Series channel multi-pool scheduling algorithm based on distributed storage compensation algorithm

Abstract

The invention discloses a series channel multi-pool scheduling algorithm based on a distributed storage compensation algorithm. The series channel multi-pool scheduling algorithm comprises the following steps: S1, collecting data at each pool node of a series channel; s2, monitoring the operation state of each pool node in real time based on the distributed storage unit; s3, automatically calling historical distributed storage data of adjacent pool nodes after determining that the pool nodes fail, and extracting water level and flow characteristic data matched with the current time period; s4, obtaining a virtual water level and a flow value of the fault node; s5, replacing the real-time data of the fault pool node with the virtual interpolation compensation value obtained through calculation, and inputting the virtual interpolation compensation value into the overall scheduling model; and S6, optimizing and updating the virtual interpolation compensation parameter when the virtual interpolation compensation parameter needs to be called subsequently. According to the method, the virtual interpolation compensation algorithm is introduced when the node data is abnormal or missing, so that the continuity of the scheduling data is effectively guaranteed, and the interruption of the whole scheduling process caused by a single-point fault is avoided.

Description

Technical Field

[0001] This invention relates to the technical field of water conservancy scheduling, and in particular to a multi-pool scheduling algorithm for serial channels based on a distributed storage compensation algorithm. Background Technology

[0002] In large and medium-sized irrigation districts and water conservancy projects, a series-channel multi-pool scheduling model is often used to allocate and transport water. This type of model is usually based on real-time water level, flow rate and other parameters of the pools, combined with optimization algorithms or prediction methods, to dynamically regulate the water intake and release processes between the pools in order to meet the needs of agricultural irrigation, industrial water supply or ecological water replenishment.

[0003] However, most existing scheduling models rely on complete and continuous monitoring data as input, including water levels, flow rates, and water quality parameters of each reservoir. When a node fails (e.g., sensor damage, communication interruption, or abnormal data fluctuations), its real-time data becomes unavailable, leading to incomplete model input and interrupting the overall scheduling calculation. This ultimately affects the water supply efficiency and safety of the canal. In actual operation, scheduling failures caused by node failures are quite common. For example, during peak irrigation periods, if data from a node is lost, the water allocation for the entire canal cannot be accurately calculated, potentially causing water supply imbalances between upstream and downstream areas or even water waste. Existing technologies mainly remedy this through manual intervention or single-node redundancy, but these methods are often slow to react and cannot guarantee the continuity and accuracy of scheduling. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a serial channel multi-pool scheduling algorithm based on a distributed storage compensation algorithm, comprising the following steps: S1. Data is collected at each water pool node in the series channel, and the data is stored in a distributed storage unit to form distributed data segments corresponding to each water pool. S2. Based on the above distributed storage unit, the operating status of each water pool node is monitored in real time. When an abnormality is detected in the data acquisition or communication of a certain water pool node, it is determined that the node has failed. S3. After determining that a water tank node is faulty, the historical distributed storage data of adjacent water tank nodes of the faulty water tank node is automatically called to extract water level and flow characteristic data that match the current time period. S4. Based on the data of the adjacent nodes, perform virtual interpolation compensation calculation to obtain the virtual water level and flow rate values ​​of the faulty node; S5. Replace the real-time data of the faulty pool node with the virtual interpolation compensation value calculated above and input it into the overall scheduling model to maintain the continuity and stability of multi-pool scheduling in the series channel. S6. After the faulty water pool node recovers, its actual data is compared with the calculated compensation value, and the virtual interpolation compensation parameter is optimized and updated when it is needed to be called in the future, so as to optimize the virtual interpolation compensation calculation in the subsequent scheduling process.

[0006] As a preferred embodiment of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm described in this invention, the fault determination of the node specifically includes the following steps: S2.1 Receive and buffer the detection timestamp and measurement value from the edge controller; S2.2. Compare whether each water pool node uploads data within the preset disconnection threshold. If the disconnection threshold time is exceeded, it is determined to be a communication failure. S2.3. Perform range and rate of change checks on key data. If the data exceeds the feasible range, it is considered a fault. S2.4. By comparing the flow rate / water level relationship of adjacent water pool nodes, if the difference exceeds the threshold, it is determined that the node data is abnormal. S2.5 If any of the above fault conditions are met, then the node is marked as faulty.

[0007] As a preferred embodiment of the multi-pool scheduling algorithm for serial channels based on the distributed storage compensation algorithm described in this invention, the retrieval of historical distributed storage data of adjacent pool nodes specifically includes the following steps: S3.1. Determine the upstream and downstream water tank nodes of the faulty water tank node based on the topology diagram, and list the selected adjacent water tank nodes. S3.2, retrieve relevant data from the upstream and downstream water pool nodes from the distributed storage; S3.3 Prioritize calling real-time data to ensure the timeliness of compensation results. When real-time data is missing or abnormal, automatically call back historical data as a reference.

[0008] As a preferred embodiment of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm described in this invention, the virtual interpolation compensation calculation specifically includes the following steps: S4.1 Identify the faulty water tank nodes that need compensation; obtain data on adjacent water tank nodes; determine the compensation indicators, namely the flow rate and water level of the faulty water tank nodes; S4.2 Data processing: Preprocess the data of adjacent water tank nodes; S4.3. Perform weighted summation on the data of adjacent water tank nodes to obtain virtual interpolation compensation; S4.4 Output the obtained virtual interpolation compensation values.

[0009] As a preferred embodiment of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm described in this invention, the specific operation for updating the virtual interpolation compensation parameters is as follows: S6.1 Determine the fault type of the faulty water tank node. Fault types include communication faults and equipment faults. S6.2 If it is a communication failure, the real value cached during the failure period will be used to replace the virtual interpolation compensation. S6.3 If it is a equipment failure, after recovery, compare the actual value at the initial recovery stage with the virtual interpolation compensation to calculate the average deviation; S6.4 Store the replacement real value or the average deviation between the real value and the virtual interpolation compensation into the distributed storage unit.

[0010] As a preferred embodiment of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm described in this invention, the specific operation of replacing the virtual interpolation compensation with the cached real value during the fault period is as follows: S6.21, The faulty water pool node is restored and the stored local cache is sent back; S6.22. Align the cached data according to the original virtual interpolation compensation time sequence; S6.23 Replace all virtual interpolation compensation values ​​generated during the fault period with the real values ​​returned from the cache; S6.24. Write the replaced real value into the distributed storage.

[0011] As a preferred embodiment of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm described in this invention, the specific method for virtual interpolation compensation correction during the fault period is as follows: S6.31. Collect the first M valid samples after node recovery; S6.32. For the samples collected above, take the virtual interpolation compensation of the system at the same relative time and calculate the average deviation; S6.32. Store the above average deviation. If the data of the faulty pool node during the fault period is needed in subsequent scheduling, update the virtual interpolation compensation value for that period.

[0012] Secondly, the present invention provides a serial channel multi-pool scheduling system based on a distributed storage compensation algorithm, comprising: The field sensing unit is used to collect data such as water level, water flow, and gate status of each pool in real time, and temporarily store the collected results through a local caching mechanism. The output data is accompanied by a timestamp to ensure data consistency and traceability. The distributed time-series storage unit is used to store real-time and historical data of each water pool node, and supports fast querying by time window and node identifier; The fault detection and status management module determines whether a water tank node is in a faulty or unavailable state by monitoring the data latency and abnormal data range of the water tank node, and triggers the compensation process. The adjacent node data retrieval module retrieves real-time or historical data from adjacent water pools from distributed storage or edge cache according to the water pool topology when a water pool node fails, and completes preliminary time alignment. The virtual interpolation compensation engine generates compensation values ​​for faulty water tank nodes using a weighted average method based on adjacent water tank node data and historical data. Scheduling engine: Receives normal or compensation data and generates execution instructions for gates or pumps according to the scheduling model of a multi-pool series system; The learning and adaptive update module compares the actual value of the faulty node with the compensation value during the fault period after the faulty node is recovered, and automatically corrects the compensation parameters when necessary. The audit and operations management module records all compensation decisions and update processes, and supports operations monitoring and fault traceability. Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm described in the first aspect of the present invention.

[0013] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm described in the first aspect of the present invention.

[0014] The beneficial effects of this invention are: This invention introduces a virtual interpolation compensation algorithm when node data is abnormal or missing. It can automatically call real-time or historical data from adjacent nodes for interpolation compensation, effectively ensuring the continuity of scheduling data and avoiding interruption of the entire scheduling process due to a single point of failure.

[0015] This invention improves the overall scheduling accuracy by comparing the actual data with the compensation value after the faulty node is restored and adjusting the compensation parameters accordingly, thereby gradually improving the compensation accuracy in subsequent scheduling processes.

[0016] This invention utilizes an adjacent node data retrieval mechanism. Instead of simply determining a faulty node as invalid, it substitutes and calculates data from adjacent upstream and downstream nodes, thereby improving the system's fault tolerance and robustness and achieving the technical effect that local node failures do not affect the overall scheduling. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart of the serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm proposed in this invention; Figure 2 This is a flowchart illustrating the multi-pool scheduling algorithm for serial channels based on a distributed storage compensation algorithm proposed in this invention. Figure 3 This is a system architecture diagram of the serial channel multi-pool scheduling system based on the distributed storage compensation algorithm proposed in this invention. Detailed Implementation

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0020] Reference Figure 1-3 This invention provides a multi-pool scheduling algorithm for serial channels based on a distributed storage compensation algorithm, comprising the following steps: S1. Data is collected at each water tank node in the series channel and stored in a distributed storage unit to form distributed data segments corresponding to each water tank. The data collection specifically includes: water level data of each water tank (acquired through pressure level sensors, reflecting the water storage status of each water tank and serving as the basis for scheduling decisions), flow data (acquired through electromagnetic flowmeters, reflecting the water transport speed and flow capacity in the channel, used to calculate downstream inflow / outflow balance), and gate opening / pump operating status (acquired through angle encoders and motor current sensors, determining the water flow control methods). This provides a highly available, low-latency, and traceable time-series data foundation, ensuring that the distributed storage can still provide sufficient historical / adjacent data to support virtual interpolation compensation even in the event of a node failure. S2. Based on the above distributed storage unit, the operating status of each water pool node is monitored in real time. When an abnormality is detected in the data acquisition or communication of a certain water pool node, it is determined that the node has failed. The fault determination of a node specifically includes the following steps: S2.1 Receive and cache the detection timestamps and measurement values ​​from the edge controller; record the detection time and measurement values ​​of the controllers in each water tank node for subsequent fault detection; S2.2. Compare whether each water tank node has uploaded data within the preset disconnection threshold. If the disconnection threshold is exceeded, it is determined to be a communication failure. Record the last monitoring timestamp of the water tank node. The current time is , The threshold for loss of contact, if If the system fails to upload data for three consecutive times, it is determined that the communication is lost. This system can quickly identify network faults and trigger compensation calculations in a very short time, avoiding interruption of scheduling due to waiting for real-time data. For example: Water pool node A uploads water level data every 10 seconds. The system's loss threshold is set to 30 seconds. If water pool node A fails to upload data for three consecutive times, it is determined that water pool node A is in communication failure. S2.3. Perform range and rate of change checks on key data. If the data exceeds the feasible range, it is considered a fault. Set physical threshold ranges for the data uploaded by each water tank node. If n consecutive sampling points exceed the physical threshold range, it is considered a fault, such as water level. ,when Water level at any time Within the physical threshold range If it is normal, then it is normal. Water level at any time Exceeding its upper and lower limits, i.e. , If the value exceeds its upper and lower limits after n consecutive samplings, it is considered a fault; simultaneously, the rate of change of the continuous sampling values ​​of each water tank node is calculated, and if the rate of change exceeds the rate of change threshold, i.e. , The preset interval time, If the water level changes by more than 20cm within one minute, it is considered a fault. Error data is removed in advance to reduce the transmission of error data. At the same time, the calculation is simple, requiring only threshold comparison and simple difference operation to ensure real-time performance. S2.4. Compare the flow rate / water level relationship between adjacent water tank nodes. If the difference exceeds a threshold, the data of that node is determined to be abnormal. , Calculate the pool nodes exist outflow rate at any time With pool node exist Inflow at any time The difference , Theoretically, the water tank node The outflow rate is the water tank node. Inflow rate; when the difference between the two exceeds a preset threshold for a certain period of time. If this happens, one of the nodes may fail; at the same time, the water levels of adjacent pool nodes should be compared. If the fault persists for a certain period of time, it is considered a malfunction. for Time Pool Node water level, For water level transmission delay, Pool Node Water level before the water level transmission delay To allow for error; in a series channel system, the pool node Changes in the water level of the upstream pool will experience a certain hydraulic transmission delay. Subsequently, this is reflected in the downstream water tank node. At the water level, therefore under normal circumstances and It has a strong correlation. Due to disturbances such as evaporation, leakage, and measurement errors, the water level will not be completely consistent. Therefore, by setting an allowable error, misjudgment can be avoided. When the difference between the two values ​​is consistently greater than the allowable error, it indicates that the water level transmission relationship between the two nodes has been disrupted. It can quickly identify sensor anomalies at a single node to avoid isolated node errors. S2.5 If any of the above fault conditions are met, then the node is marked as faulty; By employing a three-step method of communication detection, numerical rationality verification, and consistency comparison with neighboring nodes, we can quickly determine node failures with low computational complexity. This avoids over-reliance on complex algorithms, meets the real-time and stability requirements of the scheduling system, and provides a reliable triggering mechanism for subsequent compensation calculations. S3. After determining that a water tank node is faulty, the historical distributed storage data of adjacent water tank nodes of the faulty water tank node is automatically called to extract water level and flow characteristic data that match the current time period. The specific steps for retrieving historical distributed storage data from adjacent water tank nodes are as follows: S3.1. Based on the topology diagram, determine the upstream and downstream water tank nodes of the faulty water tank node, and list the selected adjacent water tank nodes. ; In the system's topology table, query the direct upstream and downstream water tank nodes of the faulty water tank node (preferably the two directly connected nodes). If any adjacent water tank node does not exist or its data is unavailable, expand to the two nearest available connected water tank nodes based on the nearest hydraulic distance or the two nearest online water tank nodes within the same segment, and record the list of selected adjacent water tank nodes and their node types; ensure that the object being called is hydraulically most relevant, prioritize the use of data from directly connected nodes to improve the representativeness of the estimation, and automatically expand if there are insufficient direct neighbors to maintain the redundancy and robustness of the compensation input; S3.2, retrieve relevant data from the upstream and downstream water pool nodes from the distributed storage; for each selected adjacent water pool node... Construct a dataset including real-time data: traffic. Water level timestamp Add M additional historical data sampling points: , M, The sampling interval is used to predict the failure of water tank nodes using real-time data. S3.3 Prioritize the use of real-time data to ensure the timeliness of compensation results. When real-time data is missing or abnormal, historical data is automatically recalled as a reference. First, real-time data is read from the edge cache to reduce latency. When the cache is unavailable, it falls back to retrieve data from distributed storage. At the same time, a quick pre-check is performed on the data to check whether its timestamp is within the allowed time window. All retrieved data is aligned by time (using its timestamp). By combining real-time data with historical data, subsequent compensation becomes more stable and reliable. S4. Perform virtual interpolation compensation calculation based on adjacent node data to obtain the virtual water level and flow rate values ​​of the faulty node; The virtual interpolation compensation calculation specifically includes the following steps: S4.1 Identify the faulty water tank nodes that need compensation; obtain data on adjacent water tank nodes; determine the compensation indicators, namely the flow rate and water level of the faulty water tank nodes; S4.2 Data Processing: Preprocess the data from adjacent water tank nodes to identify any abnormal data in the real-time data (the judgment method for abnormal data is the same as in S2.3, determining whether it exceeds its physical threshold range) and missing data. If the real-time data is abnormal or missing, query the historical data of adjacent water tank nodes in the distributed storage. Weighted average processing of historical data , ,in Historical data weights (which can be set based on their proximity to the current time, with weights increasing closer to the current time) are illustrated in the following example: If water tank node 2 fails, real-time data for upstream water tank node 1 is missing, but data for downstream water tank node 3 is available, the three most recent sampling points for upstream water tank node 1 will be used. {2.4,2.5,2.3}m 3 / s, set weight {0.5, 0.3, 0.2}, weighted average m 3 / s; Combining historical and real-time data ensures the continuity and rationality of compensation, while avoiding scheduling stagnation due to data loss. S4.3. Perform a weighted summation of the data from adjacent water tank nodes to obtain virtual interpolation compensation; the specific calculation method is as follows: , ,in: , These are weighting coefficients, which can be set based on actual water conservancy models or experience; they reflect the differences in influence between upstream and downstream areas through weighting, thereby improving the accuracy of compensation. S4.4 Output the obtained virtual interpolation compensation values, and calculate the results. , The data is stored in the system and marked as "compensation data" for subsequent scheduling algorithms to continue water allocation and pump control; this ensures the continuity of scheduling and avoids the interruption of the entire series channel scheduling due to faulty nodes. The compensation data can be seamlessly connected with the actual water tank node data, which facilitates the fusion and monitoring of subsequent data. The virtual interpolation compensation calculation described above can generate virtual data of fault nodes simply and quickly, ensuring scheduling continuity. At the same time, weighting coefficients can be set as needed to improve simulation accuracy and flexibly adapt to different channel conditions. This avoids complex modeling and calculation, ensuring feasibility and system robustness. S5. Replace the real-time data of the faulty pool node with the virtual interpolation compensation value calculated above and input it into the overall scheduling model to maintain the continuity and stability of multi-pool scheduling in the series channel. S6. After the faulty water pool node recovers, its actual data is compared with the calculated compensation value, and the virtual interpolation compensation parameter is optimized and updated when it is needed to be called in the future, so as to optimize the virtual interpolation compensation calculation in the subsequent scheduling process. The specific steps for updating the virtual interpolation compensation parameters are as follows: S6.1 Determine the fault type of the faulty water tank node. Fault types include communication faults and equipment faults. Determine the fault type and adopt different update methods according to different fault types. Read the equipment cache in the faulty node to identify whether there is cached data during the fault period and whether the data is within a reasonable range. If so, it is a communication fault. If there is no data or a certain amount of data is not within a reasonable range, it is an equipment fault. S6.2 If it is a communication failure, the cached real value during the failure period will replace the virtual interpolation compensation; the real measurement value is better than any estimated value, and the virtual interpolation compensation will be restored to the real observation value, which improves the accuracy of future virtual interpolation compensation calculations; The specific steps for replacing the virtual interpolation compensation with the cached real value during a fault are as follows: S6.21. The faulty water pool node is restored and the stored local cache (timestamp and measurement value) is sent back. S6.22. Align the cached data according to the original virtual interpolation compensation time sequence; S6.23 Replace all virtual interpolation compensation values ​​generated during the fault period with the real values ​​returned from the cache; S6.24. Write the replaced real value into the distributed storage; The actual measured value is better than any estimated value. Direct write-back can correct the basic data of historical records and statistical models, restore the historical data to the actual observed value, facilitate subsequent analysis, and is simple to implement. S6.3 If it is a equipment failure, after recovery, the actual value at the initial recovery stage is compared with the virtual interpolation compensation to calculate the average deviation; the average deviation between the actual data after recovery and the virtual interpolation compensation is calculated to ensure the accuracy of future virtual interpolation compensation calculations. The specific method for virtual interpolation compensation correction during the fault period is as follows: S6.31. After node recovery, collect the first M valid samples. The sample size must be within a tolerable range, and the data used must be authentic and accurate, not just noise or jitter. S6.32. For the samples collected above, take the virtual interpolation compensation of the system at the same relative time. (Obtained according to steps S3 and S4 above). To calculate the virtual interpolation compensation value at the time point corresponding to the valid sample in S6.31 above, based on the virtual interpolation compensation calculation, and to calculate the average deviation, the details are as follows: The systematic bias of the pool nodes was estimated using the restored real samples in a representative manner. S6.32. Store the above average deviation. If the data of the faulty pool node during the fault period is needed in subsequent scheduling, update the virtual interpolation compensation value for that period, as follows: ;in: This is the virtual interpolation compensation value for the flow rate of the faulty water tank node after the fault period. This is the virtual interpolation compensation value for the flow rate of the faulty water tank node during the fault period; For learning rate, ,permanent =0.5, used to control the update magnitude; it is not directly written to the history record, but only updated when the data of this time period is needed in the future, to avoid tampering with the history record based on a few recovered samples, and at the same time, it can be updated when the data is needed, thus ensuring the accuracy of future compensation; Example as follows: During the failure of node 1 in the faulty water tank, there was no buffering. After recovery, M=3 flow samples were collected {3.1, 3.05, 3.12}, and the corresponding virtual interpolation compensation was {2.9, 2.95, 2.92}. The calculated values ​​were... =0.1667, and If the value is 0.5, then when retrieving historical data from the period of failure, the virtual interpolation compensation needs to be increased by 0.5 × 0.1667 = 0.0833m. 3 / s; S6.4 Store the replacement real value or the average deviation between the real value and the virtual interpolation compensation into the distributed storage unit.

[0021] This embodiment also provides a serial channel multi-pool scheduling system based on a distributed storage compensation algorithm, including: The field sensing unit is used to collect data such as water level, flow rate, and gate status of each pool in real time, and temporarily stores the collected results through a local caching mechanism. The output data is accompanied by a timestamp to ensure data consistency and traceability; this ensures the real-time and completeness of hydrological information and provides an accurate basis for subsequent scheduling and compensation calculations. The distributed time-series storage unit is used to store real-time and historical data of each water pool node, and supports fast querying by time window and node identifier; it ensures the traceability of historical data and facilitates the use of data from adjacent water pools for compensation when a water pool node fails. The fault detection and status management module monitors the data latency and abnormal data range of the water tank nodes to determine whether a water tank node is in a faulty or unavailable state and triggers the compensation process; it achieves efficient and simplified fault identification and avoids redundant compensation caused by misjudgment. The adjacent node data retrieval module retrieves real-time or historical data from adjacent water pools from distributed storage or edge cache according to the water pool topology when a water pool node fails, and performs preliminary time alignment; ensuring the reliability and integrity of the data source required for compensation calculation. The virtual interpolation compensation engine generates compensation values ​​for faulty water pool nodes using a weighted average method based on data from adjacent water pool nodes and historical data; this ensures the continuity of the scheduling process and avoids system instability caused by data interruption. The scheduling engine receives normal or compensation data and generates execution instructions for gates or pumps according to the scheduling model of the multi-pool series system; ensuring that the scheduling process can continue to operate according to the preset goals even during a fault. The learning and adaptive update module compares the actual value of a faulty node with the compensation value during the fault period after the fault node recovers, and automatically corrects the compensation parameters when necessary; it gradually optimizes the accuracy of the compensation algorithm and improves the system's self-healing capability. The audit and operation and maintenance management module records all compensation decisions and update processes, supports operation and maintenance monitoring and fault traceability, and improves the system's traceability and operation and maintenance efficiency.

[0022] This embodiment also provides a computer device applicable to the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm proposed in the above embodiment.

[0023] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0024] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0025] In summary, this invention introduces a virtual interpolation compensation algorithm when node data is abnormal or missing. This algorithm automatically calls real-time or historical data from adjacent nodes for interpolation compensation, effectively ensuring the continuity of scheduling data and preventing interruptions in the entire scheduling process due to single-point failures. Furthermore, after a faulty node recovers, this invention compares its actual data with the compensation value and adjusts the compensation parameters accordingly, gradually improving the compensation accuracy in subsequent scheduling processes and thus enhancing the overall scheduling accuracy.

[0026] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm, characterized in that: Includes the following steps: S1. Data is collected at each water pool node in the series channel, and the data is stored in a distributed storage unit to form distributed data segments corresponding to each water pool. S2. Based on the above distributed storage unit, the operating status of each water pool node is monitored in real time. When an abnormality is detected in the data acquisition or communication of a certain water pool node, it is determined that the node has failed. S3. After determining that a water tank node is faulty, the historical distributed storage data of adjacent water tank nodes of the faulty water tank node is automatically called to extract water level and flow characteristic data that match the current time period. S4. Based on the data of the adjacent nodes, perform virtual interpolation compensation calculation to obtain the virtual water level and flow rate values ​​of the faulty node; S5. Replace the real-time data of the faulty pool node with the virtual interpolation compensation value calculated above and input it into the overall scheduling model to maintain the continuity and stability of multi-pool scheduling in the series channel. S6. After the faulty water pool node recovers, its actual data is compared with the calculated compensation value, and the virtual interpolation compensation parameter is optimized and updated when it is needed to be called in the future, so as to optimize the virtual interpolation compensation calculation in the subsequent scheduling process.

2. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 1, characterized in that: The fault determination of the node specifically includes the following steps: S2.1 Receive and buffer the detection timestamp and measurement value from the edge controller; S2.

2. Compare whether each water pool node uploads data within the preset disconnection threshold. If the disconnection threshold time is exceeded, it is determined to be a communication failure. S2.

3. Perform range and rate of change checks on key data. If the data exceeds the feasible range, it is considered a fault. S2.

4. By comparing the flow rate / water level relationship of adjacent water pool nodes, if the difference exceeds the threshold, it is determined that the node data is abnormal. S2.5 If any of the above fault conditions are met, then the node is marked as faulty.

3. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 2, characterized in that: The retrieval of historical distributed storage data from adjacent water tank nodes specifically includes the following steps: S3.

1. Determine the upstream and downstream water tank nodes of the faulty water tank node based on the topology diagram, and list the selected adjacent water tank nodes. S3.2, retrieve relevant data from the upstream and downstream water pool nodes from the distributed storage; S3.3 Prioritize calling real-time data to ensure the timeliness of compensation results. When real-time data is missing or abnormal, automatically call back historical data as a reference.

4. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 3, characterized in that: The virtual interpolation compensation calculation specifically includes the following steps: S4.1 Identify the faulty water tank nodes that need compensation; obtain data on adjacent water tank nodes; determine the compensation indicators, namely the flow rate and water level of the faulty water tank nodes; S4.2 Data processing: Preprocess the data of adjacent water tank nodes; S4.

3. Perform weighted summation on the data of adjacent water tank nodes to obtain virtual interpolation compensation; S4.4 Output the obtained virtual interpolation compensation values.

5. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 1, characterized in that: The specific steps for updating the virtual interpolation compensation parameters are as follows: S6.1 Determine the fault type of the faulty water tank node. Fault types include communication faults and equipment faults. S6.2 If it is a communication failure, the real value cached during the failure period will be used to replace the virtual interpolation compensation. S6.3 If it is a equipment failure, after recovery, compare the actual value at the initial recovery stage with the virtual interpolation compensation to calculate the average deviation; S6.4 Store the replacement real value or the average deviation between the real value and the virtual interpolation compensation into the distributed storage unit.

6. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 5, characterized in that: The specific steps for replacing the virtual interpolation compensation with the cached real value during the fault period are as follows: S6.21, The faulty water pool node is restored and the stored local cache is sent back; S6.

22. Align the cached data according to the original virtual interpolation compensation time sequence; S6.23 Replace all virtual interpolation compensation values ​​generated during the fault period with the real values ​​returned from the cache; S6.

24. Write the replaced real value into the distributed storage.

7. The serial channel multi-pool scheduling algorithm based on distributed storage compensation algorithm according to claim 6, characterized in that: The specific method for virtual interpolation compensation correction during the fault period is as follows: S6.

31. Collect the first M valid samples after node recovery; S6.

32. For the samples collected above, take the virtual interpolation compensation of the system at the same relative time and calculate the average deviation; S6.

32. Store the above average deviation. If the data of the faulty pool node during the fault period is needed in subsequent scheduling, update the virtual interpolation compensation value for that period.

8. A serial channel multi-pool scheduling system based on a distributed storage compensation algorithm according to any one of claims 1-7, characterized in that: include: The field sensing unit is used to collect the water level, water flow and gate status of each pool in real time, and temporarily store the collection results through a local caching mechanism. The output data is accompanied by a timestamp to ensure data consistency and traceability. The distributed time-series storage unit is used to store real-time and historical data of each water pool node, and supports fast querying by time window and node identifier; The fault detection and status management module determines whether a water tank node is in a faulty or unavailable state by monitoring the data latency and abnormal data range of the water tank node, and triggers the compensation process. The adjacent node data retrieval module retrieves real-time or historical data from adjacent water pools from distributed storage or edge cache according to the water pool topology when a water pool node fails, and completes preliminary time alignment. The virtual interpolation compensation engine generates compensation values ​​for faulty water tank nodes using a weighted average method based on adjacent water tank node data and historical data. The scheduling engine receives normal or compensation data and generates execution instructions for gates or pumps according to the scheduling model of the multi-pool series system. The learning and adaptive update module compares the actual value of the faulty node with the compensation value during the fault period after the faulty node is recovered, and automatically corrects the compensation parameters when necessary. The audit and operations management module records all compensation decisions and update processes, and supports operations monitoring and fault traceability.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the serial channel multi-pool scheduling algorithm based on the distributed storage compensation algorithm as described in any one of claims 1-7.

Images