public class SimulatePolicies extends Object
Constructor and Description |
---|
SimulatePolicies() |
Modifier and Type | Method and Description |
---|---|
static double[] |
simulate_sS(umontreal.ssj.probdist.Distribution[] demand,
double orderCost,
double holdingCost,
double penaltyCost,
double unitCost,
double initialStock,
double[] S,
double[] s,
double confidence,
double error)
Simulation of an (s,S) policy
|
static double[] |
simulateStochaticLotSizing(umontreal.ssj.probdist.Distribution[] demand,
double orderCost,
double holdingCost,
double penaltyCost,
double unitCost,
double initialStock,
BackwardRecursionImpl recursion,
double confidence,
double error)
Simulation of a tabulated optimal policy obtained via backward recursion
|
public static double[] simulate_sS(umontreal.ssj.probdist.Distribution[] demand, double orderCost, double holdingCost, double penaltyCost, double unitCost, double initialStock, double[] S, double[] s, double confidence, double error)
demand
- the random demandorderCost
- the fixed ordering costholdingCost
- the proportional holding costpenaltyCost
- the proportional penalty costunitCost
- per proportional ordering costinitialStock
- the initial costS
- the S (order-up-to-level) valuess
- the s (reorder point) valuesconfidence
- the confidence level for the estimation of the policy expected total costerror
- the tolerated errorpublic static double[] simulateStochaticLotSizing(umontreal.ssj.probdist.Distribution[] demand, double orderCost, double holdingCost, double penaltyCost, double unitCost, double initialStock, BackwardRecursionImpl recursion, double confidence, double error)
demand
- the random demandorderCost
- the fixed ordering costholdingCost
- the proportional holding costpenaltyCost
- the proportional penalty costunitCost
- per proportional ordering costinitialStock
- the initial costrecursion
- the BackwardRecursionImpl
object containing the tabulated optimal policyconfidence
- the confidence level for the estimation of the policy expected total costerror
- the tolerated errorCopyright © 2017–2018. All rights reserved.