WO2023095328A1 - 情報処理装置、情報処理方法及びプログラム - Google Patents

情報処理装置、情報処理方法及びプログラム Download PDF

Info

Publication number
WO2023095328A1
WO2023095328A1 PCT/JP2021/043618 JP2021043618W WO2023095328A1 WO 2023095328 A1 WO2023095328 A1 WO 2023095328A1 JP 2021043618 W JP2021043618 W JP 2021043618W WO 2023095328 A1 WO2023095328 A1 WO 2023095328A1
Authority
WO
WIPO (PCT)
Prior art keywords
water distribution
plan
target
data
water
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/043618
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
力 江藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP2023563476A priority Critical patent/JP7790444B2/ja
Priority to PCT/JP2021/043618 priority patent/WO2023095328A1/ja
Priority to US18/709,919 priority patent/US20250013945A1/en
Publication of WO2023095328A1 publication Critical patent/WO2023095328A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/092—Reinforcement learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Definitions

  • the present invention relates to technology for generating an operation plan related to a water distribution plan.
  • Patent Literature 1 describes that an operation plan for a water supply and distribution process in a water supply plant is prepared by solving an optimization problem in which constraints and evaluation indices regarding the configuration of the plant are used as objective functions.
  • Patent Document 1 does not describe a specific method for calculating the evaluation index, so there is a problem that the technology described in Patent Document 1 does not necessarily optimize the operation plan. .
  • One aspect of the present invention has been made in view of the above problems, and one of its purposes is to provide a technology capable of generating a more efficient operation plan as an operation plan for water distribution plans.
  • An information processing apparatus includes acquisition means for acquiring target data related to a target water distribution plan, a cost function determined by inverse reinforcement learning using reference data related to a reference water distribution plan, and the acquisition generating means for generating an operation plan for the target water distribution plan by solving an optimization problem using the target data obtained by the means;
  • the information processing apparatus includes acquisition means for acquiring reference data relating to a reference water distribution plan, and a cost function used in an optimization problem for generating an operation plan relating to a target water distribution plan, and determining means for determining by inverse reinforcement learning with reference to the reference data.
  • an information processing method includes acquiring target data related to a target water distribution plan, a cost function determined by inverse reinforcement learning using reference data related to a reference water distribution plan, generating an operational plan for the target water distribution plan by solving an optimization problem using the target data obtained by the obtaining means.
  • the information processing method includes acquiring reference data related to a reference water distribution plan, and obtaining a cost function used in an optimization problem for generating an operation plan related to a target water distribution plan. and determining by inverse reinforcement learning with reference to reference data.
  • a program provides a computer with an acquisition process for acquiring target data related to a target water distribution plan, and a cost function determined by inverse reinforcement learning using reference data related to a reference water distribution plan. and a generation process of generating an operation plan relating to the target water distribution plan by solving an optimization problem using the target data acquired by the acquisition means.
  • the program according to one aspect of the present invention provides a computer with an acquisition process for acquiring reference data related to a reference water distribution plan and a cost function used in an optimization problem for generating an operation plan related to a target water distribution plan. , and a determination process of determining by inverse reinforcement learning with reference to the reference data.
  • a more efficient operation plan can be generated as the operation plan for the water distribution plan.
  • FIG. 1 is a block diagram showing the configuration of an information processing apparatus according to Exemplary Embodiment 1;
  • FIG. FIG. 3 is a flow diagram showing the flow of an information processing method according to exemplary embodiment 1;
  • 1 is a block diagram showing the configuration of an information processing apparatus according to Exemplary Embodiment 1;
  • FIG. FIG. 3 is a flow diagram showing the flow of an information processing method according to exemplary embodiment 1;
  • FIG. 9 is a block diagram showing the configuration of an information processing apparatus according to Exemplary Embodiment 2;
  • FIG. 11 is a diagram for explaining a water distribution planning problem according to exemplary embodiment 2;
  • FIG. 5 is a diagram showing an overview of a water distribution network according to exemplary embodiment 2;
  • FIG. 10 is a diagram showing a specific example of the operation pattern of the pump according to Exemplary Embodiment 2;
  • FIG. 11 is a diagram showing a display example of outputting an operation pattern of a pump in association with a time axis according to Exemplary Embodiment 2;
  • 1 is a block diagram showing the configuration of a computer functioning as an information processing device according to each exemplary embodiment;
  • FIG. 1 is a block diagram showing the configuration of an information processing device 1.
  • the information processing device 1 is a device that generates an operation plan related to a target water distribution plan.
  • the target of the water distribution plan is, for example, water supply infrastructure (hereinafter also referred to as "water supply infrastructure").
  • the information processing device 1 includes an acquisition unit 11 and a generation unit 12 .
  • the acquisition unit 11 acquires target data related to a target water distribution plan.
  • the target data includes, for example, information indicating the state of target water supply infrastructure. More specifically, the target data includes, by way of example, information about pumps, distribution networks, water pipelines, and/or demand points in the target water infrastructure.
  • the target data is not limited to the above example, and may include other data related to the target water distribution plan.
  • the generation unit 12 solves the optimization problem using the cost function determined by inverse reinforcement learning using the reference data related to the reference water distribution plan and the target data acquired by the acquisition unit 11, thereby obtaining the target water distribution Generate an operational plan for the plan.
  • the reference data is information about the water distribution plan for reference.
  • the reference data includes, for example, information representing the state of reference water infrastructure. More specifically, the reference data includes, by way of example, information about pumps, distribution networks, water pipelines, and/or demand points in the reference water infrastructure.
  • the reference water infrastructure may be the same as or different from the water infrastructure for which the operation plan is generated.
  • the reference data also includes, as an example, information on the operating pattern of pumps in the reference water infrastructure.
  • the reference data also includes, by way of example, information about personnel involved in the reference water infrastructure.
  • the reference data is not limited to the above example, and may include other data regarding the water distribution plan for reference.
  • the various data included in the target data and the various data included in the reference data can also be said to be state data representing the state in reverse reinforcement learning, or action data representing actions in reverse reinforcement learning.
  • the division between the state data and the action data can be appropriately changed according to the problem setting. That is, at least part of the data included in the state data can also have meaning as action data. At least part of the data included in the action data can also have meaning as state data.
  • Action data included in the reference data includes, as an example, data representing an operation plan created by an expert for the reference water infrastructure. More specifically, the behavioral data is represented by variables that are controlled based on operational rules, such as opening and closing of valves, intake of water, thresholds of pumps, etc., as an example.
  • the operation plan generated by the generation unit 12 includes, for example, information on the operation pattern of the pumps in the target water supply infrastructure.
  • the operational plan also includes, by way of example, information about personnel involved in the water infrastructure of interest.
  • the operation plan is not limited to the examples described above, and may include other information.
  • the cost function includes, for example, each cost term including each variable corresponding to each item included in the reference data.
  • the generation unit 12 uses the target data acquired by the acquisition unit 11 as a fixed variable for an optimization problem using a cost function, and among the variables included in each cost term included in the cost function, By solving the optimization problem with the variables of , the operation plan for the target water distribution plan is generated.
  • the cost function is not limited to the example described above, and may be another function.
  • the method by which the generation unit 12 solves the optimization problem is not particularly limited, but as an example, the solution may be obtained by performing processing equivalent to that of a general application program (eg, IBM ILOG CPLEX, GurobiOptimizer, SCIP). good.
  • a general application program eg, IBM ILOG CPLEX, GurobiOptimizer, SCIP.
  • the target data relating to the target water distribution plan is acquired, and the cost function determined by inverse reinforcement learning using the reference data relating to the reference water distribution plan and the obtained target data to generate an operation plan for the target water distribution plan by solving the optimization problem. Therefore, according to the information processing apparatus 1 according to this exemplary embodiment, it is possible to obtain an effect that a more efficient operation plan can be generated as an operation plan related to the water distribution plan.
  • FIG. 2 is a flow diagram showing the flow of the information processing method S10.
  • the acquisition unit 11 acquires target data related to the target water distribution plan.
  • the generating unit 12 solves the optimization problem using the cost function determined by inverse reinforcement learning using the reference data on the reference water distribution plan and the target data acquired in step S11. Generate an operation plan for the target water distribution plan.
  • the target data relating to the target water distribution plan is acquired, and the cost function determined by inverse reinforcement learning using the reference data relating to the reference water distribution plan and the obtained target data to generate an operation plan for the target water distribution plan by solving the optimization problem. Therefore, according to the information processing method S10 according to the exemplary embodiment, it is possible to obtain an effect that a more efficient operation plan can be generated as the operation plan for the water distribution plan.
  • FIG. 3 is a block diagram showing the configuration of the information processing device 2.
  • the information processing device 2 is a device that determines a cost function used for an optimization problem for generating an operation plan for a water distribution plan.
  • the information processing device 2 includes an acquisition unit 21 and a determination unit 22 .
  • the acquisition unit 21 acquires reference data relating to a reference water distribution plan.
  • the acquisition unit 21 may acquire the reference data all at once, or may acquire the reference data sequentially.
  • the determining unit 22 determines a cost function to be used in an optimization problem for generating an operation plan for a target water distribution plan by inverse reinforcement learning with reference to reference data.
  • the cost function includes, as an example, each cost term including each variable corresponding to each item included in the reference data.
  • the reference data regarding the water distribution plan for reference is obtained, and the cost function used in the optimization problem for generating the operation plan regarding the target water distribution plan is is determined by inverse reinforcement learning with reference to reference data. Therefore, according to the information processing device 2 according to the present exemplary embodiment, it is possible to determine a cost function capable of generating a more efficient operation plan as an operation plan for the water distribution plan.
  • FIG. 4 is a flow diagram showing the flow of the information processing method S2.
  • the acquisition unit 21 acquires reference data regarding the reference water distribution plan.
  • the determining unit 22 determines a cost function to be used in an optimization problem for generating an operation plan for a target water distribution plan by inverse reinforcement learning with reference to reference data.
  • the reference data regarding the water distribution plan for reference is acquired, and the cost function used in the optimization problem for generating the operation plan regarding the target water distribution plan is determined by inverse reinforcement learning with reference to reference data. Therefore, according to the information processing method S2 according to this exemplary embodiment, it is possible to determine a cost function capable of generating a more efficient operation plan as an operation plan for the water distribution plan.
  • FIG. 5 is a block diagram showing the configuration of the information processing device 1A according to this exemplary embodiment.
  • the information processing device 1A generates an operation plan regarding the water distribution plan of the water supply infrastructure.
  • the water infrastructure includes, by way of example, multiple sites such as reservoirs, distribution reservoirs, water intake facilities, water purification plants, water stations, and demand points.
  • the operation plan includes, for example, information indicating the operation pattern of pumps at each site.
  • the information processing apparatus 1A includes a control section 10A, a storage section 20A, a communication section 30A and an input/output section 40A.
  • the communication unit 30A communicates with an external device of the information processing device 1A via a communication line.
  • a communication line includes wireless LAN (Local Area Network), wired LAN, WAN (Wide Area Network), public line network, mobile data communication network, or a combination thereof.
  • the communication unit 30A transmits data supplied from the control unit 10A to other devices, and supplies data received from other devices to the control unit 10A.
  • Input/output unit 40A Input/output devices such as a keyboard, mouse, display, printer, and touch panel are connected to the input/output unit 40A.
  • the input/output unit 40A receives input of various kinds of information from the connected input device to the information processing apparatus 1A. Also, the input/output unit 40A outputs various kinds of information to the connected output device under the control of the control unit 10A.
  • an interface such as a USB (Universal Serial Bus) can be used as the input/output unit 40A.
  • Control section 10A The control unit 10A, as shown in FIG. 5, includes an acquisition unit 11A, a generation unit 12A, and a determination unit 22A.
  • the acquisition unit 11A acquires the target data TD and the reference data RD.
  • the acquisition unit 11A acquires the target data TD and the reference data RD from another device via the communication unit 30A.
  • the acquisition unit 11 may acquire the target data TD and the reference data RD input via the input/output unit 40A.
  • the acquisition unit 11 may acquire the target data TD and the reference data RD by reading the target data TD and the reference data RD from the storage unit 20A or an externally connected storage device. Details of the target data TD and the reference data RD will be described later.
  • the generation unit 12A solves the optimization problem using the cost function c determined by inverse reinforcement learning using the reference data RD related to the reference water distribution plan and the target data TD acquired by the acquisition unit 11, Generate an operation plan OP for the target water distribution plan.
  • the operation plan OP generation processing executed by the generation unit 12A will be described later.
  • the determination unit 22A determines the cost function c used in the optimization problem for generating the operation plan OP regarding the target water distribution plan by inverse reinforcement learning with reference to the reference data RD. The determination processing of the cost function c executed by the determination unit 22A will be described later.
  • the storage unit 20A stores the target data TD and the reference data RD acquired by the acquisition unit 11 .
  • the storage unit 20A also stores the operation plan OP generated by the generation unit 12A.
  • the storage unit 20A also stores the cost function c determined by the determination unit 22A and the constraint condition LC.
  • storing the cost function c in the storage unit 20A means that the parameters for determining the cost function c are stored in the storage unit 20A.
  • the target data TD is data used by the generation unit 12A to generate the operation plan OP.
  • the target data TD includes information indicating the state of the target water supply infrastructure.
  • the target data TD includes information about pumps, distribution networks, water pipelines and/or demand points in the target water infrastructure.
  • the target data TD includes, as an example, at least one of the following data (i) to (x) in the water supply infrastructure that is the target of the operation plan.
  • the data included in the target data TD is not limited to these, and may include other data.
  • power consumption at each base (ii) demand forecast margin, (iii) distribution reservoir margin, (iv) water distribution loss, (v) number of operating personnel at each base, (vi) electricity rate at each base, (vii) ) voltage at each location, (viii) water level at each location, (ix) water pressure at each location, and (x) water volume at each location.
  • the power consumption at each base indicates the power consumption at each base such as water purification plants and water supply stations.
  • demand forecast margin indicates the extent to which supply exceeds demand;
  • Reservoir margin indicates the extent to which the designed reservoir capacity exceeds the actual reservoir capacity.
  • Water distribution loss indicates the extent to which water is not being distributed to each demand point.
  • the number of operating personnel indicates the number of operating personnel at each site.
  • the reference data RD is data used when the determination unit 22A determines the cost function.
  • the reference data RD includes information representing the state of the reference water infrastructure.
  • the reference water infrastructure may be the same as or different from the water infrastructure for which the operation plan is generated. More specifically, the reference data RD includes, as an example, information about pumps, distribution networks, water pipelines, and/or demand points in the reference water infrastructure.
  • the reference data RD also includes, as an example, information on at least one of pump operating patterns and personnel in the reference water supply infrastructure. Each item included in the reference data RD may be treated as state data, or may be treated as action data.
  • the reference data RD includes, as an example, at least one of the following data (i) to (x) in the reference water supply infrastructure.
  • the data included in the reference data RD is not limited to these, and may include other data.
  • power consumption at each base (ii) demand forecast margin, (iii) distribution reservoir margin, (iv) water distribution loss, (v) number of operating personnel at each base, (vi) electricity rate at each base, (vii) ) voltage at each location, (viii) water level at each location, (ix) water pressure at each location, and (x) water volume at each location.
  • the reference data RD includes, as an example, data indicating an operation plan created by a skilled person for reference water infrastructure. More specifically, the reference data RD includes, as an example, data represented by variables controlled based on operation rules, such as opening/closing of valves, intake of water, thresholds of pumps, and the like. Such data can also be said to be data representing the decision-making history (expert's intention) of the expert who created the operational plan for reference.
  • the operational plan OP includes, by way of example, information about the operating pattern of the pumps in the water infrastructure of interest.
  • the operation plan OP also includes, as an example, information about the personnel involved in the target water supply infrastructure.
  • the cost function c includes each cost term including each variable corresponding to each item included in the reference data RD.
  • the cost function c is It can be expressed as. where i is i ⁇ [N] and N is the total number of items included in the reference data.
  • the cost term ⁇ i ⁇ f i (x i ) includes variables x i corresponding to items r i contained in the reference data.
  • a weighting factor ⁇ i is a weighting factor for each item r i .
  • the cost function c( ⁇ x i ⁇ ) is the cost term ⁇ i ⁇ f i (x i ) obtained by multiplying the weighting factor ⁇ i corresponding to the item ri and the function f(x i ) including the variable x i is the linear sum of
  • Constraint LC is a constraint for the optimization problem solved by the generator 12A. Constraints LC include, for example, the following (i) to (iv). Note that the constraint conditions LC are not limited to these, and may include other conditions. (i) The water storage volume of the reservoir/distribution reservoir is greater than or equal to threshold X and less than Y; (ii) supply exceeds demand by at least X%; (iii) All demand points are served. (iv) Do not use routes under construction.
  • generation parts generate
  • the generation unit 12A is an optimization problem using the cost function c
  • the target data TD acquired by the acquisition unit 11A is a fixed variable
  • each cost term included in the cost function c includes By solving an optimization problem using variables other than fixed variables as manipulated variables, an operation plan OP relating to the target water distribution plan is generated.
  • the generation unit 12A also outputs the generated operation plan OP.
  • the generation unit 12A may output the operation plan OP by writing it in the storage unit 20A or an external storage device, or may output it to an output device (display, printer, etc.) connected to the input/output unit 40A. good.
  • generation parts may transmit operation plan OP to another apparatus via 30 A of communication parts.
  • the determination unit 22A determines the cost function c used in the optimization problem for generating the operation plan for the target water distribution plan by inverse reinforcement learning with reference to the reference data RD.
  • the determination unit 22A obtains the weighting factor ⁇ i of the cost term ⁇ i ⁇ f i (x i ) included in the cost function c by inverse reinforcement learning using the state data and behavior data included in the reference data RD. decide.
  • the determination unit 22A prepares cost functions c having various values as the respective weighting coefficients ⁇ i , and uses these cost functions to calculate the cost for the reference data RD. Then, the value of each weighting factor ⁇ i that minimizes the cost of the reference data RD is determined.
  • the determination unit 22A may be configured to determine the cost function c by the inverse reinforcement learning technique described in Patent Document WO2021/130916.
  • the method by which the determination unit 22A determines the cost function c is not limited to this, and other methods may be used.
  • the determining unit 22A also outputs the determined cost function c.
  • the determination unit 22A may output the cost function c by writing it in the storage unit 20A or an external storage device, or may output it to an output device (display, printer, etc.) connected to the input/output unit 40A. good.
  • the generation unit 12A may transmit the cost function c to another device via the communication unit 30A.
  • FIG. 6 is a diagram for explaining a specific example of setting an optimization problem according to this exemplary embodiment.
  • the operation plan OP needs to be determined in consideration of various points of view, such as how much margin should be provided from the forecasted demand, how much power consumption should be suppressed, and how much the water level of the distribution reservoir should be considered. . Setting weights for these aspects is difficult. This is because the degree of emphasis on which point of view varies depending on the operator who operates the water supply infrastructure, and is not uniformly determined. For example, there is a case where the municipality A, which is the generator of a certain operation plan, places importance on the viewpoint of power consumption, while the municipality B places importance on the water level of the distribution reservoir.
  • the generating unit 12A determines the weighting factor ⁇ i of each cost term ⁇ i ⁇ f i (x i ) under the constraint condition LC by inverse reinforcement learning with reference to the reference data RD. Solve the optimization problem using the cost function c and the target data TD.
  • the weighting factor ⁇ i of each cost term ⁇ i ⁇ f i (x i ) included in the cost function c is determined by inverse reinforcement learning with reference to the reference data RD. It is a value that reflects the data, that is, a value that reflects the intention of the expert who generated the operation plan for reference.
  • the weighting coefficients ⁇ 1 to ⁇ 6 included in the cost function c used to generate the operation plan OP for the local government A are the skillfulness factors that generated the reference operation plan used to determine the cost function c. It is a value that reflects the intention of the person, etc.
  • the weighting coefficients ⁇ 1 to ⁇ 6 included in the cost function c used to generate the operation plan OP of the local government B reflect the intention of the expert who generated the reference operation plan used to determine the cost function c. is the value
  • the determination unit 22A determines the cost function c by referring to the reference data RD including the operation plan created by the expert a1 in the municipality A, and the cost function c determined by the determination unit 22A and the target data of the municipality A 12 A of production
  • the generation unit 12A can generate the future operation plan OP of the local government A that reflects the intention of the expert a1.
  • the determination unit 22A determines the cost function c by referring to the reference data RD including the operation plan created by the expert a1 in the municipality A, and the cost function c determined by the determination unit 22A and the target data TD of the municipality B , the generation unit 12A can also generate the future operation plan OP.
  • the generation unit 12A can generate the operation plan OP of the municipality B that reflects the intention of the expert a1.
  • FIG. 7 is a diagram showing an overview of the water distribution network 3, which is an example of the target of the operation plan OP generated by the information processing device 1A.
  • the water distribution network 3 includes a plurality of sites including water purification plants F1 and F2, a water supply station S1, a branch point B1, and demand points D1 and D2.
  • the water purification plants F1 and F2 are, for example, facilities for producing purified water from water taken from water intake targets (rivers, oceans, lakes and marshes, etc.) by water intake facilities.
  • the water purification plants F1 and F2 are provided with water storage facilities (tanks, reservoirs, etc.) and pumps.
  • the water supply station S1 is, for example, a facility that distributes water sent from water purification plants F1, F2, etc. to a specific area.
  • the water supply station S1 is provided with, for example, water storage facilities (tanks, reservoirs, etc.) and pumps.
  • Demand points D1 and D2 are facilities of consumers (for example, offices, homes, factories, and stores) that use the distributed water.
  • a branch point B1 is a facility where the water pipe L branches off. Each component (each base) of the water distribution network 3 is connected by a water pipeline L.
  • a plurality of water purification plants F1 and F2 a single water supply station S1, a branch point B1, and a plurality of demand points D1 and D2 are shown.
  • the number of water purification plants, water supply stations, branch points, and demand points is not limited to the example shown in FIG. 7, and may be larger or smaller.
  • explanatory variables used in the optimization of the operation plan for the water distribution network 3 will be described below.
  • the data used when optimizing the operation plan in the water infrastructure is not limited to the data exemplified below. Any information that can define the state of the water infrastructure and any variables that can be controlled based on the rules of operation of the water infrastructure can be used.
  • explanatory variable example 1 Information about pumps
  • the explanatory variables include, for example, information on pumps installed at each site.
  • the information about the pumps includes, for example, (i) a combination of pumps that operate at a certain timing (or time interval), (ii) water flow rate, and (iii) power consumption.
  • the water flow rate is the amount of water output (water flow rate) from the pump according to each operation pattern.
  • power consumption is the amount of power (power consumption) used by each pump.
  • explanatory variable example 2 Information on water distribution network 3
  • explanatory variables include information about the water pipeline L, as an example.
  • each water pipe L is assigned identification information that can identify the water pipe L and is expressed as a feature amount. More specifically, each water pipe L may be assigned a number from "1" to "m”, which enables identification of the water pipe L, for example. Further, as an example of the feature value of each water pipe L, the water flow rate "q i (t) [m 3 /15 min]”.
  • the explanatory variables may also include information about the demand point D.
  • the information about the demand point D is, for example, a predicted value of the demand amount at a certain timing (for example, time or time period) of each demand point.
  • the demand amount “d i (t)” in the time interval “t” at the demand point “d i (i ⁇ D)” included in the demand point node set D is represented by the following formula.
  • explanatory variable example 5 Operation pattern of the pump actually executed
  • explanatory variables may include, for example, the actual operation status of the operating pattern of the pump.
  • the explanatory variable represents, for example, a pump that operates at a certain timing (or time interval).
  • explanatory variables include, as an example, information about personnel assigned to each base included in the water distribution network 3 .
  • the information about personnel may be any data that can be expressed as a feature amount, such as information such as the number of people assigned, job type of each person (whether they are clerical workers or technical workers), years of service, and the like. Also, the work shift of an employee at each node may be used as data.
  • the information processing device 1A displays the generated operation plan OP on a display (not shown) connected to the input/output unit 50A.
  • FIG. 8 is a diagram showing a specific example of pump operation patterns included in the operation plan OP.
  • two pumps (pump A, pump B) are installed in each of the water purification plant F1 and the water purification plant F2.
  • One pump (pump C) is installed at the water supply station S1.
  • pump A and pump C may be small pumps and pump B may be a larger pump (than pumps A and C).
  • pattern 1" at the water purification plant F1 represents a pattern in which only the pump A operates
  • "operation pattern 2" represents a pattern in which only the pump B operates.
  • “Pattern 1" at the water supply station S1 represents a pattern in which only the pump C operates.
  • the information processing device 1A can output the operation plan OP by outputting the operation pattern of the pump shown in FIG. 8 in association with the time axis.
  • FIG. 9 is a diagram showing a display example in which the operating pattern of the pump is output in association with the time axis.
  • the horizontal axis indicates the time interval
  • the vertical axis indicates the operating pattern of the pump.
  • the graph in FIG. 9 represents an operation plan in which the operation pattern of the pump is changed from operation pattern 2 to operation pattern 1 in time interval 5 .
  • downsizing for example, (i) an example of operating an operation plan in a certain municipality A in a target municipality B that has downsized water facilities, and (ii) from a downsizing execution plan in municipality A An example of extracting the intention and drawing up a downsizing plan for the target municipality B is given.
  • the state data includes, for example, (a) an index representing the state of the water infrastructure, (b) the water distribution network, the capacity of the pump, the state of the drainage pipe, (c) the voltage, water level, pressure, and amount of water at each site, including.
  • Behavioral data is represented by variables that can be controlled based on operational rules, such as opening and closing of valves, intake of water, thresholds of pumps, and the like.
  • reference data examples include (a) information on water pipes and water quality, (b) information on water purification plants, (c) demographics, (d) staff information of the waterworks bureau, and (e) behavioral data of experts. ,including.
  • (a) information on water pipes and water quality includes, for example, the water quality of the water source (water purification costs are high if it contains a large amount of arsenic, iron, manganese, etc.), number, altitude, installation location of water pipes, area number of users per water pipe, population served per 1 km of water pipe, etc.
  • Information about the water purification plant includes, for example, how much water the water purification plant produces per day, the percentage of the total amount of purified water, annual production cost, annual power consumption, and so on.
  • Demographics are, for example, population trends in a 500m square area, or predicted values for population trends.
  • the staff information of the waterworks bureau is, for example, the number of administrative staff and technical staff (technical staff, meter reading staff, and contract staff may be included).
  • Behavioral data of experts, etc. is, for example, a facility consolidation and renewal plan (the number and installation locations of water purification plants), the water supply population per 1km of water pipes, and the number of staff assigned. For example, assuming that there are three water purification plants A, B, and C, the behavioral data is A: 50%, B: 20%, and C: 30% of the current total amount of purified water. The contents are changed to A: 30%, B: 10%, and C: 60%.
  • the information processing device 1A may present consolidation plans based on multiple intentions.
  • the intention of the creator of the reference water distribution plan is reflected in the cost function c determined by the determination unit 22A. That is, when the reference data RD is different, the cost function c determined by the determination unit 22A is also different.
  • the generation unit 12A generates an operation plan OP (consolidation plan) using each of the plurality of cost functions c, and presents the generated plurality of operation plans OP to the user. Moreover, at this time, the generation unit 12A may visualize and present the characteristics of each operation plan OP (weight coefficient of each cost function c, etc.).
  • the generation unit 12A when generating a plurality of operation plans OP, the generation unit 12A generates a rate simulator for each generated operation plan OP (for example, for the operation plan, aging water pipe renewal cost, water facility Calculate the income etc., calculate the charge per 1000 liters, etc.) may be presented to the user.
  • a rate simulator for each generated operation plan OP for example, for the operation plan, aging water pipe renewal cost, water facility Calculate the income etc., calculate the charge per 1000 liters, etc.
  • the generation unit 12A may display the estimated household water consumption (population change x water consumption per household) and the amount of water supplied according to the generated operation plan in a comparable display mode.
  • Some or all of the functions of the information processing apparatuses 1, 1A, and 2 may be implemented by hardware such as integrated circuits (IC chips), or may be implemented by software.
  • the information processing apparatuses 1, 1A, and 2 are implemented by computers that execute instructions of programs, which are software that implements each function, for example.
  • An example of such a computer (hereinafter referred to as computer C) is shown in FIG.
  • Computer C comprises at least one processor C1 and at least one memory C2.
  • a program P for operating the computer C as the information processing apparatuses 1, 1A, and 2 is recorded in the memory C2.
  • the processor C1 reads the program P from the memory C2 and executes it, thereby realizing each function of the information processing apparatuses 1, 1A, and 2.
  • processor C1 for example, CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit) , a microcontroller, or a combination thereof.
  • memory C2 for example, a flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.
  • the computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and temporarily storing various data.
  • Computer C may further include a communication interface for sending and receiving data to and from other devices.
  • Computer C may further include an input/output interface for connecting input/output devices such as a keyboard, mouse, display, and printer.
  • the program P can be recorded on a non-temporary tangible recording medium M that is readable by the computer C.
  • a recording medium M for example, a tape, disk, card, semiconductor memory, programmable logic circuit, or the like can be used.
  • the computer C can acquire the program P via such a recording medium M.
  • the program P can be transmitted via a transmission medium.
  • a transmission medium for example, a communication network or broadcast waves can be used.
  • Computer C can also obtain program P via such a transmission medium.
  • Appendix 2 Some or all of the above-described embodiments may also be described as follows. However, the present invention is not limited to the embodiments described below. (Appendix 1) an acquisition means for acquiring target data relating to the target water distribution plan; a cost function determined by inverse reinforcement learning using reference data for a reference water distribution plan; the target data acquired by the acquisition means; generating means for generating an operational plan for the target water distribution plan by solving an optimization problem using Information processing device equipped with.
  • the cost function includes each cost term including each variable corresponding to each item included in the reference data,
  • the generating means is an optimization problem using the cost function, using the target data acquired by the acquisition means as a fixed variable; Information according to appendix 1, wherein an operation plan for the target water distribution plan is generated by solving an optimization problem using variables other than the fixed variables among variables included in each cost term included in the cost function as manipulated variables. processing equipment.
  • the target data includes information indicating the state of the target water infrastructure, The information processing device according to appendix 1 or 2.
  • the target data includes information about pumps, distribution networks, water pipelines, and/or demand points in the target water infrastructure.
  • the information processing device according to appendix 3.
  • the operation plan generated by the generating means includes information about the operation pattern of pumps in the target water infrastructure.
  • the information processing device according to appendix 3 or 4.
  • the operation plan generated by the generating means includes information about personnel involved in the target water infrastructure. 6.
  • the information processing apparatus according to any one of Appendices 3 to 5.
  • the acquisition means acquires the reference data
  • the information processing device is 7.
  • the information processing apparatus according to any one of appendices 1 to 6, further comprising determining means for determining the cost function by inverse reinforcement learning with reference to the reference data.
  • the reference data includes: information about pumps, distribution networks, water pipelines and/or demand points in the reference water infrastructure; and information on pump operating patterns and/or personnel in said reference water infrastructure;
  • the information processing device according to appendix 7, wherein
  • (Appendix 9) obtaining means for obtaining reference data for a reference water distribution plan; and determining means for determining, by inverse reinforcement learning with reference to the reference data, a cost function to be used in an optimization problem for generating an operation plan for a target water distribution plan.
  • At least one processor performs an acquisition process for acquiring target data relating to a target water distribution plan; a cost function determined by inverse reinforcement learning using reference data relating to a reference water distribution plan; and a generation process of generating an operation plan related to the target water distribution plan by solving an optimization problem using the acquired target data.
  • the information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the generation process. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.
  • At least one processor is provided, and the processor performs an acquisition process for acquiring reference data for a reference water distribution plan, and a cost function for use in an optimization problem for generating an operation plan for a target water distribution plan, to the reference data.
  • An information processing device that executes a determination process determined by inverse reinforcement learning with reference to.
  • the information processing apparatus may further include a memory, and the memory may store a program for causing the processor to execute the acquisition process and the determination process. Also, this program may be recorded in a computer-readable non-temporary tangible recording medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2021/043618 2021-11-29 2021-11-29 情報処理装置、情報処理方法及びプログラム Ceased WO2023095328A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023563476A JP7790444B2 (ja) 2021-11-29 2021-11-29 情報処理装置、情報処理方法及びプログラム
PCT/JP2021/043618 WO2023095328A1 (ja) 2021-11-29 2021-11-29 情報処理装置、情報処理方法及びプログラム
US18/709,919 US20250013945A1 (en) 2021-11-29 2021-11-29 Information processing apparatus, information processing method, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/043618 WO2023095328A1 (ja) 2021-11-29 2021-11-29 情報処理装置、情報処理方法及びプログラム

Publications (1)

Publication Number Publication Date
WO2023095328A1 true WO2023095328A1 (ja) 2023-06-01

Family

ID=86539026

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/043618 Ceased WO2023095328A1 (ja) 2021-11-29 2021-11-29 情報処理装置、情報処理方法及びプログラム

Country Status (3)

Country Link
US (1) US20250013945A1 (https=)
JP (1) JP7790444B2 (https=)
WO (1) WO2023095328A1 (https=)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116484647B (zh) * 2023-05-24 2023-09-05 长江水利委员会长江科学院 面向统筹协调的分布式水资源配置方法及系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018185678A (ja) * 2017-04-26 2018-11-22 株式会社日立製作所 運用計画立案装置、運用制御システム、および、運用計画立案方法

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018185678A (ja) * 2017-04-26 2018-11-22 株式会社日立製作所 運用計画立案装置、運用制御システム、および、運用計画立案方法

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
EIJI UCHIHA ET AL.: "Inverse Reinforcement Learning Method Using Density Ratio Estimation", THE 32ND ANNUAL CONFERENCE OF THE ROBOTICS SOCIETY OF JAPAN (RSJ); FUKUOKA, JAPAN; SEPTEMBER 4-6, 2014, THE ROBOTICS SOCIETY OF JAPAN, JP, vol. 32, 4 September 2014 (2014-09-04) - 6 September 2014 (2014-09-06), JP, pages 118, XP009546569 *
JULIEN DOSSA ROUSSLAN FERNAND; LIAN XINYU; NOMOTO HIROKAZU; MATSUBARA TAKASHI; UEHARA KUNIAKI: "A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning", 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), IEEE, 14 July 2019 (2019-07-14), pages 1 - 8, XP033621865, DOI: 10.1109/IJCNN.2019.8852026 *
OSATO KOHEI: "Acquisition of motion from video using imitation learning", INFORMATION PROCESSING SOCIETY OF JAPAN RESEARCH REPORT COMPUTER VISION AND IMAGE MEDIA, vol. 2019, no. 11, 30 May 2019 (2019-05-30), pages 1 - 4, XP093068425 *

Also Published As

Publication number Publication date
JPWO2023095328A1 (https=) 2023-06-01
US20250013945A1 (en) 2025-01-09
JP7790444B2 (ja) 2025-12-23

Similar Documents

Publication Publication Date Title
Sharma et al. Regional resilience analysis: A multiscale approach to optimize the resilience of interdependent infrastructure
Ma et al. Resilience enhancement of distribution grids against extreme weather events
Kelly Estimating economic loss from cascading infrastructure failure: a perspective on modelling interdependency
Taieb et al. Forecasting uncertainty in electricity smart meter data by boosting additive quantile regression
Lee et al. Forecasting nonlinear time series of energy consumption using a hybrid dynamic model
Wang et al. Energy-water nexus design and operation towards the sustainable development goals
Hadzilacos et al. UtilNets: a water mains rehabilitation decision-support system
Gharabaghi et al. Integrated nonlinear daily water demand forecast model (case study: City of Guelph, Canada)
Shi et al. Thinking geographically about AI sustainability
KR101572643B1 (ko) 국민발전소 비지니스 플랫폼 연계형 전력수요자원 네모모델링 시뮬레이션 장치 및 방법
Katara et al. A time series analysis of electricity demand in Tamale, Ghana
Parreño Forecasting electricity consumption in the Philippines using ARIMA models
Marchand et al. Fast near-optimal heuristic for the short-term hydro-generation planning problem
Heydari Kushalshah et al. Hybrid modelling for urban water supply system management based on a bi-objective mathematical model and system dynamics: A case study in Guilan province.
Ponte et al. Intelligent decision support system for real-time water demand management
JP7790444B2 (ja) 情報処理装置、情報処理方法及びプログラム
Wang et al. Water and energy systems in sustainable city development: A case of Sub-Saharan Africa
Khatoon et al. Analysis and comparison of various methods available for load forecasting: An overview
Amlabu et al. Electric load forecasting: A case study of the Nigerian power sector
JPWO2023095328A5 (https=)
Warren et al. Managing uncertainty in electricity generation and demand forecasting
Efekemo et al. Electricity demand forecasting: A review
Mansor et al. Medium-term electricity load demand forecasting using holt-winter exponential smoothing and SARIMA in university campus
Parreno Forecasting the total non-coincidental monthly system peak demand in the Philippines: A comparison of seasonal autoregressive integrated moving average models and artificial neural networks
Alamri et al. Agent based modelling in digital twins for household water consumption forecasting

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21965697

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023563476

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 18709919

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21965697

Country of ref document: EP

Kind code of ref document: A1