periodic scheduling instruction;

[0086] Step S43 , aligning the time bases of the dynamic adjustment instruction and the periodic scheduling instruction through the timestamp synchronization module, generating a time-consistent scheduling instruction set, and transmitting it back to the energy router of the physical layer through the edge layer.

[0087] In some embodiments, the energy scheduling strategy is decomposed and synchronized as follows: voltage and frequency deviations (e.g., fluctuations within ±0.5 Hz) and instantaneous power changes (e.g., megawatt-level demand jumps caused by sudden crane loading) are extracted from the strategy to generate dynamic adjustment instructions. The carbon quota allocation plan (e.g., daily carbon emission cap) and energy procurement plan (e.g., hydrogen procurement volume for the next week) are also extracted to generate periodic scheduling instructions. The timestamp synchronization module uses a precise clock protocol to align the time bases of the two types of instructions. For example, the millisecond-level control instruction's effective time is bound to the start time of the periodic scheduling instruction to ensure timing consistency of instruction execution. The synchronized instruction set is transmitted to the energy router via the edge layer to avoid control failures (e.g., overcharging of energy storage) due to transmission delays.

[0088] Dynamic adjustment instructions (voltage / power transient response) and periodic scheduling instructions (carbon quota / purchase plan) are aligned in timing through the timestamp synchronization module, solving the strategy lag problem in traditional hierarchical control.

[0089] In conjunction with the first aspect, in some implementations of the first aspect, step S5 includes:

[0090] Step S51: Input the dynamic adjustment instruction into the power electronic interface of the energy router to generate a voltage regulation signal and an energy storage charge and discharge control signal;

[0091] Step S52: Input the periodic scheduling instructions into the blockchain verification module of the energy router to generate energy transaction records and carbon emission audit data;

[0092] In step S53, the energy transaction records are compared with the carbon emission audit data through the smart contract to generate energy allocation instructions, and renewable energy and energy storage resources are allocated based on the energy allocation instructions.

[0093] In some embodiments, the energy router's execution process consists of two steps: dynamic adjustment instructions are input into the power electronics interface to generate voltage regulation signals (e.g., stabilizing bus voltage through PWM modulation) and energy storage charging and discharging control signals (e.g., adjusting the duty cycle of the bidirectional converter). Periodic scheduling instructions are input into the blockchain verification module to generate energy transaction records (e.g., power purchase contract hash values) and carbon emissions audit data (e.g., ship operation carbon emissions logs). The smart contract generates energy allocation instructions by comparing the energy transaction records with the audit data (e.g., verifying the match between purchased electricity and actual consumption). For example, if the audit data indicates that a ship has exceeded its emissions quota, the smart contract can automatically freeze its carbon quota application.

[0094] The energy router executes dynamic adjustment commands (such as ±0.5Hz frequency compensation) through the power interface. The blockchain module records carbon trading data for periodic scheduling commands, and smart contracts automatically verify data consistency. This design reduces manual audit costs and enables real-time tracking of ship carbon emissions.

[0095] In combination with the first aspect, in some implementations of the first aspect, the blockchain verification module connects the port's internal energy ledger and the external carbon trading platform through a cross-chain protocol, and synchronizes energy trading records and carbon emission audit data to the external carbon trading platform.

[0096] In some embodiments, the blockchain verification module connects the port's internal energy ledger with an external carbon trading platform via a cross-chain protocol. The internal ledger records local energy transactions (e.g., energy storage lease contracts), while the external platform accesses regional carbon market data (e.g., EU carbon allowance prices). The cross-chain protocol ensures atomic synchronization of the two data types: for example, carbon allowances purchased by the port are instantly updated on the external platform to prevent double counting. Alternatively, relay chain technology or hashed time-lock protocols can be used to achieve cross-chain interaction.

[0097] The cross-chain protocol connects the port’s internal energy ledger with the external carbon trading platform, ensuring global consistency in carbon quota allocation and transaction records. For example, in the EU carbon tariff scenario, port carbon data can be automatically synchronized with the regulatory system to avoid compliance fines.

[0098] In conjunction with the first aspect, in some implementations of the first aspect, in step S2, the preprocessing includes:

[0099] Step S21, filtering the real-time operation data through the abnormality detection unit to generate a filtered data sequence;

[0100] Step S22: Synchronize the filtered data sequence with a preset clock source through a timestamp alignment module to generate a time-uniformed data stream;

[0101] Step S23: Perform feature extraction and dimensionality reduction on the time-uniform data stream through a lightweight convolutional network to generate a compressed dynamic data stream.

[0102] In some embodiments, data preprocessing includes: an anomaly detection unit employing sliding window variance analysis to identify and filter out anomalous data (e.g., zero-value drift caused by sensor failure); a timestamp alignment module synchronizing data from different devices to a unified timeline using a reference clock source (e.g., GPS timing); and a lightweight convolutional network employing depthwise separable convolutional layers to extract key features (e.g., voltage transient waveforms) and performing dimensionality reduction through pooling layers. Alternatively, anomaly detection can employ an isolation forest algorithm, and feature extraction can employ an autoencoder architecture.

[0103] In the preprocessing stage, anomaly detection, timestamp alignment, and lightweight compression are used to compress the original data stream and retain key dynamic features (such as voltage harmonics), reducing the computing load at the edge layer and improving the efficiency of cloud-based model training.

[0104] In combination with the first aspect, in some implementations of the first aspect, the real-time carbon signal data includes power grid carbon intensity data and ship emission characteristic data. The power grid carbon intensity data is acquired in real time through an external energy database, and the ship emission characteristic data is generated through analysis of a ship automatic identification system.

[0105] Real-time carbon signal data includes power grid carbon intensity data, which is obtained in real time from external energy databases via an API interface. This data reflects the current carbon emissions per megawatt-hour of power generated by the power grid. Ship emission signature data is generated by analyzing ship Automatic Identification System (AIS) logbooks (such as engine type and fuel consumption rate) and combining them with the International Maritime Organization (IMO) emission factor database. For example, when a container ship berths, its carbon emission weight is dynamically adjusted based on the fuel type (heavy fuel oil / liquefied natural gas) reported by the AIS.

[0106] The integration of power grid carbon intensity data and ship AIS emissions data has created a refined, real-time carbon signal system. For example, carbon quota weights are dynamically adjusted based on a ship's fuel type, reducing emissions accounting errors.

[0107] Example 2

[0108] like Figure 3 As shown, in a second aspect, the present invention provides a port energy dynamic optimization system based on digital twins, the system adopts the method provided by any of the above embodiments, and the system includes:

[0109] A modeling module 10 is used to construct a multi-level digital twin model of the port energy system, where the multi-level digital twin model includes a physical layer, an edge layer, and a virtual layer;

[0110] The data acquisition module 20 is deployed at the physical layer and collects real-time operating data of the port energy equipment through the sensor network;

[0111] The pre-processing module 30 is deployed in the edge layer and is used to filter, align timestamps, and reduce the dimension of features of real-time operation data, generate compressed dynamic data streams, and synchronize the dynamic data streams to the virtual layer;

[0112] The model training module 40 is deployed in the virtual layer and is used to train the physical information neural network based on the dynamic data flow and the preset physical constraint equations to generate a multi-energy flow prediction model;

[0113] Strategy generation module 50, deployed in the virtual layer, is used to combine multiple energy flow prediction models and real-time carbon signal data to generate multi-time scale energy scheduling strategies through quantum-inspired optimization algorithms;

[0114] The instruction decomposition module 60 is deployed at the edge layer and is used to decompose the energy scheduling policy into dynamic adjustment instructions and periodic scheduling instructions, and transmit them back to the energy router at the physical layer;

[0115] The execution module 70 is deployed in the energy router and is used to execute dynamic adjustment instructions to adjust the operating parameters of the port energy equipment and allocate renewable energy and energy storage resources based on periodic scheduling instructions.

[0116] This system corresponds to the method provided in Example 1 and has the following beneficial effects: First, a data-model closed loop is formed: edge layer preprocessing ensures the quality of virtual layer model input, and the model output strategy reversely controls the physical equipment through the edge layer to form a bidirectional optimization link; second, cross-time scale coupling is achieved: the quantum optimization algorithm integrates transient response and long-term planning, and the timestamp synchronization module ensures the consistency of instruction timing to avoid overcharging / discharging of energy storage; third, carbon-energy synergy is achieved: real-time carbon signals (grid strength, ship emissions) are dynamically weighted to optimize the target, so that energy distribution can meet both economic efficiency and compliance.

[0117] The present invention further provides an electronic device, comprising:

[0118] processor;

[0119] a memory for storing processor-executable instructions;

[0120] The processor is used to execute the method provided in any of the above embodiments.

[0121] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program is used to execute the method provided in any of the above embodiments.

[0122] Computer-readable storage media can be any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A port energy dynamic optimization method based on digital twin, characterized by: include: Step S1, constructing a multi-level digital twin model of the port energy system, wherein the multi-level digital twin model includes a physical layer, an edge layer, and a virtual layer; Step S2: collecting real-time operating data of the port energy equipment through the sensor network in the physical layer, pre-processing the real-time operating data in the edge layer to generate a compressed dynamic data stream, and synchronizing the dynamic data stream to the virtual layer; Step S3: In the virtual layer, a physical information neural network is trained based on the dynamic data flow and preset physical constraint equations to generate a multi-energy flow prediction model, and a multi-time-scale energy scheduling strategy is generated by combining real-time carbon signal data with a quantum-inspired optimization algorithm; Step S4, decomposing the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmitting the instructions back to the energy router of the physical layer through the edge layer; Step S5, executing the dynamic adjustment instruction through the energy router to adjust the operating parameters of the port energy equipment, and allocating renewable energy and energy storage resources based on the periodic scheduling instruction; In step S3, the specific steps of generating the energy scheduling strategy include: Step S34, inputting the energy demand forecast data output by the multi-energy flow forecasting model and the real-time carbon signal data into the quantum-inspired optimization algorithm; Step S35, decomposing the energy scheduling problem into discrete variable optimization subproblems and continuous variable optimization subproblems through the hybrid computing unit in the quantum-inspired optimization algorithm; Step S36, using a quantum annealing algorithm to generate discrete decision parameters for the discrete variable optimization subproblem, and using a gradient descent algorithm to generate continuous decision parameters for the continuous variable optimization subproblem; Step S37, combining the discrete decision parameters and the continuous decision parameters to generate the multi-time-scale energy scheduling strategy; The discrete variable optimization sub-problem includes the start and stop status of the energy storage device and the switch instructions of the energy router, and the continuous variable optimization sub-problem includes the energy storage charge and discharge rate and the energy purchase amount; The step S4 comprises: Step S41, extracting the voltage-frequency deviation and the instantaneous power variation from the energy scheduling strategy to generate the dynamic adjustment instruction; Step S42, extracting the carbon quota allocation plan and energy procurement plan from the energy scheduling strategy to generate the periodic scheduling instruction; Step S43, aligning the time bases of the dynamic adjustment instruction and the periodic scheduling instruction through a timestamp synchronization module, generating a time-consistent scheduling instruction set, and transmitting the set back to the energy router of the physical layer through the edge layer; The step S5 comprises: Step S51: inputting the dynamic adjustment instruction into the power electronic interface of the energy router to generate a voltage regulation signal and an energy storage charge and discharge control signal; Step S52: Inputting the periodic scheduling instruction into the blockchain verification module of the energy router to generate energy transaction records and carbon emission audit data; Step S53: Using a smart contract, the energy transaction record is compared with the carbon emission audit data for consistency, an energy allocation instruction is generated, and renewable energy and energy storage resources are allocated based on the energy allocation instruction; The real-time carbon signal data includes power grid carbon intensity data and ship emission characteristic data. The power grid carbon intensity data is acquired in real time through an external energy database, and the ship emission characteristic data is generated by analyzing the ship automatic identification system.

2. The method according to claim 1, characterized in that In step S3, the specific steps of training the physical information neural network include: Step S31, extracting energy device state parameters from the dynamic data stream as input; Step S32, converting the thermodynamic partial differential equation and the power network conservation equation in the physical constraint equation into residual terms, and performing weighted fusion with the output of the physical information neural network to generate a constrained optimization target; Step S33: updating the weight parameters of the physical information neural network through the distributed nodes in the joint learning algorithm so as to minimize the constrained optimization objective and generate the multi-energy flow prediction model.

3. The method according to claim 1, characterized in that The blockchain verification module connects the port's internal energy ledger and the external carbon trading platform through a cross-chain protocol, and synchronizes the energy transaction records and carbon emission audit data to the external carbon trading platform.

4. The method according to claim 1, wherein In step S2, the preprocessing includes: Step S21, filtering the real-time operation data through an abnormality detection unit to generate a filtered data sequence; Step S22, synchronizing the filtered data sequence with a preset clock source through a timestamp alignment module to generate a time-uniformed data stream; Step S23: performing feature extraction and dimensionality reduction on the time-uniformed data stream through a lightweight convolutional network to generate the compressed dynamic data stream.

5. A port energy dynamic optimization system based on digital twin, characterized by: The system adopts the method according to any one of claims 1 to 4, and the system includes: A modeling module for constructing a multi-level digital twin model of the port energy system, wherein the multi-level digital twin model includes a physical layer, an edge layer, and a virtual layer; A data acquisition module is deployed in the physical layer and collects real-time operating data of the port energy equipment through a sensor network; A preprocessing module, deployed in the edge layer, configured to filter, timestamp align, and reduce feature dimensionality of the real-time operation data, generate a compressed dynamic data stream, and synchronize the dynamic data stream to the virtual layer; A model training module, deployed in the virtual layer, for training a physical information neural network based on the dynamic data flow and preset physical constraint equations to generate a multi-energy flow prediction model; A strategy generation module, deployed in the virtual layer, for combining the multi-energy flow prediction model and real-time carbon signal data to generate a multi-time-scale energy scheduling strategy through a quantum-inspired optimization algorithm; An instruction decomposition module, deployed at the edge layer, configured to decompose the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmit the instructions in reverse to the energy router at the physical layer; an execution module, deployed on the energy router, configured to execute the dynamic adjustment instruction to adjust the operating parameters of the port energy equipment and allocate renewable energy and energy storage resources based on the periodic scheduling instruction; The specific steps of generating the energy scheduling strategy include: Step S34, inputting the energy demand forecast data output by the multi-energy flow forecasting model and the real-time carbon signal data into the quantum-inspired optimization algorithm; Step S35, decomposing the energy scheduling problem into discrete variable optimization subproblems and continuous variable optimization subproblems through the hybrid computing unit in the quantum-inspired optimization algorithm; Step S36, using a quantum annealing algorithm to generate discrete decision parameters for the discrete variable optimization subproblem, and using a gradient descent algorithm to generate continuous decision parameters for the continuous variable optimization subproblem; Step S37, combining the discrete decision parameters and the continuous decision parameters to generate the multi-time-scale energy scheduling strategy; The discrete variable optimization sub-problem includes the start and stop status of the energy storage device and the switch instructions of the energy router, and the continuous variable optimization sub-problem includes the energy storage charge and discharge rate and the energy purchase amount; Decomposing the energy scheduling strategy into dynamic adjustment instructions and periodic scheduling instructions, and transmitting the instructions in reverse to the energy router of the physical layer, including: Step S41, extracting the voltage-frequency deviation and the instantaneous power variation from the energy scheduling strategy to generate the dynamic adjustment instruction; Step S42, extracting the carbon quota allocation plan and energy procurement plan from the energy scheduling strategy to generate the periodic scheduling instruction; Step S43, aligning the time bases of the dynamic adjustment instruction and the periodic scheduling instruction through a timestamp synchronization module, generating a time-consistent scheduling instruction set, and transmitting the set back to the energy router of the physical layer through the edge layer; Executing the dynamic adjustment instruction to adjust the operating parameters of the port energy equipment and allocating renewable energy and energy storage resources based on the periodic scheduling instruction includes: Step S51: inputting the dynamic adjustment instruction into the power electronic interface of the energy router to generate a voltage regulation signal and an energy storage charge and discharge control signal; Step S52: Inputting the periodic scheduling instruction into the blockchain verification module of the energy router to generate energy transaction records and carbon emission audit data; Step S53: Using a smart contract, the energy transaction record is compared with the carbon emission audit data for consistency, an energy allocation instruction is generated, and renewable energy and energy storage resources are allocated based on the energy allocation instruction; The real-time carbon signal data includes power grid carbon intensity data and ship emission characteristic data. The power grid carbon intensity data is acquired in real time through an external energy database, and the ship emission characteristic data is generated by analyzing the ship automatic identification system.

Images