JPS6327263B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] This invention relates to an improvement of a device for estimating demand such as traffic volume and electric power load.

[Conventional technology] The traffic volume of elevators in buildings, the power load of power plants, etc. (hereinafter simply referred to as demand) may fluctuate irregularly when looked at in detail on a single day, but when looked at over several days, they fluctuate irregularly. The situation is similar at the same time of day. For example, in an office building, during morning work hours, passengers who go to the office floor for a short time concentrate on the first floor, and during the first half of lunch time, many passengers go from the office floor to the cafeteria floor. Similarly, in the second half, many passengers go from the dining room floor to the office floor. Also, during the evening hours when work is finished, the area is occupied by passengers going from the office floor to the first floor. During the daytime hours other than those mentioned above, the traffic volumes in the up and down directions are almost equal, and at night the traffic volume is very small overall.

In order to handle such changing traffic within a building with a limited number of cars, elevators are usually operated in groups. Once a hall call is registered, the hall call is temporarily assigned to each car, the waiting time of all hall calls, the possibility of fullness, etc. are predicted, and it is optimal for responding to the hall call from within the car. I try to choose a basket. To perform such predictive calculations, building-specific traffic data is required. For example, in order to predict the possibility of fullness, data on the number of people getting on and off at intermediate floors is required. Storing such ever-changing traffic data each time requires a huge amount of storage capacity, making it impractical. Therefore, by dividing the daily driving time into a plurality of time periods and storing the average traffic volume for each time period, the storage capacity can be reduced. However, shortly after a building is completed, there is a high possibility that traffic data will change as the composition of the building's personnel changes, so it is important to have good traffic data that can predict demand with high accuracy. It is difficult to obtain. Therefore, it is being considered to detect traffic conditions inside buildings and improve traffic data sequentially.

That is, the daily driving time is divided into K time periods (hereinafter referred to as sections), and the time at which the driving time is divided into section k-1 and section k (hereinafter referred to as boundary) is t _k (k=2,
3......K). t ₁ and t _k+1 are the elevator operation start time and end time, respectively. Also, the average traffic volume P _k (l) for section k on the lth day
is the following formula.

Here, X ^u _k (l) is F-, whose element is the number of passengers in the upward direction on each floor in section k on the 1st day.
It is a one-dimensional column vector (F represents the number of floors). Similarly, X ^d _k (l), Y ^u _k (l), and Y ^d _k (l) are column vectors representing the number of passengers in the down direction, the number of people getting off the train in the up direction, and the number of people getting off the train in the down direction, respectively.
This average traffic volume (hereinafter referred to as average demand) P _k (l)
is measured by a change in the load applied when the car is stopped, by an industrial television, a number of people detecting device using ultrasonic waves, etc.

First, consider sequentially correcting the representative value of the average demand P _k (l) for each time period when the boundary t _k is fixed.

Column of average demand obtained every day {P _k (1), P _k (2)……}
is considered to vary around a certain representative value P _k . Since the value of this representative value P _k is unknown,
It is necessary to estimate it by some means. in this case,
Since the representative value P _k itself may change, the following equations and linear weighted averages shown in the equations are taken, and the most recently measured average demand P _k (l) is compared to other average demands.
P _k (1)P _k (2)...It is predicted by giving more importance than P _k (l-1).

P _k ^(l)=(1-a) ^l P _k (o)+ _l 〓 ⁱ⁼¹ λ _i P _k (i)
... λ=a(1-a) ^l-1 ... Here, P _k ^(l) is predicted from the average demand P _k (1)...P _k (l) measured up to day l. Typical value,
P _k (o) is an initial value, and is set to an appropriate value in advance. λ _i is the weight of the average demand P _k (i) measured on the i-th day and varies depending on the parameter a. In other words, when increasing the value of parameter a, the most recently measured average demand P _k (l)
The estimation places more emphasis on the average demand P _k (1)...P _k than the other average demand P k (1), and the predicted representative value P _k ^(l) quickly follows changes in the representative value P _k . but,
If the value of the parameter a is too large, there is a risk that changes will become drastic due to the influence of daily data contingencies. By the way, the expressions and expressions can be rewritten as follows.

P _k ^(l)=(1-a)P _k ^(l-1)+aP _k (
l)
... P _k ^ (o) = P _k (o) ...... According to the above formula, the observed value of past average demand
There is an advantage that the weighted average of the equation can be calculated without storing P _k (i) (i=1, 2, . . . l-1).

However, even if the demand fluctuates periodically, it may be possible to predict that the demand will change temporarily. For example, when looking at the traffic volume in elevators within a building, the demand fluctuates in a different pattern than usual during holidays and New Year's holidays.

[Problems to be Solved by the Invention] The conventional demand estimating device as described above measures the demand such as the number of people boarding and alighting, the number of calls, etc. every day, and calculates the estimated value of demand by statistically processing these. I'm looking for it. This statistical processing adds predetermined weights to the estimated value up to the previous day and the current measured value, so even if demand is extremely different from weekdays, such as during holidays or New Year's holidays, ,
Since it is adopted without being distinguished from others and given the above-mentioned predetermined weighting, there is a problem that the obtained estimated value becomes less accurate.

This invention was made to solve the above problem, and even if a demand pattern different from weekdays such as holidays and holidays occurs, it is possible to estimate the demand during normal times with high accuracy without being affected by the demand pattern. An object of the present invention is to provide a demand estimating device that does the following.

[Means for Solving the Problems] The demand estimating device according to the present invention sets a weighting coefficient corresponding to each cycle, and sets the value of the weighting coefficient according to the designation of each section setting means that is manually operated. A weighting coefficient setting means for changing the weight coefficient is provided.

[Function] In this invention, the value of the weighting coefficient is set according to the designation of the external setting means, so on holidays, festivals, etc., the value of the weighting coefficient is set smaller than usual by operating the external setting means. or become unused for calculation of estimated values.

[Example] Hereinafter, an example of the present invention will be described with reference to FIGS. 1 to 10.

In Figures 1 and 2, the LDU measures the number of people moving in the upward direction at a predetermined time, totals them across all floors, and then accumulates this total value for each unit time DT (set to 5 minutes). The upward demand curve obtained by is the boundary that is the end time of the section, and PU1 and PD1 are the values obtained by accumulating the uplink demand LDU and downlink demand LDD in the section, respectively, as X ^u _k (l) and X ^d _k (l) in the formula, respectively. Further, Y ^u _k (l)=0 and Y ^d _k
The average upstream demand and average downstream demand corresponding to the average traffic volume P _k (l) when (l) = 0,
PU2 and PD2 are the average uplink demand and average downlink demand in the same section, and PU3 and PD3 are the average uplink demand and average downlink demand in the same section.

In Fig. 3, 1 is a clock that emits a time signal la every time the unit time DT elapses, and 2 is a signal 2a provided on the staff management panel that corresponds to a value of 1 to 4 depending on the position.
3 is a control device composed of an electronic computer such as a microcomputer, 3A is an input circuit that constitutes a converter for taking in input, and 3B is a central processing unit (hereinafter referred to as CPU).
), 3C is read/write memory (hereinafter referred to as RAM) that stores data such as calculation results, 3D is read-only memory (hereinafter referred to as ROM) that stores programs and fixed value data, and 3E is CPU 3B.
4 is a group management device that manages the three cars 5A to 5C in a group based on signals from the control device 3;
6A to 6C are well-known number of people detectors that are installed in cars 5A to 5C, respectively, and emit signals proportional to the number of passengers, and 7A to 7C store the minimum value of the input signal when the door is open, and this is used when the door is open. A device for calculating the number of people boarding cars 6A to 6C by subtracting the value of this input signal when closed (e.g., the one described in Japanese Patent Application Laid-Open No. 51-97115), 8A is in the upstream operation. 8B and 8C are respectively the up direction passenger number signals 8Ba and 8Ca and the down direction passenger number signals 8Bb. Switching devices 9A and 9B that emit 8Cb add inputs A to C, accumulate unit time DT of input D, and output the cumulative values as an upbound passenger number signal 9Aa and a downbound passenger number signal 9Ba, respectively. These are an up-bound number adding device and a down-bound number adding device.

In Figures 4 and 5, TIME is the time obtained from the time signal 2a, SWT is the switch data obtained from the switch signal 2a, LDU is the upstream demand corresponding to the upstream boarding signal 9Aa, and LDD is the downstream demand. Downward demand corresponding to direction boarding signal 9Ba, SA
is a weighting parameter corresponding to parameter a in the formula, J is a counter used as a variable indicating the interval ~, PU1 ~ PU3 are the average upstream demand in the ~ interval, PD1 ~
PD3 is also the average downlink demand, PUL1~PUL
3 is the representative value P _k obtained by substituting the average upstream demand PU1 to PU3 into the equation, respectively.
The predicted average upstream demand corresponding to (l), PDL1
~PDL3 is also the predicted average downlink demand, A1
~A4 are set to constant values of 0, 0.05, 0.1, and 0.2, respectively, and T1 to T4 are each set to 85 (=7:05
), 99 (8:15), 108 (=9:00) and 122 (=
10:10), and PU1 to PU3 are the initial values of predicted average upstream demand PUL1 to PUL3, which are set to 65, 130, and 109 (person/5 minutes), respectively.
PD1 to PD3 are 5, 7 and 20 (person/5 minutes) respectively.
The predicted average downlink demand PDL1~ set as
This is the initial value of PDL3.

In Figures 6 to 10, 11 is an initial value setting program for setting the initial value of each data, and 12 is a RAM (3C) that receives signals from the input circuit 3A.
13 is a weighting coefficient setting program that changes and sets the weighting coefficient; 1
4 is an upstream demand calculation program that calculates the average upstream demand PU1 to PU3 measured in the section to section, and 15 is the average downstream demand PD1.
～Download demand calculation program that calculates PD3, 1
6 is the predicted average uplink demand PUL1 to PUL3 and the predicted average downlink demand for each section to section.
Average demand estimation program that calculates PDL1 to PDL3, 7 is predicted average upstream demand PUL1 to PUL
3 and an output program for outputting the predicted average downlink demands PDL1 to PDL3 from the output circuit 3E, 21
is the operation procedure of the initial value setting program 11, 31
Y, 32 is the operating procedure of the weighting factor setting program 13, 41-48 is the operating procedure of the uplink demand calculation program 14, and 51-55 is the operating procedure of the average demand estimation program.

Next, the operation of this embodiment will be explained.

The number of people detectors 6A to 6C correspond to the cars 5A to 6C, respectively.
A signal proportional to the number of passengers in car 5C is output, and the number of people boarding cars 5A to 5C is calculated by number calculation devices 7A to 7C. These numbers are determined by switching device 8.
A to 8C are divided into upbound and downbound directions, which are added by an upbound number adding device 9A and a downbound number of people adding device 9B, respectively, and an upbound number of passengers signal 9Aa and a downbound number of passengers signal 9Ba are output, and the input circuit Sent to 3A. Further, the clock 1 outputs a count value of 1 every 5 minutes from midnight as a time signal la, and sends it to the input circuit 3A.

On the other hand, when the control device 3 is first connected to the power source, the initial setting program 11 is activated. That is, in step 21, the predicted average upstream demand PUL1~
Initial values PU1 to PU3 are set to PUL3, respectively, and initial values PD1 to PD3 are set to predicted average downlink demands PDL1 to PDL3, respectively. Next, the process moves to the input program 12.

The input program 12 is a well-known program that takes input signals from the input circuit 3A into the RAM 3C. For example, if the time is 8 o'clock, it reads the value 96 from the input circuit 3A and sets the time TIME of the RAM 3C to 96.
It is set as follows. Similarly, switch signal 2
a is taken in and set as the switch data SWT, the uplink passenger number signal 9Aa is taken in as the uplink demand LDU, and the downlink passenger number signal 9Bba is taken in as the downlink demand.
Set as LDD.

Next, the weighting factor setting program 13 is activated. In step 31, it is determined whether the time has entered the first time period in which the average demand is calculated. If the time TIME is equal to the boundary T1, the process proceeds to step 32, where a constant value is calculated according to the value of the switch data SWT. A
(SWT) is set as the weighting coefficient SA. For example, when it is known that demand that is clearly different from normal is measured during holidays, year-end and New Year holidays, etc., the staff member sets switch 2 to 1. At this time, the value of switch data SWT will also be 1, so
A constant value A1 (=0) is set as the weighting coefficient SA. Also, meetings, gatherings, etc. are held in the building.
If you know that temporary but unusual demand will be measured, set switch 2 to 2.
Or set to 3. At this time, the constant value A2 (=
0.05) or a constant value A3 (=0.1) is set as the weighting coefficient SA. In this way, when it is known in advance that demand that is different from normal is measured, the value of the weighting coefficient SA is set to zero or smaller than the normal value depending on the degree and period of the difference in the measured values, It is possible to prevent the demand estimate from being adversely affected. In step 31, the time
If TIME is not equal to the boundary T1, the above-mentioned means 31, 32 are not executed and the weighting factor SA is not modified.

In this way, the weighting factor setting program 13 sets the switch 2 before calculating the daily average demand.
Modify the weighting coefficients according to the specifications specified by.

Next, the upstream demand calculation program 14 is activated.

In step 41, it is determined whether the time period for calculating the average demand has entered. If the time TIME is smaller than the boundary T1, the process proceeds to step 42, where the average is set as an initial value for calculating the average demand. All upstream demands PU1 to PU3 are set to zero. Step 4
1 and the time TIME exceeds the boundary T1, step 43
If the time TIME is smaller than the boundary T2, the process proceeds to step 44, where the average uplink demand PU1 of the section is equal to the newly measured uplink demand.
Upstream demand per unit time DT by LDU
It is modified to increase by LDU/(T2-T1). When TIME is T2≦TIME<T3, the process proceeds from step 43 → step 45 → step 46, where the average uplink demand PU2 of the section is calculated as step 44.
is corrected in the same way. Furthermore, the time TIME is T
If 3≦TIME<T4, step 45 → step 47
→Proceed to step 48, where the average uplink demand PU3 for the section is corrected in the same manner as step 44.

In this way, the upstream demand calculation program 14
Then, the average upstream demand PU1 for the section ~ section
~PU3 will be revised sequentially.

Next, the downlink demand calculation program 15 is activated, but in the same manner as the uplink demand calculation program 14, the average downlink demand PD1 for the section to section is operated.
〜PD3 will be modified one by one, so a detailed explanation will be omitted.

Next, the average demand estimation program 16 is activated.

Boundary T4 whose time TIME is the end time of the section
The following steps 52 to 55 are executed only when they match. That is, in step 52, the counter J is set to 1.
Initialize to . A new forecast is made by adding the predicted average upstream demand PULJ calculated up to the previous day in step 53 multiplied by (1-SA) and the average upstream demand PUJ just measured on the day multiplied by SA. Set the average upstream demand PULJ. Similarly, the predicted average downlink demand PDLJ is also reset.
The value of the counter J is determined in step 54, and if it has not reached 3, 1 is added to the counter J in step 55, and the process returns to step 53 and the calculations of step 53→step 54→step 55 are repeated. Then, when the calculation is performed up to the interval, the counter J becomes 3, and step 5
Proceed to exit from 4.

In this way, the average demand estimation program 16
Then, calculations are performed to correct the predicted average uplink demands PUL1 to PUL3 and the predicted average downlink demands PDL1 to PDL3 in each section to section every day.

Next, the output program 17 operates, and the predicted average uplink demands PUL1 to PUL3 and the predicted average downlink demands PDL1 to PDL3 for each section to sections calculated by the average demand program 16 are output from the output circuit 3E.

In the above embodiment, there are three types of setting values for the weighting coefficient SA, but the present invention is not limited to this. All you have to do is set the type that matches the building.

In addition, although the same weighting coefficient SA was used for each interval, the weighting coefficient SA for each interval
You may set different SAs. In this way, highly accurate demand prediction can be made for each section.

Furthermore, it is clear that the case of predicting demand in four or more sections can also be applied to the case of predicting demand for each floor (in each direction).

Note that the present invention is not limited to estimating elevator traffic volume, but can also be applied to estimating various demands such as power demand and water demand.

[Effect of the invention] As explained above, in this invention, an estimated value of demand is calculated according to the measured value of demand in each section,
The extent to which demand measurement values are used is selected according to the specification of the external setting means, so even when demand that is clearly different from normal is measured, it is not affected by the demand, and normal demand is maintained. This has the effect of being able to estimate with high accuracy.

[Brief explanation of the drawing]

FIG. 1 is an upward demand curve diagram showing an embodiment in which the demand estimation device according to the present invention is applied to an elevator, FIG. 2 is a downward demand curve diagram, FIG. 3 is a block circuit diagram, and FIG. Figure 3
Diagram showing the contents of RAM, Figure 5 is the ROM of Figure 3
Figure 6 is an overall schematic diagram of the program, Figure 7 is a flowchart of the operation of the initial value setting program shown in Figure 6, Figure 8 is a flowchart of the operation of the weighting coefficient setting program, and Figure 9 is a diagram showing the contents of the program. 10 is a flowchart of the operation of the uplink demand calculation program, and FIG. 10 is a flowchart of the operation of the average demand estimation program. 1...Clock, 2...External setting means (switch for specifying weighting coefficient), 3...Control device, 3B...
CPU, 3C...RAM, 3D...ROM, 4...Group management device, 5A-5C...Elevator car, 6
A to 6C...Person detector, 7A to 7C...Person calculation device, 8A to 8C...Switching device, 9A...
Upbound number addition device, 9B...Descent number addition device,
13...Weighting coefficient setting means (weighting coefficient setting program), 14, 15... Demand measurement means (uplink and downlink demand calculation program), 16... Demand estimation means (average demand estimation program). Note that the same reference numerals in the figures indicate the same parts.

Claims (1)

[Claims] 1. A demand measuring means that divides one period of demand that fluctuates almost periodically into a plurality of sections each having a predetermined time interval, and measures the demand in each section at each repetition of the period. , an external setting means for specifying the use of the measured value when calculating an estimated demand value that is artificially manipulated, and a weighting coefficient corresponding to a time within each cycle, and a specification of the external setting means. a weighting coefficient setting means for changing the value of the weighting coefficient according to the demand; and a demand calculating means for calculating the estimated value of the demand in each of the sections by weighting and averaging the setting values set for each section based on the weighting coefficient. A demand estimating device comprising: estimating means. 2. Claim 1 wherein the weighting factor setting means sets the weighting factor corresponding to the latest cycle smaller than usual in accordance with the designation of the external setting means.
The demand estimation device described in Section 1. 3. The demand estimating device according to claim 1, wherein the weighting coefficient setting means sets the weighting coefficient corresponding to the latest cycle to zero in accordance with the designation by the external setting means.