RESOURCE COST OPTIMIZATION SYSTEM, METHOD, AND PROGRAM
First Claim
1. A computer implemented method for optimizing a cost of a resource under a cost structure, the method comprising:
- retaining a policy generated based on a Markov decision process and the cost structure, the policy indicating when to store the resource in a storage device and when to release the resource from the storage device;
deciding an action of storing or releasing the resource based on the policy and a state of the Markov decision process, the state including a usage amount error, an amount of resource available in the storage device, a specification of a current section among a plurality of sections during which the policy applies, and a target value.
1 Assignment
0 Petitions
Accused Products
Abstract
Apparatus and method use a Markov decision process (MDP) to reduce the cost of variations in electric power usage. The user notifies a power company of a predicted value for a period. The period is divided into subsections. For each subsection, on the basis of a MDP including a state that depends on an electric power usage amount error, charge amount, and set target, the amount of charging and discharging of a storage battery as an action at any given time is optimally decided depending on the electric power usage amount error, charge amount, time, and set target at that time. A predetermined time in a subsection is a target setting time, at which a future target is further set as the action. The action includes deciding the charging and discharging amount in that subsection and deciding a future target in a subsection whose target should be set.
-
Citations
18 Claims
-
1. A computer implemented method for optimizing a cost of a resource under a cost structure, the method comprising:
-
retaining a policy generated based on a Markov decision process and the cost structure, the policy indicating when to store the resource in a storage device and when to release the resource from the storage device; deciding an action of storing or releasing the resource based on the policy and a state of the Markov decision process, the state including a usage amount error, an amount of resource available in the storage device, a specification of a current section among a plurality of sections during which the policy applies, and a target value. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A non-transitory computer executed program product for optimizing a cost of a resource under a cost structure, the program product causing the computer to execute:
-
a step of retaining a policy generated based on a Markov decision process and the cost structure, the policy indicating when to store the resource in a storage device and when to release the resource from the storage device; a step of deciding an action of storing or releasing the resource based on the policy and a state of the Markov decision process, the state including a usage amount error, an amount of resource available in the storage device, a specification of a current section among a plurality of sections during which the policy applies, and a target value. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A computer implemented system for optimizing a cost of a resource under a cost structure, the system comprising:
-
a storage device configured to store the resource and release the resource; means for retaining a policy generated based on a Markov decision process and the cost structure, the policy indicating when to store the resource in the storage device and when to release the resource from the storage device; means for deciding an action of storing or releasing the resource by the storage device based on the policy and a state of the Markov decision process, the state including a usage amount error, an amount of resource available in the storage device, a specification of a current section among a plurality of sections during which the policy applies, and a target value. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification