Prediction system, prediction method, and program

Abstract

This technology provides a method for predicting weather information about the location of a moving object at the time of its passage. [Solution] The prediction system comprises weather information measured at each of a plurality of measurement points, a database that records information on the date and time and location of the measurement of the weather information, and a weather information prediction unit that, when a moving object moves along a predetermined path, predicts the weather information for the date and time the moving object will pass through each waypoint at each waypoint, based on the weather information recorded in the database of the measurement points located near the waypoint.

Description

Technical Field

[0001] The present disclosure relates to a prediction system, a prediction method, and a program.

Background Art

[0002] A refrigerated vehicle that transports goods while controlling the temperature of a cold storage compartment may be required to perform long-distance transportation, and one operation often takes about a week. As the transportation time lengthens, the power and fuel required for temperature control of the cold storage compartment increase accordingly. The temperature control of the cold storage compartment is performed by a refrigerator mounted on the refrigerated vehicle. Even if the temperature inside the cold storage compartment is controlled to the same temperature, the energy consumption such as the power required for the temperature control varies greatly depending on the outside air temperature and weather. If traveling a short distance, the fluctuations in the outside air temperature and weather can be ignored. However, in the case of long-distance transportation, the energy consumption required for temperature control cannot be accurately grasped without considering the changes in the outside air temperature and weather up to a week ahead. Also, the environmental conditions such as the outside air temperature and weather are considered to vary greatly depending on the route traveled. From the perspective of energy conservation, it is desirable to select a route that is as cost-effective as possible to transport goods.

[0003] As a related technique, Patent Document 1 discloses a technique for measuring physical quantities related to the weather (such as air temperature, humidity, wind speed, etc.) while moving together with a moving object, correcting the measured physical quantities according to the situation around the moving object (such as the presence of rivers or seas, parks or green spaces, paved roads or wind-blocking objects, etc. around), and calculating a representative physical quantity of the weather for the area using the corrected physical quantities related to the weather and the physical quantities of the weather measured at fixed points in that area.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] To predict the energy consumption required for temperature control of refrigerated vehicles, it is desirable to know the temperature at the vehicle's location along its route and at the time of vehicle passage. However, Patent Document 1 does not disclose a method for calculating such physical quantities of weather. A method is needed to predict weather information at the location where a moving object passes.

[0006] This disclosure provides a prediction system, prediction method, and program that can solve the above-mentioned problems. [Means for solving the problem]

[0007] The prediction system of this disclosure comprises a database that records weather information measured at each of a plurality of measurement points, information on the date and time and location information of the weather information measured, and a weather information prediction unit that, when a moving object moves along a predetermined path, predicts the weather information for each of the waypoints provided along the path for the date and time the moving object passes through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint.

[0008] Furthermore, the prediction method of this disclosure includes a prediction system that has a database recording weather information measured at each of a plurality of measurement points, as well as information on the date and time and location of the measurement of the weather information. When a moving object moves along a predetermined path, the system predicts, for each of the waypoints provided along the path, the weather information for the date and time the moving object will pass through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint.

[0009] Furthermore, the program of this disclosure causes a computer capable of accessing a database that records weather information measured at each of a plurality of measurement points, as well as information on the date and time and location of the measurement of the weather information, and reading the information recorded in the database, to perform a process in which, when a moving object moves along a predetermined path, the program predicts the weather information at each of the waypoints provided along the path for the date and time the moving object will pass through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint. [Effects of the Invention]

[0010] According to the above-described prediction system, prediction method, and program, it is possible to predict weather information for the date and time of passage of a moving object at its current location. [Brief explanation of the drawing]

[0011] [Figure 1] This figure shows an example of a prediction system according to the embodiment. [Figure 2] This figure shows an example of a database for accumulating weather information according to the embodiment. [Figure 3] This figure shows an example of waypoints and measurement points according to the embodiment. [Figure 4] This diagram illustrates the method for predicting outside temperature according to the embodiment. [Figure 5] This figure shows an example of an outside temperature prediction model according to the embodiment. [Figure 6] This figure shows an example of a consumption prediction model according to the present invention. [Figure 7] This diagram illustrates the method for predicting energy consumption according to the embodiment. [Figure 8] This figure shows an example of the predicted energy consumption results according to this embodiment. [Figure 9] This flowchart shows an example of the prediction process for outside temperature and energy consumption according to the embodiment. [Figure 10]This figure shows an example of the hardware configuration of the prediction system according to the embodiment. [Modes for carrying out the invention]

[0012] <Embodiment> A prediction system according to one embodiment of this disclosure will be described below with reference to Figures 1 to 10.

[0013] (Configuration of the prediction system) Figure 1 shows an example of a prediction system in an embodiment. As shown in Figure 1, the prediction system 100 includes a server 10, a plurality of refrigerated vehicles 1a, 1b, ..., a plurality of fixed observation stations 5a, 5b, ..., and a user terminal 20. Refrigerated vehicle 1a is equipped with a control device 2a, a sensor 3a for measuring weather information, a positioning sensor 4a, a refrigeration unit 7a, and a cold storage compartment 8a. Similarly, refrigerated vehicle 1b is equipped with a control device 2b, a sensor 3b for measuring weather information, a positioning sensor 4b, a refrigeration unit 7b, and a cold storage compartment 8b. The control device 2a is, for example, the control device for the refrigeration unit 7a in refrigerated vehicle 1a. The same applies to the control device 2b. Weather information includes outside temperature, humidity, wind direction, wind speed, precipitation, solar radiation, etc. In the following explanation, we will use the example where sensors 3a and 3b are temperature sensors measuring ambient temperature, but they may also be sensors that measure other things such as humidity, wind direction, wind speed, precipitation, and solar radiation. Furthermore, refrigerated vehicles 1a and 1b may be equipped with multiple types of sensors that measure weather information. Positioning sensors 4a and 4b are receivers of GNSS (Global Navigation Satellite System) or the like, and determine their own position information. The position information of refrigerated vehicle 1 determined by positioning sensor 4a and the ambient temperature around refrigerated vehicle 1a measured by sensor 3a are output to control device 2a. The position information of refrigerated vehicle 1b determined by positioning sensor 4b and the ambient temperature around refrigerated vehicle 1b measured by sensor 3b are output to control device 2b. There may be two or more refrigerated vehicles. In the following, where distinction is not necessary, refrigerated vehicles 1a and 1b will be referred to as refrigerated vehicle 1, control devices 2a and 2b as control device 2, sensors 3a and 3b as sensor 3, positioning sensors 4a and 4b as positioning sensor 4, refrigerators 7a and 7b as refrigerator 7, and cold storage units 8a and 8b as cold storage unit 8. Fixed observation station 5a is equipped with sensor 6a for measuring weather information. Similarly, fixed observation station 5b is equipped with sensor 6b for measuring weather information. In the following explanation, the case where sensors 6a and 6b are temperature sensors and measure outside temperature will be used as an example, but sensors 6a and 6b may also be sensors that measure other things such as humidity, wind direction, wind speed, precipitation, solar radiation. There may be two or more fixed observation stations.Hereinafter, when there is no need for distinction, the fixed-point observation points 5a and 5b are described as the fixed-point observation point 5, and the sensors 6a and 6b are described as the sensor 6.

[0014] The server 10, the control device 2, the user terminal 20, and the fixed-point observation point 5 are communicably connected via the network NW. The control device 2 combines the outside air temperature around the refrigerated vehicle 1 measured by the sensor 3, the position information of the refrigerated vehicle 1 measured by the positioning sensor 4 at the same time, and their measurement times, and transmits them to the server 10 via the network NW at a predetermined control cycle. The server 10 stores the outside air temperature and position information measured at all times when the refrigerated vehicle 1 transports goods across the country. The fixed-point observation point 5 is equipped with an information processing terminal and a communication device not shown. The information processing device not shown combines the outside air temperature measured by the sensor 6, the position information (for example, latitude and longitude) of the fixed-point observation point 5, and the measurement time of the outside air temperature, and transmits them to the server 10 via the network NW at a predetermined control cycle. The server 10 stores the outside air temperature and position information measured at all times at the fixed-point observation points 5 across the country.

[0015] In the embodiment, the outside air temperature measured by the refrigerated vehicle 1 equipped with the sensor 3 etc. is stored in the server 10. However, not limited to the refrigerated vehicle 1, the sensor 3 may be provided on other vehicles or other moving bodies to collect information such as the outside air temperature in various places.

[0016] The user terminal 20 is an information processing device such as a PC or a tablet terminal used by a user who formulates the transport route of the refrigerated vehicle 1. When formulating the transport route of the refrigerated vehicle 1 that performs long-distance transport, the user gives the candidate routes to the server 10. Then, the server 10 predicts the energy consumption consumed by the refrigerator 7 for each route and outputs the prediction result to the user terminal 20. The user can determine an efficient route by comparing the predicted energy consumption.

[0017] The server 10 includes a sensor value acquisition unit 11, a route setting unit 12, a weather information prediction unit 13, an energy consumption prediction unit 14, and a storage unit 15.

[0018] The sensor value acquisition unit 11 acquires the outside air temperature measured by the sensor 3 from the refrigerated vehicle 1, the position information of the refrigerated vehicle 1 measured by the positioning sensor 4 when the outside air temperature was measured, and the date and time when they were measured, associates them, and records them in the storage unit 15. Similarly, the sensor value acquisition unit 11 acquires the outside air temperature measured by the sensor 6 from the regular observation site 5, the date and time when the outside air temperature was measured, and the position information of the regular observation site 5, associates them, and records them in the storage unit 15. An example of the data recorded in the storage unit 15 is shown in FIG. 2. The database in FIG. 2 has columns for measurement point, outside air temperature, latitude, longitude, measurement date (day number), and measurement time zone. The measurement point is an identifier for the location where the outside air temperature was measured. The outside air temperature records the temperatures measured by the sensors 3 and 6. The latitude and longitude record the position information measured by the positioning sensor 4 and the position information of the fixed-point observation site 5. The measurement date (day number) records the value obtained by converting the date when the outside air temperature was measured into a day number. The day number is a value indicating which day the date is as counted from January 1st (January 1st is 1). For example, the day number of January 2nd is "2", and the day number of December 31st is "365". The measurement time zone records the value obtained by converting the time when the outside air temperature was measured into a time zone. For example, the time zone from 12:00 to 12:59 at noon can be set as "12", and the time zone from 5:00 to 5:59 in the evening can be set as "17". The sensor value acquisition unit 11 converts the date and time when the outside air temperature was measured into a day number and a time zone and records them in the database of FIG. 2. In the database illustrated in FIG. 2, data accumulates every time the refrigerated vehicle 1 travels. Also, the outside air temperatures measured at the regular observation sites 5 in various locations are accumulated in this database. Regarding the position information of the measurement points, in addition to the latitude and longitude, the elevation of each measurement point may be recorded in the database.

[0019] The route setting unit 12 receives input from the user, such as the departure date and time, arrival date and time, and multiple candidate routes for the transport route, and sets the multiple candidate routes as targets for energy consumption prediction. Alternatively, if a large number of routes are pre-registered in the storage unit 15, and the user inputs the departure point and arrival point, departure date and / or arrival date and time, the route setting unit 12 may extract multiple routes from the pre-registered number of routes from the specified departure point to the arrival point and set them as targets for energy consumption prediction. Multiple waypoints are set for a single route. Waypoints may be set at predetermined intervals, or they may be set at locations with landmarks or characteristics, such as intersections or near large buildings. Based on the departure date and / or arrival date and time input by the user, the route setting unit 12 predicts and sets the time at which the refrigerated vehicle 1 will pass each waypoint if it travels along that route. To predict the time of passing through waypoints, you can use the actual time taken to travel between waypoints when this route was previously traveled, or you can simply predict the time of passing through each waypoint by dividing the length of the route between waypoints by the travel speed.

[0020] The weather information forecasting unit 13 predicts the outside temperature when the refrigerated vehicle 1 passes through each waypoint on the route set by the route setting unit 12. Figure 3 shows an example of a waypoint and its neighboring measurement points. In Figure 3, r is a candidate route. The circular points w1 to w6 on route r are waypoints. The triangulation points m1 to m16 are measurement points. When predicting the outside temperature of waypoint w4, a circle c1 with radius R is drawn centered on waypoint w4, and the area within this circle c1 is considered the neighborhood. Then, focusing on the measurement points m3, m4, m5, m11, m12, m13, and m14 included in circle c1, the outside temperature of waypoint w1 is predicted.

[0021] (Method 1 for predicting outside temperature) The method for predicting the outside temperature will be explained with reference to Figure 4. Assume that the measurement points in the vicinity of waypoint w30 are measurement points m31 to m33. The weather information prediction unit 13 may predict the outside temperature of waypoint w30 by calculating a coefficient corresponding to the reciprocal of the distance between waypoint w30 and measurement points m31 to m33 and using a weighted sum based on this coefficient, or by calculating a coefficient corresponding to the proximity of the measurement dates and times between waypoint w30 and measurement points m31 to m33 and using a weighted sum based on this coefficient, or by using both of these coefficients to predict the outside temperature of waypoint w30. Here, we will explain the method of prediction using both a coefficient corresponding to the reciprocal of the distance and a coefficient corresponding to the proximity of the measurement dates and times. As will be described later, the proximity of the measurement dates and times consists of a coefficient corresponding to the proximity of the day numbers and a coefficient corresponding to the proximity of the time periods.

[0022] (Coefficient corresponding to the reciprocal of the distance) Let R1 be the distance between measurement point m31 and waypoint w30, R2 be the distance between measurement point m32 and waypoint w30, and R3 be the distance between measurement point m33 and waypoint w30. The weather information forecasting unit 13 calculates coefficients corresponding to the reciprocals of the distances. Let α10 be the coefficient corresponding to the reciprocal of the distance between waypoint w30 and measurement point m31, α20 be the coefficient corresponding to the reciprocal of the distance between waypoint w30 and measurement point m32, and α30 be the coefficient corresponding to the reciprocal of the distance between waypoint w30 and measurement point m33. Then the ratio of coefficients α10, α20, and α30 is 1 / R1:1 / R2:1 / R3, and the weather information forecasting unit 13 adjusts the values ​​of each coefficient so that the sum of coefficients α10 to α30 is 1. For example, if R1:R2:R3 is 3:2:1, then α10=2 / 11, α20=3 / 11, and α30=6 / 11.

[0023] Here, the coefficient is calculated based on the reciprocal of the distance between measurement point m31 and waypoint w30 in a plane, but elevation difference may also be considered. Even if the distance in a plane is short, if there is an elevation difference, such as between flat land and mountains, it is thought that a difference in outside temperature will occur. For example, if the elevation difference between waypoint A and measurement point B is greater than a predetermined height, a correction such as adding a predetermined value to the distance in a plane between waypoint A and measurement point B may be made, and then the coefficient corresponding to the reciprocal of the distance may be calculated. Also, even if the distance in a plane and elevation difference between waypoint A and measurement point B are small, if there is a mountain or a tall building between waypoint A and measurement point B, differences in weather conditions such as wind and clouds may occur, which may result in a difference in outside temperature. In such cases as well, the weather information forecasting unit 13 may make a correction such as adding a predetermined value to the distance in a plane between waypoint A and measurement point B, and then calculate the coefficient corresponding to the reciprocal of the distance. For example, if there is a mountain to the north of measurement point 1, a rule such as "add Y km to the distance for waypoints north of measurement point 1" may be registered in advance, and when predicting the outside temperature of a waypoint north of measurement point 1, the weather information forecasting unit 13 may add Y km to the distance between that waypoint and measurement point 1 in the plane, and then calculate a coefficient corresponding to the reciprocal of the distance.

[0024] (Coefficient based on proximity of day numbers) Let the day number for the measurement date and time of the outside temperature at measurement point m31 be 100, the day number for the measurement date and time of the outside temperature at measurement point m32 be 200, the day number for the measurement date and time of the outside temperature at measurement point m33 be 300, and the day number for the predicted date and time when the refrigerated vehicle will pass waypoint w30 be 150. The weather information forecasting unit 13 calculates a coefficient according to the proximity of the day numbers (the closer the day numbers are, the larger the coefficient value). Note that the difference between day number 1 (January 1st) and day number 365 (December 31st) is calculated as 1, not 355. In this example, the difference in day numbers between waypoint w30 and measurement point m31 is 50, the difference between waypoint w30 and measurement point m32 is also 50, and the difference between waypoint w30 and measurement point m33 is 150. The weather information forecasting unit 13 may also calculate a coefficient according to the reciprocal of the difference in day numbers. Let β10 be a coefficient corresponding to the proximity of the day numbers of waypoint w30 and measurement point m31, β20 be a coefficient corresponding to the proximity of the day numbers of waypoint w30 and measurement point m32, and β30 be a coefficient corresponding to the proximity of the day numbers of waypoint w30 and measurement point m33. The weather information forecasting unit 13 calculates values ​​for coefficients β10 to β30 such that the ratio of coefficients β10, β20, and β30 is 1 / 50:1 / 50:1 / 150, and the sum of coefficients β10 to β30 is 1. In the above example, β10 = 3 / 7, β20 = 3 / 7, and β30 = 1 / 7.

[0025] (Coefficient based on proximity of time zone) Let the time period for measuring the outside temperature at measurement point m31 be 17, the time period for measuring the outside temperature at measurement point m32 be 13, the time period for measuring the outside temperature at measurement point m33 be 8, and the time period for the predicted date and time when a refrigerated vehicle will pass waypoint w30 be 15. The weather information forecasting unit 13 calculates a coefficient according to the proximity of the time periods (the closer the time periods, the larger the coefficient value). Note that the difference between time period 23 (23:00 to 23:59) and time period 0 (0:00 to 0:59) is calculated as 1, not 23. For example, the difference in time periods between waypoint w30 and measurement point m31 is 2, the difference between waypoint w30 and measurement point m32 is also 2, and the difference between waypoint w30 and measurement point m33 is 7. The weather information forecasting unit 13 may also calculate a coefficient according to the reciprocal of the difference in time periods. Let γ10 be a coefficient corresponding to the proximity of the time zones between waypoint w30 and measurement point m31, γ20 be a coefficient corresponding to the proximity of the time zones between waypoint w30 and measurement point m32, and γ30 be a coefficient corresponding to the proximity of the time zones between waypoint w30 and measurement point m33. The weather information forecasting unit 13 calculates values ​​for coefficients γ10 to γ30 such that the ratio of coefficients γ10, γ20, and γ30 is 1 / 2:1 / 2:1 / 7, and the sum of coefficients γ10 to γ30 is 1. In the above example, γ10 = 7 / 16, γ20 = 7 / 16, and γ30 = 2 / 16.

[0026] (Outside temperature prediction formula) With the above, coefficients α10 to α30 corresponding to the reciprocal of the distance and coefficients β10 to β30 and γ10 to γ30 corresponding to the proximity of the measurement date and time were obtained. If the outside temperature at waypoint w30 is T0, the outside temperature measured at measurement point m31 is T1, the outside temperature measured at measurement point m32 is T2, and the outside temperature measured at measurement point m33 is T3, then the outside temperature T0 at the date and time when refrigerated vehicle 1 passes through waypoint w30 can be predicted by the following equation (1). T0=α10×β10×γ10×T1+α20×β20×γ20×T2+α30×β30×γ30×T3...(1)

[0027] The weather information forecasting unit 13 may also predict the outside temperature T0 of waypoint w30 using only coefficients α10 to α30 corresponding to the reciprocal of the distance. In this case, T0 can be predicted using the following equation (2). T0=α10×T1+α20×T2+α30×T3...(2)

[0028] The weather information forecasting unit 13 may also predict the outside temperature T0 of waypoint w30 using only coefficients β10 to β30 corresponding to the proximity of the day numbers. In this case, T0 can be predicted using the following equation (3). T0=β10×T1+β20×T2+β30×T3...(3)

[0029] The weather information forecasting unit 13 may also predict the outside temperature T0 of waypoint w30 using only coefficients γ10 to γ30 corresponding to the proximity of the time period. In this case, T0 can be predicted using the following equation (4). T0=γ10×T1+γ20×T2+γ30×T3...(4)

[0030] Similarly, the weather information forecasting unit 13 may predict the outside temperature T0 using a coefficient corresponding to the proximity of the day number and a coefficient corresponding to the proximity of the time period. In this case, the outside temperature T0 is predicted by a weighted sum of the values ​​obtained by multiplying the temperature at each measurement point by a coefficient βx (x=1~3) corresponding to the proximity of the day number and a coefficient γx (x=1~3) corresponding to the proximity of the time period. Alternatively, the weather information forecasting unit 13 may predict the outside temperature T0 using a coefficient corresponding to the reciprocal of the distance and a coefficient corresponding to the proximity of the day number, or by using a coefficient corresponding to the reciprocal of the distance and a coefficient corresponding to the proximity of the time period. In either case, T0 can be predicted by summing the values ​​obtained by multiplying the temperature at each measurement point by the two corresponding coefficients.

[0031] (Method 2 for predicting outside temperature) The method for predicting outside temperature will be explained with reference to Figure 5. The weather information forecasting unit 13 may use a dataset of location information (latitude and longitude), measurement date (day number), measurement time period, and outside temperature data stored in the database exemplified in Figure 2 as training data, and learn the relationship between location information (latitude and longitude), measurement date (day number), measurement time period, and outside temperature using machine learning to create an outside temperature prediction model 51 exemplified in Figure 5. The outside temperature prediction model 51 is configured to output the outside temperature at a given location and time when the latitude and longitude of the location to be predicted, and the day number and time period of the date and time to be predicted are input. The weather information forecasting unit 13 inputs the latitude and longitude of waypoint w30 and the day number and time period of the date and time when the refrigerated vehicle 1 passes through waypoint w30 to the outside temperature prediction model 51 and obtains the predicted outside temperature value output by the outside temperature prediction model 51. The weather information forecasting unit 13 predicts the obtained predicted outside temperature value as the outside temperature when the refrigerated vehicle 1 passes through waypoint w30.

[0032] If there is insufficient training data when creating the outside temperature prediction model 51, for example, if the distance between a certain measurement point A and a measurement point B adjacent to measurement point A is greater than a predetermined value, the weather information prediction unit 13 may create a virtual measurement point C at the midpoint between measurement point A and measurement point B, estimate the outside temperature of measurement point C using the method described in Figure 4, and add the latitude and longitude, day number, time zone, and outside temperature of the virtual measurement point C to the training data to create the outside temperature prediction model 51. In this case, the day number and time zone of the virtual measurement point C may be the date and time midway between measurement point A and measurement point B, or predetermined fixed values ​​may be set as the day number and time zone.

[0033] In this example, the weather information forecasting unit 13 is used to predict the outside temperature, but humidity, wind speed, solar radiation, etc., may be predicted using a similar method.

[0034] The energy consumption prediction unit 14 predicts the energy consumption required by the refrigeration unit 7 when the refrigeration vehicle 1 is operated under the weather conditions indicated by the weather information of the waypoints that the refrigeration vehicle 1 will pass through. The energy consumption of the refrigeration unit 7 is the amount of electricity consumed by the refrigeration unit 7 if it is powered by a battery, or the amount of fuel consumed by the refrigeration unit 7 if it is powered by the engine of the refrigeration vehicle 1. The energy consumption prediction unit 14 may predict the energy consumption of the refrigeration unit 7 using any known technology. For example, the energy consumption prediction unit 14 may create a consumption prediction model 61, as illustrated in Figure 6, for each type (specification) of refrigeration unit 7 or for each refrigeration vehicle 1, and use this consumption prediction model 61 to predict the amount of electricity or fuel consumed by the refrigeration unit 7. For example, the storage unit 15 stores driving data from past runs for each refrigeration vehicle 1. The driving data includes weather conditions (sunny, rainy, cloudy, snowy, etc.) measured at predetermined intervals during past driving, outside temperature, humidity, temperature and target temperature of the refrigerator 8, and power (kW) of the chiller 7. The energy consumption prediction unit 14 converts the power (kW) of the chiller 7 into an amount of electricity or fuel consumed per unit time, and learns the relationship between outside temperature and electricity or fuel consumption, or the relationship between outside temperature and other weather information (humidity, weather, etc.) and electricity or fuel consumption, assuming that the chiller 7 is operated for that unit time under the weather conditions indicated by the weather information measured at predetermined intervals, and creates an energy consumption prediction model 61. The energy consumption prediction unit 14 inputs the outside temperature of the waypoint predicted by the weather information prediction unit 13 and other explanatory variables (weather, humidity, target temperature, etc.) as needed into the energy consumption prediction model 61. The energy consumption prediction unit 14 outputs the amount of electricity or fuel that the chiller 7 will consume if it is driven for that unit time under the input conditions.

[0035] The energy consumption prediction unit 14 converts the amount of electricity or fuel per unit time (e.g., 60 minutes) output by the energy consumption prediction model 61 into, for example, the amount of electricity or fuel to be consumed up to the next waypoint. For example, regarding the amount of electricity consumed by the chiller 7 when moving from WP[i-1] to WP[i] as shown in Figure 7, the energy consumption prediction unit 14 inputs the outside temperature when passing WP[i-1] into the energy consumption prediction model 61 to obtain the amount of electricity per 60 minutes. Let's assume that the amount of electricity at this time is X (kWh). Next, the energy consumption prediction unit 14 calculates the time required to move from WP[i-1] to WP[i] from the passing times of WP[i-1] and WP[i] set by the route setting unit 12. Let's assume that this move takes 10 minutes. In this case, the energy consumption prediction unit 14 predicts that "X × 10 minutes / 60 minutes" (kWh) is required to move from WP[i-1] to WP[i]. The energy consumption prediction unit 14 similarly predicts the amount of electricity consumed by the chiller 7 when traveling from WP[i] to WP[i+1], and similarly predicts the energy consumption between other waypoints. Then, it integrates the energy consumption between each waypoint from the starting point to the destination point and predicts the amount of electricity or fuel consumed by the chiller 7 when traveling along each candidate route.

[0036] The energy consumption prediction unit 14 may linearly interpolate the outside temperature between waypoints and, each time the outside temperature changes, predict the amount of electricity or fuel to be consumed using the energy consumption prediction model 61 and then accumulate them. Alternatively, the energy consumption prediction unit 14 may switch to the outside temperature of the next waypoint at the midpoint between waypoints and, using the energy consumption prediction model 61, predict the amount of electricity or fuel to be consumed and then accumulate them.

[0037] The energy consumption prediction unit 14 predicts the amount of electricity or fuel that the refrigeration unit 7 will consume if it travels along each candidate route, and outputs the prediction result. An example of the prediction result output is shown in Figure 8. In the graph 81 of Figure 8, the vertical axis represents the predicted value of the outside temperature, and the horizontal axis represents the progress relative to the entire route when each waypoint is reached. Graph 81 shows the changes in the predicted outside temperature value for route 1 81a and route 2 81b. Within the frame 82, the predicted fuel consumption value for the refrigeration unit 7 when traveling along route 1 and the predicted fuel consumption value for the refrigeration unit 7 when traveling along route 2 are displayed. The user can use these prediction results to select the route that the refrigerated vehicle 1 should travel.

[0038] The storage unit 15 is a storage medium that stores data acquired by the sensor value acquisition unit 11 (database in Figure 2), routes set by the route setting unit 12, an outside temperature prediction model 51, a consumption prediction model 61, and the like. The storage unit 15 may also be an external storage device located outside the server 10.

[0039] (operation) Next, the operation of the prediction system 100 will be described with reference to Figure 9. Figure 9 is a flowchart showing an example of the prediction process for outside temperature and energy consumption according to this embodiment. The sensor value acquisition unit 11 acquires ambient temperature, measurement date and time, and location information from multiple refrigerated vehicles 1 and multiple fixed observation stations 5, and stores the ambient temperature, etc. in the database (Figure 2) of the storage unit 15 (Step S1). Next, the user inputs multiple candidate routes for the refrigerated vehicle 1 to the server 10 using the user terminal 20. The route setting unit 12 sets the input multiple routes as routes for which energy consumption will be predicted (Step S2). Next, the route setting unit 12 selects one route from the routes set in Step S2 (Step S3). The route setting unit 12 outputs the selected route to the user terminal 20. The user confirms the selected route and inputs the departure date and time and / or the target arrival date and time. The route setting unit 12 sets the input departure date and time and / or arrival date and time (Step S4). Next, the route setting unit 12 sets the waypoint passage dates and times based on the set departure date and time and / or arrival date and time (Step S5). For example, if a departure date and time are set, the route setting unit 12 calculates the travel time from the departure point to the first waypoint based on the distance from the departure point to the first waypoint, and predicts the date and time of passing the first waypoint by adding the calculated travel time to the departure date and time. Thereafter, the route setting unit 12 repeats the same process until the arrival point, predicting the date and time of passing each waypoint and recording it in the storage unit 15. If an arrival date and time are set, the route setting unit 12 calculates the travel time from the waypoint immediately preceding the arrival date and time to the arrival point based on the distance, and predicts the date and time of passing the waypoint immediately preceding the arrival date and time by subtracting the calculated travel time from the arrival date and time. Thereafter, the route setting unit 12 repeats the same process until the departure point, predicting the date and time of passing each waypoint and recording it in the storage unit 15. Next, the weather information forecasting unit 13 predicts the outside temperature at the date and time of passing the waypoint (step S6). The weather information forecasting unit 13 predicts the outside temperature at the time the refrigerated vehicle 1 passes through each waypoint, as explained with reference to Figures 3 to 5, and records the predicted outside temperature for each waypoint in the storage unit 15. Next, the energy consumption forecasting unit 14 predicts the energy consumption (step S7).The energy consumption prediction unit 14 predicts the energy consumption (amount of electricity consumed or amount of fuel consumed) that the refrigeration unit 7 will consume when the refrigerated vehicle 1 travels along the route selected in step S3, using the process described with reference to Figures 6 to 8, and records the prediction result in the storage unit 15 in association with the route. Next, the route setting unit 12 determines whether energy consumption has been predicted for all routes set in step S2 (step S8). If the prediction for all routes is not completed (step S8; No), the process from step S3 is repeated. If the prediction for all routes is completed (step S8; Yes), the energy consumption prediction unit 14 outputs the predicted energy consumption result for each route to the user terminal 20 (step S9). The user terminal 20 receives the energy consumption for each route. The energy consumption prediction unit 14 may also read the outside temperature of the waypoints recorded in the storage unit 15 to create a graph 81 as exemplified in Figure 8, and output the predicted energy consumption result for each route along with the created graph. The user can then understand which route can reduce energy consumption the most. The energy consumption prediction unit 14 may predict the energy consumption required for the refrigerated vehicle 1 to travel, in addition to the energy consumption of the refrigeration unit 7, and output both the energy consumption of the refrigeration unit 7 and the energy consumption required for the refrigerated vehicle 1 to the user terminal 20. The energy consumption required for the refrigerated vehicle 1 to travel may be predicted simply by multiplying the travel time from departure to arrival by a predetermined coefficient, or the actual fuel consumption value when traveling that route in the past may be used as the predicted value for the energy consumption required for travel. For example, if the result is that route 1 has low energy consumption for travel but high energy consumption for the refrigeration unit 7, and route 2 has high energy consumption for travel but low energy consumption for the refrigeration unit 7, the user may compare the total energy consumption for travel and the total energy consumption for the refrigeration unit 7 to select the route that the refrigerated vehicle 1 should travel.

[0040] (effect) As described above, according to this embodiment, it is possible to predict weather information for the time and date of passage at the location where the moving object will travel along its route. Furthermore, the predicted values ​​of this weather information can be used to predict physical quantities that are affected by weather information. For example, if the moving object is a refrigerated vehicle 1, the temperature control of the refrigerated compartment 8 of the refrigerated vehicle 1 is affected by weather conditions indicated by the weather information at the location and time of passage, such as outside temperature, humidity, and solar radiation. The prediction method of this embodiment can be used to predict the energy consumption of the refrigeration unit 7 when the refrigerated vehicle 1 travels along a certain route over a certain period of time. Furthermore, by comparing the results of predicting the energy consumption of the refrigeration unit 7 for multiple routes, it can also be used to select a route for the refrigerated vehicle 1.

[0041] Figure 10 shows an example of the hardware configuration of the prediction system according to the embodiment. The computer 900 includes a CPU 901, main memory 902, auxiliary memory 903, input / output interface 904, and communication interface 905. The control device 2, server 10, and user terminal 20 described above are implemented in the computer 900. The functions described above are stored in auxiliary storage device 903 in the form of programs. The CPU 901 reads the programs from auxiliary storage device 903, loads them into main memory 902, and executes the above processes according to the programs. The CPU 901 also allocates memory space in main memory 902 according to the programs. The CPU 901 also allocates memory space in auxiliary storage device 903 to store data being processed according to the programs.

[0042] A program to implement all or part of the functions of the control device 2, server 10, and user terminal 20 may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be loaded into a computer system and executed to perform processing by each functional unit. Here, "computer system" includes hardware such as the OS and peripheral devices. Furthermore, if a WWW system is used, "computer system" also includes the homepage provisioning environment (or display environment). Furthermore, "computer-readable recording medium" refers to portable media such as CDs, DVDs, USBs, and storage devices such as hard disks built into the computer system. Furthermore, if this program is distributed to computer 900 via a communication line, computer 900 that receives the distribution may load the program into main memory 902 and execute the above processing. Furthermore, the above program may be for implementing only a part of the functions described above, and may also be able to implement the above functions in combination with programs already recorded in the computer system.

[0043] As described above, several embodiments relating to this disclosure have been explained, but all of these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be carried out in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0044] <Note> The prediction system, prediction method, and program described in each embodiment can be understood, for example, as follows:

[0045] (1) A prediction system according to the first embodiment includes a database that records weather information measured at each of a plurality of measurement points, information on the date and time and location information of the weather information measured, and a weather information prediction unit that, when a moving body moves along a predetermined path, predicts the weather information for the date and time the moving body will pass through each waypoint at each waypoint based on the weather information recorded in the database of the measurement point located near the waypoint. This makes it possible to predict weather information at the time and date a moving object passes through a waypoint.

[0046] (2) A prediction system according to a second embodiment is the prediction system of (1), wherein the weather information prediction unit predicts the weather information for the date and time the moving body will pass through the waypoint by using a weighted sum of the weather information recorded in the database of the measurement point located near the waypoint, with coefficients being a value corresponding to the reciprocal of the distance between the waypoint and the measurement point located near the waypoint, and a value corresponding to the proximity between the date and time the moving body will pass through the waypoint and the date and time information recorded in the database of the measurement point located near the waypoint. This makes it possible to predict weather information at the time and date a moving object passes through a waypoint.

[0047] (3) A prediction system according to the third embodiment is the prediction system of (1) to (2), wherein the weather information prediction unit predicts the weather information for the date and time the moving body will pass through the waypoint by a weighted sum of the weather information recorded in the database of the measurement point located near the waypoint, using a coefficient that corresponds to the proximity between the date and time the moving body will pass through the waypoint and the date indicated by the date and time information recorded in the database of the measurement point located near the waypoint, the coefficient having a larger value the closer the proximity. This makes it possible to predict weather information at the time and date a moving object passes through a waypoint.

[0048] (4) A prediction system according to the fourth embodiment is the prediction system of (1) to (3), wherein the weather information prediction unit predicts the weather information for the date and time the moving body will pass through the waypoint by a weighted sum of the weather information recorded in the database of the measurement point located near the waypoint, using a coefficient corresponding to the proximity between the time period during which the moving body will pass through the waypoint and the time period indicated by the date and time information recorded in the database of the measurement point located near the waypoint. This makes it possible to predict weather information at the time and date a moving object passes through a waypoint.

[0049] (5) The prediction system according to the fifth embodiment is the prediction system according to (1) to (4), wherein the weather information prediction unit uses the weather information of the measurement point recorded in the database, the date and time information and the location information as learning data, learns the relationship between the date and time information and the location information of the learning data and the weather information, and when the location information of the waypoint and the date and time of passage of the waypoint are input, it creates a weather information prediction model that outputs the weather information for the date and time of passage at the waypoint, and uses the created weather information prediction model to predict the weather information for the date and time of passage of the moving object at the waypoint. This makes it possible to predict weather information at the time and date a moving object passes through a waypoint.

[0050] (6) The prediction system according to the sixth embodiment is the prediction system according to (5), wherein the weather information prediction unit sets a virtual measurement point and predicts the weather information at a predetermined date and time at the virtual measurement point by weighted sum of the weather information recorded in the database of the measurement point located near the virtual measurement point, with a coefficient corresponding to the reciprocal of the distance between the virtual measurement point and the measurement point located near the virtual measurement point, and adds the dataset of the virtual measurement point, the predetermined date and time, and the predicted weather information to the training data to create the weather information prediction model. This allows us to supplement the training data.

[0051] (7) A prediction system according to the seventh embodiment is the prediction system according to (1) to (6), wherein the moving body is a refrigerated vehicle, and further comprises an energy consumption prediction unit that predicts the energy consumption of the refrigeration unit when the refrigerated vehicle moves along the route, based on the weather information prediction unit predicting the date and time the moving body will pass through the waypoint, and a consumption prediction model created by learning the relationship between the weather information and the energy consumption per unit time consumed by the refrigeration unit installed in the refrigerated vehicle under the weather conditions indicated by the weather information. This makes it possible to predict the energy consumption of the refrigeration unit as the refrigerated vehicle travels its route.

[0052] (8) The prediction system according to the eighth aspect is the prediction system of (1) to (7), wherein the energy consumption prediction unit predicts the energy consumption that the refrigeration unit will consume when the refrigerated vehicle travels along each of the plurality of routes, and outputs the predicted energy consumption for each of the plurality of routes. This allows for a comparison of energy consumption across multiple routes.

[0053] (9) A prediction method according to the ninth embodiment includes a prediction system that has a database recording meteorological information measured at each of a plurality of measurement points, information on the date and time and location information of the meteorological information measured, and when a moving body moves along a predetermined path, the system predicts for each of all waypoints provided along the path the meteorological information for the date and time the moving body will pass through the waypoint, based on the meteorological information recorded in the database of the measurement point located near the waypoint.

[0054] (10) The program according to the tenth embodiment causes a computer that can access a database that records weather information measured at each of a plurality of measurement points, as well as information on the date and time and location of the weather information measured, and read the information recorded in the database, to perform the following process when a moving body moves along a predetermined path, for each of the waypoints provided along the path, to predict the weather information at the date and time when the moving body will pass through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint. [Explanation of Symbols]

[0055] 10. Server 11. Sensor value acquisition unit 12. Route setting section 13. Weather Forecasting Department 14. Energy Consumption Forecasting Section 15...Storage section 1, 1a, 1b... Refrigerated vehicles 2, 2a, 2b...control device 3, 3a, 3b... Sensors 4, 4a, 4b... Positioning sensors 5, 5a, 5b... Fixed observation stations 6, 6a, 6b... Sensors 7, 7a, 7b...Freezer 8, 8a, 8b... Refrigerated storage 20. User terminals 100... Prediction System NW... Network 900... Computer 901···CPU 902...Main memory 903...Auxiliary storage device 904... Input / Output Interface 905...Communication Interface

Claims

1. A database that records weather information measured at each of multiple measurement points, information on the date and time the weather information was measured, and location information. When a moving object moves along a predetermined path, a weather information prediction unit predicts, for each of the waypoints provided along the path, the weather information for the date and time the moving object will pass through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint. A prediction system equipped with the following features.

2. The weather information forecasting unit predicts the weather information for the date and time the moving object passes through the waypoint by using a weighted sum of the weather information recorded in the database of the measurement point located near the waypoint, with coefficients being a value corresponding to the reciprocal of the distance between the waypoint and the measurement point located near the waypoint, and a value corresponding to the proximity between the date and time the moving object passes through the waypoint and the date and time information recorded in the database of the measurement point located near the waypoint. The prediction system according to claim 1.

3. The weather information forecasting unit predicts the weather information for the date and time the moving object will pass through the waypoint by weighting the weather information recorded in the database of the measurement points located near the waypoint, using a coefficient that corresponds to the proximity between the date on which the moving object will pass through the waypoint and the date indicated by the date and time information recorded in the database of the measurement points located near the waypoint, wherein the closer the proximity, the larger the value of the coefficient. The prediction system according to claim 1.

4. The weather information forecasting unit predicts the weather information for the date and time the moving object passes through the waypoint by weighting the weather information recorded in the database of the measurement points located near the waypoint, using a coefficient that corresponds to the proximity between the time period during which the moving object passes through the waypoint and the time period indicated by the date and time information recorded in the database of the measurement points located near the waypoint, wherein the closer the proximity, the larger the value of the coefficient. The prediction system according to claim 1.

5. The weather information forecasting unit uses the weather information of the measurement point recorded in the database, the date and time information, and the location information as learning data, learns the relationship between the date and time information and the location information of the learning data and the weather information, and creates a weather information forecasting model that outputs the weather information for the date and time the waypoint passes through when the location information of the waypoint and the date and time the waypoint passes through are input, and uses the created weather information forecasting model to predict the weather information for the date and time the moving object passes through the waypoint. The prediction system according to claim 1.

6. The weather information forecasting unit sets a virtual measurement point and predicts the weather information for a predetermined date and time at the virtual measurement point by weighting the weather information recorded in the database for the measurement points located near the virtual measurement point, using a coefficient that is the reciprocal of the distance between the virtual measurement point and the measurement points located near the virtual measurement point. The unit then adds the dataset of the virtual measurement point, the predetermined date and time, and the predicted weather information to the training data to create the weather information forecasting model. The prediction system according to claim 5.

7. The aforementioned mobile vehicle is a refrigerated vehicle, An energy consumption prediction unit predicts the energy consumption of the refrigeration unit when the refrigeration vehicle travels along the route, based on the weather information for the date and time the moving object will pass through the waypoint as predicted by the weather information prediction unit, and a consumption prediction model created by learning the relationship between the weather information and the energy consumption per unit time consumed by the refrigeration unit of the refrigeration vehicle under the weather conditions indicated by the weather information. A prediction system according to any one of claims 1 to 5, further comprising the above.

8. The energy consumption prediction unit predicts the energy consumption of the refrigeration unit when the refrigerated vehicle travels along each of the multiple routes, and outputs the predicted energy consumption for each of the multiple routes. The prediction system according to claim 7.

9. A prediction system comprising a database that records weather information measured at each of multiple measurement points, as well as information on the date and time and location of the measurement, When a moving object travels along a predetermined path, for each of the waypoints provided along the path, the weather information for the date and time the moving object will pass through the waypoint is predicted based on the weather information recorded in the database of the measurement point located near the waypoint. Prediction method.

10. A computer capable of accessing a database that records weather information measured at each of multiple measurement points, as well as the date and time and location information of the weather information measured, and reading the information recorded in the database, When a moving object moves along a predetermined path, a process is performed to predict, for each of the waypoints provided along the path, the weather information for the date and time the moving object will pass through the waypoint, based on the weather information recorded in the database of the measurement point located near the waypoint. A program that executes the command.

Images