Harbor district flexible load adjustable potential rapid measuring and calculating system and method

Abstract

The invention discloses a system and a method for rapidly measuring and calculating the adjustable potential of a flexible load of a harbor district. A data acquisition module is mainly used for acquiring power load data of the harbor district in real time; the load dynamic baseline module establishes a load dynamic baseline model based on historical operation data of equipment, and generates a load dynamic baseline curve influenced by multiple factors; the adjustable potential calculation module compares the real-time operation data with the load dynamic baseline curve of the corresponding time period to calculate and obtain the load adjustable interval of each load device; the edge computing node cluster module is configured with a real-time data processing engine to realize distributed parallel computing of load adjustable potential; the scheduling optimization module generates a load adjustment instruction set influenced by multiple factors based on a power grid demand response instruction and adjustable potential data reported by each partition edge node; the method has the advantages that the adjustable potential of the load is accurately calculated through the load dynamic baseline curve and edge calculation, and the flexibility and reliability of power load management of the harbor district are improved.

Description

Technical Field

[0001] The present invention relates to potential calculation, and in particular to a system and method for quickly calculating the potential of a flexible load adjustable port area. Background Art

[0002] The background technology of the method for quickly calculating the adjustable potential of port power load comes from the challenges of the increasing demand for power and the complexity of power dispatching in the process of modernization of ports. As important logistics hubs, ports play a key role in global trade, so their power load demand is highly dynamic and variable. The power load of ports is affected by many factors, including the operating status of port facilities, cargo throughput, the number of ships docked, the intensity of loading and unloading operations, and the power supply status of surrounding areas. With the expansion of port scale and the improvement of the degree of automation, the demand for power in ports is increasing, which makes power dispatching more difficult, especially during peak load periods, when the power system's allocation and load balancing face greater pressure.

[0003] Current load adjustment potential measurement systems on the market often suffer from slow response speeds, insufficient accuracy, and poor real-time performance. Traditional methods mostly rely on static load models or simplified prediction algorithms, which cannot effectively take into account the complex multi-factor environment and dynamic changes of equipment in the port area, resulting in low flexibility and accuracy in load adjustment. These systems usually rely on a single centralized computing model, which is prone to computing bottlenecks when processing massive amounts of data, affecting the efficiency and accuracy of real-time scheduling. At the same time, traditional methods do not fully consider the impact of equipment health and environmental changes on load fluctuations in load baseline predictions, which is prone to prediction errors. Summary of the Invention

[0004] To complement existing systems and methods for calculating load scalability potential, a rapid calculation system and method for flexible load scalability potential in port areas is provided. This method uses intelligent algorithms and edge computing to accurately calculate load scalability potential and optimize scheduling plans. Leveraging dynamic baseline models and machine learning techniques, the system can efficiently predict load fluctuations, improving the flexibility and reliability of port power load management.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] The port area flexible load adjustable potential rapid calculation system includes:

[0007] Data acquisition module: The data acquisition module is mainly used to obtain real-time port power load data, including smart meter data, equipment operation status data, environmental sensor data and port operation scheduling data;

[0008] Load dynamic baseline module: The load dynamic baseline module establishes a load dynamic baseline model based on the historical operation data of the equipment and generates a load dynamic baseline curve affected by multiple factors;

[0009] Adjustable potential calculation module: The adjustable potential calculation module calculates the load adjustable range of each load device by comparing the real-time operation data with the load dynamic baseline curve of the corresponding period;

[0010] Edge computing node cluster module: The edge computing node cluster module is deployed in the port terminal operation area, warehousing and logistics area, and office service area. Each edge computing node is equipped with a real-time data processing engine to achieve distributed parallel computing with load-adjustable potential.

[0011] Dispatch Optimization Module: This module optimizes multi-timescale dispatching schemes based on grid demand response instructions and adjustable potential data reported by edge nodes in each partition, generating a load adjustment instruction set influenced by multiple factors.

[0012] Interactive interface module: The interactive interface module provides a three-dimensional visual operation interface, supports dynamic adjustment of parameters and comparative analysis between various scheduling schemes.

[0013] Preferably, the data acquisition module specifically includes:

[0014] Obtain electrical parameter data and topology information data through distributed smart meter arrays;

[0015] Obtain power equipment status data, electrical equipment health, and operating status parameter data through embedded monitoring terminals;

[0016] Obtain meteorological parameters and corrosive environmental parameters through multi-parameter environmental monitoring stations;

[0017] Obtain operation plan data, equipment scheduling instruction data, and energy constraint data in real time through the port operation system.

[0018] Preferably, the load dynamic baseline module specifically includes:

[0019] Feature extraction unit: The feature extraction unit is mainly used to integrate multi-source data such as equipment operation timing, environmental parameters and port operation events, and extract high-dimensional feature vectors containing periodic features, event-driven responses and environmental sensitivity factors;

[0020] Hybrid model architecture unit: The hybrid model architecture unit uses a hybrid architecture of GRU neural network and LightGBM, combined with the attention mechanism to enhance the impact of key operation events and optimize time series prediction results;

[0021] Dynamic baseline generation unit: The dynamic baseline generation unit is mainly used to calibrate historical similar working conditions based on dynamic time regularization, and output an adaptive baseline curve and an elastic adjustment interval.

[0022] Preferably, the feature extraction unit specifically includes:

[0023] Extract daily cycle, weekly cycle harmonic components and port special cycle based on Fourier transform to extract periodic features;

[0024] Extract event-driven features based on the load change gradient in the leading time window of loading and unloading events;

[0025] The temperature load response curve is constructed based on the piecewise linear regression fitting of the load change slopes in different temperature zones.

[0026] Preferably, the hybrid model architecture unit specifically includes:

[0027] Based on a three-layer gated recurrent unit network, 72 hours of historical equipment operation time series data is processed to build a basic time series model. The features of the feature extraction unit are input and multi-source data is fused through feature splicing and normalization.

[0028] Enhance modeling through the spatiotemporal attention mechanism, and set the attention weight coefficient in the time dimension for the time period before and after the device is running;

[0029] Use LightGBM to perform high-order nonlinear modeling on discrete features, build an explanatory model, and use feature importance ranking to screen key influencing factors;

[0030] Based on the time series base model and the explanatory model, a hybrid model is constructed. Through multi-task joint training, the main task is to perform load baseline regression prediction, and the auxiliary task is to complete the load fluctuation range estimation and abnormal working condition binary classification.

[0031] Preferably, the dynamic baseline generating unit specifically includes:

[0032] Based on the obtained hybrid model, the DTW algorithm is used to calculate the multi-dimensional distance between the current operating condition data and the equipment's historical operating data, and the similarity is calculated;

[0033] Select the five sets of time series prediction data with the highest similarity as the baseline to generate candidate sets, and remove abnormal data;

[0034] The current load sequence is mapped to the historical sequence on a nonlinear time axis, the matched historical sequence is dynamically time-calibrated, and a dynamic load baseline curve is synthesized by weighted averaging.

[0035] Output the load dynamic baseline generation results for each time period and add the job event timestamp annotation.

[0036] Preferably, the adjustable potential calculation module specifically includes:

[0037] Based on the real-time collected load data, it is interpolated and aligned with the load dynamic baseline curve in the corresponding time period;

[0038] Based on the baseline deviation calculation, the deviation value is obtained. A positive deviation indicates that the load can be adjusted downward, and a negative deviation indicates that the load can be adjusted upward.

[0039] Based on the real-time health score of each device, a dynamic attenuation coefficient is applied to the adjustable potential, and the load adjustable range is dynamically corrected;

[0040] Cross-validate the calculation results of adjacent nodes in edge computing devices to eliminate misjudgments caused by single-point data anomalies.

[0041] Furthermore, the rapid calculation method of the flexible load adjustable potential of the port area includes:

[0042] The distributed smart meter array collects the electrical parameters and topological relationship data of the port area, and simultaneously obtains the status characteristics of the equipment vibration and temperature monitoring terminals;

[0043] Baseline prediction based on a three-layer GRU-LightGBM hybrid model, optimized by performing dynamic time warping;

[0044] Based on the edge computing cluster, the port area load adjustment potential is calculated, dynamic deviation analysis is performed, and cross-node collaborative verification is carried out;

[0045] Multi-time scale scheduling optimization is carried out based on the adjustable potential of port area load.

[0046] Compared with the prior art, the advantages of the present invention are:

[0047] Through multi-level data collection, dynamic baseline generation, adjustable potential calculation and scheduling optimization, the control accuracy and response speed of the port area's power load have been effectively improved. The system collects real-time power load data, equipment operating status, environmental sensor data and port operation scheduling data in the port area, and combines advanced machine learning and data analysis technologies to establish a load dynamic baseline model to accurately predict load change trends. The adjustable potential calculation module uses the comparison of real-time load data and dynamic baseline curves to quickly calculate the adjustable range of load equipment, and performs parallel processing through edge computing node clusters, ensuring the efficiency and real-time performance of large-scale data processing. In addition, the system corrects the load adjustable potential through a dynamic attenuation coefficient, eliminating the impact caused by different equipment health status and ensuring the stability and reliability of the scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of the system proposed by the present invention;

[0049] Figure 2 A schematic diagram of the method proposed in the present invention;

[0050] Figure 3 The data acquisition module workflow diagram proposed by the present invention;

[0051] Figure 4 This is a schematic diagram of the load dynamic baseline module proposed by the present invention;

[0052] Figure 5 This is the workflow diagram of the feature extraction unit proposed in the present invention;

[0053] Figure 6 This is the workflow diagram of the hybrid model architecture unit proposed by the present invention;

[0054] Figure 7 This is the workflow diagram of the dynamic baseline generation unit proposed by the present invention;

[0055] Figure 8 This is a workflow diagram of the adjustable potential calculation module proposed by the present invention;

[0056] Figure 9 This is a diagram of the architecture of the electronic equipment in this solution;

[0057] Figure 10 This is a schematic diagram of the computer-readable storage medium structure in this solution. DETAILED DESCRIPTION

[0058] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0059] See Figure 1 As shown in the figure, the rapid calculation system for the flexible load adjustable potential of the port area includes:

[0060] Data acquisition module: The data acquisition module is mainly used to obtain real-time port power load data, including smart meter data, equipment operation status data, environmental sensor data and port operation scheduling data;

[0061] Load dynamic baseline module: The load dynamic baseline module establishes a load dynamic baseline model based on the historical operation data of the equipment and generates a load dynamic baseline curve affected by multiple factors;

[0062] Adjustable potential calculation module: The adjustable potential calculation module calculates the load adjustable range of each load device by comparing the real-time operation data with the load dynamic baseline curve of the corresponding period;

[0063] Edge computing node cluster module: The edge computing node cluster module is deployed in the port terminal operation area, warehousing and logistics area, and office service area. Each edge computing node is equipped with a real-time data processing engine to achieve distributed parallel computing with load-adjustable potential.

[0064] Dispatch Optimization Module: This module optimizes multi-timescale dispatching schemes based on grid demand response instructions and adjustable potential data reported by edge nodes in each partition, generating a load adjustment instruction set influenced by multiple factors.

[0065] Interactive interface module: The interactive interface module provides a three-dimensional visual operation interface, supports dynamic adjustment of parameters and comparative analysis between various scheduling schemes.

[0066] See Figure 2 As shown in the figure, the rapid calculation method of the flexible load adjustable potential of the port area includes:

[0067] The distributed smart meter array collects the electrical parameters and topological relationship data of the port area, and simultaneously obtains the status characteristics of the equipment vibration and temperature monitoring terminals;

[0068] Baseline prediction based on a three-layer GRU-LightGBM hybrid model, optimized by performing dynamic time warping;

[0069] Based on the edge computing cluster, the port area load adjustment potential is calculated, dynamic deviation analysis is performed, and cross-node collaborative verification is carried out;

[0070] Multi-time scale scheduling optimization is carried out based on the adjustable potential of port area load.

[0071] See Figure 3 As shown, the data acquisition module specifically includes:

[0072] Obtain electrical parameter data and topology information data through distributed smart meter arrays;

[0073] Obtain power equipment status data, electrical equipment health, and operating status parameter data through embedded monitoring terminals;

[0074] Obtain meteorological parameters and corrosive environmental parameters through multi-parameter environmental monitoring stations;

[0075] Obtain operation plan data, equipment scheduling instruction data, and energy constraint data in real time through the port operation system.

[0076] See Figure 4 As shown in the figure, the load dynamic baseline module specifically includes:

[0077] Feature extraction unit: The feature extraction unit is mainly used to integrate multi-source data such as equipment operation timing, environmental parameters and port operation events, and extract high-dimensional feature vectors containing periodic features, event-driven responses and environmental sensitivity factors;

[0078] Hybrid model architecture unit: The hybrid model architecture unit uses a hybrid architecture of GRU neural network and LightGBM, combined with the attention mechanism to enhance the impact of key operation events and optimize time series prediction results;

[0079] Dynamic baseline generation unit: The dynamic baseline generation unit is mainly used to calibrate historical similar working conditions based on dynamic time regularization, and output an adaptive baseline curve and an elastic adjustment interval.

[0080] See Figure 5 As shown, the feature extraction unit specifically includes:

[0081] Extract daily cycle, weekly cycle harmonic components and port special cycle based on Fourier transform to extract periodic features;

[0082] Extract event-driven features based on the load change gradient in the leading time window of loading and unloading events;

[0083] The temperature load response curve is constructed based on the piecewise linear regression fitting of the load change slopes in different temperature zones.

[0084] Specifically, based on the acquired time series data x(t), the frequency domain signal data is obtained through fast Fourier transform, and the formula is:

[0085]

[0086] Where f is the frequency and j is the imaginary unit;

[0087] From X(f) obtained by Fourier transform, the amplitude |X(f)| and phase arg(X(f)) information at different frequencies are extracted. The frequencies corresponding to the daily cycle (24 hours) and the weekly cycle (7 days) are:

[0088]

[0089] If a port has special periodicity (such as each shift, working day, etc.), the specific periodic components can be extracted by observing the frequency components related to these periods in the spectrum. The harmonic components of the daily and weekly periods, such as the first, second, and third harmonics, can be extracted and their amplitude and phase changes can be observed to determine the significance of the periodic characteristics.

[0090] The load change gradient refers to the rate of change of the load value within a time window. The gradient is obtained by calculating the difference of the load within the time window. The formula is:

[0091]

[0092] Where Δx is the time window size. Observe the gradient change pattern within the time window. If the gradient change is large, it can be considered that the load fluctuation may be driven by the upcoming operation event.

[0093] According to the distribution of temperature data T(t), different temperature intervals are divided. For each temperature interval, a linear regression model is used to fit the relationship between load and temperature, and the slope of load change is calculated, which represents the rate of change of load with temperature in this temperature interval.

[0094] See Figure 6 As shown in Figure 2, the hybrid model architecture unit specifically includes:

[0095] Based on a three-layer gated recurrent unit network, 72 hours of historical equipment operation time series data is processed to build a basic time series model. The features of the feature extraction unit are input and multi-source data is fused through feature splicing and normalization.

[0096] Enhance modeling through the spatiotemporal attention mechanism, and set the attention weight coefficient in the time dimension for the time period before and after the device is running;

[0097] Use LightGBM to perform high-order nonlinear modeling on discrete features, build an explanatory model, and use feature importance ranking to screen key influencing factors;

[0098] Based on the time series base model and the explanatory model, a hybrid model is constructed. Through multi-task joint training, the main task is to perform load baseline regression prediction, and the auxiliary task is to complete the load fluctuation range estimation and abnormal working condition binary classification.

[0099] Specifically, GRU is a variant of the gated recurrent unit network that can effectively process long-term dependencies in time series data. The input layer receives the processed 72 hours of historical running data to form a shape of (n s amples, 72, n f Eatures), and use a three-layer GRU network to learn the long-term dependencies of time series:

[0100] h t =GRU(h t-1 , x t )

[0101] Among them, h t is the hidden state, x t is the input of the current time step;

[0102] The main task of the output layer is to perform load baseline regression prediction using the time series features extracted by the GRU layer, while the auxiliary tasks are load fluctuation range estimation and abnormal operating condition classification.

[0103] Convert discrete features (such as equipment type, working status, etc.) into a format suitable for the LightGBM model, use LightGBM to model discrete features, train the model by selecting an appropriate loss function, rank the features using the feature importance method, and select the features that have the greatest impact on load forecasting;

[0104] Based on the combination of time series models and explanatory models, multi-task joint training is used to achieve stronger predictive capabilities. Its main task is to perform load baseline regression prediction, using the GRU network and spatiotemporal attention mechanism to obtain the load baseline prediction. The auxiliary task is to estimate the load fluctuation range, using regression methods to predict the upper and lower limits of load fluctuations. Abnormal working conditions are classified into two categories, and classification methods are used to predict whether the equipment is in an abnormal working condition.

[0105] The total loss function of the hybrid model is obtained by weighted summation of the loss functions of the main task and the auxiliary task, and the formula is:

[0106] L total =λ1L MSE +λ2L CE +λ3L regression

[0107] Among them, L MSE is the main task loss function, L CE is the auxiliary task loss function.

[0108] See Figure 7 As shown, the dynamic baseline generation unit specifically includes:

[0109] Based on the obtained hybrid model, the DTW algorithm is used to calculate the multi-dimensional distance between the current operating condition data and the equipment's historical operating data, and the similarity is calculated;

[0110] Select the five sets of time series prediction data with the highest similarity as the baseline to generate candidate sets, and remove abnormal data;

[0111] The current load sequence is mapped to the historical sequence on a nonlinear time axis, the matched historical sequence is dynamically time-calibrated, and a dynamic load baseline curve is synthesized by weighted averaging.

[0112] Output the load dynamic baseline generation results for each time period and add the job event timestamp annotation.

[0113] Specifically, based on the current sequence x current ={x1, x2, ..., x T} and history sequence Xi ={x i1 , x i2 ,...,x iT}, define the DTW distance matrix D, where D(t, j) represents the cumulative minimum distance from the current sequence to some subsequences of the historical sequence, and the formula is:

[0114] D(t, j) = dist(x t , x ij )+min(D(t-1,j-1),D(t-1,j),D(t,j-1))

[0115] Among them, dist(x t , x ij ) is the distance measure between the current moment t and the historical moment j, usually using the Euclidean distance;

[0116] Outliers are eliminated based on the five sets of historical time series data with the smallest DTW distance between the current load series and the historical series. The time axis is nonlinearly mapped using the radial basis function to transform the time coordinates of the historical series into the time coordinates of the current load data.

[0117] Perform dynamic time calibration on the matched historical time series data, use interpolation methods to adjust the historical data so that the data points on its time axis correspond one-to-one with the current working condition data points, and align the calibrated historical data with the time step of the current load sequence;

[0118] Based on the calibrated historical sequence, a weight is assigned to each historical sequence, and the final load dynamic baseline curve is synthesized through weighted average. The formula is:

[0119]

[0120] in, The weight is proportional to the similarity between the current load sequence and the historical sequence after calibration. It is calculated by the similarity. The formula is:

[0121]

[0122] Correlate time points in the load dynamic baseline curve with job event timestamps to highlight key time points in equipment operation in charts or reports.

[0123] See Figure 8 As shown, the adjustable potential calculation module specifically includes:

[0124] Based on the real-time collected load data, it is interpolated and aligned with the load dynamic baseline curve in the corresponding time period;

[0125] Based on the baseline deviation calculation, the deviation value is obtained. A positive deviation indicates that the load can be adjusted downward, and a negative deviation indicates that the load can be adjusted upward.

[0126] Based on the real-time health score of each device, a dynamic attenuation coefficient is applied to the adjustable potential, and the load adjustable range is dynamically corrected;

[0127] Cross-validate the calculation results of adjacent nodes in edge computing devices to eliminate misjudgments caused by single-point data anomalies.

[0128] Specifically, calculate the deviation between the real-time load data and the dynamic baseline curve: δ(t) = x current (t)-y baseline (t), when δ(t)>0, it means the load exceeds the baseline and there is no potential for adjustment; when δ(t)<0, it means the load is below the baseline and the load can be adjusted upward;

[0129] Based on health score S i (t), calculate the dynamic attenuation coefficient α i (t), this coefficient is used to adjust the load adjustable potential. Usually a linear relationship is used to calculate the attenuation coefficient. The formula is:

[0130]

[0131] Among them, S max is the maximum value of the equipment health score, and a dynamic attenuation coefficient is applied to the load adjustable space to obtain the corrected load adjustable space;

[0132] In the edge computing device, for any two adjacent nodes j1 and j2, calculate their load deviation difference Δδ(t) = δ j1 (t)-δ j2 (t), if the deviation difference between two nodes exceeds a certain threshold ∈, it means that the calculation result of one of the nodes may be abnormal. For the node with a large deviation difference, the weighted average of the neighboring nodes is used to correct the deviation value of the node. The formula is:

[0133]

[0134] Among them, w1 and w2 are weighting coefficients, which are usually inversely proportional to the distance between nodes.

[0135] In the edge computing node cluster module, the node cluster deployment is as follows:

[0136] Port terminal operation area: The load mainly comes from loading and unloading equipment, transportation tools, etc., and the load is monitored and dispatched in real time.

[0137] Warehousing and logistics area: The load comes from the warehousing system, cargo storage and retrieval equipment, automated transportation system, etc.

[0138] Office service area: The load mainly consists of office equipment, air conditioning, lighting, etc.

[0139] The scheduling optimization module makes scheduling decisions at multiple time scales (short-term, medium-term, and long-term).

[0140] Short-term scheduling optimization focuses on matching grid demand response instructions with the load regulation capabilities of each node. The goal is to ensure that the load within the partition can be balanced under the grid demand response instructions, while taking into account the health status of the equipment and the impact of external factors.

[0141] Medium-term dispatch optimization usually focuses on the effectiveness of the grid's demand response instructions, as well as long-term factors such as equipment health and load forecast errors. The goal is to smoothly dispatch loads within a day to avoid excessive load fluctuations.

[0142] Long-term scheduling optimization takes into account more factors, including equipment maintenance cycles, grid load growth trends, and the volatility of renewable energy generation. The goal is to ensure load balance and avoid long-term load accumulation;

[0143] According to the optimization results, the load adjustment instructions at each moment are generated, and for each load adjustment instruction, the corresponding adjustment cost and efficiency are given.

[0144] Furthermore, the method according to the embodiment of the present application can also be used with the aid of Figure 9 The electronic device architecture shown in FIG. Figure 9 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the system and method for rapidly calculating the adjustable potential of flexible loads in a port area provided in this application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 9 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 9 One or more components of an electronic device are shown.

[0145] Figure 10 This is a schematic diagram of the computer-readable storage medium structure provided by an embodiment of the present application. Figure 10As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the system and method for quickly calculating the adjustable potential of flexible load in the port area according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0146] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0148] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. Rapid calculation system of flexible load adjustable potential in port area, characterized by: include: Data acquisition module: The data acquisition module is mainly used to obtain real-time port power load data, including smart meter data, equipment operation status data, environmental sensor data and port operation scheduling data; Load dynamic baseline module: The load dynamic baseline module establishes a load dynamic baseline model based on the historical operation data of the equipment and generates a load dynamic baseline curve affected by multiple factors; Adjustable potential calculation module: The adjustable potential calculation module calculates the load adjustable range of each load device by comparing the real-time operation data with the load dynamic baseline curve of the corresponding period; Edge computing node cluster module: The edge computing node cluster module is deployed in the port terminal operation area, warehousing and logistics area, and office service area. Each edge computing node is equipped with a real-time data processing engine to achieve distributed parallel computing with load-adjustable potential. Dispatch Optimization Module: This module optimizes multi-timescale dispatching schemes based on grid demand response instructions and adjustable potential data reported by edge nodes in each partition, generating a load adjustment instruction set influenced by multiple factors. Interactive interface module: The interactive interface module provides a three-dimensional visual operation interface, supports dynamic adjustment of parameters and comparative analysis between various scheduling schemes.

2. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 1 is characterized in that: The data acquisition module specifically includes: Obtain electrical parameter data and topology information data through distributed smart meter arrays; Obtain power equipment status data, electrical equipment health, and operating status parameter data through embedded monitoring terminals; Obtain meteorological parameters and corrosive environmental parameters through multi-parameter environmental monitoring stations; Obtain operation plan data, equipment scheduling instruction data, and energy constraint data in real time through the port operation system.

3. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 1 is characterized in that: The load dynamic baseline module specifically includes: Feature extraction unit: The feature extraction unit is mainly used to integrate multi-source data such as equipment operation timing, environmental parameters and port operation events, and extract high-dimensional feature vectors containing periodic features, event-driven responses and environmental sensitivity factors; Hybrid model architecture unit: The hybrid model architecture unit uses a hybrid architecture of GRU neural network and LightGBM, combined with the attention mechanism to enhance the impact of key operation events and optimize time series prediction results; Dynamic baseline generation unit: The dynamic baseline generation unit is mainly used to calibrate historical similar working conditions based on dynamic time regularization, and output an adaptive baseline curve and an elastic adjustment interval.

4. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 3 is characterized in that: The feature extraction unit specifically includes: Extract daily cycle, weekly cycle harmonic components and port special cycle based on Fourier transform to extract periodic features; Extract event-driven features based on the load change gradient in the leading time window of loading and unloading events; The temperature load response curve is constructed based on the piecewise linear regression fitting of the load change slopes in different temperature zones.

5. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 3 is characterized in that: The hybrid model architecture unit specifically includes: Based on a three-layer gated recurrent unit network, 72 hours of historical equipment operation time series data is processed to build a basic time series model. The features of the feature extraction unit are input and multi-source data is fused through feature splicing and normalization. Enhance modeling through the spatiotemporal attention mechanism, and set the attention weight coefficient in the time dimension for the time period before and after the device is running; Use LightGBM to perform high-order nonlinear modeling on discrete features, build an explanatory model, and use feature importance ranking to screen key influencing factors; Based on the time series base model and the explanatory model, a hybrid model is constructed. Through multi-task joint training, the main task is to perform load baseline regression prediction, and the auxiliary task is to complete the load fluctuation range estimation and abnormal working condition binary classification.

6. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 3 is characterized in that: The dynamic baseline generation unit specifically includes: Based on the obtained hybrid model, the DTW algorithm is used to calculate the multi-dimensional distance between the current operating condition data and the equipment's historical operating data, and the similarity is calculated; Select the five sets of time series prediction data with the highest similarity as the baseline to generate candidate sets, and remove abnormal data; The current load sequence is mapped to the historical sequence on a nonlinear time axis, the matched historical sequence is dynamically time-calibrated, and a dynamic load baseline curve is synthesized by weighted averaging. Output the load dynamic baseline generation results for each time period and add the job event timestamp annotation.

7. The rapid calculation system for the flexible load adjustable potential of the port area according to claim 1 is characterized in that: The adjustable potential calculation module specifically includes: Based on the real-time collected load data, it is interpolated and aligned with the load dynamic baseline curve in the corresponding time period; Based on the baseline deviation calculation, the deviation value is obtained. A positive deviation indicates that the load can be adjusted downward, and a negative deviation indicates that the load can be adjusted upward. Based on the real-time health score of each device, a dynamic attenuation coefficient is applied to the adjustable potential, and the load adjustable range is dynamically corrected; Cross-validate the calculation results of adjacent nodes in edge computing devices to eliminate misjudgments caused by single-point data anomalies.

8. A method for rapidly calculating the adjustable potential of flexible load in a port area is characterized by: include: The distributed smart meter array collects the electrical parameters and topological relationship data of the port area, and simultaneously obtains the status characteristics of the equipment vibration and temperature monitoring terminals; Baseline prediction based on a three-layer GRU-LightGBM hybrid model, optimized by performing dynamic time warping; Based on the edge computing cluster, the port area load adjustment potential is calculated, dynamic deviation analysis is performed, and cross-node collaborative verification is carried out; Multi-time scale scheduling optimization is carried out based on the adjustable potential of port area load.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for quickly calculating the adjustable potential of flexible load in a port area as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the method for quickly calculating the adjustable potential of flexible load in a port area according to any one of claims 1 to 7 is implemented.

Images