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

Abstract

The application relates to an elevator operation scheduling method and system based on an energy storage module and a computer device. The method comprises the following steps: a server acquires 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; in the case that the integrity check of the elevator operation data is passed, the current electricity price information and the current elevator operation data are input into a trained elevator load prediction model to obtain an elevator energy-saving strategy for a current period, the elevator energy-saving strategy is sent to the terminal, and the terminal controls the operation of an elevator module according to the elevator energy-saving strategy. The method can reduce the operation cost of an elevator system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator energy saving, in particular to an elevator operation scheduling method and system based on an energy storage module and a computer device. BACKGROUND

[0002] With the increase in the number of elevators in buildings, the energy consumption of elevator operation accounts for an increasing proportion of the total building energy consumption. Traditional elevators mostly rely on direct power supply from the power grid, and when the power grid is at peak price, the cost of elevator operation increases significantly. In addition, when the elevator brakes, heavy loads descend or light loads ascend, regenerative power is generated, but most current systems either directly feed the power back to the power grid or dissipate it in the form of heat, failing to effectively recycle and utilize it.

[0003] In the traditional technology, a battery module (i.e., an energy storage unit) is used for regenerative energy recovery and partial power supply of the elevator. However, the peak-valley electricity price period is different in different provinces and regions or in different months and years in the same region, and each time the peak-valley electricity price is changed, the local period needs to be changed, which increases the maintenance cost and resource waste, and the load peak value and frequency of daily elevator operation have obvious rules, but the traditional method cannot predict according to real-time trends and historical data, which may cause the battery to be insufficient in capacity during peak electricity price period and be forced to use high-priced commercial power. SUMMARY

[0004] Therefore, it is necessary to provide an elevator operation scheduling method and system based on an energy storage module for an energy storage elevator to reduce the operation cost of the elevator system.

[0005] In a first aspect, the present application provides an elevator operation scheduling method based on an energy storage module, comprising:

[0006] obtaining electricity price information and receiving elevator operation data sent by a terminal; the electricity price information includes peak-valley periods and corresponding electricity prices; the elevator operation data includes total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters;

[0007] in the case where the integrity check of the elevator operation data is passed, 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 a current period; the elevator energy saving strategy includes an elevator operation strategy in a preset time period after the current time;

[0008] sending the elevator energy saving strategy to the terminal to enable the terminal to control the elevator module to operate according to the elevator energy saving strategy.

[0009] In one of the embodiments, the training process of the elevator load prediction model comprises:

[0010] According to historical electricity price information and historical operation data, a historical sample sequence is obtained, the historical sample sequence is subjected to abnormality processing and completion processing, and a historical training sequence is obtained;

[0011] According to a preset step size, the historical training sequence is divided into a plurality of time windows;

[0012] A lift load prediction model is constructed;

[0013] With minimizing a prediction power curve error as an optimization objective, the lift load prediction model is trained by using the historical training sequence in a current time window in sequence until a training stop condition is met, and the trained lift load prediction model is verified by using test set data.

[0014] In one of the embodiments, the lift energy-saving strategy carries a strategy identifier; the method further includes:

[0015] A consistency verification request sent by a terminal is received; the consistency verification request carries a to-be-verified identifier;

[0016] In a case where the to-be-verified identifier is consistent with the strategy identifier, a consistency success identifier is returned to the terminal;

[0017] In a case where the to-be-verified identifier is inconsistent with the strategy identifier and no lift energy-saving strategy currently exists, an unfinished identifier is sent to the terminal;

[0018] In a case where the to-be-verified identifier is inconsistent with the strategy identifier and a lift energy-saving strategy currently exists, the lift energy-saving strategy at the current time is sent to the terminal.

[0019] In a second aspect, the application further provides a lift operation scheduling method based on an energy storage module, including:

[0020] In a case where the server is in an online state, lift operation data is sent to the server; the lift operation data includes total power of a lift module, lift operation state, lift load, and energy storage battery parameters;

[0021] A lift energy-saving strategy sent by the server is received, and the lift module is controlled to operate according to the lift energy-saving strategy; the lift energy-saving strategy includes a lift operation strategy in a preset time period after the current time;

[0022] In a case where the server is in an offline state, the lift module is controlled to operate based on a preset operation strategy and a locally stored lift energy-saving strategy.

[0023] In one of the embodiments, the step of controlling the lift module to operate based on the preset operation strategy and the locally stored lift energy-saving strategy includes:

[0024] In the case that the local stored elevator energy saving strategy is verified to be passed according to the energy storage battery parameters, the elevator module is controlled to operate according to the local stored elevator energy saving strategy;

[0025] In the case that the local stored elevator energy saving strategy is not verified to be passed, or there is no local stored elevator energy saving strategy, the elevator module is controlled to operate according to the preset operation strategy.

[0026] In one of the embodiments, the step of controlling the elevator module to operate according to the preset operation strategy comprises:

[0027] In the case that the local time period division strategy exists, or the time period division strategy sent by the server is received, the operation time period corresponding to the current time is determined according to the time period division strategy;

[0028] In the case that the local time period division strategy does not exist, and the time period division strategy sent by the server is not received, the operation time period corresponding to the current time is determined according to the preset division strategy;

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

[0030] In one of the embodiments, the method further comprises:

[0031] A consistency verification request is sent to the server, and the consistency verification request carries a to-be-verified identifier;

[0032] In the case that a consistency success identifier returned by the server is received, the elevator module is controlled to operate according to the current elevator energy saving strategy;

[0033] In the case that an unfinished identifier returned by the server is received, the elevator module is controlled to operate according to the preset operation strategy;

[0034] In the case that the elevator energy saving strategy of the current time returned by the server is received, the elevator module is controlled to operate according to the elevator energy saving strategy of the current time.

[0035] In one of the embodiments, the method further comprises:

[0036] In the process of controlling the elevator module to operate according to the elevator energy saving strategy, the current charging power is acquired;

[0037] In the case that the elevator energy saving strategy is not verified to be passed based on the current charging power, or a power failure signal is received, the process of controlling the elevator module to operate according to the elevator energy saving strategy is stopped.

[0038] In a third aspect, the application further provides an elevator operation scheduling system based on an energy storage module, comprising:

[0039] An elevator module;

[0040] a storage module, configured to store the energy storage battery and provide the energy required for the operation of the elevator module and receive the regenerated energy generated by the elevator module;

[0041] a server, configured to obtain electricity price information and receive the elevator operation data sent by the terminal, wherein the electricity price information comprises peak and valley time periods and corresponding electricity prices, the elevator operation data comprises total power of the elevator module, elevator operation state, elevator load, and storage battery parameters, and the server is further configured to input the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain an elevator energy-saving strategy for a current period if the integrity check of the elevator operation data is passed, and send the elevator energy-saving strategy to the terminal;

[0042] a terminal, configured to send the elevator operation data to the server if the server is in an online state, 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, and control the operation of the elevator module based on a preset operation strategy and the locally stored elevator energy-saving strategy if the server is in an offline state.

[0043] In a fourth aspect, the present application further provides an elevator operation scheduling device based on a storage module, comprising:

[0044] a data receiving module, configured to obtain electricity price information and receive the elevator operation data sent by the terminal, wherein the electricity price information comprises peak and valley time periods and corresponding electricity prices, and the elevator operation data comprises total power of the elevator module, elevator operation state, elevator load, and storage battery parameters;

[0045] a strategy generating module, configured to input the current electricity price information and the current elevator operation data into the trained elevator load prediction model to obtain an elevator energy-saving strategy for a current period if the integrity check of the elevator operation data is passed, and the elevator energy-saving strategy comprises an elevator operation strategy in a preset time period after the current time;

[0046] a strategy issuing module, configured to 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.

[0047] In a fifth aspect, the present application further provides an elevator operation scheduling device based on a storage module, comprising:

[0048] a data sending module, configured to send the elevator operation data to the server if the server is in an online state, and the elevator operation data comprises total power of the elevator module, elevator operation state, elevator load, and storage battery parameters;

[0049] The strategy receiving module is configured to receive the elevator energy-saving strategy sent by the server and control the elevator module to operate according to the elevator energy-saving strategy; the elevator energy-saving strategy comprises an elevator operation strategy in a preset time period after the current time.

[0050] The operation scheduling module is configured to control the elevator module to operate based on the preset operation strategy and the locally stored elevator energy-saving strategy when the server is in an offline state.

[0051] In a sixth aspect, the present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method steps of any one of the first aspect or the second aspect when executing the computer program.

[0052] In a seventh aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the method steps of any one of the first aspect or the second aspect when executed by a processor.

[0053] In an eighth aspect, the present application further provides a computer program product comprising a computer program, and the computer program implements the method steps of any one of the first aspect or the second aspect when executed by a processor.

[0054] The above elevator operation scheduling method, system and computer device based on the energy storage module, the server obtains the electricity price information, receives the elevator operation data sent by the terminal, inputs the current electricity price information and the current elevator operation data into the trained elevator load prediction model when the integrity verification of the elevator operation data is passed, obtains the elevator energy-saving strategy in the current period, sends the elevator energy-saving strategy to the terminal, so that the terminal controls the elevator module to operate according to the elevator energy-saving strategy, which can reduce the consumption of high-price commercial power, recover the regenerated electric energy when the elevator brakes and is heavily loaded, avoid the dissipation of energy in the form of heat consumption, reduce the waste of electric energy, adapt to the electricity price changes in different regions and different time periods, reduce the maintenance cost, balance the power supply proportion of commercial power and the energy storage module through strategic control, reduce the peak load pressure of the power grid, and improve the energy utilization efficiency of the elevator system. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0056] Figure 1 An application environment diagram of the elevator operation scheduling method based on the energy storage module in an 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 is composed of energy storage batteries, a high-voltage loop control module, and a battery management system (BMS), is the energy carrier part of the entire system, is responsible for providing backup power required for elevator operation and receiving regenerative power generated by the elevator when braking, heavy load down or light load up. The energy storage battery is composed of multiple strings of power cells, providing DC energy storage capability at the system level, supporting charging, discharging, and regenerative energy recovery, and the output power and capacity are uniformly scheduled by the BMS and the energy management system. The high-voltage loop control module includes high-voltage contactors, pre-charge circuits, fuses, isolation devices, and other key components, is responsible for implementing safe connection between the battery pack and the power supply switching unit, pre-charge and disconnection control, providing high-voltage insulation detection, short-circuit protection, over-current protection, and other functions. The battery management system (BMS) is responsible for monitoring the battery voltage, temperature, SOC, SOH, real-time evaluation of battery available capacity, maximum charging power, maximum discharging power, and collaborative execution of charge and discharge limits, balance control, and safety strategies (overvoltage, undervoltage, overtemperature, short circuit, etc.).

[0066] The server 300 is located in a remote server or cloud platform, undertakes advanced intelligent strategy generation, model training, and system operation and maintenance functions, and includes a data management and analysis module, an AI model training module, a strategy optimization and pushing module, and a remote monitoring and operation and maintenance module. The data management and analysis module has the functions of receiving massive operation data from each site, cleaning, aggregating, and statistically analyzing the data, which is the basis for AI model training and strategy optimization. The AI model training module can train and update the elevator load prediction model, the elevator energy consumption prediction model, the elevator regenerative energy prediction model, and the SOH inference model. The strategy optimization and pushing module generates the optimal strategy according to the prediction results and electricity price information and pushes it to the terminal, which further refines the execution in combination with the local real-time situation. The remote monitoring and operation and maintenance module can detect elevator energy consumption, battery health, and real-time battery information online, can calculate revenue, can provide fault alarm and predictive maintenance, can perform OTA firmware upgrade, and can remotely adjust parameters and update strategies.

[0067] The terminal 400 comprises a data acquisition unit, a control and protection unit, a model terminal processing unit, and a remote communication unit. The data acquisition unit acquires data including key parameters and real-time data. The key parameters include the counterweight weight of each elevator, the rated power of the battery module, and the rated total pressure. The real-time data is divided into model data and display data. The model data includes the real-time total power of the elevator system, the current operating state of each elevator (up, down, standby, and shutdown), the real-time load of each elevator, the charging and discharging power of the battery module, the SOC, the SOH, the operating state (charging, discharging, standby, hibernation, and shutdown), the maximum allowable charging and discharging power, the allowable charging and discharging signal, and the emergency stop instruction (if there is a battery fire or over-temperature fire hazard that affects the safety of the entire elevator system, the system safety protection instruction needs to be entered). The display data includes the battery cell voltage, temperature, and balancing information, battery management system fault information, protection threshold, and detailed information and adjustment parameters of the elevator working current, which do not participate in the model algorithm. The data acquisition unit obtains the required data from the battery management system, the elevator central system, or the data system of each elevator, the elevator system total line meter, and the battery module line meter through wired forms such as CAN bus, RS485, UART, and industrial Ethernet.

[0068] The model terminal processing unit is used for local execution of AI models, prediction models, or rule strategies, and comprises local strategies, offline self-processing software strategies, and online cloud collaborative software strategies. The local strategies are used for local control and protection, such as receiving the emergency stop instruction of the battery management system, stopping the execution of the model strategy, directly controlling the switch protection, and broadcasting the emergency stop event. In the event of a power outage, the system switches to battery power and waits for the elevator to automatically execute the automatic emergency function and perform emergency leveling and evacuation. The offline self-processing software strategy is used for local independent completion of the energy strategy and the battery module charging and discharging strategy within a short period (30 minutes to 24 hours) of the elevator system and the inherent mode of valley price period charging without prediction algorithm when there is no network or cloud available. The strategy has the ability to ensure energy-saving operation and power supply safety of the elevator offline. The online cloud collaborative strategy is used for receiving, dynamically updating, and executing the 24-hour prediction and optimization strategy issued by the cloud when the network is normal and the interaction with the cloud is normal. The strategy executes the scheduling instruction and configuration of the cloud, uploads the real-time data collected locally to the cloud for model training and updating, and displays the data. Through local and cloud collaboration, the system has both immediate responsiveness and long-term optimization capability.

[0069] The remote communication unit is used to realize the data interaction between the local device and the cloud server, which can use various communication media, including but not limited to wired Ethernet such as accessing the local area network or industrial control network of the building through the RJ45 physical interface, cellular mobile communication network (such as 4G LTE, 5G NR, NB-loT) using built-in SIM card slot / eSIM to realize remote wireless connection, low-power wireless way of accessing the local area network of the building through WiFi, Bluetooth, Sub-GHz, etc., satellite communication way of Starlink specially applied to remote island areas. It can support various industrial and Internet communication protocols such as UDP protocol, Modbus TCP, MQTT protocol, HTTPS / REST API, CoAP, and the communication protocol can be automatically switched or combined as needed to adapt to the reliability and bandwidth conditions of different network environments.

[0070] To ensure the privacy and integrity of the elevator system data, the remote communication unit has the following security functions: (1) Transmission encryption: support TLS / SSL encryption for MQTT, HTTPS and other protocols, support symmetric / asymmetric hybrid encryption method. (2) Identity authentication: realize device identity verification through device certificate, Token or key file, support cloud authorization mechanism and access control. (3) Data integrity check: use hash algorithm to check the message to prevent tampering. (4) Security isolation and protection: support port access restriction, firewall strategy, illegal access detection, and communication involving sensitive parameters uses encrypted storage and secondary check.

[0071] In addition, the elevator operation scheduling system also includes a mains module 500 and a power supply switching module 600. The mains module 500 provides basic power supply for the elevator module 100, which is the default power supply source and also provides charging power for the energy storage battery. Combined with the EMS strategy, it can charge during the low price valley stage and reduce the use of mains during the high price stage, realizing energy saving and peak regulation. The power supply switching module 600 is the energy exchange hub between the elevator module 100, the mains module 500 and the energy storage module 200, which automatically switches the mains power supply and the battery power supply, feeds the regenerative braking energy generated by the elevator operation back to the energy storage module 200, has the functions of anti-backflow, anti-island, safety isolation and state monitoring, receives terminal control instructions, realizes millisecond-level switching, and ensures the continuity of the operation of the elevator module 100.

[0072] In one exemplary embodiment, as shown in Figure 2 , a kind of elevator operation scheduling method based on energy storage module is provided, which is applied to server 300 in Figure 1 As an example for illustration, including the following steps 202 to step 206. Wherein:

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

[0074] Optionally, the peak and valley time periods and the electricity prices are manually queried on the cloud or automatically obtained through an API, entered into the server system, and pushed to all terminal devices in the same region. The cloud service can obtain the electricity prices through a time period electricity price query API and update them regularly. For regions where the API cannot query, the electricity prices can be actively queried from the electricity price website, manually entered into the cloud service platform, and regularly confirmed for changes and updated. These time period 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 the local device and extracts data for the model. The real-time data includes real-time total power of the elevator system, current operation state of each elevator (up, down, standby, and shutdown), real-time load of each elevator, charging and discharging power of the battery module, SOC, SOH, operation state (charging, discharging, standby, hibernation, and shutdown), maximum allowable charging and discharging power, etc. In the initial stage of establishing a connection between the device and the cloud, at least one week of data needs to be collected as historical data for model training. After the collection is completed, the prediction model can be executed, and the time domain data of the model optimizer is rolled over according to a T period of time (5-30 minutes). The latest strategy generated by the model is pushed to the local device.

[0075] S204: In the case where the integrity check 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 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 time.

[0076] Optionally, after receiving the elevator operation data sent by the terminal, the server judges whether the preprocessed data meets the integrity requirements of the AI model prediction. If not, the terminal continues to collect data and report it to the server. In the case where the integrity check of the elevator operation data is passed, the server calls the trained elevator load prediction AI model, performs prediction once every T period of time, combines the peak and valley electricity price time periods, and generates an elevator operation strategy for a future preset time period, such as an elevator energy-saving strategy for the next 24 hours.

[0077] The elevator load prediction model is essentially a time series prediction model (i.e., a machine learning model trained based on historical data, such as LSTM, time series attention model, etc.), and the principle is to use the time series law in the historical electricity price and historical operation data (such as the peak load of the morning peak on weekdays), combine real-time data, minimize the optimization target of the prediction power curve error, accurately predict the elevator load change and energy consumption demand in a preset time period (such as 1 hour), and then generate an adaptive strategy (such as charging the energy storage during the valley period, using the energy storage for power supply during the peak period, or recovering the electric energy to the energy storage module during braking).

[0078] S206: Send the elevator energy-saving strategy to the terminal to control the elevator module to operate according to the elevator energy-saving strategy.

[0079] Optionally, after the elevator energy-saving strategy is generated, the energy-saving strategy (including the operation period, power supply mode, power control parameter, etc.) is sent to the terminal through a specified communication protocol (such as TCP / IP). The terminal serves as an execution unit to control the power supply switching (such as switching between mains power and energy storage module) and operation parameter adjustment (such as optimizing car scheduling and reducing invalid operation energy consumption during off-peak period) of the elevator according to the strategy. Through the distributed architecture of server decision-terminal execution, the real-time landing of the strategy is realized, and the accurate execution of the scheduling instruction is ensured.

[0080] In the above elevator operation scheduling method based on the energy storage module, the server obtains the electricity price information and receives the elevator operation data sent by the terminal. In the case that the integrity check 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 of the current period, and the elevator energy-saving strategy is sent to the terminal to control the elevator module to operate according to the elevator energy-saving strategy. This can reduce the consumption of high-priced mains power, recover the regenerative electric energy during elevator braking and heavy downward travel, avoid the dissipation of energy in the form of heat consumption, reduce energy waste, adapt to the changes of electricity prices in different regions and different periods, reduce maintenance costs, balance the power supply proportion of mains power and energy storage module through strategic control, reduce the peak load pressure of the power grid, and improve 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 according to historical electricity price information and historical operation data, performing abnormality processing and completion processing on the historical sample sequence to obtain a historical training sequence; dividing the historical training sequence into a plurality of time windows according to a preset step length; constructing an elevator load prediction model; and training the elevator load prediction model by using the historical training sequence in the current time window as an optimization target to minimize the prediction power curve error, until the training stopping condition is met, and then stopping, and verifying the trained elevator load prediction model by using test set data.

[0082] Optionally, the historical sample sequence is the core data basis for model learning, and needs to contain historical electricity price information (peak and valley period, electricity price fluctuation) and historical operation data (total power, load, battery parameters, etc.) at the same time, to ensure that the model can associate electricity price characteristics with elevator operation characteristics. In the collation process, all raw data will be cleaned first, such as removing abnormal data, filling in breakpoints or missing values, and then aligning in chronological order, so that "elevator group state, battery state, load behavior" at each time can form a complete set of input information. Subsequently, the model will divide these continuous data into multiple sliding time windows, so that the model can use the past operation state to predict future energy consumption changes. For example, using a week of multi-elevator operation data as input, the model learns how to predict the power demand and load changes in 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, which can understand the linkage relationship between elevators, the periodicity of morning and evening peak, and the trend of battery power change over time. In the training process, the model will continuously adjust its internal parameters, so that its prediction value gradually approaches the actual historical data. The optimization goal is usually to minimize the error of the predicted power curve, and at the same time, a special penalty term for peak power is added in the training, so that the model pays special attention to the prediction accuracy of morning and evening peak. When the model is repeatedly trained with a large amount of historical data, and the prediction error of the validation set stabilizes and decreases, the training will automatically stop. Subsequently, the model is verified on independent test data to test its stability, peak identification ability and overall accuracy of 24-hour prediction on unseen data. The finally trained model will be deployed to the cloud or edge server for real-time inference at a minute level or shorter, to continuously provide future power and demand prediction curves for the energy management system, as an important basis for subsequent charging and discharging strategies.

[0084] Among them, the prediction strategy model is divided into a prediction layer and a decision layer. The prediction layer is based on real-time power, operation state, load, and battery management system (BMS) (SOC, SOH, charging and discharging power) of each elevator to predict the power demand and regenerative energy (granularity of 10 minutes) at each time in the next 24 hours, and outputs the predicted load demand, predicted regenerative energy, and uncertainty estimation (confidence interval) at each time step. The decision layer takes the prediction results, electricity price time sequence, and battery constraints as input to solve the 24-hour charging and discharging strategy (battery charging / discharging power at each time and power supply source allocation). The prediction layer provides input, and the optimizer executes in a 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 t (kW) and regenerative energy Rt (kW), and give the uncertainty. The model adopts Transformer to process population time series, plus Multi-Layer Perceptron (MLP) to fuse static features (including SOC, SOH). The input is the real-time total power history sequence of the elevator group , the history sequence of the running state of each elevator (e.g. up, down, standby, shutdown), the history sequence of the real-time load (kg) of each elevator , the history sequence of the battery module charging power , the history sequence of the battery module discharging power , the history sequence of SOC (%), the history sequence of SOH, the history sequence of temperature, the current city power price curve c t , time information (time, workday / weekend, holiday, peak identification), and the history sequence of the influence factor k normalized due to the increase of load (people flow) in a certain period of time caused by weather, activities, etc. The output is the future elevator group load and regenerative power at each time step. The loss function L is used to measure the deviation between the model output result and the real running data , and its mathematical expression is:

[0086]

[0087] In this embodiment, through data preprocessing, the input quality is ensured, the local time sequence features are captured through time window division, and the target is optimized, which can ensure the accurate prediction of the future load and power demand of the elevator, thereby improving the reliability of the elevator energy saving strategy and ensuring the reliability of the elevator operation scheduling.

[0088] In one exemplary embodiment, the elevator energy saving strategy carries a strategy identifier; the method further comprises: receiving a consistency verification request sent by a terminal; the consistency verification request carries a to-be-verified identifier; in the case that the to-be-verified identifier is consistent with the strategy identifier, returning a consistency success identifier to the terminal; in the case that the to-be-verified identifier is inconsistent with the strategy identifier, and there is no current elevator energy saving strategy, sending an unfinished identifier to the terminal; in the case that the to-be-verified identifier is inconsistent with the strategy identifier, and there is a current elevator energy saving strategy, sending the elevator energy saving strategy at the current time to the terminal.

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

[0090] Optionally, when the identifiers are consistent, it is confirmed that the current policy to be executed by the terminal matches the latest policy issued by the server, a success identifier is returned, and execution is allowed, avoiding the terminal executing an incorrect policy. When the identifiers are inconsistent and there is no current policy, the server has not generated a new valid policy, an incomplete identifier is returned, and the terminal is informed that there is no valid policy to execute, triggering the terminal's fallback mechanism. When the identifiers are inconsistent but there is a current policy, the server has generated a latest policy (not synchronized by the terminal), and the policy at the current time is issued to the terminal, ensuring that the terminal executes the latest scheduling policy.

[0091] In this embodiment, through the identifier uniqueness verification, the real-time performance of the elevator energy-saving policy can be ensured, the accuracy of policy execution can be ensured, and thus the reliability of the elevator energy-saving policy can be improved, and the reliability of the elevator operation scheduling can be ensured.

[0092] In one exemplary embodiment, as shown in Figure 3 , a method for elevator operation scheduling based on an energy storage module is provided. Taking the terminal 400 in Figure 1 as an example, the method includes the following steps 302 to 306. Wherein:

[0093] S302: In the case that the server is in an online state, elevator operation data is sent to the server; the elevator operation data includes total power of the elevator module, elevator operation state, elevator load, and energy storage battery parameters.

[0094] Optionally, the terminal judges whether the server is online in real time through network connectivity detection. The core principle is based on the link state feedback of network communication to ensure that 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, the total power is collected and calculated in real time through current / voltage sensors, the elevator running state (up / down / stop) is detected through travel switches and encoders, the elevator load is collected through weight sensors, and the energy storage battery parameters (voltage, power SOC, temperature) are obtained through the battery management system (BMS). The terminal encapsulates these scattered data in a preset format to ensure uniform data structure and facilitate server parsing. The specified communication protocol is used to transmit data to avoid data loss or transmission errors and ensure that the server receives complete and accurate operation data to provide reliable input for strategy generation.

[0095] S304: receiving the elevator energy-saving strategy sent by the server and controlling the elevator module to operate according to the elevator energy-saving strategy; the elevator energy-saving strategy includes an elevator operation strategy in a preset time period after the current time.

[0096] Optionally, the terminal receives the energy-saving strategy issued by the server through a communication link homologous to data uploading, parses the core parameters in the strategy (such as the power supply mode in the preset time period: energy storage power supply / mains power supply, elevator operation priority, and regenerative power recovery threshold), maps the abstract strategy to executable instructions of the elevator module and the energy storage module, and realizes the conversion from software strategy to hardware action. As the execution core, the terminal sends control signals to the modules according to the parsed instructions to ensure that the energy-saving requirements in the strategy are accurately implemented.

[0097] S306: In the case where the server is in an offline state, controlling the elevator module to operate based on the preset operation strategy and the locally stored elevator energy-saving strategy.

[0098] Optionally, the terminal is built-in with a local storage module to cache the effective energy-saving strategy previously issued by the server. When the server is offline, the terminal first reads the local storage strategy, verifies it in combination with the energy storage battery parameters (such as whether the SOC is ≥ 30% and whether the temperature is within the safe range), judges the feasibility of the strategy through the battery state, and if the SOC is too low, the energy storage power supply instruction in the local strategy is invalid, avoiding operation failure caused by mismatched battery state. If the local strategy fails to verify or there is no local storage strategy, the terminal automatically enables the preset operation strategy, which is a basic energy-saving logic (such as default peak-valley period division, priority mains power supply, and regenerative power recovery) pre-embedded in the terminal. Through the hierarchical logic of local storage strategy priority and preset strategy backup, it is ensured that the elevator can still maintain safe operation and consider energy saving when the server is offline, avoiding shutdown or disordered power consumption.

[0099] In the above elevator operation scheduling method based on the energy storage module, the terminal sends elevator operation data to the server when the server is online, 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. When the server is in an offline state, the operation of the elevator module is controlled based on the preset operation strategy and the locally stored elevator energy-saving strategy. This can ensure that the energy-saving strategy generated by the server is accurately matched with the actual operation state of the elevator and the current electricity price, reduce the operation cost, avoid abnormal operation of the elevator when the server is offline by using the locally pre-stored strategy, and further reduce energy waste.

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

[0101] Optionally, the terminal collects the core parameters of the energy storage battery in real time through the battery management system (BMS), including the remaining power (SOC), working voltage, temperature, cycle life state, etc. These parameters are the core basis for determining the feasibility of the local strategy. The terminal analyzes the locally stored elevator energy-saving strategy and compares the current parameters of the battery. If the strategy requires energy storage power supply, the SOC must be greater than or equal to the preset threshold (such as 30%), the temperature must be within the safe range (such as 0-45℃), the voltage must be stable, and there must be no overcharging or over-discharging risk. If the SOC is too low (such as <20%), the temperature is out of range, 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 an energy-saving strategy that is issued by the server when online and verified to be effective, and contains scheduling logic that adapts to elevator operation rules (such as peak load in the morning rush hour and renewable energy generation period) and electricity price characteristics. After verification, the strategy is executed to avoid the decline in energy-saving effect caused by directly switching to the basic strategy when the server is offline, and to use the locally cached strategy without the need for recalculation, thereby improving response speed. The preset operation strategy is a basic energy-saving logic that is pre-fixed in the local memory of the terminal and does not depend on server issuance. The core includes basic rules such as general peak-valley period division (such as default peak time in the morning from 7 to 9 o'clock and in the evening from 18 to 20 o'clock), power supply mode priority (such as priority power supply from the grid when the energy storage capacity is insufficient, and forced recovery of renewable energy during braking), and power control threshold. When the local strategy verification fails (such as battery status not supported) or there is no local storage strategy (such as first-time operation or loss of local cache), the terminal automatically triggers the strategy to provide a minimum guaranteed operation logic, avoiding elevator downtime while ensuring basic energy-saving effect. Moreover, the strategy does not require complex calculations and is stable and reliable in operation.

[0103] In this embodiment, the energy storage battery parameter verification avoids the execution of strategies that do not match the battery status. The terminal uses hierarchical strategy logic to autonomously respond to complex scenarios such as server offline and local strategy failure, which can further reduce energy waste and reduce operating costs.

[0104] In one exemplary embodiment, the step of controlling the elevator module to operate in accordance with the preset operation strategy includes: in the case that a time period division strategy exists locally or a time period division strategy sent by the server is received, determining the operation time period corresponding to the current time according to the time period division strategy; in the case that no time period division strategy exists locally and no time period division strategy sent by the server is received, determining the operation time period corresponding to the current time according to a preset division strategy; and controlling the elevator module to operate in accordance with the time period energy-saving strategy corresponding to the operation time period.

[0105] Optionally, the time period division strategy stored locally by the terminal (issued by the server when online and cached) or the real-time time period division strategy sent by the server has a higher priority than the preset division strategy that is pre-fixed. Such strategies are individualized time period divisions that adapt to the current region and current electricity price policy, and are more in line with actual electricity price characteristics than general preset strategies, which can improve energy-saving accuracy. Whether it is a local / server time period division strategy or a preset division strategy, the essence is a mapping rule of time interval-time period type (peak / valley / flat) (such as peak time: 7:00-9:00, 18:00-20:00; valley time: 0:00-6:00; the rest is flat). The terminal obtains the current time through the system clock, classifies the current time into corresponding peak, valley, or flat periods, and determines the electricity price attribute (high / low / flat) of the current time period through standardized time matching logic, thereby providing a basis for subsequent energy-saving strategy execution.

[0106] Optionally, the terminal predefines a fixed mapping relationship of the time period type-energy saving strategy (such as peak time: preferentially using energy storage power supply, turning off unnecessary auxiliary energy consumption, and maximizing recycled renewable energy; valley time: preferentially using commercial power to charge the energy storage, and maintaining the basic running power of the elevator; flat section: balanced use of commercial power and energy storage), which is fixed in the terminal storage and does not need server intervention. After determining the running time period, the terminal automatically calls the energy saving strategy of the corresponding time period, and sends control instructions (such as switching the power supply circuit and adjusting the charging power) to the elevator module and the energy storage module, so as to ensure that the adaptive energy saving action is performed in different electricity price time periods, and to avoid energy waste caused by indiscriminate running.

[0107] For example, if there is no peak-valley time period (such as during the initial installation and debugging period or without using the prediction model of the cloud, and without setting the peak-valley time period locally), the default peak-valley time period is used, the peak section is 8:00-11:00 16:00-24:00, the flat section is 11:00-16:00, and the valley section is 0:00-8:00. If there is a peak-valley time period (such as a parameter set manually locally or a parameter updated from the cloud to the local), the existing peak-valley time period is used. According to the current local device system time, the peak-valley time period in which the time point is located is obtained. If it is in the valley section, the battery is charged, the charging power is the maximum allowed charging power of the BMS, until it is charged to a high power threshold (such as 90%), the elevator directly uses commercial power, and the regenerated energy is stored in the battery. If it is full, it is switched back to battery power until the battery power is lower than the high power threshold (such as SOC reduced to 90%), and then switched back to commercial power. The discharging power is determined by the actual elevator system traction machine action and is not in the control item. If it is in the flat section, commercial power is used, the elevator regenerated energy is stored in the battery, if it is full, it is switched back to battery power until the battery power is lower than the high power threshold (such as SOC reduced to 90%), and then switched back to commercial power. The discharging power is determined by the actual elevator system traction machine action and is not in the control item. If it is in the peak section, the battery storage power is used, the elevator regenerated energy is stored in the battery, and the discharging power is determined by the actual elevator system traction machine action and is not in the control item. If the battery power is lower than the low power threshold (such as SOC less than 30%), commercial power is used, the elevator regenerated energy is stored in the battery. The remaining power is used as a backup power supply and battery protection for emergency use and to avoid deep discharge. The discharging power is determined by the actual elevator system traction machine action and is not in the control item.

[0108] In this embodiment, the terminal realizes differentiated scheduling of peak and valley through time period division, which can reduce high-price commercial power consumption during peak time, avoid waste of regenerated energy, adapt to accurate time period division issued by the server online, and ensure operation through preset division when there is no personalized strategy, thereby further reducing operation cost.

[0109] In an exemplary embodiment, the method further comprises: sending a consistency verification request to the server; the consistency verification request carrying the identifier to be verified; in the case of receiving a consistency success identifier returned by the server, controlling the elevator module to operate according to the current elevator energy-saving strategy; in the case of receiving an unfinished identifier returned by the server, controlling the elevator module to operate according to the preset operation strategy; in the case of receiving the elevator energy-saving strategy at the current time returned by the server, controlling the elevator module to operate according to the elevator energy-saving strategy at the current time.

[0110] Optionally, the identifier to be verified is a unique identity code of the terminal local cache or the current strategy to be executed, used to identify the identity of the strategy to be executed on the terminal side. The terminal sends a verification request to the server through a reliable communication protocol homologous to data uploading, and ensures that the request is received by the server through an acknowledgement mechanism of the protocol, while carrying the identifier to be verified to provide a comparison benchmark for the server, and check whether the strategy on the terminal side is synchronized with the latest strategy on the server side.

[0111] Optionally, in the case of receiving the consistency success identifier, it indicates that the server confirms that the identifier to be verified is consistent with the identifier of the latest strategy of the server, and it is explained that the strategy to be executed on the terminal at present is the latest valid strategy approved by the server. At this time, the terminal executes the strategy, avoiding that the terminal executes an out-of-date or incorrect strategy. In the case of receiving the unfinished identifier, it indicates that the server currently does not generate a valid and available elevator energy-saving strategy (for example, the strategy calculation is not completed, or data anomaly causes the strategy to be unable to be generated). At this time, the terminal automatically switches to the preset operation strategy, and the preset strategy is a basic operation logic pre-solidified in the terminal, ensuring that the elevator can still operate safely without losing the basic energy-saving effect when there is no valid strategy. In the case of receiving the elevator energy-saving strategy at the current time, it indicates that the identifier to be verified on the terminal does not match the identifier of the latest strategy of the server, and the server identifies that the strategy on the terminal is not synchronized through the verification request, and then supplements the valid strategy at the current time. The terminal executes the supplemented strategy to quickly synchronize the latest accurate strategy.

[0112] In the embodiment, through the identifier consistency verification, the energy-saving failure caused by the unsynchronized strategy can be avoided, the strategy update can be completed without manual intervention, the real-time performance of scheduling is ensured, and therefore the operation cost is reduced.

[0113] In an exemplary embodiment, the method further comprises: in the process of controlling the elevator module to operate according to the elevator energy-saving strategy, acquiring the current charging power; in the case of failing to pass the rationality verification of the elevator energy-saving strategy based on the current charging power, or receiving a power failure signal, stopping the process of controlling the elevator module to operate according to the elevator energy-saving strategy.

[0114] Optionally, the terminal collects data in real time through the battery management system (BMS) of the energy storage module, current sensor, and voltage sensor, providing real-time input for rationality verification. The terminal pre-stores the safe operation parameter threshold of the energy storage module (such as the maximum allowed charging power, the upper limit of charging power fluctuation, and the power limit associated with 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 strategy preset power and the safe threshold range, if the current charging power exceeds the maximum allowed value (such as the strategy requires 3kW charging, and the actual value reaches 8kW, exceeding the safe upper limit of the energy storage battery), or the power fluctuation amplitude exceeds the threshold (such as a sudden increase from 2kW to 6kW within 1 second, which may be a circuit failure), or the charging power does not match the battery state (such as continuous high-power charging after the battery is fully charged), the rationality verification is determined to be failed.

[0115] Further, the terminal is built-in with a power grid voltage detection module to monitor the state of the mains power supply in real time. When it is detected that the mains voltage is lower than the preset power-off threshold, it is determined as a power-off signal, and the emergency mechanism is triggered through the power grid power supply state feedback. At this time, the instructions in the energy-saving strategy about power supply mode switching, charging / discharging power control, etc. are terminated, and the safe operation mode is automatically switched to balance safety and operation continuity.

[0116] In this embodiment, through the charging power rationality verification, overcharging, overcurrent, and overheating faults of the energy storage battery caused by energy-saving strategy parameter deviation, circuit failure, etc. are avoided, which can avoid invalid power consumption and energy waste, and prevent chain faults caused by strategy failure, thereby improving the reliability of operation scheduling.

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

[0118] The terminal sends elevator operation data to the server when the server is in an online state, the elevator operation data including total power of the elevator module, elevator operation state, elevator load, and energy storage battery parameters, receives an elevator energy saving strategy sent by the server, and controls the elevator module to operate according to the elevator energy saving strategy; the elevator energy saving strategy including an elevator operation strategy in a preset time period after the current time; when the server is in an offline state, the terminal controls the elevator module to operate according to a locally stored elevator energy saving strategy when the locally stored elevator energy saving strategy is verified to be correct according to the energy storage battery parameters; when the locally stored elevator energy saving strategy is verified to be incorrect or does not exist, determines an operation time period corresponding to the current time according to a time period division strategy when the time period division strategy exists locally or when the time period division strategy sent by the server is received; when the time period division strategy does not exist locally and the time period division strategy sent by the server is not received, determines an operation time period corresponding to the current time according to a preset division strategy; and controls the elevator module to operate according to a time period energy saving strategy corresponding to the operation time period.

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

[0120] The server inputs current electricity price information and current elevator operation data into a trained elevator load prediction model when integrity verification of the elevator operation data is passed, and obtains an elevator energy saving strategy for a current period; the elevator energy saving strategy including an elevator operation strategy in a preset time period after the current time.

[0121] The training process of the elevator load prediction model includes: obtaining historical sample sequences according to historical electricity price information and historical operation data, performing abnormality processing and completion processing on the historical sample sequences to obtain historical training sequences; dividing the historical training sequences into a plurality of time windows according to a preset step length; constructing an elevator load prediction model; and training the elevator load prediction model by using historical training sequences in a current time window in sequence until a training stop condition is met, and verifying the trained elevator load prediction model by using test set data.

[0122] The server sends an elevator energy saving strategy to the terminal to enable the terminal to control the elevator module to operate according to the elevator energy saving strategy; the elevator energy saving strategy carrying a strategy identifier.

[0123] The terminal sends a consistency verification request to the server; the consistency verification request carries a to-be-verified identifier; in the case of receiving a consistency success identifier returned by the server, the elevator module is controlled to operate according to the current elevator energy-saving strategy; in the case of receiving an unfinished identifier returned by the server, the elevator module is controlled to operate according to a preset operation strategy; in the case of receiving an elevator energy-saving strategy at the current time returned by the server, the elevator module is controlled to operate according to the elevator energy-saving strategy at the current time.

[0124] The server receives a consistency verification request sent by the terminal; the consistency verification request carries a to-be-verified identifier; in the case of the to-be-verified identifier being consistent with the strategy identifier, a consistency success identifier is returned to the terminal; in the case of the to-be-verified identifier being inconsistent with the strategy identifier and no elevator energy-saving strategy currently existing, an unfinished identifier is sent to the terminal; in the case of the to-be-verified identifier being inconsistent with the strategy identifier and an elevator energy-saving strategy currently existing, the elevator energy-saving strategy at the current time is sent to the terminal.

[0125] In the process of controlling the elevator module to operate according to the elevator energy-saving strategy, the terminal acquires the current charging power; in the case of the current charging power failing to pass the rationality verification of the elevator energy-saving strategy or receiving a power failure signal, the process of controlling the elevator module to operate according to the elevator energy-saving strategy is stopped.

[0126] In the embodiment, the server acquires the electricity price information and receives the elevator operation data sent by the terminal, inputs the current electricity price information and the current elevator operation data into the trained elevator load prediction model in the case of the integrity verification of the elevator operation data passing, obtains the elevator energy-saving strategy of the current period, and sends the elevator energy-saving strategy to the terminal, so that the terminal controls the elevator module to operate according to the elevator energy-saving strategy, which can reduce the consumption of high-price commercial power, recover the regenerated electric energy when the elevator brakes and is heavily loaded and goes down, avoid the dissipation of energy in the form of heat consumption, reduce the waste of electric energy, adapt to the price changes of different regions and different time periods, reduce the maintenance cost, balance the power supply proportion of commercial power and energy storage module through strategic control, reduce the peak load pressure of the power grid, and improve the energy utilization efficiency of the elevator system.

[0127] It should be understood that although each step in the flowchart involved in the above embodiments is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0128] Based on the same inventive concept, the embodiments of the present application also provide a storage module-based elevator operation scheduling device for implementing the above-mentioned storage module-based elevator operation scheduling method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more storage module-based elevator operation scheduling device embodiments provided below can refer to the limitations of the storage module-based elevator operation scheduling method in the above text, which will not be repeated here.

[0129] In one exemplary embodiment, as shown in Figure 5 a storage module-based elevator operation scheduling device is provided, comprising: a data receiving module 502, a strategy generating module 504, and a strategy issuing module 506, wherein:

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

[0131] The strategy generating module 504 is configured to input current electricity price information and current elevator operation data into a trained elevator load prediction model to obtain an elevator energy-saving strategy for a current period if the integrity check of the elevator operation data passes; the elevator energy-saving strategy includes an elevator operation strategy in a preset time period after the current time.

[0132] The strategy issuing module 506 is configured to send the elevator energy-saving strategy to the terminal to enable the terminal to control the elevator module to operate according to the elevator energy-saving strategy.

[0133] In an example embodiment, the policy generation module 504 is further configured to obtain a historical sample sequence according to historical electricity price information and historical operation data, perform abnormality processing and completion processing on the historical sample sequence to obtain a historical training sequence, divide the historical training sequence into a plurality of time windows according to a preset step size, construct an elevator load prediction model, and train the elevator load prediction model by using the historical training sequence in a current time window in sequence until a training stop condition is met.

[0134] In an example embodiment, the elevator energy-saving policy carries a policy identifier; the policy issuing module 506 is further configured to receive a consistency verification request sent by a terminal, the consistency verification request carrying a to-be-verified identifier, return a consistency success identifier to the terminal in a case where the to-be-verified identifier is consistent with the policy identifier, send an unfinished identifier to the terminal in a case where the to-be-verified identifier is inconsistent with the policy identifier and no elevator energy-saving policy currently exists, and send the current elevator energy-saving policy to the terminal in a case where the to-be-verified identifier is inconsistent with the policy identifier and an elevator energy-saving policy currently exists.

[0135] In an example embodiment, as shown in FIG. 6, Figure 6 An elevator operation scheduling device based on an energy storage module is provided, which includes a data sending module 602, a policy receiving module 604, and an operation scheduling module 606, wherein:

[0136] The data sending module 602 is configured to send elevator operation data to a server in a case where the server is in an online state, the elevator operation data including total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters.

[0137] The policy receiving module 604 is configured to receive an elevator energy-saving policy sent by the server and control the elevator module to operate according to the elevator energy-saving policy, the elevator energy-saving policy including an elevator operation policy in a preset time period after a current time.

[0138] The operation scheduling module 606 is configured to control the elevator module to operate based on a preset operation policy and a locally stored elevator energy-saving policy in a case where the server is in an offline state.

[0139] In an example embodiment, the operation scheduling module 606 is further configured to control the elevator module to operate according to the locally stored elevator energy-saving policy in a case where the locally stored elevator energy-saving policy is verified to be correct according to the energy storage battery parameters, and control the elevator module to operate according to the preset operation policy in a case where the locally stored elevator energy-saving policy is verified to be incorrect or no locally stored elevator energy-saving policy exists.

[0140] In an example embodiment, the running scheduling module 606 is further configured to determine the running period corresponding to the current time according to the time period division strategy if the time period division strategy exists locally or if the time period division strategy sent by the server is received; determine the running period corresponding to the current time according to the preset division strategy if the time period division strategy does not exist locally and the time period division strategy sent by the server is not received; and control the elevator module to run according to the time period energy saving strategy corresponding to the running period.

[0141] In an example embodiment, the running scheduling module 606 is further configured to send a consistency verification request to the server, the consistency verification request carrying a to-be-verified identifier; control the elevator module to run according to the current elevator energy saving strategy if a consistency success identifier returned by the server is received; control the elevator module to run according to the preset running strategy if an unfinished identifier returned by the server is received; and control the elevator module to run according to the elevator energy saving strategy of the current time if the elevator energy saving strategy of the current time returned by the server is received.

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

[0143] The above-mentioned various modules in the elevator running scheduling device based on the energy storage module can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0144] In an example embodiment, a computer device is provided, which can be a server, and the internal structure diagram of the computer device can be as shown in Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store elevator operation data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with the terminal outside through network connection. The computer program is executed by the processor to realize an elevator operation scheduling method based on energy storage module.

[0145] In one exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps: obtaining electricity price information and receiving elevator operation data sent by a terminal; the electricity price information includes peak and valley periods and corresponding electricity prices; the elevator operation data includes total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters; in the case that the integrity check of the elevator operation data is passed, inputting the current electricity price information and the current elevator operation data into the 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 in a preset time period after the current time; sending the elevator energy saving strategy to the terminal to enable the terminal to control the elevator module to operate 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 according to historical electricity price information and historical operation data, performing abnormality processing and completion processing on the historical sample sequences to obtain historical training sequences; dividing the historical training sequences into a plurality of time windows according to a preset step length; constructing an elevator load prediction model; training the elevator load prediction model through the historical training sequences in the current time window in sequence with the optimization objective of minimizing the prediction power curve error until the training stop condition is met, and verifying the trained elevator load prediction model through test set data.

[0147] In one embodiment, the elevator energy saving strategy carries a strategy identifier; the processor, when executing the computer program, further implements the following steps: receiving a consistency verification request sent by a terminal; the consistency verification request carries a to-be-verified identifier; in the case that the to-be-verified identifier is consistent with the strategy identifier, returning a consistency success identifier to the terminal; in the case that the to-be-verified identifier is inconsistent with the strategy identifier and no elevator energy saving strategy currently exists, sending an unfinished identifier to the terminal; in the case that the to-be-verified identifier is inconsistent with the strategy identifier and an elevator energy saving strategy currently exists, sending the elevator energy saving strategy at the current time to the terminal.

[0148] In one exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the processor, when executing the computer program, implementing the following steps: in the case that a server is in an online state, sending elevator operation data to the server; the elevator operation data comprising total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters; receiving an elevator energy saving strategy sent by the server, and controlling the elevator module to operate according to the elevator energy saving strategy; the elevator energy saving strategy comprising an elevator operation strategy in a preset time period after the current time; in the case that the server is in an offline state, controlling the elevator module to operate based on a preset operation strategy and a locally stored elevator energy saving strategy.

[0149] In one embodiment, the processor, when executing the computer program, involves controlling the elevator module to operate based on the preset operation strategy and the locally stored elevator energy saving strategy, comprising: in the case that the locally stored elevator energy saving strategy is verified to be passed according to the energy storage battery parameters, controlling the elevator module to operate according to the locally stored elevator energy saving strategy; in the case that the locally stored elevator energy saving strategy is verified to be failed or no locally stored elevator energy saving strategy exists, controlling the elevator module to operate according to the preset operation strategy.

[0150] In one embodiment, the processor, when executing the computer program, involves controlling the elevator module to operate according to the preset operation strategy, comprising: in the case that a time period division strategy exists locally or a time period division strategy sent by the server is received, determining the operation time period corresponding to the current time according to the time period division strategy; in the case that no time period division strategy exists locally and no time period division strategy sent by the server is received, determining the operation time period corresponding to the current time according to a preset division strategy; controlling the elevator module to operate according to the time period energy saving strategy corresponding to the operation time period.

[0151] In one embodiment, the processor, when executing the computer program, further implements the following steps: sending a consistency verification request to the server; the consistency verification request carrying the identifier to be verified; in the case of receiving a consistency success identifier returned by the server, controlling the elevator module to operate according to the current elevator energy-saving strategy; in the case of receiving an unfinished identifier returned by the server, controlling the elevator module to operate according to the preset operation strategy; in the case of receiving the elevator energy-saving strategy at the current time returned by the server, controlling the elevator module to operate according to the elevator energy-saving strategy at the current time.

[0152] In one embodiment, the processor, when executing the computer program, further implements the following steps: in the process of controlling the elevator module to operate according to the elevator energy-saving strategy, acquiring the current charging power; in the case of failing to pass the rationality verification of the elevator energy-saving strategy based on the current charging power or receiving a power failure signal, stopping the process of controlling the elevator module to operate according to the elevator energy-saving strategy.

[0153] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0154] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0155] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0156] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0157] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for elevator operation scheduling based on energy storage module, characterized in that, The application is applied to a server, and the method comprises: Obtaining electricity price information and receiving elevator operation data sent by a terminal; the electricity price information comprises peak and valley time periods and corresponding electricity prices; the elevator operation data comprises total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters; In the case that the integrity of the elevator operation data is verified, current electricity price information and current elevator operation data are input into a trained elevator load prediction model to obtain an elevator energy-saving strategy for a current period; the elevator energy-saving strategy comprises an elevator operation strategy in a preset time period after a current time; the training process of the elevator load prediction model comprises: obtaining historical sample sequences according to historical electricity price information and historical operation data, performing abnormality 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 length; constructing an elevator load prediction model; and training the elevator load prediction model through the historical training sequences in a current time window in sequence until a training stop condition is met, and verifying the trained elevator load prediction model through test set data. The elevator energy-saving strategy is sent to the terminal to control the elevator module to operate according to the elevator energy-saving strategy.

2. The method of claim 1, wherein, The elevator energy-saving strategy carries a strategy identifier; the method further comprises: Receiving a consistency verification request sent by the terminal; the consistency verification request carries a to-be-verified identifier; In the case that the to-be-verified identifier is consistent with the strategy identifier, a consistency success identifier is returned to the terminal; In the case that the to-be-verified identifier is inconsistent with the strategy identifier and there is no current elevator energy-saving strategy, an unfinished identifier is sent to the terminal; In the case that the to-be-verified identifier is inconsistent with the strategy identifier and there is a current elevator energy-saving strategy, the elevator energy-saving strategy at a current time is sent to the terminal.

3. A method for operating scheduling of an energy storage elevator module, characterized by, The application is applied to a terminal, and the method comprises: In the case that a server is in an online state, elevator operation data is sent to the server; the elevator operation data comprises total power of an elevator module, elevator operation state, elevator load, and energy storage battery parameters; The elevator energy-saving strategy of claim 1 is received, and the elevator module is controlled to operate according to the elevator energy-saving strategy; the elevator energy-saving strategy comprises an elevator operation strategy in a preset time period after a current time; In the case that the server is in an offline state, the elevator module is controlled to operate based on a preset operation strategy and a locally stored elevator energy-saving strategy.

4. The method of claim 3, wherein, The elevator module is controlled to operate based on the preset operation strategy and the locally stored elevator energy-saving strategy, which comprises: In the case that the locally stored elevator energy-saving strategy is verified according to the energy storage battery parameters, the elevator module is controlled to operate according to the locally stored elevator energy-saving strategy; In the case that the locally stored elevator energy-saving strategy is not verified to be passed or there is no locally stored elevator energy-saving strategy, the elevator module is controlled to operate according to a preset operation strategy.

5. The method of claim 4, wherein, The control of the elevator module according to the preset operation strategy comprises: In the case that a time period division strategy exists locally or the time period division strategy sent by the server is received, a running time period corresponding to the current time is determined according to the time period division strategy; In the case that no time period division strategy exists locally and the time period division strategy sent by the server is not received, a running time period corresponding to the current time is determined according to a preset division strategy; The elevator module is controlled to operate according to the time period energy-saving strategy corresponding to the running time period.

6. The method of claim 3, wherein, The method further comprises: sending a consistency verification request to the server, the consistency verification request carrying a to-be-verified identifier; in the case that a consistency success identifier returned by the server is received, the elevator module is controlled to operate according to the current elevator energy-saving strategy; in the case that an unfinished identifier returned by the server is received, the elevator module is controlled to operate according to the preset operation strategy; in the case that the elevator energy-saving strategy of the current time returned by the server is received, the elevator module is controlled to operate according to the elevator energy-saving strategy of the current time.

7. The method of claim 3, wherein, The method further comprises: in the process of controlling the elevator module to operate according to the elevator energy-saving strategy, the current charging power is acquired; in the case that the current charging power is not verified to be passed based on the current charging power or a power failure signal is received, the process of controlling the elevator module to operate according to the elevator energy-saving strategy is stopped.

8. An energy storage module based elevator operation scheduling system, characterized by, comprise: an elevator module; an energy storage module comprising an energy storage battery, configured to provide the elevator module with power required for operation and receive regenerated power generated by the elevator module; a server configured to acquire electricity price information and receive elevator operation data sent by a terminal, the electricity price information comprising peak and valley time periods and corresponding electricity prices, the elevator operation data comprising total power of the elevator module, elevator operation state, elevator load and energy storage battery parameters, and further configured to, in the case that the integrity of the elevator operation data is verified to be passed, input current electricity price information and current elevator operation data into a trained elevator load prediction model to obtain an elevator energy-saving strategy of a current period; The elevator energy-saving strategy comprises an elevator operation strategy in a preset time period after a current time; wherein, the training process of the elevator load prediction model comprises: obtaining a historical sample sequence according to historical electricity price information and historical operation data, performing abnormality processing and completion processing on the historical sample sequence to obtain a historical training sequence; dividing the historical training sequence into a plurality of time windows according to a preset step length; constructing an elevator load prediction model; training the elevator load prediction model through the historical training sequence in a current time window in sequence with a minimum prediction power curve error as an optimization target, stopping until a training stop condition is met, and verifying the trained elevator load prediction model through test set data; and further used for sending the elevator energy-saving strategy to the terminal; The terminal is used for sending elevator operation data to the server when the server is in an online state; further used for receiving the elevator energy-saving strategy sent by the server and controlling the elevator module to operate according to the elevator energy-saving strategy; and further used for controlling the elevator module to operate based on a preset operation strategy and a locally stored elevator energy-saving strategy when the server is in an offline state. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

Images