Elevator group control energy-saving scheduling method and system based on load prediction

Abstract

The application relates to the technical field of elevator dispatching optimization, in particular to an elevator group control energy-saving dispatching method and system based on load prediction, which comprises the following steps: analyzing actual passenger flow with the same time property as the current time in elevator historical operation data, constructing a first prediction factor, taking the first prediction factor as a benchmark prediction value, analyzing the similarity of the first prediction factor with all historical operation data, assigning a contribution weight to the historical operation data of each day, constructing a second prediction factor, obtaining a passenger flow prediction value, and finally correcting the passenger flow prediction value in real time according to the difference between the passenger flow prediction value and the actual passenger flow load of the day; and constructing an adaptive inertia weight of a particle swarm algorithm based on the passenger flow prediction correction value, and finding an optimal solution for response scheduling. The application aims to improve the dispatching efficiency of the whole elevator group.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator dispatching optimization, in particular to an elevator group control energy-saving dispatching method and system based on load prediction. BACKGROUND

[0002] Elevators are key facilities for vertical transportation. With the development of the construction industry, the height and area of high-rise buildings in cities are becoming larger and larger. Large-scale elevator groups are usually equipped in buildings to meet the needs and efficiency of people going up and down. With the continuous development of various sensor technologies and intelligent control devices, the elevator control system is no longer limited to single elevator control. The demand for group control elevator systems in buildings is increasing. In order to improve the operation efficiency of elevators in the whole building, how to efficiently judge the demand for elevators to intelligently dispatch the elevator group, and design a more intelligent and efficient energy-saving elevator group control dispatching method is an important problem.

[0003] Most of the current elevator group control dispatching methods are based on traditional dispatching algorithms or intelligent heuristic optimization algorithms to calculate the comprehensive evaluation value of the elevator responding to the actual call request according to multiple performance indicators of the elevator. Then, the elevators are dispatched to complete the demand for elevators at the actual call request according to the comprehensive evaluation value of each elevator. However, this elevator group control dispatching method does not take into account the actual passenger flow load data of each floor at different time periods, which leads to poor elevator floor at time periods corresponding to early and late passenger flow load peaks, long waiting time for users, and affects the efficiency of elevator dispatching. On the other hand, when facing actual call requests, large elevator group control systems will dispatch multiple elevators to work. When the passenger flow is small, it is inevitable to cause the empty running of multiple elevators, which increases the use frequency and start-stop times of elevators, resulting in a large waste of energy and affecting the efficiency of elevator dispatching. SUMMARY

[0004] In view of the above, it is necessary to provide an elevator group control energy-saving dispatching method and system based on load prediction to solve the above problems.

[0005] The first aspect of the present application provides an elevator group control energy-saving dispatching method based on load prediction, which comprises:

[0006] Using the historical operation data of the elevator group, the periodic distribution characteristics of the actual passenger flow of each floor at the current time period and the similarity degree with the distribution of the actual passenger flow in the historical operation data are analyzed to determine the passenger flow prediction value of each floor at the current time period.

[0007] determining a crowd flow prediction error of each floor in the current time period based on the overall variation characteristics of the difference between the crowd flow prediction value and the actual crowd flow in all reference correction time periods of the current time period, correcting the crowd flow prediction value to obtain a crowd flow prediction correction value of each floor in the current time period;

[0008] judging the load vacancy of the elevator based on the crowd flow prediction correction value and the actual load capacity of the elevator, and adjusting the fixed inertia weight of the particle swarm algorithm based on the crowd flow prediction correction value of all floors in the current time period to find an optimal solution for response scheduling.

[0009] The process of determining the crowd flow prediction value of each floor in the current time period includes:

[0010] determining a first prediction factor of each floor in the current time period based on the periodic distribution characteristics;

[0011] analyzing the distribution similarity between the first prediction factor and the actual crowd flow in the historical operation data to determine a second prediction factor of each floor in the current time period;

[0012] For each floor in each time period, the first prediction factor and the second prediction factor are weighted, and the integer value of the weighted sum is taken as the crowd flow prediction value.

[0013] The first prediction factor of each floor in the current time period is determined by:

[0014] In the historical operation data corresponding to the current time, the average value of the actual crowd flow of each floor in the same time period is obtained, which is the same as the week number of the current time, as the first prediction factor of each floor in the current time period.

[0015] The second prediction factor of each floor in the current time period is determined by:

[0016] encoding all the first prediction factors obtained on the day to obtain an encoding matrix;

[0017] encoding all the actual crowd flow of each day in the historical operation data of the day to obtain each reference encoding matrix corresponding to the current time;

[0018] calculating the similarity between the encoding matrix of the day and each reference encoding matrix thereof, and taking the proportion of the similarity between the encoding matrix of the day and each reference encoding matrix thereof as the weight of the actual crowd flow of each floor in the current time period of the corresponding historical day, and weighting and summing to obtain the second prediction factor of each floor in the current time period.

[0019] Wherein, each row of the encoding matrix corresponds to each time period of the day, and each column corresponds to each floor.

[0020] Wherein, the current time period each floor flow prediction error is determined, and the specific process is:

[0021] For each reference correction time period of the current time period each floor, the difference between the flow prediction value and the actual flow is calculated, and the negative correlation mapping of the flow prediction value is positively fused, and the average of the positive fusion results of all reference correction time periods is obtained. The flow prediction error of each floor in the current time period is obtained.

[0022] Wherein, the current time period each floor flow prediction correction value is obtained, and the specific process is:

[0023] The difference between the natural number 1 and the flow prediction error of each time period each floor is calculated, and then the flow prediction value of each time period each floor is positively fused to obtain the flow prediction correction value of each time period each floor.

[0024] Wherein, the load empty condition of the elevator is judged, and the specific process is:

[0025] For the ratio of the current time period each floor flow prediction correction value to the actual load capacity of the elevator, when the ratio is greater than or equal to the preset threshold, a virtual call request is sent to the corresponding floor; otherwise, it is not triggered.

[0026] Wherein, the fixed inertia weight of the particle swarm algorithm is adjusted, and the specific process is:

[0027] If the elevator sends a virtual call request, for the current time period, the total number of flow prediction correction values of all floors is calculated; the average of the actual flow of all floors in the same time period as the current time in the historical operation data is calculated; the ratio between the total number and the average is calculated, and then multiplied by the preset fixed weight to obtain the adaptive inertia weight.

[0028] In a second aspect, the embodiments of the present application also provide an elevator group control energy-saving scheduling system based on load prediction, comprising a memory, a processor and a computer program stored in the memory and running on the processor. The processor executes the computer program to realize the steps of the method described in any one of the above aspects.

[0029] The present application has at least the following beneficial effects:

[0030] The application first analyzes the overall distribution characteristics of the actual passenger flow in the historical operation data of the elevator group with the same time property as the current time for each floor, determines the first prediction factor of each floor in the current time period, and uses the historical data, especially the elevator operation data of the same week and time period as the current time, to establish a baseline prediction model reflecting the periodicity and regularity of passenger flow, providing a more accurate preliminary prediction to help the system identify regular and stable passenger flow time periods, and helping to predict the load of elevators in each floor in the time period to avoid overcrowding or empty loading of elevators in some floors.

[0031] Secondly, the similarity of the first prediction factor and the distribution of the actual passenger flow in the historical operation data is analyzed to determine the second prediction factor of each floor in the current time period. By comparing the first prediction value and the distribution of the actual passenger flow, the prediction is further adjusted to ensure that the prediction is closer to the actual situation, better cope with possible changes in the actual environment, and more accurately reflect the specific passenger flow status of the current time period, thereby avoiding overestimation or underestimation of passenger flow.

[0032] Further, the concept of reference correction time period is introduced to compare the differences between the current time period and the similar past time period, and further correct the passenger flow prediction. Through the correction error, a more accurate passenger flow prediction correction value can be obtained, which can adapt to the particularity of different floors and time periods, make the elevator dispatching more flexible, avoid errors caused by single prediction mode, reduce the fluctuation of elevator load by correcting prediction error, and improve the stability of the elevator group control system.

[0033] Based on the passenger flow prediction correction value and the actual load capacity of the elevator, it is determined whether the elevator sends a virtual call request. The key is that the actual load capacity of the elevator matches the predicted passenger flow. In this stage, if the prediction value indicates that the elevator load is close to saturation in a certain time period, the system may trigger a virtual call request to dispatch the elevator in advance. By predicting the load of the elevator in advance, overcrowding of the elevator can be avoided, the dispatching response can be started in advance, the waiting time can be reduced, more elevator resources can be allocated during peak periods, and passengers in some floors can be avoided from waiting for a long time due to insufficient elevator capacity.

[0034] Finally, if the elevator sends a virtual call request, the fixed inertia weight of the particle swarm algorithm is adjusted based on the passenger flow prediction correction value of all floors in the current time period to find the optimal solution for response scheduling. After the virtual call request is sent, the inertia weight of the elevator dispatching is adjusted using the particle swarm optimization algorithm to optimize the elevator dispatching scheme. The particle swarm algorithm simulates group behavior to find the optimal solution, thereby achieving more efficient dispatching decisions. By dynamically adjusting the inertia weight, the optimal solution can be quickly found in a complex elevator dispatching environment to ensure optimal allocation of resources and improve the efficiency of the entire elevator group. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A step flow chart of the load prediction based energy saving scheduling method of elevator group control provided by an embodiment of the present application is shown in FIG. 1.

[0036] Figure 2 A flow chart of obtaining the passenger flow prediction correction value provided by an embodiment of the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0037] In the description of the embodiments of the present application, the words "exemplary", "or", "for example", and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of the words "exemplary", "or", "for example" is intended to present related concepts in a specific way.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terminology used in the specification of the present application is only for the purpose of describing specific embodiments and is not intended to limit the present application.

[0039] In addition, it should be pointed out that the terms "first", "second" in the present application and the drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method, and the execution order of the steps can be interchanged with each other without departing from the scope of the present application, and some steps can also be deleted.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0041] The specific solutions of the load prediction based energy saving scheduling method and system of elevator group control provided by the present application will be specifically described below in combination with the drawings.

[0042] Please refer to Figure 1 A step flow chart of the load prediction based energy saving scheduling method of elevator group control provided by an embodiment of the present application is shown in FIG. 1, which includes the following steps:

[0043] First step: obtaining the running data of the elevator group.

[0044] Obtain the operation data of the elevator group. The operation data includes: the number of floors of the current building, the number of elevators, the current state of each elevator (floor, running state: up / down / stationary, arrival floor), actual call request (floor, number, time), passenger flow load data of the elevator.

[0045] Among them, the current state of the elevator, the actual call request data is obtained through the elevator control system; the passenger flow load data of the elevator is obtained through the infrared counter at the entrance of the elevator. Specifically, the passenger flow load refers to the total number of people entering all elevators in the elevator group in a period of time.

[0046] For each day, obtain the historical operation data of the elevator group. The historical operation data of the elevator group includes historical actual call request and historical passenger flow load data of the elevator. The number of days for obtaining the historical operation data is days, and the implementer can set it according to the implementation scene, without special limitation. In this embodiment, the value is 45.

[0047] The second step: using the historical operation data of the elevator group, analyzing the periodic distribution characteristics of the actual passenger flow of each floor in the current time period, and the similarity degree with the distribution of the actual passenger flow in the historical operation data, to determine the passenger flow prediction value of each floor in the current time period.

[0048] In the dispatching control of the elevator group, the traditional dispatching algorithm usually selects the optimal elevator for dispatching based on the real-time call request and the current running state of each elevator, which can realize fast response to dispatching tasks. However, these methods do not fully consider the passenger flow load data in different time periods, so the elevator control system only starts to dispatch the elevator when it receives the actual call request. In the morning and evening peak period, the passenger flow is large, and some elevators may be at a floor with low demand, resulting in a long waiting time for passengers. In addition, during the low-usage period, the elevator control system fails to predict the change of passenger flow, which may dispatch multiple elevators to run at the same time, causing some elevators to run empty, thereby causing energy waste. Therefore, accurate passenger flow load prediction and the accuracy of prediction data are of great significance to improve the efficiency and energy-saving effect of elevator group dispatching.

[0049] ​Traditional passenger flow load prediction methods usually rely on daily historical data in the short term and use simple time series average method for prediction. However, these methods fail to fully consider the significant influence of building type, working day and working time on passenger flow pattern, resulting in low accuracy of the prediction model and difficulty in effectively reflecting actual passenger flow fluctuations and elevator demand, thereby affecting the efficiency and energy saving effect of elevator group scheduling control. The traditional method assumes that the distribution of passenger flow remains fixed in different days and the same time period, but in fact, the passenger flow patterns of different types of buildings (such as office buildings, shopping malls, entertainment venues, etc.) differ greatly. If these heterogeneous data are treated indiscriminately, it is easy to cause the prediction result to deviate from the actual situation and fail to accurately reflect the real passenger flow pattern.

[0050] For some specific types of buildings, such as office buildings and school teaching buildings, there is a clear fixed pattern of uplink and downlink flow during working days, and there are significant different distribution characteristics during non-working days. Therefore, the present application takes 7 days as a cycle, considers the distribution characteristics of passenger flow data with the same week number as the current time in the historical operation data of the elevator to extract the periodic and regular passenger flow characteristics, and then obtains the statistically significant baseline prediction value.

[0051] Specifically, a day is divided into a preset number of time periods and numbered in chronological order. In this embodiment, each time period corresponds to a time length of 15 minutes, and the implementer can adjust it according to the actual situation; in the historical operation data corresponding to the current time, the average of the actual passenger flow of each floor in the same time period is obtained, which is the same as the week number of the current time, as the first prediction factor of each floor in the current time period.

[0052] Specifically, the formula of the first prediction factor in this embodiment is:

[0053]

[0054] In the formula, count represents the count parameter; D represents the number of days of historical operation data; % represents the modulo operation; d represents the order in the historical operation data that is the same as the week number of the current time; represents the actual passenger flow of the kth floor in the jth time period of the dth day in the historical operation data; represents the floor of the kth floor in the jth time period of the dth day in the historical operation data;

[0055] ​​​​​​​​The average of the passenger flow corresponding to the day with the same week number as the current time in the historical data is calculated as the baseline prediction value reflecting the periodicity of the passenger flow. This method can effectively exclude the interference of special factors such as holidays on the prediction results, and ensure that the prediction is more in line with the passenger flow mode of regular working days.

[0056] However, the first prediction factor only relies on the average of the historical running data with the same week number, which ignores the potential complex changes and uncertainty factors in the historical data. When special circumstances interfere, the first prediction factor cannot reflect the impact of these interference factors on the passenger flow, resulting in deviation of the results from the actual demand.

[0057] Further, in order to better quantify the impact of the fluctuating changes of the passenger flow under special circumstances on the periodicity, the similarity between the first prediction factor and the passenger flow load data in the historical running data is analyzed to obtain a more realistic passenger flow mode.

[0058] The first prediction factor and the passenger flow load data in the historical running data in the entire building are encoded: each row of the encoding matrix corresponds to each time period, and each column corresponds to each floor, to obtain the respective corresponding encoding matrix , ; wherein, represents the encoding matrix of the first prediction factor on the day; represents the dth reference encoding matrix in the historical running data on the day; K represents the number of time periods in a day; represents the total number of floors; represents the matrix. The similarity between the encoding matrix of the first prediction factor on the day and each reference encoding matrix thereof is calculated, and in this embodiment, the similarity between the two matrices is determined by normalized mutual information, wherein the normalized mutual information is a prior art and its specific process will not be repeated.

[0059] The similarity between the encoding matrix on the day and each reference encoding matrix thereof is calculated, and the proportion of the similarity between the corresponding encoding matrix on the day and each reference encoding matrix thereof is taken as the weight of the actual passenger flow of each floor at the current time period of each day, and the weighted sum is taken to obtain the second prediction factor of each floor at the current time period.

[0060] Specifically, in this embodiment, the specific formula of the second prediction factor is:

[0061]

[0062] In the formula, represents the second prediction factor of the kth time period and the fth floor; similarity between the encoding matrix of the first prediction factor of the kth time period and the fth floor and the dth reference encoding matrix; number of days representing historical operation data; the kth time period and the fth floor in the dth day of historical operation data; the kth time period and the fth floor in the dth day of historical operation data; the kth time period and the fth floor in the dth day of historical operation data; the kth time period and the fth floor in the dth day of historical operation data.

[0063] It should be understood that in the formula, the numerator represents the similarity between the encoding matrix of the first prediction factor and the encoding matrix of the historical operation data of the dth day, and the denominator represents the sum of the similarities between the encoding matrix of the first prediction factor and the encoding matrix of the historical operation data of all days.

[0064]

[0065]

[0066]

[0067] ​​​​​​​​​​​​​​​​​​​​​​The third step is to preset reference correction time periods for each time period, compare the overall change characteristics of the difference between the predicted and actual pedestrian flow in all reference correction time periods of the current time period, determine the pedestrian flow prediction error for each floor in the current time period, correct the pedestrian flow prediction value, and obtain the corrected pedestrian flow prediction value for each floor in the current time period.

[0068] The first and second predictive factors predict pedestrian flow from the perspectives of periodic regularity and similarity of pedestrian flow patterns, respectively. In order to further improve the accuracy of the pedestrian flow prediction correction value, the pedestrian flow prediction correction value is corrected in real time by analyzing the error difference between the actual pedestrian flow pattern before the day and the pedestrian flow prediction value.

[0069] Specifically, the first day A period of time before Using a time period as a reference correction period for the k-th time period of the day, we analyze the prediction error of pedestrian flow at each level and construct an error correction term. The size can be set by the implementer according to the implementation scenario, without special restrictions. In this embodiment... The value is 4; where the reference correction period is the same day as the current period.

[0070] Furthermore, for each floor in the current time period, the difference between the predicted and actual pedestrian flow for each reference correction time period is calculated, and positive fusion is performed with the negative correlation mapping of the predicted pedestrian flow. The average of the positive fusion results obtained from all reference correction time periods is calculated to obtain the pedestrian flow prediction error for each floor in the current time period. In this embodiment, the difference between two variables is calculated using the difference value, and the negative correlation mapping result of the variables is calculated using the reciprocal of the variables. It should be noted that to prevent the denominator from being 0, a preset value needs to be added to the denominator. In this embodiment, the preset value is 0.01. The positive fusion of multiple variables is performed using a multiplication calculation method. The formula for calculating the pedestrian flow prediction error of the f-th floor in the k-th time period of the day is as follows:

[0071]

[0072] In the formula, Indicates the first The first time period Error in predicting pedestrian traffic on each floor Indicates the first The t-th reference correction time period of the t-th time period Predicted pedestrian traffic for each floor Indicates the first The t-th reference correction time period of the t-th time period The actual foot traffic on each floor represents a preset value, and the value is 0.01; T represents the number of reference correction time periods of a time period.

[0073] In particular, when the number is less than or equal to 4, the average of the actual passenger flow of all time periods before the time period of the number in the historical operation data is calculated. The error is calculated.

[0074] Finally, the passenger flow prediction correction value of each time period and each floor is specifically: the difference between the natural number 1 and the passenger flow prediction error of each time period and each floor is calculated, and then the passenger flow prediction value obtained for each time period and each floor is positively fused to obtain the passenger flow prediction correction value of each time period and each floor. In this embodiment, the calculation method of multiplication is adopted for the positive fusion of the plurality of variables. The flowchart for obtaining the passenger flow prediction correction value is shown in Figure 2

[0075] When the passenger flow prediction error is negative, it indicates that the predicted passenger flow in the previous time period of the time period is less than the real passenger flow. In order to avoid error accumulation leading to inaccurate prediction results, the difference between the natural number 1 and the passenger flow prediction error is used to increase the passenger flow prediction correction value of the time period. Conversely, when the passenger flow prediction error is positive, it indicates that the predicted passenger flow in the previous time period of the time period is higher than the real passenger flow, and then the passenger flow prediction correction value of the time period is reduced. By continuously comparing the predicted passenger flow with the actual passenger flow, the prediction result can be adjusted in real time, thereby reducing the deviation. This dynamic correction method enables the prediction to be continuously optimized according to the changes of the scene, thereby improving the accuracy of the passenger flow prediction.

[0076] The fourth step: based on the passenger flow prediction correction value and the actual load capacity of the elevator, the load empty condition of the elevator is judged, and based on the passenger flow prediction correction value of all floors in the current time period, the fixed inertia weight of the particle swarm algorithm is adjusted to find the optimal solution for response scheduling.

[0077] Further, the elevator group control scheduling is performed based on the passenger flow prediction correction value and the operation data of the elevator group. The specific steps are as follows:

[0078] The first time period is divided into a plurality of time periods, and the passenger flow prediction error of each time period is calculated. ​​​​​​​​​​The predicted correction value of the passenger flow of each floor in each time period is sorted from large to small, a virtual call request is generated in the elevator control system, and an elevator is dispatched to the floor with a larger passenger flow intensity to wait, and the elevator responding to the virtual call request does not include an elevator that is running, so that the user waiting time is reduced by scheduling the elevator to run in advance during a passenger flow peak period.

[0079] Further, the predicted correction value of the passenger flow of each floor is divided by the actual load capacity of the elevator, wherein represents the actual load capacity of the elevator, if the elevator control system does not trigger a virtual call request for the floor, and the elevator remains in a standby state; otherwise, the elevator control system triggers a virtual call request for the floor. The purpose is to dispatch the elevator to respond to an actual call request when the predicted passenger flow of multiple floors is low, to keep part of the elevators in a standby state, to avoid waste of resources caused by frequent empty running of the elevators, and to improve the energy-saving effect of the elevator system.

[0080] Further, for an actual call request of the elevator system, an adaptive inertia weight is constructed based on the predicted correction value of the passenger flow, and specifically, for a current time period, the total number of the predicted correction values of the passenger flow of all floors is calculated; the average of the actual passenger flow of all floors in the same time period as the current time in the historical operation data is calculated; the ratio between the total number and the average is calculated, and then multiplied by a preset fixed weight to obtain the adaptive inertia weight.

[0081] In the embodiment, the specific formula of the adaptive inertia weight is: wherein represents the total number of the predicted correction values of the passenger flow of all floors in the current time period, represents the average of the total number of the passenger flow of all floors in the first time period in the historical operation data, represents the inertia weight of the particle swarm algorithm, and the setting method is a known technology, which will not be described here; represents the size of the predicted correction value of the passenger flow in the first time period relative to the average of the total number of the passenger flow in the first time period in the historical operation data.

[0082] The greater the value is, the more the current passenger flow is, and the more the passenger flow in this time period is relative to the historical operation data, and the inertia weight is increased to improve the global exploration ability of the particle swarm algorithm, and to increase the exploration space to find the optimal solution under a high passenger flow load; when the smaller the value is, the less the current passenger flow is, and the less the passenger flow in this time period is relative to the historical operation data, and the inertia weight is reduced , tend to local fine search, quickly find the optimal solution to respond to scheduling. According to the intensity of the flow of people to dynamically adjust the search strategy of the particle swarm algorithm, so as to realize the adaptive exploration of the elevator scheduling scheme, improve the scheduling efficiency and energy saving effect of the elevator control system. Among them, the particle swarm optimization algorithm used for elevator scheduling is the prior art, which will not be described here.

[0083] Based on the same inventive concept as the above method, the embodiment of the application also provides an elevator group control energy-saving scheduling system based on load prediction, comprising a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of the method described in any one of the above methods when executing the computer program.

[0084] The flowcharts and block diagrams in the drawings show the possible implementation architecture, function and operation of the system, method and computer program product according to the embodiments of the application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logic function. In some alternative implementations, the functions annotated in the blocks can also occur in different order from that annotated in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. In the description corresponding to the flowchart and block diagram in the drawings, the operations or steps corresponding to different blocks can also occur in different order from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0085] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the essential characteristics of the present application. Therefore, the above-described embodiments of the present application should be regarded as exemplary and non-limiting in any respect; any modification to the technical solutions described in the foregoing embodiments, or equivalent replacement of part of the technical features, does not make the essence of the corresponding technical solution deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A load prediction based energy saving dispatching method for elevator group control, characterized in that, The method includes the following steps: By using historical operation data of the elevator group, we can analyze the periodic distribution characteristics of the actual passenger flow on each floor during the current time period and the degree of similarity between the distribution of actual passenger flow and the historical operation data, and determine the predicted value of passenger flow on each floor during the current time period. Preset reference correction time periods for each time period, compare the overall change characteristics of the difference between the predicted and actual pedestrian flow in all reference correction time periods of the current time period, determine the pedestrian flow prediction error for each floor in the current time period, correct the pedestrian flow prediction value, and obtain the pedestrian flow prediction correction value for each floor in the current time period. Based on the predicted passenger flow correction value and the actual load capacity of the elevator, the load availability of the elevator is determined, and based on the predicted passenger flow correction value of all floors in the current time period, the fixed inertia weight of the particle swarm algorithm is adjusted to find the optimal solution for response scheduling. The process of determining the predicted pedestrian flow for each floor in the current time period is as follows: In the historical data corresponding to the current moment, obtain the average actual passenger flow of each floor in the same time period that has the same week number as the current moment, and use it as the first predictor for each floor in the current time period; Encode all the first predictor factors obtained on the same day to obtain the encoding matrix; Encode all actual passenger flow for each day in the historical operational data of the day, and obtain each reference coding matrix corresponding to the current moment; Calculate the similarity between the coding matrix of the day and each of its reference coding matrices. Use the similarity ratio between the coding matrix of the day and each of its reference coding matrices as the weight of the actual foot traffic of each floor in the current time period of each historical day. Sum the weighted data to obtain the second prediction factor for each floor in the current time period. For each time period and each floor, the first and second predictive factors are weighted respectively, and the weighted sum is rounded down to obtain the predicted pedestrian flow value.

2. The load prediction based energy saving dispatching method of elevator group control according to claim 1, wherein, Each row of the encoding matrix corresponds to a time period of the day, and each column corresponds to a floor.

3. The load prediction based energy saving scheduling method of elevator group control according to claim 1, wherein, The specific process for determining the predicted pedestrian flow error for each floor during the current time period is as follows: For each floor in the current time period, calculate the difference between the predicted and actual pedestrian flow for each reference correction time period, and perform positive fusion with the negative correlation mapping of the predicted pedestrian flow. Average the positive fusion results obtained from all reference correction time periods to obtain the pedestrian flow prediction error for each floor in the current time period.

4. The load prediction based energy saving scheduling method of elevator group control according to claim 1, wherein, The specific process for obtaining the predicted and corrected pedestrian flow values ​​for each floor during the current time period is as follows: Calculate the difference between the natural number 1 and the predicted pedestrian flow error for each floor in each time period, and then perform a positive fusion with the predicted pedestrian flow value obtained for each floor in each time period to obtain the corrected pedestrian flow prediction value for each floor in each time period.

5. The load prediction based energy saving scheduling method of elevator group control according to claim 1, wherein, The determination of the elevator's load availability is specifically as follows: For the ratio of the predicted passenger flow correction value for each floor in the current time period to the actual load capacity of the elevator, when the ratio is greater than or equal to a preset threshold, a virtual response request is sent to the corresponding floor; otherwise, it is not triggered.

6. The load prediction based energy saving scheduling method of elevator group control according to claim 1, wherein, The adjustment of the fixed inertia weights in the particle swarm optimization algorithm is specifically as follows: If the elevator sends a virtual call request, the total number of the traffic flow prediction correction values of all floors in the current time period is calculated; the mean value of the actual traffic flow of all floors in the same time period as the current time in the historical operation data is calculated; The ratio between the total number and the mean value is calculated, and then multiplied by a preset fixed weight to obtain an adaptive inertia weight.

7. An elevator group control energy-saving scheduling system based on load prediction, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that, The processor implements the steps of the method of any one of claims 1-6 when executing the computer program.

Images