Supply Chain Analysis Tools



Similar documents
Course Supply Chain Management: Inventory Management. Inventories cost money: Reasons for inventory. Types of inventory

Tema 4: Supply Chain Management

D Lab: Supply Chains

Agenda. TPPE37 Manufacturing Control. A typical production process. The Planning Hierarchy. Primary material flow

Ud Understanding di inventory issues

Inventory Management and Risk Pooling. Xiaohong Pang Automation Department Shanghai Jiaotong University

MGT Exam 2 Formulas. Item $ Usage % of $ usage Cumulative % of $ Cumulative % of no. of items Class

Key Concepts: Week 8 Lesson 1: Inventory Models for Multiple Items & Locations

Agenda. Real System, Transactional IT, Analytic IT. What s the Supply Chain. Levels of Decision Making. Supply Chain Optimization

Inventory Management. Topics on inventory management

Inventory Control. Contents 1. FRAMEWORK OF PLANNING DECISIONS...1

講 師 : 周 世 玉 Shihyu Chou

Lot size/reorder level (Q,R) Models

A Programme Implementation of Several Inventory Control Algorithms

Inventory Management and Risk Pooling

Risk Pooling Strategies to Reduce and Hedge Uncertainty

Supply Chain Management: Inventory Management

Chapter 9. Inventory management

Package SCperf. February 19, 2015

Supply Chain Inventory Management Chapter 9. Copyright 2013 Pearson Education, Inc. publishing as Prentice Hall 09-01

Inventory Management: Fundamental Concepts & EOQ. Chris Caplice ESD.260/15.770/1.260 Logistics Systems Oct 2006

1 The EOQ and Extensions

INTEGRATED OPTIMIZATION OF SAFETY STOCK

2.1 Model Development: Economic Order Quantity (EOQ) Model

Small Lot Production. Chapter 5

Agenda. Managing Uncertainty in the Supply Chain. The Economic Order Quantity. Classic inventory theory

MATERIALS MANAGEMENT. Module 9 July 22, 2014

Single item inventory control under periodic review and a minimum order quantity

Inventory Control Subject to Known Demand

What is the Bullwhip Effect caused by?

Modeling Stochastic Inventory Policy with Simulation

How human behaviour amplifies the bullwhip effect a study based on the beer distribution game online

Inventory management

Supply Chain Management: Risk pooling

EVERYTHING YOU NEED TO KNOW ABOUT INVENTORY

Analysis of Various Forecasting Approaches for Linear Supply Chains based on Different Demand Data Transformations

A Synchronized Supply Chain for Reducing Decoupling Stock

Inventory: Independent Demand Systems

SPARE PARTS INVENTORY SYSTEMS UNDER AN INCREASING FAILURE RATE DEMAND INTERVAL DISTRIBUTION

Material Requirements Planning (MRP)

Case Study on Forecasting, Bull-Whip Effect in A Supply Chain

Chapter 7. Production, Capacity and Material Planning

Introduction. How Important Is Inventory Control?

Mathematical Modeling of Inventory Control Systems with Lateral Transshipments

Economic Production Quantity (EPQ) Model with Time- Dependent Demand and Reduction Delivery Policy

Chapter Introduction. Distribution Strategies. Traditional Warehousing Intermediate Inventory Storage Point Strategies

INDUSTRIAL STATISTICS AND OPERATIONAL MANAGEMENT. 7. Inventory Management

Web based Multi Product Inventory Optimization using Genetic Algorithm

Forecasting in supply chains

Inventory Management I: Economic Order Quantity (EOQ)

HYPOTHESIS TESTING: POWER OF THE TEST

INVENTORY MANAGEMENT. 1. Raw Materials (including component parts) 2. Work-In-Process 3. Maintenance/Repair/Operating Supply (MRO) 4.

MULTI-ECHELON INVENTORY MANAGEMENT. Stijn Rutjes & Martijn Cornelissen

Operations Management

10.2 Series and Convergence

Inventory Management - A Teaching Note

Inventory Theory 935

Contracts. David Simchi-Levi. Professor of Engineering Systems

Chapter 14 Inventory Management

Inventory Management. Material Requirements Planning. Chris Caplice ESD.260/15.770/1.260 Logistics Systems Oct 2006

Inventory Models for Special Cases: A & C Items and Challenges

2.6. Probability. In general the probability density of a random variable satisfies two conditions:

Project procurement and disposal decisions: An inventory management model

Multi-Echelon Inventory Optimization

Operations and Supply Chain Management Prof. G. Srinivasan Department of Management Studies Indian Institute of Technology, Madras

STOCHASTIC PERISHABLE INVENTORY CONTROL SYSTEMS IN SUPPLY CHAIN WITH PARTIAL BACKORDERS

MAINTAINED SYSTEMS. Harry G. Kwatny. Department of Mechanical Engineering & Mechanics Drexel University ENGINEERING RELIABILITY INTRODUCTION

The aim behind the calculations of EOQ and ROL is to weigh up these, and other advantages and disadvantages and to find a suitable compromise level.

Chapter 6. Inventory Control Models

Equations for Inventory Management

Confidence Intervals for the Difference Between Two Means

Inventory Control Models

A Combined Inventory-Location Model for Distribution Network Design

An Overview on Theory of Inventory

An Entropic Order Quantity (EnOQ) Model. with Post Deterioration Cash Discounts

List of Tables. Table No Title Page No 2.1 Market Segments in Indian retail 25

We consider a two-echelon inventory system with a capacitated centralized production facility and several

Inventory Theory Inventory Models. Chapter 25 Page 1

Stochastic Models for Inventory Management at Service Facilities

Risk-Pooling Effects of Emergency Shipping in a Two-Echelon Distribution System

Inventory Management. Multi-Items and Multi-Echelon. Chris Caplice ESD.260/15.770/1.260 Logistics Systems Nov 2006

The Newsvendor Model

Inventory Management & Optimization in Practice

Math 461 Fall 2006 Test 2 Solutions

APPENDIX B. The Risk Pool Game B.1 INTRODUCTION

Inventory Models (Stock Control)

GESTION DE LA PRODUCTION ET DES OPERATIONS PICASSO EXERCICE INTEGRE

Logistics Management Customer Service. Özgür Kabak, Ph.D.

The Next Generation of Inventory Optimization has Arrived

Reorder level = demand during lead time = lead time x demand per unit time ROL = LT x D

Applying Actual Usage Inventory Management Best Practice in a Health Care Supply Chain

Perishable Items in Multi-Level Inventory Systems

EXPONENTIAL DEPENDENT DEMAND RATE ECONOMIC PRODUCTION QUANTITY (EPQ) MODEL WITH FOR REDUCTION DELIVERY POLICY

Effect of Forecasting on Bullwhip Effect in Supply Chain Management

FIXED CHARGE UNBALANCED TRANSPORTATION PROBLEM IN INVENTORY POOLING WITH MULTIPLE RETAILERS

Supply and Demand Uncertainty in Multi-Echelon Supply Chains

CHAPTER 6 AGGREGATE PLANNING AND INVENTORY MANAGEMENT 명지대학교 산업시스템공학부

CHAPTER 6: Continuous Uniform Distribution: 6.1. Definition: The density function of the continuous random variable X on the interval [A, B] is.

Math 431 An Introduction to Probability. Final Exam Solutions

Objectives of Chapters 7,8

Transcription:

Supply Chain Analysis Tools MS&E 262 Supply Chain Management April 14, 2004 Inventory/Service Trade-off Curve Motivation High Inventory Low Poor Service Good Analytical tools help lower the curve! 1

Outline EOQ Newsvendor Lot Size Reorder (Q,R) Model Periodic Review (T,S) Model Random Lead Times Risk Pooling/Consolidation Example Multi-echelon Example Other Improvements Economic Order Quantity Model How much to order/produce? Fixed order cost of $ K Inventory holding cost of $ h = $ Ic Shortages prohibited Deterministic (constant) demand rate per year, D Inventory Level Slope = -D Q T (T = Q/D) Time, t 2

EOQ Model - Derivation Annual Holding + Setup Cost G(Q) = cd + KD/Q + IcQ/2 Purchasing Setup Holding Total = G(Q)-cD Holding = IcQ/2 Q* Q * = 2KD Ic Setup = KD/Q Q EOQ Model Sensitivities/Shortcomings 40 20 02 rule 40 % error in an input parameter results in 20 % error in Q The result is a 2 % increase in the costs, G(Q) Cost function is relatively insensitive to errors in Q Shortcomings of EOQ Model? Zero lead time (easily extended to fixed lead time) Infinite production rate (finite production rate, P, if P > D) No shortages allowed (easily extendable) Constant, deterministic demand rate 3

Newsvendor Model How much to order/produce? Underage cost/unit c u Overage cost/unit c o Likelihood f(d) Mean Demand, d Newsvendor Model (cont.) F( Q * ) = c u cu + c o Shortcomings of Newsvendor Model? No consideration of positive lead times One shot model (can be extended to multiple periods) No setup cost for placing orders included 4

Lot Size Reorder Point (Q,R) Model We need to decide two things: How much to order each time we place an order (Q)? At which reorder point (R) do we place an order? Inventory Position R s Q τ Safety Stock Time τ= Lead Time (Q,R) Model Notations Average demand rate/year Setup cost Variable cost Holding cost Order quantity Reorder point Lead time Safety stock λ K c h=ic Q R τ s 5

(Q,R) Model Unit Shortage Cost p The expected total annual cost is Kλ Q λ G ( Q, R) = + Ic + R λτ + p ( x R) f ( x) dx Q 2 Q R Setup Holding Shortage n Defining n(r) = E [# of units short in a cycle] we obtain 2λ( K + pn( R)) Q = Ic QIc F( R) = 1 pλ (Q,R) Model Unit Shortage Cost p (cont.) For normally distributed demand, define where z = (R-µ L )/σ L. Hence n(r) = σ L L(z) Use the approximate solution: Q = EOQ Obtain z from tables for L(z) R = µ L + zσ L L ( z) = ( t z) φ( t) dt µ L : mean lead time demand; σ L : standard deviation of lead time demand z 6

(Q,R) Model Service Level Approaches Type 1: α = Prob(no stock-out in lead time) Type 2: β = Proportion of demand met from on-hand stock Recall n(r) = E[# of units short in cycle] n( R) σ LL( z) = = 1 β Q Q Bad Better (1 β ) Q L( z) = σ L Periodic Review (T,S) Model Review every T units Order up to S units at every review Response Time = T+τ Inventory Lead Time S Τ τ Time τ 7

(T,S) Model (cont.) Where T = EOQ/λ S = µ τ+t τ+t + z σ τ+t τ+t µ τ+t = mean demand over τ+t periods σ τ+t = standard deviation of demand over τ+t periods z see (Q,R) model Hence Safety Stock = z σ τ+t Lead Time Demand Variability Expectation of Sum = Sum of Expectations General Variance Formula (Lead time = τ periods, demand in period i = d i ) σ 2 d LT = τ i= 1 σ 2 d i + 2 i< j COV ( d i, d j ), where d LT = τ i= 1 d i Variance of Sum = Sum of Variances (for independent variables) Example: Lead time demand * Mean µ L = τ µ Variance σ L2 = τ σ 2 * assuming independence between periods 8

Random Lead Times If lead time is random, with mean τ and variance s 2 And demand in time t has mean µt and variance σ 2 t Then the demand during (random) lead time has * Mean µ L = τµ Variance σ L2 = µ 2 s 2 +τσ 2 * Assuming orders do not cross and successive lead times are independent Lead Time Example Supplier s Production Time = 3 weeks Transportation Time from Supplier = 4 weeks End Product Demand, per week ~ N(µ,σ 2 ) Case 1: No variability in transportation time ~ N(4,0) weeks τ = 7 weeks µ L = 7µ, σ L2 = 7σ 2 Case 2: Transportation Time from Supplier ~ N(4,0.81) weeks τ = 7 weeks µ L = 7µ, σ L2 = µ 2 (0.81) + 7σ 2 9

Uniform vs. Non-uniform Service Levels Risk Pooling/Consolidation Multi-Echelon Analysis Postponement Lead-time Reduction Review Period Reduction Variable Lead-time Risk Pooling/Consolidation What is meant by Risk Pooling? Example Laser Printer Supply Chain 10

Laser Printer: Finished Goods Logistics Penang, Malaysia Long Beach CA, USA Memphis TN, USA Represents a DC location for distributor D1 http://www.ups.com/maps UPS Ground Map for Memphis, TN http://www.ups.com/maps 11

Laser Printer s Distributor Network Assume the following distributor network: 5 Independent Distributors (D1, D2, D3, D4, D5) Each distributor operates 8 DCs across the US Who are the distributors customers? Who owns the printer inventory? Relevant inventory metrics for a DC? Laser Printer s Distributor Network Opportunity for Risk Pooling For any particular distributor? For any particular location (e.g., Memphis, TN)? For the original equipment mfg (OEM)? 12

Assume that: 1. 2. 3. 4. 5. 6. Laser Printer s Distributor Network Demands at the multiple DCs are statistically independent. The means and standard deviations of demand for the multiple product DCs are identical. The leadtimes for the multiple DCs are identical/constant. The review periods at the DCs are identical. The safety factors for the DCs are identical. All DCs have the same inventory value. Laser Printer s Distributor Network Let: σ i = standard deviation of demand per period at DC i; L i = lead time for DC i; T i = review period for DC i; z i = safety factor for DC i; n = number of DCs in a region (e.g., DCs in Memphis, TN). 13

Laser Printer s Distributor Network Safety Stock at DC i = z i a i T i + L i n Total System Safety Stock = > i=1 z i a i T i + L i Safety Stock, Unpooled Total = nza T + L Safety Stock, Pooled Total = za Pooled T + L a Pooled = > i a i2 = a n Laser Printer s Distributor Network Reduction Effect through Pooling: SafetyStock,Unpooled Total?SafetyStock,Pooled Total SafetyStock,Unpooled Total 1? za Pooled T + L nza T + L = 1? a n na = 1? 1 n Reduction Effect in Memphis (n = 5): 55.3% Recall, the Distributors operate 8 separate DCs across the US 14

Laser Printer s Distributor Network What Happened? Benefit to the OEM in a particular region? Cost Savings attributed to Risk Pooling? Benefits, other than logistics? Multi-Echelon Supply Chain Analysis Concept Interactions of various levels in supply chain Levels are referred to as echelons Example Beer Game 15

Multi-Echelon Beer Game O I O I O I ORDER FLOW BEER! Retailer Wholesaler Distributor Factory D D D D D D D D Inventory Inventory Inventory Inventory PRODUCT FLOW Multi-Echelon Beer Game What Happened During Play? Communication? Lead Time? Holding vs. Backlogging Costs? Time Horizon/Duration? 16

Multi-Echelon Beer Game Applying Inventory Theory: Holding vs. Backlogging Costs? (p = $1/wk, h = $0.50/wk) Lead Time Effects? Information Sharing? What policy could you play? Postponement/Delayed Differentiation Concept Delay product differentiation until as late as possible in the production process Examples Advantages? Trade-offs? 17

Lead Time Reduction Advantages? Trade-offs? How to do analysis? Review Period Reduction Advantages? Trade-offs? How to do analysis? 18

Summary Avoid black box approach Understand underlying assumptions Perform sensitivity analysis on different parameters At worst, simulate the system! Analytical tools can help significantly improve supply chain performance! 19