Energy recovery system and method based on digital power supply
By introducing data acquisition, preprocessing and predictive analysis modules into the digital power energy recovery system, the recovery and release strategies are dynamically adjusted, and the problems of low energy recovery efficiency and lag in the existing technology are solved, achieving efficient and flexible energy Management improves the robustness and energy utilization of the system.
Patent Information
- Application Number
- CN202411204962.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
AI Technical Summary
The existing digital power energy recovery system is inefficient and cannot effectively adjust the residual power recovery and release strategy according to changes in power supply and electricity consumption demand. The lack of intelligent adjustment mechanism leads to insufficient system performance, low system integration and mutual communication between functional modules. Poor operationality.
A energy recovery system based on digital power supply was designed, including the receiving end, the recycling module, the conveying module, the energy storage module, the control module, the acquisition module, the detection module, the prediction and analysis module and the adjustment module. Through data acquisition, preprocessing, and abnormalities Detection and predictive analysis, dynamic adjustment of recovery and release strategies, adaptive power supply tasks and grid environment changes, and optimize energy recovery.
Real-time monitoring and optimization of energy recovery are achieved, energy utilization is maximized, energy waste is reduced, system robustness and flexibility are improved, energy recovery is always in the optimal state, and adapt to different power supply tasks and environmental changes.
Smart Images

Figure CN119093349A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital power supply, and in particular to an energy recovery system and method based on digital power supply. Background Art
[0002] The core of digital power products is their efficient energy storage. The recycling system of digital power products can achieve more efficient, stable and reliable use effects by optimizing the system operation mode. For digital power products, different battery types require different system control methods, which need to be weighed according to actual needs. In the recycling process, the impact of system internal losses and external environmental factors on recycling efficiency needs to be considered. After recycling, the energy needs to be stored or directly applied;
[0003] In the process of energy recovery, the existing technology has low efficiency in recovering surplus power, resulting in a large amount of power wasted and unable to fully utilize the recovered power. Insufficient attention is paid to the collected data, making it difficult to effectively adjust the surplus power recovery and release strategies according to the changes in actual power supply and power demand, and lacks flexibility.
[0004] The lack of effective predictive analysis models makes it impossible to make accurate predictions of future trends based on historical and current data, resulting in delayed policy adjustments. The lack of an intelligent policy adjustment mechanism makes it impossible to adjust the start and stop cycles and priorities of each recycling node in a timely manner according to actual conditions, affecting the overall performance of the system. In the existing technologies, the system integration is low and the interoperability between functional modules is poor, resulting in insufficient coordination of the overall system and difficulty in achieving efficient management. Summary of the invention
[0005] 1. Technical issues to be resolved
[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides an energy recovery system based on a digital power supply and a method thereof, which can effectively solve the problems of the prior art.
[0007] (II) Technical solution
[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0009] The present invention discloses an energy recovery system based on a digital power supply, comprising:
[0010] The receiving end is used to connect to the recycling nodes of several power supply targets and customize the start and stop cycles of the recycling nodes;
[0011] The recycling module is used to deploy the functional components for surplus power recycling, and recycle the surplus power of the recycling node after being triggered;
[0012] A transmission module, used to rectify and transmit the recovered surplus electricity according to a preset surplus electricity recovery strategy;
[0013] The energy storage module is used to receive the excess power transmitted back and store it in the battery pack. When it is called, the stored DC power is converted into AC power.
[0014] The control module is used to edit and issue surplus power release and recovery strategies through control strategies according to load demand and energy supply data;
[0015] The collection module is used to collect the operation data of the recycling module and the transport module, the power grid environment data and the power supply task data of the current cycle, and pre-process the collected data into a corresponding machine-readable format;
[0016] The detection module is used to analyze and calculate the fluctuation coefficient of the actual recovery income and the expected recovery income of the currently applied surplus power recovery strategy through an abnormal detection algorithm based on the collected data pre-processed by the collection module;
[0017] The prediction and analysis module is used to build a prediction and analysis model. When the fluctuation coefficient detected by the detection module reaches the preset standard, the operation is triggered. Based on the currently collected data and future power supply tasks, the prediction and output of the operation data of the recovery module and the transmission module and the power grid environment data for the next one or more cycles are carried out;
[0018] A judgment module, used to judge whether the current operation settings of the recovery module and the conveying module need to be adjusted according to the data predicted by the prediction and analysis module;
[0019] The adjustment module is used to trigger the strategy adjustment mechanism after receiving the adjustment instruction. The strategy adjustment mechanism presets the load status of each functional module and functional component under the future power supply task based on the data predicted by the prediction and analysis module. Based on the preset load status, it generates the collection objects and their weights and frequencies in the collection tasks corresponding to the collection module in the future period.
[0020] Furthermore, the control strategy implemented by the control module obtains the voltage, frequency and load change data in the power grid environment data collected in real time by the acquisition module through a preset mutation data standard, so that the detection module automatically identifies the mutation data in the power grid environment data, and according to the data mutation state of the detected mutation data, the prediction and analysis module performs a prediction output of the mutation data, and the control module re-updates the surplus power release and recovery strategy.
[0021] Furthermore, the data basis of the prediction analysis model constructed by the prediction analysis module includes: collected data and historical data, with the historical data used as training samples and test samples;
[0022] The establishment logic of the forecast analysis model includes: extracting basic time series characteristics, calculating periodic indicators, trend characteristics, periodic and seasonal components, generating lagged variables, extracting the interactive characteristics of a certain indicator based on the load items of the previous cycle, and obtaining the influencing parameters of a certain indicator and the corresponding load items in the future.
[0023] Furthermore, the judgment criteria of the judgment module are:
[0024] a. Manually log in to the judgment module, check the data predicted by the prediction and analysis module, and issue a custom judgment command;
[0025] b. The judgment module automatically issues judgment commands based on preset judgment logic.
[0026] Furthermore, the adjustment module is interactively connected to a storage module via a wireless network, and the storage module is used to record historical cases of actual data that are consistent with the predicted data of the predictive analysis module. When the adjustment module is triggered, if matching data appears in the storage module, the historical data can be directly called.
[0027] Furthermore, the strategy adjustment mechanism customized by the adjustment module is sent to the control module. After receiving it, the control module performs secondary configuration of the surplus power recovery strategy of the recovery module and the transmission module, and reconfigures the start and stop cycle and priority of each recovery node at the receiving end.
[0028] Furthermore, the receiving end is interactively connected to the recovery module through a wireless network, the recovery module, the conveying module and the collection module are interactively connected through a wireless network, the conveying module is interactively connected to the energy storage module through a wireless network, the control module is interactively connected to the collection module and the adjustment module through a wireless network, the collection module is interactively connected to the detection module through a wireless network, the detection module is interactively connected to the prediction and analysis module through a wireless network, and the judgment module is interactively connected to the adjustment module and the prediction and analysis module through a wireless network.
[0029] An energy recovery method based on digital power supply comprises the following steps:
[0030] Step 1: Set up recycling nodes for connecting to several power supply targets, and customize the start and stop cycles and priorities of these recycling nodes;
[0031] Step 2: Deploy the functional components for surplus power recovery, and when triggered, recover the surplus power of the recovery node, and rectify and transmit the recovered surplus power according to the preset surplus power recovery strategy;
[0032] Step 3: Monitor and record the charge and discharge status of the battery pack and the load demand change coefficient in real time, and receive and store the recovered surplus power to the battery pack;
[0033] Step 4: Collect the operation data of the surplus power recovery function component and the rectification and transmission function component of the current cycle, and collect the power grid environment data and power supply task data at the same time;
[0034] Step 5: Based on the pre-processed collected data, the fluctuation coefficient of the actual recycling income and the expected recycling income of the currently applied surplus power recycling strategy is analyzed through anomaly detection algorithm;
[0035] Step 6: Construct a prediction analysis model. When the fluctuation coefficient reaches the preset standard, the operation is triggered. The prediction analysis model predicts the operation data of the surplus power recovery function component and the rectification and transmission function component and the grid environment data of the next one or more cycles based on the current collected data and future power supply tasks.
[0036] Step 7: Based on the predicted data, determine whether the current operation settings of the residual power recovery function component and the rectification and transmission function component need to be adjusted. The judgment criteria include manual login inspection and automatic judgment based on preset judgment logic;
[0037] Step 8: After receiving the adjustment instruction, the strategy adjustment mechanism is triggered to preset the load status of each functional module and functional component under the future power supply task based on the predicted data.
[0038] Furthermore, the fluctuation coefficient in step 5 reflects the discreteness of a certain project data, so as to reflect whether the prediction analysis model in step 6 triggers the operation behavior. The calculation formula of the fluctuation coefficient is:
[0039]
[0040] Where CV stands for coefficient of fluctuation, N stands for the number of data points in the project, and x i represents the value of the i-th data point, representing each observation in the project, Y represents the weighted average of the data, w i Represents the weight of the ith data point.
[0041] Furthermore, the weighted average of the data represented by Y is calculated as follows:
[0042]
[0043] (III) Beneficial effects
[0044] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects:
[0045] 1. Through data collection, preprocessing and predictive analysis, the changes in the power grid environment and power supply tasks are monitored in real time. When it is detected that the benefits of the existing strategy fluctuate greatly from the expected benefits, the system automatically triggers the strategy adjustment mechanism, optimizes the surplus power recovery strategy based on the predicted data, ensures that the energy recovery process is always in the optimal state, sets and controls the start and stop cycle of the recovery node, and the system can recover energy at the optimal time point to reduce energy waste. The surplus power recovery functional components and the rectifier transmission components recover and convert the surplus power in time after being triggered, so as to maximize the energy utilization rate.
[0046] 2. By collecting the operating data, power grid environment data and power supply task data of the current cycle, and pre-processing and analyzing the data, the effectiveness of the current strategy is evaluated through the anomaly detection algorithm, and a predictive analysis model is built to provide data-driven decision support and reduce the uncertainty caused by human intervention. The system dynamically adjusts the surplus power release and recovery strategy through control strategies based on load demand and energy supply data to adapt to different power supply tasks and environmental changes. The establishment of the predictive analysis model and the triggering of the adjustment mechanism make the system have adaptive capabilities.
[0047] 3. Through real-time collection and analysis of the operating data of the current cycle, timely feedback on the effect of the recovery strategy through anomaly detection and predictive analysis, real-time monitoring and feedback mechanisms ensure that the system is always in the best working state. When the strategy adjustment mechanism is triggered, historical cases can be called for reference to increase the reliability of decision-making. The call of historical data ensures that the system can find the best response strategy in various situations and improve the robustness of the digital power energy recovery system. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0049] Figure 1 It is a schematic diagram of the framework of the energy recovery system based on digital power supply in the present invention.
[0050] The numbers in the figure represent, respectively, 1. receiving end; 2. recovery module; 3. transportation module; 4. energy storage module; 5. control module; 6. acquisition module; 7. detection module; 8. prediction and analysis module; 9. judgment module; 10. adjustment module; 11. storage module. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0052] The present invention will be further described below in conjunction with the embodiments.
[0053] Example 1
[0054] An energy recovery system based on a digital power supply in this embodiment, such as Figure 1 As shown, including:
[0055] The receiving end 1 is used to connect to the recycling nodes of several power supply targets and customize the start and stop cycles of the recycling nodes. By customizing the start and stop cycles of the recycling nodes of several power supply targets, the system can be flexibly adjusted according to actual needs to improve energy efficiency.
[0056] Recycling module 2 is used to deploy the functional components for surplus power recycling, and recycle the surplus power of the recycling node after being triggered;
[0057] The transmission module 3 is used to rectify and transmit the recovered surplus electricity according to a preset surplus electricity recovery strategy;
[0058] The energy storage module 4 is used to receive the returned surplus electricity and store it in the battery pack, and convert the stored direct current into alternating current when it is called;
[0059] The control module 5 is used to edit and issue the surplus power release and recovery strategy through the control strategy according to the load demand and energy supply data. The control strategy implemented by the control module 5 obtains the voltage, frequency and load change data in the power grid environment data collected in real time by the acquisition module 6 through the preset mutation data standard, so that the detection module 7 automatically identifies the mutation data in the power grid environment data, and according to the data mutation state of the detected mutation data, the prediction and analysis module 8 performs the prediction output of the mutation data, and the control module 5 re-updates the surplus power release and recovery strategy; the system is adapted to the changing power grid environment, and the strategy is dynamically adjusted through the detection and prediction of mutation data, so as to improve the response speed and flexibility of the system and optimize energy recovery and utilization;
[0060] The acquisition module 6 is used to collect the operation data of the recycling module 2 and the transmission module 3, the power grid environment data and the power supply task data of the current cycle, and pre-process the acquired data into a corresponding machine-readable format to ensure the accuracy and readability of the data and provide a reliable data basis for subsequent analysis;
[0061] The detection module 7 is used to analyze and calculate the fluctuation coefficient of the actual recycling income and the expected recycling income of the currently applied surplus power recycling strategy based on the collected data pre-processed by the collection module 6 through an abnormal detection algorithm, provide accurate recycling effect evaluation, and help optimize the strategy;
[0062] The prediction and analysis module 8 is used to construct a prediction and analysis model. When the fluctuation coefficient detected by the detection module 7 reaches a preset standard, the operation is triggered. Based on the currently collected data and future power supply tasks, the prediction and output of the operation data of the recovery module 2 and the transmission module 3 and the power grid environment data for the next one or more cycles are performed to improve the accuracy of the prediction and help foresee the future power demand and recovery effect.
[0063] The data basis of the prediction analysis model constructed by the prediction analysis module 8 includes: collected data and historical data, with the historical data used as training samples and test samples;
[0064] The establishment logic of the prediction and analysis model includes: by extracting basic time series characteristics, calculating periodic indicators, trend characteristics, periodic and seasonal components, generating lagged variables, extracting the interactive characteristics of a certain indicator based on the load items of the previous cycle, and obtaining the influencing parameters of a certain indicator and the corresponding load items in the future; Among them, the collected data includes: the output of the power node, the remaining power recovered, the charging and discharging status of the storage battery and the load demand change coefficient; the historical data includes: the power demand pattern, energy supply situation and the execution effect data of the recovery strategy;
[0065] The judgment module 9 is used to judge whether the current operation settings of the recovery module 2 and the conveying module 3 need to be adjusted according to the data predicted by the prediction and analysis module 8; the judgment criteria of the judgment module 9 are:
[0066] a. Manually log in to the judgment module 9, check the prediction data obtained by the prediction analysis module 8, and issue a custom judgment command;
[0067] b. The judgment module 9 automatically issues a judgment command based on a preset judgment logic;
[0068] Ensure that the energy recovery system is always in the best operating state by adjusting the strategy in real time;
[0069] The adjustment module 10 is used to trigger the strategy adjustment mechanism after receiving the adjustment instruction. The strategy adjustment mechanism is based on the data predicted by the prediction analysis module 8, presets the load status of each functional module and functional component under the future power supply task, and generates the collection objects and their weights and frequencies in the corresponding collection tasks of the collection module 6 in the future period based on the preset load status. The adjustment module 10 is interactively connected to the storage module 11 through a wireless network. The storage module 11 is used to record historical cases of actual data that meet the prediction data of the prediction analysis module 8. When the adjustment module 10 is triggered, if the storage module 11 has matching data, the historical data can be directly called, and the reliability and effectiveness of the adjustment strategy can be improved by using the historical data;
[0070] The customized strategy adjustment mechanism of the adjustment module 10 is sent to the control module 5. After receiving, the control module 5 performs secondary configuration of the surplus power recovery strategy of the recovery module 2 and the transmission module 3, and reconfigures the start and stop cycle and priority of each recovery node of the receiving end 1.
[0071] As a preferred implementation in this embodiment, Figure 1 As shown, the receiving end 1 is interactively connected with the recovery module 2 through a wireless network, the recovery module 2, the conveying module 3 and the acquisition module 6 are interactively connected through a wireless network, the conveying module 3 and the energy storage module 4 are interactively connected through a wireless network, the control module 5 is interactively connected with the acquisition module 6 and the adjustment module 10 through a wireless network, the acquisition module 6 is interactively connected with the detection module 7 through a wireless network, the detection module 7 is interactively connected with the prediction and analysis module 8 through a wireless network, and the judgment module 9 is interactively connected with the adjustment module 10 and the prediction and analysis module 8 through a wireless network.
[0072] Compared with existing technologies, the energy recovery system based on digital power supply achieves efficient energy recovery and utilization through intelligent control and data-driven decision-making. Its advantage lies in dynamically adjusting strategies through logically rigorous data collection, preprocessing, analysis and prediction to adapt to different power supply requirements and environmental changes, thereby maximizing the energy utilization and reliability of the system.
[0073] Example 2
[0074] In other aspects, this embodiment also provides an energy recovery method based on a digital power supply, comprising the following steps:
[0075] Step 1: Set up recycling nodes for connecting to several power supply targets, and customize the start and stop cycles and priorities of these recycling nodes. Perform secondary configuration on each recycling node, including the start and stop cycles and priorities, to ensure efficient operation of the system.
[0076] Step 2: Deploy the functional components for surplus power recovery, and when triggered, recover the surplus power of the recovery node, and rectify and transmit the recovered surplus power according to the preset surplus power recovery strategy;
[0077] Step 3: Monitor and record the charge and discharge status of the battery pack and the load demand change coefficient in real time, and receive and store the recovered surplus power to the battery pack;
[0078] Step 4: Collect the operating data of the surplus power recovery function component and the rectification and transmission function component of the current cycle, and collect the grid environment data and power supply task data at the same time, and pre-process the collected data into a machine-readable format for subsequent analysis and use;
[0079] Step 5: Based on the pre-processed collected data, the fluctuation coefficient of the actual recycling income and the expected recycling income of the currently applied surplus power recycling strategy is analyzed through anomaly detection algorithm. This analysis helps to evaluate the effectiveness of the existing strategy and make necessary adjustments;
[0080] Step 6: Construct a prediction analysis model. When the fluctuation coefficient reaches the preset standard, the operation is triggered. The prediction analysis model predicts the operation data of the surplus power recovery function component and the rectification and transmission function component and the power grid environment data of the next one or more cycles based on the current collected data and future power supply tasks. The data basis of the prediction analysis model includes collected data and historical data. The periodic indicators and trend characteristics are calculated by extracting time series features.
[0081] Step 7: Based on the predicted data, determine whether the current operating settings of the surplus power recovery functional component and the rectification and transmission functional component need to be adjusted. The judgment criteria include manual login inspection and automatic judgment based on preset judgment logic. After receiving the adjustment instruction, the strategy adjustment mechanism is triggered to preset the load status of each functional module and functional component under the future power supply task based on the predicted data.
[0082] Step 8: After receiving the adjustment instruction, the strategy adjustment mechanism is triggered. Based on the predicted data, the load status of each functional module and functional component under the future power supply task is preset. The surplus power recovery strategy will be reconfigured according to the customized strategy adjustment mechanism, and the start and stop cycle and priority of each recovery node will be reconfigured.
[0083] In specific implementation, the efficiency of waste power recovery and the overall performance of the system can be greatly improved, and the flexibility and intelligence of the system can be enhanced.
[0084] As a preferred implementation in this embodiment, the fluctuation coefficient reflects the discreteness of a certain project data to reflect whether the prediction analysis model in step 6 triggers the operation behavior. The calculation formula of the fluctuation coefficient is:
[0085]
[0086] Where CV stands for coefficient of fluctuation, N stands for the number of data points in the project, and x i represents the value of the i-th data point, representing each observation in the project, Y represents the weighted average of the data, w i represents the weight of the i-th data point, indicating the importance of each data point, (x i -Y) 2 Represents the square of the deviation between the ith data point and the weighted mean, indicating the degree of dispersion of each data point. Represents the weighted standard deviation, which indicates the overall fluctuation of the data. It stands for weighted variance, which means the sum of the weighted discreteness of all data points, and the weighted average of the data represented by Y. Its calculation formula is:
[0087] Through the above steps, we can get the volatility coefficient of a certain project. The lower the volatility coefficient, the more stable the data and the more effective the strategy. The higher the volatility coefficient, the greater the data fluctuation and the strategy may need to be adjusted.
[0088] Compared with the existing technology, it provides an effective predictive analysis model, makes accurate predictions on future trends based on historical data and current data, avoids delays in strategy adjustments, and can timely adjust the start and stop cycles and priorities of each recovery node according to actual conditions to prevent affecting the overall performance of the energy recovery structure. It can dynamically adjust strategies according to changes in actual power supply and power demand to improve flexibility.
[0089] In summary, the energy recovery system and energy recovery method provided in the present invention can firstly perform secondary configuration by setting the start and stop cycle and priority of the recovery node to ensure that the system can operate flexibly and efficiently under different power supply requirements, deploy surplus power recovery functional components, rectify and transmit the surplus power according to the preset strategy, maximize the recovery efficiency, and reduce the waste of electric energy;
[0090] By real-time monitoring of the charge and discharge status of the battery pack and changes in load demand, it ensures that the recycled surplus electricity can be reasonably stored and utilized, improves the overall energy efficiency of the system, collects and pre-processes the operating data of functional components, power grid environment data, and power supply task data, and provides a reliable data basis for subsequent analysis and decision-making. It uses anomaly detection algorithms to analyze the fluctuations between actual recycling benefits and expected benefits, helps evaluate and optimize existing strategies, and improves recycling efficiency and system stability.
[0091] By building a predictive analysis model, future trend forecasts are made based on collected data and historical data, and the operating settings of the surplus power recovery functional components and the rectification and transmission functional components are adjusted in advance to ensure the system's ability to respond to future power supply needs. By combining manual and automatic judgment, the strategy adjustment mechanism is triggered, and the start and stop cycles and priorities of each recovery node are reconfigured according to the predicted data, thereby improving the flexibility and response speed of the system.
[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. An energy recovery system based on digital power supply, characterized in that: include: The receiving end (1) is used to connect to the recovery nodes of several power supply targets and customize the start and stop cycles of the recovery nodes; A recycling module (2), which is used to deploy a functional component for recycling surplus power and to recycle surplus power of a recycling node after being triggered; A transmission module (3) is used to rectify and transmit the recovered surplus electricity according to a preset surplus electricity recovery strategy; An energy storage module (4) is used to receive the returned surplus electricity and store it in a battery pack, and when called upon, convert the stored direct current into alternating current; A control module (5) is used to edit and issue surplus power release and recovery strategies through control strategies according to load demand and energy supply data; A collection module (6) is used to collect the operation data of the recycling module (2) and the transport module (3), the power grid environment data and the power supply task data of the current cycle, and pre-process the collected data into a corresponding machine-readable format; A detection module (7) is used to analyze and calculate the fluctuation coefficient of the actual recovery income and the expected recovery income of the currently applied surplus power recovery strategy through an abnormal detection algorithm based on the collected data pre-processed by the collection module (6); A prediction analysis module (8) is used to construct a prediction analysis model, trigger an operation when the fluctuation coefficient detected by the detection module (7) reaches a preset standard, and perform prediction output of the operation data of the recovery module (2) and the transmission module (3) and the power grid environment data for the next one or more cycles based on the currently collected data and the future power supply tasks; A judgment module (9) is used to judge whether the current operation settings of the recovery module (2) and the conveying module (3) need to be adjusted based on the data predicted by the prediction analysis module (8); The adjustment module (10) is used to trigger a strategy adjustment mechanism after receiving an adjustment instruction. The strategy adjustment mechanism presets the load state of each functional module and functional component under the future power supply task based on the data predicted by the prediction analysis module (8), and generates the collection objects and their weights and frequencies in the corresponding collection tasks of the collection module (6) in the future period based on the preset load state.
2. The energy recovery system based on digital power supply according to claim 1, characterized in that: The control strategy implemented by the control module (5) obtains the voltage, frequency and load change data in the power grid environment data collected in real time by the collection module (6) by means of a preset mutation data standard, so that the detection module (7) automatically identifies the mutation data in the power grid environment data, and according to the data mutation state of the detected mutation data, the prediction and analysis module (8) performs a prediction output of the mutation data, and the control module (5) re-updates the surplus power release and recovery strategy.
3. The energy recovery system based on digital power supply according to claim 1, characterized in that: The data basis of the prediction analysis model constructed by the prediction analysis module (8) includes: collected data and historical data, with the historical data serving as training samples and test samples; The establishment logic of the forecast analysis model includes: extracting basic time series characteristics, calculating periodic indicators, trend characteristics, periodic and seasonal components, generating lagged variables, extracting the interactive characteristics of a certain indicator based on the load items of the previous cycle, and obtaining the influencing parameters of a certain indicator and the corresponding load items in the future.
4. The energy recovery system based on digital power supply according to claim 1, characterized in that: The judgment criteria of the judgment module (9) are: a. Manually log in to the judgment module (9), check the prediction and analysis module (8) to predict the data, and issue a custom judgment command; b. The judgment module (9) automatically issues judgment commands based on preset judgment logic.
5. The energy recovery system based on digital power supply according to claim 1, characterized in that: The adjustment module (10) is interactively connected to a storage module (11) via a wireless network. The storage module (11) is used to record historical cases of actual data that match the predicted data of the prediction analysis module (8). When the adjustment module (10) is triggered, if matching data appears in the storage module (11), the historical data can be directly called.
6. The energy recovery system based on digital power supply according to claim 1, characterized in that: The strategy adjustment mechanism customized by the adjustment module (10) is sent to the control module (5), and after receiving the control module (5), the control module (5) performs secondary configuration of the surplus power recovery strategy of the recovery module (2) and the transmission module (3), and reconfigures the start and stop cycles and priorities of each recovery node at the receiving end (1).
7. The energy recovery system based on digital power supply according to claim 1, characterized in that: The receiving end (1) is interactively connected to the recovery module (2) via a wireless network; the recovery module (2), the transport module (3) and the collection module (6) are interactively connected via a wireless network; the transport module (3) is interactively connected to the energy storage module (4) via a wireless network; the control module (5) is interactively connected to the collection module (6) and the adjustment module (10) via a wireless network; the collection module (6) is interactively connected to the detection module (7) via a wireless network; the detection module (7) is interactively connected to the prediction and analysis module (8) via a wireless network; and the judgment module (9) is interactively connected to the adjustment module (10) and the prediction and analysis module (8) via a wireless network.
8. An energy recovery method based on digital power supply, the method is an implementation method of an energy recovery system based on digital power supply according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Set up recycling nodes for connecting to several power supply targets, and customize the start and stop cycles and priorities of these recycling nodes; Step 2: Deploy the functional components for surplus power recovery, and when triggered, recover the surplus power of the recovery node, and rectify and transmit the recovered surplus power according to the preset surplus power recovery strategy; Step 3: Monitor and record the charge and discharge status of the battery pack and the load demand change coefficient in real time, and receive and store the recovered surplus power to the battery pack; Step 4: Collect the operation data of the surplus power recovery function component and the rectification and transmission function component of the current cycle, and collect the power grid environment data and power supply task data at the same time; Step 5: Based on the pre-processed collected data, the fluctuation coefficient of the actual recycling income and the expected recycling income of the currently applied surplus power recycling strategy is analyzed through anomaly detection algorithm; Step 6: Construct a prediction analysis model. When the fluctuation coefficient reaches the preset standard, the operation is triggered. The prediction analysis model predicts the operation data of the surplus power recovery function component and the rectification and transmission function component and the grid environment data of the next one or more cycles based on the current collected data and future power supply tasks. Step 7: Based on the predicted data, determine whether the current operation settings of the residual power recovery function component and the rectification and transmission function component need to be adjusted. The judgment criteria include manual login inspection and automatic judgment based on preset judgment logic; Step 8: After receiving the adjustment instruction, the strategy adjustment mechanism is triggered to preset the load status of each functional module and functional component under the future power supply task based on the predicted data.
9. The energy recovery method based on digital power supply according to claim 8, characterized in that: The fluctuation coefficient in step 5 reflects the discreteness of a certain project data, so as to reflect whether the prediction analysis model in step 6 triggers the operation behavior. The calculation formula of the fluctuation coefficient is: Where CV stands for coefficient of fluctuation, N stands for the number of data points in the project, and x i represents the value of the i-th data point, representing each observation in the project, Y represents the weighted average of the data, w i Represents the weight of the ith data point.
10. The energy recovery method based on digital power supply according to claim 9, characterized in that: The weighted average of the data represented by Y is calculated as follows:
Citation Information
Cited By
Resource recycling data processing method for low-tin-content material
CN120104070A
A data processing method for resource recovery of materials with low tin content
CN120104070B
