Elevator operation scheduling method and system based on energy storage module and computer equipment

Abstract

The invention relates to an elevator operation scheduling method and system based on an energy storage module and computer equipment. The method comprises the steps that a server obtains electricity price information and receives elevator operation data sent by a terminal; the electricity price information comprises peak and valley time periods and corresponding electricity prices, inputting the current electricity price information and the current elevator operation data into the trained elevator load prediction model under the condition that the integrity verification of the elevator operation data is passed, obtaining an elevator energy-saving strategy of the current period, and sending the elevator energy-saving strategy to a terminal, and the terminal controls the elevator module to operate according to the elevator energy-saving strategy. By adopting the method, the operation cost of the elevator system can be reduced.

Description

Technical Field

[0001] This application relates to the field of elevator energy-saving technology, and in particular to an elevator operation scheduling method, system and computer equipment based on an energy storage module. Background Technology

[0002] As the number of elevators in buildings increases, the energy consumption of elevator operation accounts for a continuously rising proportion of the building's total energy consumption. Traditional elevators mostly rely on direct grid power supply, and when the grid's peak electricity price is reached, elevator operating costs increase significantly. Furthermore, elevators generate regenerative energy during braking, heavy-load descent, or light-load ascent, but most current systems either directly feed this energy back to the grid or dissipate it as heat, failing to effectively recover and utilize it.

[0003] Traditional technologies utilize battery modules (i.e., energy storage units) for the recovery of regenerative energy and partial power supply in elevators. However, peak and off-peak electricity prices vary across different provinces and regions, and even within the same region, they differ across months and years. Each change in peak and off-peak electricity prices necessitates local adjustments to the time periods, increasing maintenance costs and resource waste. Furthermore, while the daily peak load and frequency of elevator operation exhibit clear patterns, traditional methods cannot predict these based on real-time trends and historical data. This can lead to insufficient battery capacity during peak electricity price periods, forcing the use of higher-priced grid electricity. Summary of the Invention

[0004] Therefore, it is necessary to provide an elevator operation scheduling method, system, and computer equipment based on an energy storage module for energy storage elevators that can reduce the operating costs of elevator systems, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides an elevator operation scheduling method based on an energy storage module, including:

[0006] It acquires electricity price information and receives elevator operation data sent by the terminal; the electricity price information includes peak and off-peak periods and corresponding electricity prices; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters;

[0007] After the integrity verification of the elevator operation data is passed, the current electricity price information and the current elevator operation data are input into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes the elevator operation strategy for the preset time period after the current moment;

[0008] Send elevator energy-saving strategies to the terminal so that the terminal controls the operation of the elevator module according to the elevator energy-saving strategies.

[0009] In one embodiment, the training process of the elevator load prediction model includes:

[0010] Based on historical electricity price information and historical operation data, historical sample sequences are obtained, and anomaly processing and completion processing are performed on the historical sample sequences to obtain historical training sequences.

[0011] The historical training sequence is divided into multiple time windows according to the preset step size;

[0012] Construct an elevator load prediction model;

[0013] With minimizing the error of the predicted power curve as the optimization objective, the elevator load prediction model is trained sequentially using historical training sequences within the current time window until the training stops when the stopping condition is met. The trained elevator load prediction model is then validated using test set data.

[0014] In one embodiment, the elevator energy-saving strategy carries a strategy identifier; the method further includes:

[0015] The receiving terminal sends a consistency verification request; the consistency verification request carries an identifier to be verified.

[0016] If the identifier to be verified matches the policy identifier, a consistency success flag is returned to the terminal.

[0017] If the identifier to be verified does not match the policy identifier and there is no elevator energy-saving policy at present, send an incomplete flag to the terminal.

[0018] If the identifier to be verified is inconsistent with the policy identifier, and an elevator energy-saving policy exists, the elevator energy-saving policy at the current moment will be sent to the terminal.

[0019] Secondly, this application also provides an elevator operation scheduling method based on an energy storage module, including:

[0020] When the server is online, elevator operation data is sent to the server; the elevator operation data includes the total power of the elevator module, the elevator operation status, the elevator load, and the energy storage battery parameters.

[0021] The system receives elevator energy-saving strategies from the server and controls the operation of the elevator modules according to these strategies. The elevator energy-saving strategies include elevator operation strategies for a preset time period after the current moment.

[0022] When the server is offline, the elevator module operation is controlled based on the preset operation strategy and the elevator energy-saving strategy stored locally.

[0023] In one embodiment, the steps of controlling the operation of the elevator module based on a preset operating strategy and a locally stored elevator energy-saving strategy include:

[0024] If the locally stored elevator energy-saving strategy is verified based on the energy storage battery parameters, the elevator module is controlled to operate according to the locally stored elevator energy-saving strategy.

[0025] If the verification of the locally stored elevator energy-saving strategy fails or there is no locally stored elevator energy-saving strategy, the elevator module will be controlled to operate according to the preset operation strategy.

[0026] In one embodiment, the step of controlling the elevator module to operate according to a preset operating strategy includes:

[0027] If a time-sharing strategy exists locally, or if a time-sharing strategy is received from the server, the runtime segment corresponding to the current time is determined according to the time-sharing strategy.

[0028] If there is no time-sharing strategy on the local machine and no time-sharing strategy has been received from the server, the runtime segment corresponding to the current time is determined according to the preset time-sharing strategy.

[0029] The elevator module operation is controlled according to the energy-saving strategy corresponding to the operating period.

[0030] In one embodiment, the method further includes:

[0031] Send a consistency verification request to the server; the consistency verification request carries an identifier to be verified;

[0032] Upon receiving a consistency success flag from the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy.

[0033] Upon receiving an incomplete flag from the server, the elevator module is controlled to operate according to the preset operating strategy.

[0034] Upon receiving the elevator energy-saving strategy for the current moment from the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy.

[0035] In one embodiment, the method further includes:

[0036] During the process of controlling the operation of the elevator module in accordance with the elevator energy-saving strategy, the current charging power is obtained;

[0037] If the rationality verification of the elevator energy-saving strategy based on the current charging power fails, or if a power outage signal is received, the process of controlling the elevator module to operate according to the elevator energy-saving strategy will be stopped.

[0038] Thirdly, this application also provides an elevator operation scheduling system based on an energy storage module, including:

[0039] Elevator module;

[0040] An energy storage module, including an energy storage battery, is used to provide the electrical energy required for the operation of the elevator module and to receive the regenerated electrical energy generated by the elevator module.

[0041] The server is used to obtain electricity price information and receive elevator operation data sent by the terminal. The electricity price information includes peak and off-peak periods and corresponding electricity prices. The elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters. It is also used to input the current electricity price information and the current elevator operation data into the trained elevator load prediction model after the integrity verification of the elevator operation data passes, so as to obtain the elevator energy-saving strategy for the current period. The elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current moment. It is also used to send the elevator energy-saving strategy to the terminal.

[0042] The terminal is used to send elevator operation data to the server when the server is online; it is also used to receive elevator energy-saving strategies sent by the server and control the operation of the elevator module according to the elevator energy-saving strategies; and it is also used to control the operation of the elevator module based on the preset operation strategy and the locally stored elevator energy-saving strategy when the server is offline.

[0043] Fourthly, this application also provides an elevator operation scheduling device based on an energy storage module, comprising:

[0044] The data receiving module acquires electricity price information and receives elevator operation data sent by the terminal. The electricity price information includes peak and off-peak hours and corresponding electricity prices. The elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters.

[0045] The strategy generation module is used to input the current electricity price information and the current elevator operation data into the trained elevator load prediction model after the integrity verification of the elevator operation data has passed, so as to obtain the elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes the elevator operation strategy for the preset time period after the current moment;

[0046] The strategy delivery module is used to send elevator energy-saving strategies to the terminal, so that the terminal can control the operation of the elevator module according to the elevator energy-saving strategy.

[0047] Fifthly, this application also provides an elevator operation scheduling device based on an energy storage module, comprising:

[0048] The data transmission module is used to send elevator operation data to the server when the server is online. The elevator operation data includes the total power of the elevator module, the elevator operation status, the elevator load, and the energy storage battery parameters.

[0049] The strategy receiving module is used to receive elevator energy-saving strategies sent by the server and control the operation of the elevator module according to the elevator energy-saving strategies; the elevator energy-saving strategies include the elevator operation strategies for a preset time period after the current time.

[0050] The operation scheduling module is used to control the operation of elevator modules based on preset operation strategies and locally stored elevator energy-saving strategies when the server is offline.

[0051] In a sixth aspect, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of either the first aspect or the second aspect.

[0052] In a seventh aspect, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps of either the first or second aspect.

[0053] Eighthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps of either the first or second aspect.

[0054] The aforementioned elevator operation scheduling method, system, and computer equipment based on energy storage modules involve a server that acquires electricity price information and receives elevator operation data sent by the terminal. After verifying the integrity of the elevator operation data, the server inputs the current electricity price information and the current elevator operation data into a trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period. This strategy is then sent to the terminal, enabling the terminal to control the elevator module operation according to the energy-saving strategy. This reduces the consumption of high-priced mains electricity, recovers regenerative energy during elevator braking and heavy-load descent, avoids energy dissipation as heat, reduces energy waste, adapts to electricity price changes in different regions and time periods, reduces maintenance costs, and balances the power supply ratio between the mains and the energy storage module through strategic control, reducing peak load pressure on the power grid and improving the energy utilization efficiency of the elevator system. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is an application environment diagram of an elevator operation scheduling method based on an energy storage module in one embodiment;

[0057] Figure 2 This is one of the flowcharts illustrating an elevator operation scheduling method based on an energy storage module in one embodiment;

[0058] Figure 3 This is a second flowchart illustrating an elevator operation scheduling method based on an energy storage module in one embodiment;

[0059] Figure 4 This is a flowchart illustrating an elevator operation scheduling method based on an energy storage module in another embodiment;

[0060] Figure 5 This is one of the structural block diagrams of an elevator operation scheduling device based on an energy storage module in one embodiment;

[0061] Figure 6 This is a second structural block diagram of an elevator operation scheduling device based on an energy storage module in one embodiment;

[0062] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0064] This application provides an elevator operation scheduling system based on an energy storage module, such as... Figure 1 As shown, the system includes: an elevator module 100, an energy storage module 200, a server 300, and a terminal 400. The energy storage module 200 includes an energy storage battery to provide the elevator module 100 with the electrical energy required for operation and to receive regenerated electrical energy generated by the elevator module 100. The server 300 is used to obtain electricity price information and receive elevator operation data sent by the terminal 400. After verifying the integrity of the elevator operation data, it inputs the current electricity price information and the current elevator operation data into a trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period and sends the elevator energy-saving strategy to the terminal 400. The terminal 400, when the server 300 is online, sends elevator operation data to the server 300, receives the elevator energy-saving strategy sent by the server 300, and controls the operation of the elevator module 100 according to the elevator energy-saving strategy. When the server 300 is offline, it controls the operation of the elevator module 100 based on a preset operation strategy and a locally stored elevator energy-saving strategy.

[0065] The energy storage module 200, consisting of an energy storage battery, a high-voltage circuit control module, and a battery management system (BMS), is the energy carrier of the entire system. It provides backup power for elevator operation and receives regenerative energy generated during braking, heavy-load descent, or light-load ascent. The energy storage battery comprises multiple series-parallel power cells, providing system-level DC energy storage capability, supporting charging, discharging, and regenerative energy recovery. Output power and capacity are uniformly scheduled by the BMS and energy management system. The high-voltage circuit control module includes key components such as high-voltage contactors, pre-charge circuits, fuses, and isolation devices. It is responsible for ensuring safe connection, pre-charge, and disconnection control between the battery pack and the power supply switching unit, and provides functions such as high-voltage insulation detection, short-circuit protection, and overcurrent protection. The battery management system (BMS) monitors individual battery cell voltage, temperature, SOC, and SOH, assesses the battery's available capacity, maximum charging power, and maximum discharging power in real time, and coordinates the execution of charge / discharge limits, equalization control, and safety strategies (overvoltage, undervoltage, overtemperature, short circuit, etc.).

[0066] Server 300, located on a remote server or cloud platform, is responsible for advanced intelligent strategy generation, model training, and system operation and maintenance. It includes a data management and analysis module, an AI model training module, a strategy optimization and push module, and a remote monitoring and operation and maintenance module. The data management and analysis module receives massive amounts of operational data from various sites and performs data cleaning, aggregation, and statistical analysis, forming the foundation for AI model training and strategy optimization. The AI ​​model training module can train and update elevator load prediction models, elevator energy consumption prediction models, elevator regenerative energy prediction models, and SOH inference models. The strategy optimization and push module generates optimal strategies based on prediction results and electricity price information and pushes them to the terminal, which then further refines the execution based on local real-time conditions. The remote monitoring and operation and maintenance module can monitor elevator energy consumption, battery health, and real-time battery information online; it can calculate revenue; provide fault alarms and predictive maintenance; support OTA (Over-The-Air) upgrades; and perform remote parameter tuning and strategy updates.

[0067] The terminal 400 includes a data acquisition unit, a control and protection unit, a model terminal processing unit, and a remote communication unit. The data acquisition unit collects key parameters and real-time data. Key parameters include the counterweight weight of each elevator, the rated capacity and rated total voltage of the battery modules, and real-time data divided into model data and display data. Model data includes the real-time total power of the elevator system, the current operating status of each elevator (up, down, standby, stopped), the real-time load of each elevator, the charging and discharging power, SOC, SOH, operating status (charging, discharging, standby, hibernation, stopped) of the battery modules, the maximum allowable charging and discharging power, allowable charging and discharging signals, and emergency stop commands (instructions to activate system safety protection in case of events such as battery fire or overheating that could affect the safety of the entire elevator system). Display data includes individual battery voltage, temperature, equalization information, battery management system fault information, protection thresholds, elevator operating current, and other detailed information and adjustment parameters; this data is not used in the model algorithm. The data acquisition unit obtains necessary data from the battery management system, elevator central system, or individual elevator data systems, elevator system main incoming power meter, and battery module incoming power meter via wired connections using CAN bus, RS485, UART, or industrial Ethernet. The control and protection unit is responsible for the actual control of relays, circuit breakers, and other switching components in the power supply switching unit, performing energy switching, scheduling, and protection. It controls the elevator to use mains power, battery power, or switch to regenerative energy recovery mode. The unit has millisecond-level response capability, providing fast and safe energy scheduling for the elevator.

[0068] The model terminal processing unit is used to execute AI models, prediction models, or rule-based strategies locally, including local strategies, offline self-processing software strategies, and online cloud-based collaborative software strategies. Local strategies are used for local control and protection. For example, upon receiving an emergency stop command from the battery management system, it stops executing model strategies, directly controls the switch protection, and broadcasts the emergency stop event. In the event of a mains power outage, it switches to battery power and waits for the elevator to automatically execute its emergency function, leveling and releasing passengers. Offline self-processing software strategies are used to independently complete energy consumption strategies and battery module charging / discharging strategies for short periods (30 minutes to 24 hours) of the elevator system, as well as the inherent charging mode during off-peak hours without prediction algorithms, when there is no network or cloud access. This ensures energy-saving operation and power supply safety even offline. Online cloud-based collaborative strategies are used when the network and cloud interaction are normal. They receive, dynamically update, and execute 24-hour prediction and optimization strategies issued by the cloud, execute cloud scheduling instructions and configurations, and upload locally collected data to the cloud in real time for model training, updates, and display. Through local and cloud collaboration, the system possesses both immediate responsiveness and long-term optimization capabilities.

[0069] The remote communication unit enables data interaction between local devices and cloud servers. It can use various communication media, including but not limited to wired Ethernet connecting to building LANs or industrial control networks via physical interfaces such as RJ45; cellular mobile communication networks (such as 4G LTE, 5G NR, NB-IoT) enabling remote wireless connections via carrier networks and using built-in SIM card slots / eSIMs; low-power wireless methods connecting to building LANs via WiFi, Bluetooth, and Sub-GHz; and satellite communication methods specifically designed for remote and isolated areas using Starlink. It supports multiple industrial and internet communication protocols, such as UDP, Modbus TCP, MQTT, HTTPS / REST API, and CoAP. Communication protocols can be automatically switched or combined on demand based on the media to adapt to the reliability and bandwidth conditions of different network environments.

[0070] To ensure the privacy and integrity of elevator system data, the remote communication unit has the following security functions: (1) Transmission encryption: Supports TLS / SSL encryption for protocols such as MQTT and HTTPS, and supports symmetric / asymmetric hybrid encryption methods. (2) Identity authentication: Implements device authentication through device certificates, tokens, or key files, and supports cloud authorization mechanisms and access control. (3) Data integrity verification: Uses hash algorithms to verify messages to prevent tampering. (4) Security isolation and protection: Supports port access restrictions, firewall policies, and illegal access detection. Communication involving sensitive parameters adopts encrypted storage and secondary verification.

[0071] In addition, the elevator operation scheduling system also includes a mains power module 500 and a power supply switching module 600. The mains power module 500 provides basic power to the elevator module 100, serving as the default power source, and also provides charging power to the energy storage battery. Combined with the EMS strategy, it can charge during off-peak electricity periods and reduce mains power usage during peak periods, achieving energy saving and peak regulation. The power supply switching module 600 is the energy exchange hub between the elevator module 100, the mains power module 500, and the energy storage module 200. It automatically switches between mains power and battery power, feeding back the regenerative braking energy generated during elevator operation to the energy storage module 200. It features anti-backflow, anti-islanding, safety isolation, and status monitoring functions, receives terminal control commands, and achieves millisecond-level switching to ensure the continuous operation of the elevator module 100.

[0072] In one exemplary embodiment, such as Figure 2 As shown, an elevator operation scheduling method based on an energy storage module is provided, which can be applied to... Figure 1 Taking server 300 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0073] S202: Obtain electricity price information and receive elevator operation data sent by the terminal; the electricity price information includes peak and off-peak periods and corresponding electricity prices; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters.

[0074] Optionally, peak and off-peak hours and electricity prices can be manually queried or automatically obtained via API in the cloud, entered into the server system, and pushed to all terminal devices in the same region. The cloud service can obtain electricity prices through the time-of-use price query API and update them regularly. For regions where the API cannot be used, electricity prices can be actively queried on the electricity price website, manually entered into the cloud service platform, and regularly checked for changes and updated. These time-of-use changes can be directly synchronized to all terminal devices in the region by the cloud service. On the other hand, the server continuously receives real-time data sent by local devices and extracts data for the model. This real-time data includes the total real-time power of the elevator system, the current operating status of each elevator (up, down, standby, stopped), the real-time load of each elevator, the charging and discharging power, SOC, SOH, operating status (charging, discharging, standby, hibernation, stopped), and maximum allowable charging and discharging power of the battery modules. In the initial stage of establishing a connection between the device and the cloud, data for at least one week needs to be collected as historical data for model training. Once the data collection is complete, the prediction model can be executed. Subsequently, the model optimizer's time-domain data is rolled over according to the T-cycle time (5-30 minutes), and the latest strategy generated by the model will be pushed to the local device.

[0075] S204: If the integrity verification of the elevator operation data passes, input the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes the elevator operation strategy for the preset time period after the current moment.

[0076] Optionally, after receiving elevator operation data from the terminal, the server determines whether the preprocessed data meets the integrity requirements of the AI ​​model's prediction. If not, the terminal continues to collect data and report it to the server. If the integrity verification of the elevator operation data passes, the server calls the trained elevator load prediction AI model, performs a prediction once every T-cycle time, and generates an elevator operation strategy for a future preset time period, such as an elevator energy-saving strategy for the next 24 hours, in conjunction with the peak and off-peak electricity prices of the power grid.

[0077] The elevator load prediction model is essentially a time-series prediction model (i.e., a machine learning model trained on historical data, such as LSTM, time-series attention model, etc.). The principle is to use the time-series patterns in historical electricity prices and historical operating data (such as peak load on weekday mornings) and combine them with real-time data to accurately predict elevator load changes and energy consumption demand in a future preset time period (such as within 1 hour) by minimizing the error of the prediction power curve. This will generate an adaptation strategy (such as energy storage charging during off-peak hours, prioritizing the use of energy storage power supply during peak hours, or recovering electrical energy to the energy storage module during braking).

[0078] S206: Send the elevator energy-saving strategy to the terminal so that the terminal controls the operation of the elevator module according to the elevator energy-saving strategy.

[0079] Optionally, after the elevator energy-saving strategy is generated, the energy-saving strategy (including operating time, power supply mode, power control parameters, etc.) is sent to the terminal via a specified communication protocol (such as TCP / IP). The terminal, as the execution unit, controls the elevator's power supply switching (such as switching between mains power and energy storage modules) and adjusts operating parameters (such as optimizing car scheduling during off-peak hours and reducing ineffective operating energy consumption) according to the strategy. Through a distributed architecture of server decision-making and terminal execution, the strategy is implemented in real time, ensuring accurate execution of scheduling instructions.

[0080] In the aforementioned elevator operation scheduling method based on energy storage modules, the server obtains electricity price information and receives elevator operation data sent by the terminal. After verifying the integrity of the elevator operation data, the server inputs the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period. The server then sends the elevator energy-saving strategy to the terminal so that the terminal can control the operation of the elevator module according to the elevator energy-saving strategy. This reduces the consumption of high-priced mains electricity, recovers regenerative energy during elevator braking and heavy-load descent, avoids energy dissipation in the form of heat, reduces energy waste, adapts to electricity price changes in different regions and at different times, reduces maintenance costs, and balances the power supply ratio between mains electricity and energy storage modules through strategic control, reducing peak load pressure on the power grid and improving the energy utilization efficiency of the elevator system.

[0081] In an exemplary embodiment, the training process of the elevator load prediction model includes: obtaining a historical sample sequence based on historical electricity price information and historical operating data; performing anomaly processing and completion processing on the historical sample sequence to obtain a historical training sequence; dividing the historical training sequence into multiple time windows according to a preset step size; constructing an elevator load prediction model; training the elevator load prediction model sequentially through the historical training sequence within the current time window with the optimization objective of minimizing the prediction power curve error, until the training stops when the stopping condition is met, and verifying the trained elevator load prediction model using test set data.

[0082] Optionally, historical sample sequences are the core data foundation for model learning. They must include both historical electricity price information (peak and off-peak periods, price fluctuations) and historical operational data (total power, load, battery parameters, etc.) to ensure the model can correlate electricity price characteristics with elevator operational characteristics. During the data processing, all raw data is first cleaned, such as removing outliers and imputing broken or missing values. Then, it is aligned chronologically so that the "elevator group status, battery status, and load behavior" at each moment constitute a complete set of input information. Subsequently, the model divides this continuous data into multiple sliding time windows, allowing the model to use past operational status to predict future energy consumption changes. For example, using one week's worth of multi-elevator operational data as input allows the model to learn how to predict power demand and load changes over the next 24 hours.

[0083] Optionally, for the model structure, a deep learning model suitable for multivariate time series (such as the Transformer architecture) is adopted. These models can simultaneously understand the linkage between elevators, the periodic patterns of elevator peak hours, and the trend of battery charge changes over time. During training, the model continuously adjusts its internal parameters to gradually bring its predictions closer to actual historical data. The optimization objective is usually to minimize the error of the predicted power curve, while a special penalty term for peak power is added during training to make the model pay special attention to the prediction accuracy of peak hours. After the model has been repeatedly trained on a large amount of historical data and the prediction error on the validation set has stabilized and decreased, training will automatically stop. The model is then validated on independent test data to test its stability on unseen data, peak recognition ability, and overall accuracy of 24-hour predictions. Finally, the trained model is deployed to the cloud or edge server for real-time inference at minute-level or shorter intervals, continuously providing the energy management system with predicted curves of future power and demand as an important basis for subsequent charging and discharging strategies.

[0084] The prediction strategy model is divided into a prediction layer and a decision layer. The prediction layer, based on the real-time power, operating status, load, and battery management system (BMS) of each elevator (SOC, SOH, charging / discharging power), predicts the power demand and regenerative energy at each moment for the next 24 hours (granularity 10 minutes), outputting the predicted load demand, predicted regenerative energy, and uncertainty estimate (confidence interval) for each time step. The decision layer, taking the prediction results, electricity price time series, and battery constraints as input, solves for the 24-hour charging / discharging strategy (battery charging / discharging power at each moment, and power source allocation). The prediction layer provides the input, and the optimizer executes in the rolling time domain (MPC) and updates every 10 minutes.

[0085] For example, the goal of the prediction layer is to predict the total power demand D for the next 24 hours. t (kW), Renewable Energy Rt (kW), and give the uncertainty. The model uses Transformer to process the group's time series, plus Multi-Layer Perceptron (MLP) to fuse static features (including SOC and SOH). The input is the historical sequence of the elevator group's real-time total power. Historical sequence of operating status for each elevator (e.g., up, down, standby, stopped), real-time load (kg) historical sequence for each elevator Historical sequence of battery module charging power Historical sequence of battery module discharge power Historical SOC (%) series, historical SOH series, historical temperature series, current mains electricity price curve c t The model outputs historical sequences of time information (time of day, weekday / weekend, holiday, peak commuting time), and factors affecting increased load (pedestrian flow) during a specific time period due to weather, events, etc., normalized into influencing factor k. The output is the elevator group load and regenerative power for each future time step t. A loss function L is used to measure the model's output. Compared with actual operating data The deviation between them is expressed mathematically as follows:

[0086]

[0087] In this embodiment, by preprocessing data to ensure input quality, capturing local temporal features through time window segmentation, and optimizing targets in a targeted manner, the model can accurately predict the future load and power demand of the elevator, thereby improving the reliability of the elevator energy-saving strategy and ensuring the reliability of elevator operation scheduling.

[0088] In an exemplary embodiment, the elevator energy-saving strategy carries a strategy identifier; the method further includes: receiving a consistency verification request sent by a terminal; the consistency verification request carries a to-be-verified identifier; if the to-be-verified identifier matches the strategy identifier, returning a consistency success identifier to the terminal; if the to-be-verified identifier does not match the strategy identifier and there is currently no elevator energy-saving strategy, sending an incomplete identifier to the terminal; if the to-be-verified identifier does not match the strategy identifier and there is currently an elevator energy-saving strategy, sending the current elevator energy-saving strategy to the terminal.

[0089] Optionally, both the policy identifier and the identifier to be verified are unique identifiers (such as a combination of UUID, timestamp, and policy number) to ensure that each elevator energy-saving policy corresponds to a unique identity code, fundamentally avoiding confusion between policies of different cycles and versions, and confirming information consistency through unique identifiers. The verification request sent by the terminal is essentially a policy identity verification application. The identifier to be verified is transmitted through a reliable communication protocol. After receiving it, the server triggers the identifier comparison logic, quickly verifying whether the two identifiers are completely consistent based on a string matching algorithm, ensuring verification efficiency and accuracy.

[0090] Optionally, when the identifiers match, the system confirms that the policy currently to be executed by the terminal matches the latest policy issued by the server, returns a success flag, and allows execution to proceed, preventing the terminal from executing an incorrect policy. When the identifiers do not match and there is no current policy, the server has not generated a new valid policy and returns an incomplete flag, informing the terminal that there is no valid policy to execute, triggering the terminal's fallback mechanism. When the identifiers do not match but there is a current policy, and the server has a newly generated policy (not synchronized by the terminal), the server issues the current policy to the terminal, ensuring that the terminal executes the latest scheduling policy.

[0091] In this embodiment, the real-time nature of the elevator energy-saving strategy and the accuracy of its execution can be ensured by verifying the uniqueness of the identifier, thereby improving the reliability of the elevator energy-saving strategy and ensuring the reliability of elevator operation scheduling.

[0092] In one exemplary embodiment, such as Figure 3 As shown, an elevator operation scheduling method based on an energy storage module is provided, which can be applied to... Figure 1 Taking terminal 400 as an example, the explanation includes the following steps 302 to 306. Wherein:

[0093] S302: When the server is online, send elevator operation data to the server; the elevator operation data includes the total power of the elevator module, the elevator operation status, the elevator load, and the energy storage battery parameters.

[0094] Optionally, the terminal determines the server's online status in real time through network connectivity detection. The core principle is based on network communication link status feedback, ensuring data transmission is initiated only when the server can interact normally, avoiding invalid communication. The terminal integrates multi-dimensional sensors and monitoring modules. For example, total power is collected and calculated in real time by current / voltage sensors; elevator operating status (up / down / stop) is detected by limit switches and encoders; elevator load is collected by weight sensors; and energy storage battery parameters (voltage, SOC, temperature) are obtained through the battery management system (BMS). The terminal encapsulates this scattered data in a preset format to ensure a unified data structure for easy server parsing. A specified communication protocol is used for data transmission to avoid data loss or transmission errors, ensuring the server receives complete and accurate operational data, providing reliable input for strategy generation.

[0095] S304: Receive the elevator energy-saving strategy sent by the server and control the operation of the elevator module according to the elevator energy-saving strategy; the elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current time.

[0096] Optionally, the terminal receives the energy-saving strategy from the server via a communication link originating from the same source as the data upload. It then parses the core parameters of the strategy (such as the power supply mode within a preset time period: energy storage power supply / mains power supply, elevator operation priority, and regenerative energy recovery threshold), mapping the abstract strategy into executable instructions for the elevator module and energy storage module, thus transforming the software strategy into hardware actions. As the execution core, the terminal, based on the parsed instructions, coordinates with the elevator module and energy storage module, sending control signals to each module to ensure the precise implementation of the energy-saving requirements in the strategy.

[0097] S306: When the server is offline, control the operation of the elevator module based on the preset operation strategy and the locally stored elevator energy-saving strategy.

[0098] Optionally, the terminal has a built-in local storage module to cache valid energy-saving strategies previously issued by the server. When the server is offline, the terminal first reads the locally stored strategy and verifies it in conjunction with energy storage battery parameters (such as whether the SOC is ≥30% and whether the temperature is within a safe range). The feasibility of the strategy is judged by the battery status. If the SOC is too low, it means that the energy storage power supply command in the local strategy is invalid, avoiding operational failures due to battery status mismatch. If the local strategy verification fails or there is no locally stored strategy, the terminal automatically activates the preset operation strategy. This strategy is the basic energy-saving logic pre-embedded in the terminal (such as default peak and valley time division, priority of mains power supply and regenerative energy recovery). Through the hierarchical logic of prioritizing the locally stored strategy and using the preset strategy as a fallback, it ensures that the elevator can still maintain safe operation and energy saving when the server is offline, avoiding shutdowns or disorderly power consumption.

[0099] In the aforementioned elevator operation scheduling method based on energy storage modules, the terminal sends elevator operation data to the server when the server is online, receives elevator energy-saving strategies sent by the server, and controls the operation of the elevator module according to the energy-saving strategies. When the server is offline, the terminal controls the operation of the elevator module based on preset operation strategies and locally stored elevator energy-saving strategies. This ensures that the energy-saving strategies generated by the server are accurately matched with the actual operating status of the elevator and the current electricity price, reducing operating costs. It also avoids controlling elevator operation through locally stored strategies when the server is offline, preventing elevator malfunctions and further reducing energy waste.

[0100] In an exemplary embodiment, the step of controlling the operation of an elevator module based on a preset operation strategy and a locally stored elevator energy-saving strategy includes: if the locally stored elevator energy-saving strategy is verified to be valid according to the energy storage battery parameters, controlling the elevator module to operate according to the locally stored elevator energy-saving strategy; if the locally stored elevator energy-saving strategy is not verified to be valid, or if there is no locally stored elevator energy-saving strategy, controlling the elevator module to operate according to the preset operation strategy.

[0101] Optionally, the terminal collects core parameters of the energy storage battery in real time through the Battery Management System (BMS), including remaining charge (SOC), operating voltage, temperature, and cycle life status. These parameters are the core basis for judging the feasibility of the local strategy. The terminal analyzes the locally stored elevator energy-saving strategy and compares it with the current battery parameters. If the strategy requires energy storage power supply, it needs to verify that the SOC is greater than or equal to a preset threshold (e.g., 30%), the temperature is within a safe range (e.g., 0-45℃), the voltage is stable, and there is no risk of overcharging or over-discharging. If the SOC is too low (e.g., <20%), the temperature exceeds the standard, or the energy storage power required by the strategy exceeds the current output capacity of the battery, the verification fails.

[0102] Optionally, the local storage strategy is a proven energy-saving strategy issued by the server when it is online. It includes scheduling logic adapted to elevator operating patterns (such as morning peak load and periods of regenerative energy generation) and electricity price characteristics. Once verified, this strategy is executed, avoiding the energy-saving effect reduction caused by switching directly to the basic strategy when the server is offline. Furthermore, utilizing the locally cached strategy eliminates the need for recalculation, improving response speed. The preset operating strategy is basic energy-saving logic pre-installed in the terminal's local storage, independent of server issuance. Its core includes general peak-valley time divisions (e.g., defaulting to 7-9 AM and 6-8 PM as peak times), power supply mode priorities (e.g., prioritizing mains power when energy storage is insufficient, and forcibly recovering regenerative energy during braking), and power control thresholds. When the local strategy fails verification (e.g., battery status does not support it) or there is no locally stored strategy (e.g., first run, local cache loss), the terminal automatically triggers this strategy, providing minimum guaranteed operating logic. This avoids elevator shutdown while ensuring basic energy-saving effects. This strategy requires no complex calculations and operates stably and reliably.

[0103] In this embodiment, by verifying the parameters of the energy storage battery, strategies that are not compatible with the battery state are avoided. The terminal can autonomously cope with complex scenarios such as server offline and local strategy failure through hierarchical strategy logic, which can further reduce energy waste and lower operating costs.

[0104] In an exemplary embodiment, the step of controlling the operation of the elevator module according to a preset operation strategy includes: if a time period division strategy exists locally or a time period division strategy is received from the server, determining the operating segment corresponding to the current moment according to the time period division strategy; if a time period division strategy does not exist locally and a time period division strategy is not received from the server, determining the operating segment corresponding to the current moment according to a preset division strategy; and controlling the operation of the elevator module according to the time period energy-saving strategy corresponding to the operating segment.

[0105] Optionally, the time-sharing strategy stored locally on the terminal (delivered and cached by the server when online) or the real-time time-sharing strategy sent by the server has higher priority than the pre-fixed preset strategy. This type of strategy is a personalized time-sharing strategy adapted to the current region and current electricity price policy, which is more in line with actual electricity price characteristics than a general preset strategy and can improve the accuracy of energy saving. Whether it's a local / server-based time-sharing strategy or a preset strategy, the essence is a mapping rule between time intervals and time-sharing types (peak / valley / flat) (e.g., peak hours: 7:00-9:00, 18:00-20:00; valley hours: 0:00-6:00; the rest are flat periods). The terminal obtains the current time through the system clock, assigns the current time to the corresponding peak, valley, or flat period, and, through standardized time matching logic, clarifies the electricity price attribute (high price / low price / flat price) of the current time period, providing a basis for the subsequent execution of energy-saving strategies.

[0106] Optionally, the terminal predefines a fixed mapping relationship between time period type and energy-saving strategy (e.g., during peak hours: prioritize using energy storage power, shut down unnecessary auxiliary energy consumption, and maximize the recovery of regenerated energy; during off-peak hours: prioritize using mains power to charge energy storage and maintain the basic operating power of the elevator; during flat hours: use mains power and energy storage in a balanced manner). This mapping relationship is stored in the terminal and requires no server intervention. After determining the operating period, the terminal automatically calls the corresponding energy-saving strategy and sends control commands (such as switching power supply circuits and adjusting charging power) to the elevator module and energy storage module to ensure that appropriate energy-saving actions are performed during different electricity price periods, avoiding energy waste caused by indiscriminate operation.

[0107] For example, if there are no peak / valley periods (e.g., during the initial installation and commissioning phase, or when the cloud-based prediction model is not used and no peak / valley periods are set locally), the default peak / valley periods are used: Peak period: 8:00-11:00, 16:00-24:00; Flat period: 11:00-16:00; Valley period: 0:00-8:00. If peak / valley periods exist (e.g., parameters manually set locally or parameters updated locally from the cloud), the existing peak / valley periods are used. The peak / valley period is obtained based on the current time of the local device system. If in a valley, the battery is charged at the maximum allowable charging power of the BMS until it reaches a high charge threshold (e.g., 90%). The elevator then uses mains power, and regenerated energy is stored in the battery. If the battery is full, it switches back to battery power until the battery charge drops below the high charge threshold (e.g., SOC drops to 90%), at which point it switches back to mains power. The discharge power is determined by the actual traction machine operation of the elevator system and is not within the control parameters. During off-peak hours, mains power is used, and the elevator's regenerative energy is stored in the battery. Once the battery is full, the system switches back to battery power until the battery level drops below a high charge threshold (e.g., SOC drops to 90%), at which point it switches back to mains power. The discharge power is determined by the actual elevator system's traction machine operation and is not within the control parameters. During peak hours, the battery stores energy, and the elevator's regenerative energy is stored in the battery. The discharge power is determined by the actual elevator system's traction machine operation and is not within the control parameters. If the battery level drops below a low charge threshold (e.g., SOC less than 30%), mains power is used, and the elevator's regenerative energy is stored in the battery. The remaining energy serves as a backup power source and battery protection, for emergency use and to prevent deep discharge. The discharge power is determined by the actual elevator system's traction machine operation and is not within the control parameters.

[0108] In this embodiment, the terminal achieves peak-valley differentiated scheduling through time period division, which can reduce the consumption of high-priced mains power during peak hours and avoid the waste of renewable energy. It is compatible with the precise time period division issued by the server when it is online, and also ensures operation through preset division when there is no personalized strategy, further reducing operating costs.

[0109] In an exemplary embodiment, the method further includes: sending a consistency verification request to the server; the consistency verification request carrying a verification identifier; upon receiving a consistency success identifier returned by the server, controlling the elevator module to operate according to the current elevator energy-saving strategy; upon receiving an incomplete identifier returned by the server, controlling the elevator module to operate according to a preset operation strategy; and upon receiving the elevator energy-saving strategy for the current moment returned by the server, controlling the elevator module to operate according to the elevator energy-saving strategy for the current moment.

[0110] Optionally, the identifier to be verified is a unique identification code of the policy to be executed in the terminal's local cache or the current policy to be executed, used to identify the identity of the policy to be executed on the terminal side. The terminal sends a verification request to the server through a reliable communication protocol with the same source as the data upload. The acknowledgment and response mechanism of the protocol ensures that the request is received by the server, and at the same time carries the identifier to be verified, providing the server with a comparison benchmark to verify whether the policy on the terminal side is synchronized with the latest policy on the server side.

[0111] Optionally, upon receiving a consistency success flag, the server confirms that the identifier to be verified matches the identifier of its latest policy by comparing the two. This indicates that the policy to be executed by the terminal is the latest valid policy recognized by the server. The terminal then executes this policy to avoid executing outdated or incorrect policies. Upon receiving an incomplete flag, it indicates that the server has not yet generated a valid and usable elevator energy-saving policy (e.g., policy calculation incomplete, data anomalies preventing generation). The terminal automatically switches to a preset operating policy, which is the basic operating logic pre-embedded in the terminal, ensuring that the elevator can still operate safely without losing basic energy-saving effects when no valid policy is available. Upon receiving the current elevator energy-saving policy, it indicates that the terminal's original identifier to be verified does not match the server's latest policy identifier. The server identifies the unsynchronized terminal policy through the verification request and immediately reissues the current valid policy. The terminal executes this reissued policy to quickly synchronize the latest and most accurate policy.

[0112] In this embodiment, identifier consistency verification can avoid energy-saving failures caused by policy asynchrony, policy updates can be completed without manual intervention, ensuring real-time scheduling and thus reducing operating costs.

[0113] In an exemplary embodiment, the method further includes: acquiring the current charging power during the process of controlling the elevator module to operate according to the elevator energy-saving strategy; and stopping the process of controlling the elevator module to operate according to the elevator energy-saving strategy if the rationality verification of the elevator energy-saving strategy based on the current charging power fails or a power outage signal is received.

[0114] Optionally, the terminal collects data in real time through the battery management system (BMS), current sensor, and voltage sensor of the energy storage module to provide real-time input for rationality verification. The terminal pre-stores the safety operating parameter thresholds of the energy storage module (such as the maximum allowable charging power, the upper limit of charging power fluctuation, and the power limit related to battery temperature), and simultaneously analyzes the preset charging power target value in the energy-saving strategy. By comparing the current actual charging power with the preset power and safety threshold range of the strategy, if the current charging power exceeds the maximum allowable value (e.g., the strategy requires 3kW charging, but the actual power reaches 8kW, exceeding the safety limit of the energy storage battery), or the power fluctuation exceeds the threshold (e.g., a sudden increase from 2kW to 6kW within 1 second, which may be a circuit fault), or the charging power does not match the battery state (e.g., the battery continues to charge at high power after it is fully charged), then the rationality verification is deemed unsuccessful.

[0115] Furthermore, the terminal has a built-in grid voltage detection module that monitors the mains power supply status in real time. When the mains voltage is detected to be lower than the preset power outage threshold, it is determined as a power outage signal, and the emergency mechanism is triggered through grid power supply status feedback. At this time, the instructions in the energy-saving strategy regarding power supply mode switching and charging / discharging power control are terminated, and the terminal automatically switches to a safe operation mode to balance safety and operational continuity.

[0116] In this embodiment, by verifying the rationality of charging power, overcharging, overcurrent, and overheating faults of energy storage batteries caused by deviations in energy-saving strategy parameters and circuit failures are avoided. This can prevent ineffective power consumption and energy waste, while also preventing cascading failures caused by strategy failures and improving the reliability of operation scheduling.

[0117] In one exemplary embodiment, such as Figure 4 As shown, an elevator operation scheduling method based on an energy storage module is provided, which includes the following steps:

[0118] When the server is online, the terminal sends elevator operation data to the server. This data includes the total power of the elevator module, elevator operating status, elevator load, and energy storage battery parameters. It receives elevator energy-saving strategies from the server and controls the elevator module operation according to these strategies. These energy-saving strategies include elevator operation plans for a preset time period following the current moment. When the server is offline, if the locally stored elevator energy-saving strategy is verified successfully based on the energy storage battery parameters, the terminal controls the elevator module operation according to the locally stored strategy. If the verification fails or no locally stored strategy exists, the terminal determines the current operating segment based on the time period division strategy if a local time period division strategy exists or if a time period division strategy is received from the server. If no local time period division strategy exists and no time period division strategy is received from the server, the terminal determines the current operating segment based on a preset division strategy and controls the elevator module operation according to the time period energy-saving strategy corresponding to that operating segment.

[0119] The server obtains electricity price information and receives elevator operation data sent by the terminal; the electricity price information includes peak and off-peak periods and corresponding electricity prices; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters.

[0120] Once the integrity verification of the elevator operation data is passed, the server inputs the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period. The elevator energy-saving strategy includes the elevator operation strategy for the preset time period after the current moment.

[0121] The training process of the elevator load prediction model includes: obtaining historical sample sequences based on historical electricity price information and historical operating data; performing anomaly processing and completion processing on the historical sample sequences to obtain historical training sequences; dividing the historical training sequences into multiple time windows according to a preset step size; constructing the elevator load prediction model; training the elevator load prediction model sequentially through the historical training sequences within the current time window with the optimization objective of minimizing the prediction power curve error, until the training stops when the stopping condition is met, and verifying the trained elevator load prediction model using test set data.

[0122] The server sends elevator energy-saving policies to the terminal, enabling the terminal to control the elevator module operation according to the policies. These energy-saving policies carry a policy identifier.

[0123] The terminal sends a consistency verification request to the server; the consistency verification request carries a verification identifier; upon receiving a consistency success flag from the server, the terminal controls the elevator module to operate according to the current elevator energy-saving strategy; upon receiving an incomplete flag from the server, the terminal controls the elevator module to operate according to the preset operation strategy; upon receiving the current elevator energy-saving strategy from the server, the terminal controls the elevator module to operate according to the current elevator energy-saving strategy.

[0124] The server receives a consistency verification request sent by the terminal; the consistency verification request carries an identifier to be verified; if the identifier to be verified matches the policy identifier, the server returns a consistency success flag to the terminal; if the identifier to be verified does not match the policy identifier and there is no elevator energy-saving policy at present, the server sends an incomplete flag to the terminal; if the identifier to be verified does not match the policy identifier and there is an elevator energy-saving policy at present, the server sends the current elevator energy-saving policy to the terminal.

[0125] During the process of controlling the elevator module to operate according to the elevator energy-saving strategy, the terminal obtains the current charging power; if the rationality verification of the elevator energy-saving strategy based on the current charging power fails or a power outage signal is received, the process of controlling the elevator module to operate according to the elevator energy-saving strategy is stopped.

[0126] In this embodiment, the server obtains electricity price information and receives elevator operation data sent by the terminal. After verifying the integrity of the elevator operation data, the server inputs the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period. The server then sends the elevator energy-saving strategy to the terminal so that the terminal can control the operation of the elevator module according to the elevator energy-saving strategy. This reduces the consumption of high-priced mains electricity, recovers regenerative energy during elevator braking and heavy-load descent, avoids energy dissipation in the form of heat, reduces energy waste, adapts to electricity price changes in different regions and at different times, reduces maintenance costs, and balances the power supply ratio between mains electricity and energy storage modules through strategic control, reducing the load pressure on the power grid during peak hours and improving the energy utilization efficiency of the elevator system.

[0127] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0128] Based on the same inventive concept, this application also provides an elevator operation scheduling device based on an energy storage module for implementing the elevator operation scheduling method based on an energy storage module described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the elevator operation scheduling device based on an energy storage module provided below can be found in the limitations of the elevator operation scheduling method based on an energy storage module above, and will not be repeated here.

[0129] In one exemplary embodiment, such as Figure 5 As shown, an elevator operation scheduling device based on an energy storage module is provided, including: a data receiving module 502, a strategy generation module 504, and a strategy distribution module 506, wherein:

[0130] The data receiving module 502 acquires electricity price information and receives elevator operation data sent by the terminal; the electricity price information includes peak and off-peak periods and corresponding electricity prices; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters.

[0131] The strategy generation module 504 is used to input the current electricity price information and the current elevator operation data into the trained elevator load prediction model after the integrity verification of the elevator operation data has passed, so as to obtain the elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes the elevator operation strategy for the preset time period after the current moment.

[0132] The strategy distribution module 506 is used to send elevator energy-saving strategies to the terminal so that the terminal controls the operation of the elevator module according to the elevator energy-saving strategy.

[0133] In an exemplary embodiment, the strategy generation module 504 is further configured to obtain a historical sample sequence based on historical electricity price information and historical operating data, perform anomaly processing and completion processing on the historical sample sequence to obtain a historical training sequence; divide the historical training sequence into multiple time windows according to a preset step size; construct an elevator load prediction model; train the elevator load prediction model sequentially through the historical training sequence within the current time window with the optimization objective of minimizing the prediction power curve error, until the training stops when the training stopping condition is met, and verify the trained elevator load prediction model through test set data.

[0134] In an exemplary embodiment, the elevator energy-saving strategy carries a strategy identifier; the strategy distribution module 506 is also used to receive a consistency verification request sent by the terminal; the consistency verification request carries a verification identifier; if the verification identifier is consistent with the strategy identifier, a consistency success flag is returned to the terminal; if the verification identifier is inconsistent with the strategy identifier and there is no elevator energy-saving strategy at present, an incomplete flag is sent to the terminal; if the verification identifier is inconsistent with the strategy identifier and there is an elevator energy-saving strategy at present, the elevator energy-saving strategy at the current moment is sent to the terminal.

[0135] In one exemplary embodiment, such as Figure 6 As shown, an elevator operation scheduling device based on an energy storage module is provided, including: a data transmission module 602, a strategy receiving module 604, and an operation scheduling module 606, wherein:

[0136] The data transmission module 602 is used to send elevator operation data to the server when the server is online; the elevator operation data includes the total power of the elevator module, the elevator operation status, the elevator load, and the energy storage battery parameters.

[0137] The strategy receiving module 604 is used to receive the elevator energy-saving strategy sent by the server and control the operation of the elevator module according to the elevator energy-saving strategy; the elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current time.

[0138] The operation scheduling module 606 is used to control the operation of the elevator module based on the preset operation strategy and the locally stored elevator energy-saving strategy when the server is offline.

[0139] In an exemplary embodiment, the operation scheduling module 606 is further configured to control the elevator module to operate according to the locally stored elevator energy-saving strategy if the verification of the locally stored elevator energy-saving strategy based on the energy storage battery parameters is successful; and to control the elevator module to operate according to a preset operation strategy if the verification of the locally stored elevator energy-saving strategy fails or if there is no locally stored elevator energy-saving strategy.

[0140] In an exemplary embodiment, the operation scheduling module 606 is further configured to determine the running segment corresponding to the current moment according to the time period division strategy when a time period division strategy exists locally or a time period division strategy is received from the server; and to determine the running segment corresponding to the current moment according to a preset division strategy when a time period division strategy does not exist locally and a time period division strategy is not received from the server; and to control the elevator module to operate according to the time period energy saving strategy corresponding to the running segment.

[0141] In an exemplary embodiment, the operation scheduling module 606 is further configured to send a consistency verification request to the server; the consistency verification request carries a verification identifier; upon receiving a consistency success identifier returned by the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy; upon receiving an incomplete identifier returned by the server, the elevator module is controlled to operate according to a preset operation strategy; upon receiving the current elevator energy-saving strategy returned by the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy.

[0142] In an exemplary embodiment, the operation scheduling module 606 is further configured to obtain the current charging power during the process of controlling the operation of the elevator module according to the elevator energy-saving strategy; and to stop the process of controlling the operation of the elevator module according to the elevator energy-saving strategy if the rationality verification of the elevator energy-saving strategy based on the current charging power fails or a power outage signal is received.

[0143] The various modules in the aforementioned elevator operation scheduling device based on energy storage modules can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0144] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores elevator operation data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an elevator operation scheduling method based on an energy storage module.

[0145] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring electricity price information and receiving elevator operation data sent by a terminal; the electricity price information includes peak and off-peak periods and corresponding electricity prices; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters; if the integrity verification of the elevator operation data passes, inputting the current electricity price information and the current elevator operation data into a trained elevator load prediction model to obtain an elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes an elevator operation strategy for a preset time period after the current moment; and sending the elevator energy-saving strategy to the terminal so that the terminal controls the operation of the elevator module according to the elevator energy-saving strategy.

[0146] In one embodiment, the training process of the elevator load prediction model involved when the processor executes the computer program includes: obtaining historical sample sequences based on historical electricity price information and historical operating data; performing anomaly processing and completion processing on the historical sample sequences to obtain historical training sequences; dividing the historical training sequences into multiple time windows according to a preset step size; constructing an elevator load prediction model; training the elevator load prediction model sequentially through the historical training sequences within the current time window with the optimization objective of minimizing the prediction power curve error, until the training stops when the stopping condition is met, and verifying the trained elevator load prediction model using test set data.

[0147] In one embodiment, the elevator energy-saving strategy carries a strategy identifier; when the processor executes the computer program, it further implements the following steps: receiving a consistency verification request sent by the terminal; the consistency verification request carries a verification identifier; if the verification identifier matches the strategy identifier, returning a consistency success flag to the terminal; if the verification identifier does not match the strategy identifier and there is no elevator energy-saving strategy at present, sending an incomplete flag to the terminal; if the verification identifier does not match the strategy identifier and there is an elevator energy-saving strategy at present, sending the current elevator energy-saving strategy to the terminal.

[0148] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: when the server is online, sending elevator operation data to the server; the elevator operation data includes the total power of the elevator module, the elevator operation status, the elevator load, and energy storage battery parameters; receiving an elevator energy-saving strategy sent by the server, and controlling the operation of the elevator module according to the elevator energy-saving strategy; the elevator energy-saving strategy includes an elevator operation strategy for a preset time period after the current moment; when the server is offline, controlling the operation of the elevator module based on the preset operation strategy and the locally stored elevator energy-saving strategy.

[0149] In one embodiment, when the processor executes a computer program, it controls the operation of the elevator module based on a preset operating strategy and a locally stored elevator energy-saving strategy, including: if the locally stored elevator energy-saving strategy is verified to be valid according to the energy storage battery parameters, controlling the elevator module to operate according to the locally stored elevator energy-saving strategy; if the locally stored elevator energy-saving strategy is not verified to be valid, or if there is no locally stored elevator energy-saving strategy, controlling the elevator module to operate according to the preset operating strategy.

[0150] In one embodiment, the process of the processor executing a computer program to control the operation of the elevator module according to a preset operating strategy includes: determining the operating segment corresponding to the current moment according to the time-sharing strategy when a time-sharing strategy exists locally or a time-sharing strategy is received from the server; determining the operating segment corresponding to the current moment according to the preset time-sharing strategy when a time-sharing strategy does not exist locally and a time-sharing strategy is not received from the server; and controlling the operation of the elevator module according to the time-sharing energy-saving strategy corresponding to the operating segment.

[0151] In one embodiment, when the processor executes the computer program, it further performs the following steps: sending a consistency verification request to the server; the consistency verification request carries a verification identifier; upon receiving a consistency success identifier returned by the server, controlling the elevator module to operate according to the current elevator energy-saving strategy; upon receiving an incomplete identifier returned by the server, controlling the elevator module to operate according to a preset operation strategy; upon receiving the elevator energy-saving strategy for the current moment returned by the server, controlling the elevator module to operate according to the elevator energy-saving strategy for the current moment.

[0152] In one embodiment, when the processor executes the computer program, it further implements the following steps: during the process of controlling the operation of the elevator module according to the elevator energy-saving strategy, obtaining the current charging power; and stopping the process of controlling the operation of the elevator module according to the elevator energy-saving strategy if the rationality verification of the elevator energy-saving strategy based on the current charging power fails or a power outage signal is received.

[0153] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0154] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An elevator operation scheduling method based on an energy storage module, characterized in that, Applied to a server; the method includes: The system acquires electricity price information and receives elevator operation data sent by the terminal. The electricity price information includes peak and off-peak hours and corresponding electricity prices. The elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters. If the integrity verification of the elevator operation data passes, the current electricity price information and the current elevator operation data are input into the trained elevator load prediction model to obtain the elevator energy-saving strategy for the current period; the elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current moment. The elevator energy-saving strategy is sent to the terminal so that the terminal controls the operation of the elevator module according to the elevator energy-saving strategy.

2. The method according to claim 1, characterized in that, The training process of the elevator load prediction model includes: Based on historical electricity price information and historical operation data, historical sample sequences are obtained, and anomaly processing and completion processing are performed on the historical sample sequences to obtain historical training sequences. The historical training sequence is divided into multiple time windows according to a preset step size; Construct an elevator load prediction model; With minimizing the error of the predicted power curve as the optimization objective, the elevator load prediction model is trained sequentially using historical training sequences within the current time window until the training stops when the stopping condition is met. The trained elevator load prediction model is then validated using test set data.

3. The method according to claim 1, characterized in that, The elevator energy-saving strategy carries a strategy identifier; the method further includes: Receive a consistency verification request sent by the terminal; the consistency verification request carries a verification identifier; If the identifier to be verified matches the policy identifier, a consistency success flag is returned to the terminal. If the identifier to be verified is inconsistent with the policy identifier and there is currently no elevator energy-saving policy, an incomplete flag is sent to the terminal. If the identifier to be verified is inconsistent with the policy identifier and an elevator energy-saving policy exists, the elevator energy-saving policy at the current moment will be sent to the terminal.

4. A method for scheduling the operation of an energy storage elevator module, characterized in that, Applied to a terminal; the method includes: When the server is online, elevator operation data is sent to the server; the elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters. The system receives the elevator energy-saving strategy sent by the server and controls the operation of the elevator module according to the elevator energy-saving strategy; the elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current time. When the server is offline, the elevator module is controlled to operate based on a preset operating strategy and a locally stored elevator energy-saving strategy.

5. The method according to claim 4, characterized in that, The elevator module operation is controlled based on a preset operating strategy and a locally stored elevator energy-saving strategy, including: If the locally stored elevator energy-saving strategy is verified to be successful based on the energy storage battery parameters, the elevator module is controlled to operate according to the locally stored elevator energy-saving strategy. If the verification of the locally stored elevator energy-saving strategy fails or there is no locally stored elevator energy-saving strategy, the elevator module is controlled to operate according to the preset operation strategy.

6. The method according to claim 5, characterized in that, The step of controlling the elevator module to operate according to a preset operating strategy includes: If a time-sharing strategy exists locally, or if a time-sharing strategy is received from the server, the runtime segment corresponding to the current time is determined according to the time-sharing strategy. If there is no time-sharing strategy on the local machine and no time-sharing strategy is received from the server, the runtime segment corresponding to the current time is determined according to the preset division strategy. The elevator module is controlled to operate according to the time period energy-saving strategy corresponding to the operating segment.

7. The method according to claim 4, characterized in that, The method further includes: A consistency verification request is sent to the server; the consistency verification request carries a verification identifier. Upon receiving a consistency success flag from the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy. Upon receiving an incomplete flag from the server, the elevator module is controlled to operate according to the preset operating strategy. Upon receiving the elevator energy-saving strategy for the current moment returned by the server, the elevator module is controlled to operate according to the elevator energy-saving strategy for the current moment.

8. The method according to claim 4, characterized in that, The method further includes: During the process of controlling the operation of the elevator module according to the elevator energy-saving strategy, the current charging power is obtained; If the rationality verification of the elevator energy-saving strategy based on the current charging power fails, or if a power outage signal is received, the process of controlling the operation of the elevator module according to the elevator energy-saving strategy shall be stopped.

9. An elevator operation scheduling system based on an energy storage module, characterized in that, include: Elevator module; An energy storage module, including an energy storage battery, is used to provide the elevator module with the electrical energy required for operation and to receive the regenerated electrical energy generated by the elevator module. The server is used to acquire electricity price information and receive elevator operation data sent by the terminal. The electricity price information includes peak and off-peak periods and corresponding electricity prices. The elevator operation data includes the total power of the elevator module, elevator operation status, elevator load, and energy storage battery parameters. It is also used to input the current electricity price information and the current elevator operation data into a trained elevator load prediction model, after the integrity verification of the elevator operation data passes, to obtain the elevator energy-saving strategy for the current period. The elevator energy-saving strategy includes the elevator operation strategy for a preset time period after the current moment. It is also used to send the elevator energy-saving strategy to the terminal; The terminal is used to send elevator operation data to the server when the server is online; it is also used to receive elevator energy-saving strategies sent by the server and control the operation of the elevator module according to the elevator energy-saving strategies; and it is also used to control the operation of the elevator module based on a preset operation strategy and a locally stored elevator energy-saving strategy when the server is offline.

10. 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 method according to any one of claims 1 to 8.

Images