inventory control in operation research

Upload: huyen-le-thi-thanh

Post on 01-Mar-2018

215 views

Category:

Documents


0 download

TRANSCRIPT

  • 7/25/2019 Inventory control in Operation Research

    1/23

    Dr Valentina Plekhanova

    CISM02: Decision Support for Management

    Unit 8

    Inventory Systems

    Unit 8: Learning Outcomes

    2CISM02 Decision Support for Management Unit 8

    1. To understand the inventory problems

    2. To be able to distinguish between a variety of the major stock costs

    3. To understand the nature of demands

    4. To understand the simple Economic Order Quantity (EOQ) model

    5. To construct an algebraic model for a simple inventory system

    6. To be able to apply inventory models to the practical problems

    7. To be able to explain the limitations of inventory control models

  • 7/25/2019 Inventory control in Operation Research

    2/23

    Inventory

    3

    Inventory: Stock of items for internal or external demand.

    Tools, machinery , equipment

    Raw materials

    Working capital

    Finished goods

    Thepurpose of inventory managementis to determine the amount

    of inventory to keep in stock.

    CISM02 Decision Support for Management Unit 8

    Inventory Management

    4

    The word inventory was first recorded in 1601. The French term inventaire, or

    "detailed list of goods," dates back to 1415.

    Inventory management is primarily about specifying the size and placement of

    stocked goods.

    Inventory management is required at different locations within a facility or

    within multiple locations of a supply network to protect the regular and planned

    course of production against the random disturbance of running out of

    materials or goods.

    The scope of inventory managementalso concerns the fine lines between

    replenishment lead time, carrying costs of inventory, asset management,

    inventory forecasting, inventory valuation, inventory visibility, future inventory

    price forecasting, physical inventory, available physical space for inventory,

    quality management, replenishment, returns and defective goods and demand

    forecasting.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    3/23

    Basic Inventory Problem

    5

    Any inventory problem gives an answer to the following questions:

    How much to order?

    When to order?

    CISM02 Decision Support for Management Unit 8

    Inventory Control

    6

    The problem of inventory exists in all companies whether big or small.

    Exceeding inventory has contributed to the failure of many companies.

    If stock is taken regularly to honour a demand at any time, a company

    will never be out of stock and thereby lose the sales and goodwill of its

    customers. But the cost of investment and keeping up the inventory

    (holding cost) will increase.

    Less inventory leads to frequent orders and stock out and costs

    increase as a result.

    The ideal inventory policy is to find out the break-even of these costs.

    Also the policy should be adjustable to suit the existing system.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    4/23

    Buffer Stocks

    7

    Many organisations keep an additional amount of inventory called

    safetyorbuffer stocksfor the following reasons:

    Variations in demand

    High seasonal demand

    Variations in supplier deliveries

    Volume discounts

    High ordering price

    etc.

    CISM02 Decision Support for Management Unit 8

    Inventory Costs

    8

    Inventory must be sufficient to provide high quality customer service.

    Inventory Costs:

    Carrying costs/holding costsare the costs of holding an item in

    inventory (rent, heating, cooling, lighting, security, refrigeration,

    record keeping, deterioration, taxes, etc.)Ordering costsincrease/decrease with the number/size of orders

    Shortage costsinsufficient inventory for customer demand

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    5/23

    Inventory Models:Economic Parameters

    9

    Set-up cost: This involves the fixed charge associated with theplacement of an order or with the initial preparation of a production

    facility. The set-up cost is usually assumed independent of the quantity

    ordered or produced.

    Purchase price or production cost: This parameter is of special interest

    when quantity discounts or price breaks can be secured or when large

    production runs may result in a decrease in the production cost. Under

    these conditions, the order quantity must be adjusted to take advantage

    of these price breaks.

    CISM02 Decision Support for Management Unit 8

    Inventory Models:Economic Parameters

    10

    Holding cost: This represents the cost of carrying inventory in storage.

    It includes the interest on invested capital, storage costs, handling

    costs, depreciation costs, etc. Holding costs usually are assumed to

    vary directly with the level of inventory as well as the length of time

    the item is held in stock. As the inventory increases, this cost

    increases.

    Shortage cost or penalty cost: These are the penalty costs incurred asa result of running out of stock when the commodity is needed (i.e.

    when the demand is fulfilled). They generally include costs due to

    loss in customersgoodwill and potential loss in income.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    6/23

    Inventory Models: Terminology

    11

    Replenishment: An inventory system may operate with delivery lags, the

    actual replenishment of stock may occur instantaneously or uniformly.

    Lead Time or time lag or delivery lag: The time between placing an

    order and its arrival in stock. If the lead time is known and is not equal to

    zero, and if demand is known, all that one needs to do is to order in

    advance by an amount of time equal to the lead time. If, however, it is a

    variable that is known only probabilistically, the question of when to

    order is more difficult one. If either the demand or the lead time is known

    only probabilistically, the amount and timing of replenishment if found by

    considering expected costs of holding and storage over the lead time

    period.

    CISM02 Decision Support for Management Unit 8

    Water Tank Analogy for Inventory

    12

    Supply Rate

    Inventory Level

    Demand Rate

    Inventory LevelBuffers Demand Ratefrom Supply Rate

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    7/23

    Two Forms of Demand

    13

    Dependent:

    items used to produce final products (table top, legs, hardware, paint, etc.)Demand determined once we know the type and number of final products

    Independent:items demanded by external customers (Kitchen Tables; Cars,appliances, computers, and houses are examples of independent demand

    inventory)

    Independent demand

    Uncertain / forecasted

    Continuous Review / Periodic Review

    Dependent demand

    Requirements/ planned

    Materials Requirements Planning / Just in Time

    CISM02 Decision Support for Management Unit 8

    Nature of Demand

    14

    Sometimes, the demand is known with certainty with its rate remaining the

    same or not in relation to time. If demand is certain it is called a

    deterministic demand.

    Depending upon whether the rate of demand remains the same or not

    with respect to time it is called staticor dynamicdemand.

    Instead of a deterministic demand, sometimes a demand is expressed in

    terms of probability distribution in which case it is termed a probabilistic

    demand. In this case also the demand may change in relation to time.

    If it does not change it is called stationary, and if it does as non-

    stationary.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    8/23

    Reasons to Hold Inventory (1)

    15

    Meet variations in customer demand:Meet unexpected demandSmooth seasonal or cyclical demand

    Pricing related:Temporary price discountsHedge against price increasesTake advantage of quantity discounts

    Process & supply surprisesInternalupsets in parts of or our own processesExternaldelays in incoming goods

    Transit

    CISM02 Decision Support for Management Unit 8

    Reasons to Hold Inventory (2)

    16

    Meet unexpected demand

    Smooth seasonal or cyclical demand

    Meet variations in customer demand

    Take advantage of price discounts

    Hedge against price increases

    Quantity discounts

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    9/23

    Reasons to Not Hold Inventory

    17

    Carrying cost

    Financially calculable

    Takes up valuable factory space

    Especially for in-process inventory

    Inventory covers up problems

    That are best exposed and solved

    CISM02 Decision Support for Management Unit 8

    Inventory Control Systems

    18

    Functions of Inventory Management

    Track inventory

    How much to order

    When to order

    Prioritization (e.g. ABC classification/prioritization)

    Inventory Management ApproachEOQ

    Continuous / Periodic

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    10/23 1

    Inventory Control Objectives

    19

    Inventory Control Objectives Twofold:

    1. Maximize customer service

    2. Minimize costs

    Cost Objective: Minimize sum of relevant costs

    Service Objective: desired customer service levels significantly impact

    inventory levels.

    CISM02 Decision Support for Management Unit 8

    Inventory Control Models

    20

    Service level may be defined in a number of ways, such as:

    Inventory Control Models

    Remindertwo important issues in inventory control:

    order quantity and order timing.

    Two general classes of models:

    1. continuous review (fixed order quantity)

    2. periodic review (fixed order period)

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    11/23

    Inventory Control Systems:

    Continuous & Periodic

    21

    In a continuous system, an order is placed for the same constant amountwhenever the inventory on hand decreases to a certain level, whereas in

    a periodic system, an order is placed for a variable amount after specific

    regular intervals.

    Fixed-order-quantity system ( or Continuous Review or Q-systems) -

    constant amount ordered when inventory declines to predetermined level

    Fixed-time-period system (or Periodic review or P-systems) - order

    placed for variable amount after fixed passage of time

    CISM02 Decision Support for Management Unit 8

    Inventory Control Systems:Continuous

    22

    In a continuous inventory system (also referred to as a perpetual system

    and a fixed-order-quantity system), a continual record of the inventory

    level for every item is maintained. Whenever the inventory on hand

    decreases to a predetermined level, referred to as the reorder point,a

    new order is placed to replenish the stock of inventory.

    The order that is placed is for a fixed amount that minimizes the total

    inventory costs. This amount, called the economic order quantity.

    A positive feature of a continuous system is that the inventory level is

    continuously monitored, so management always knows the inventory

    status. This is advantageous for critical items such as replacement parts

    or raw materials and supplies. However, maintaining a continual record of

    the amount of inventory on hand can also be costly.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    12/23 1

    Inventory Control Systems:

    Continuous

    23

    Continuous Review or Fixed Order Quantity Systems (Q-systems)

    Multi period models

    1. Fixed order quantity, variable time between orders (EOQ, EPQ,

    and Quantity Discount)

    2. On-hand inventory balance serves as order trigger (R)

    3. Perpetual inventory count

    4. 2-bin system

    Single period Model

    CISM02 Decision Support for Management Unit 8

    Inventory Control Systems: Periodic

    24

    In a periodic inventory system (also referred to as a fixed-time-period

    systemor a periodic review system), the inventory on hand is counted at

    specific time intervals; for example, every week or at the end of each

    month.

    After the inventory in stock is determined, an order is placed for an

    amount that will bring inventory back up to a desired level. In this system

    the inventory level is not monitored at all during the time interval between

    orders, so it has the advantage of little or no required record keeping.

    The disadvantage is less direct control. This typically results in larger

    inventory levels for a periodic inventory system than in a continuous

    system to guard against unexpected stockouts early in the fixed period.

    Such a system also requires that a new order quantity be determined

    each time a periodic order is made.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    13/23 1

    Inventory Control Systems: Periodic

    25

    Periodic Review or Fixed Order Period Systems (P-systems)

    1. Variable order quantity, fixed time between orders

    2. Time serves as order trigger

    3. Periodic count

    4. Process: When a predetermined amount of time has elapsed, a

    physical inventory count is taken. Based upon the number of units in

    stock at that time, OH, and a target inventory of TI units, an order is

    placed for Q = (TI-OH) units

    CISM02 Decision Support for Management Unit 8

    Single Item Static Model

    26

    The simplest type of inventory model occurs when demand is constant

    over time with instantaneous replenishment and no shortages.

    Typical situations to which this model may apply are

    Use of light bulbs in a building

    Use of clerical suppliers, such as paper, pads, and pencils, in an office

    Use of certain industrial suppliers such as blots and nuts.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    14/23 1

    Single Item Static Model:

    Economic Order Quantity (EOQ) Model (1)

    27

    This model known as the economic order quantitymodel is the oldest

    and best known inventory model which originated as early as 1915 with

    Wilson and so the formula derived under this model to decide the

    ordering quantity is called the Wilson formula (i.e. Wilsons economic

    lot size).

    It basically answers the question how much to order. Out of the four

    components of inventory cost, here we are considering only two of

    them, namely, theset-up costand theholding cost.

    The other two costsshortage cost and purchasing cost, we adjust in

    such a way that shortage is not allowed and the holding cost takes care

    of purchasing cost which is possible to some extent with theassumption that there is no price break possible even if we order

    quantity in big lots.

    CISM02 Decision Support for Management Unit 8

    Single Item Static Model:Economic Order Quantity (EOQ) Model (2)

    28

    Our aim is to reduce thetotal costper unit(TCU) time. This is expressed

    it terms of inventory as we are finding out the optimal inventory level

    which reduces TCU.

    With our assumptions TCU can be expressed as

    TCU= set-up cost per unit time+holding cost per unit time

    Let us denote

    B = rate of demand or consumption

    Y= quantity to be ordered

    H= holding cost per unit per item

    K = set-up cost per order

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    15/23 1

    Single Item Static Model:Economic Order Quantity (EOQ) Model

    29

    Figure: Variation of the Inventory Level

    Points in time at which orders are placed

    Inventory Level

    Time

    SS

    Average Inventory:Y/2

    Y

    t0=Y/B

    CISM02 Decision Support for Management Unit 8

    Single Item Static Model:Economic Order Quantity (EOQ) Model

    30

    The smaller the order quantity Y, the more frequent will be the placement of new orders. However, the

    average level of inventory held in stock will be reduced. On the other hand, larger order quantities

    indicate larger inventory level but less frequent placement of orders.

    Inventory Level

    TimeSS

    Low ordering frequency

    High ordering frequency

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    16/23 1

    Single Item Static Model:Economic Order Quantity (EOQ) Model (3)

    31

    Holding cost per unit time= Average inventory x Holding cost per unit per item ==Y x H / 2

    Y/2becoming average inventory.

    The cycle time is denoted byt0 and defined as

    Set-up cost per unit time= K x Number of orders per unit time =K x B/Y =

    = K/ (Y/B)

    Reminder:TCU= set-up cost per unit time+holding cost per unit time

    or TCU = K x B/Y + (Y/2) H

    0

    0

    2( )

    YK H t

    TCU Y

    t

    0

    Yt

    B

    CISM02 Decision Support for Management Unit 8

    Single Item Static Model:Economic Order Quantity (EOQ) Model (4)

    32

    Using the calculus method to find the optimal inventory we have to differentiate

    TCUwith respect toY (assuming Y is a continuous variable)and equate to zero:

    This will give us the value ofY as

    (2 ) /Y KB H

    2

    ( )0

    2

    dTCU Y KB H

    dY Y

    The above order quantity is usually referred as Wilsons economic lot size.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    17/23 1

    Single Item Static Model:an Example

    33

    The daily demand for a commodity is approximately100 units. Every time anorder is placed, a fixed cost of100is incurred. The daily holding cost per unit

    inventory is0.02. If the lead time is12days, determine the economic lot size

    and reorder point.

    From the above formulas, the economic lot size is:

    * 2 2 100 1001000 ( )

    0.02

    KBY units

    H

    Since the lead time is12 daysand the cycle length is10 days, reordering

    occurs when the level of inventory is sufficient to satisfy the demand for two

    (12-10)days. Thus, the quantityY*=1000is ordered when the level of inventory

    reaches2 x 100 = 200 units. And the optimum costTCUis defined as

    100 1000( ) 0.02 20 ( per day)

    10002 2

    100

    K YTCU Y H

    Y

    B

    CISM02 Decision Support for Management Unit 8

    Single Item Static Model:Remarks

    34

    The assumptions of the above model are usually rarely satisfied for real

    situations, mainly because demand is probabilistic.

    Nevertheless, a crudeprocedure has evolved among practitioners

    which, while retaining the simplicity of applying the economic lot size

    model, does not completely ignore the effect of probabilistic demand.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    18/23 1

    Quantity Discount Model

    35

    Form of an economic order quantity (EOQ) model that takes into accountquantity discounts. Quantity discountsare price reductions designed to induce

    large orders.

    If quantity discounts are offered, the buyer must weigh the potential benefits of

    reduced purchase price and fewer orders against the increase in carrying costs

    caused by higher average inventories. Hence, the buyer's goal in this case is to

    select the order quantity that will minimize total costs, where total cost is the sum

    of carrying cost, ordering cost, andpurchase cost:

    Total Cost = Carrying Cost + Ordering Cost + Purchase Cost =

    C x Q/2 + O x (D/Q) + P x D

    where C= carrying cost per unit, O= ordering cost per order, D= annual

    demand, P= unit price, and Q= order quantity.

    CISM02 Decision Support for Management Unit 8

    Inventory Models

    36

    More models:

    Single Item Static Model withSimultaneous Production and Sales

    Single Item Static Model with Simultaneous Production and Sales

    whereShortage is allowed

    Single Item Static Modelwith Time LagSingle Item Static Model withPrice Breaks

    Multiple-Item Static Model with Storage LimitationSingle-Item N-Period Dynamic Model

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    19/23 1

    Prioritization (e.g. ABC classification/prioritization)

    37

    ABC Inventory Classification

    Inventory control based on a form of Pareto analysis. The inventory

    items are divided into three categories (A, B, and C), according to a

    criterion such as revenue generation, turnover, or value.

    Typically, Aitems represent 20 percent in terms of quantity and 75 to

    80 percent in terms of the value.

    CISM02 Decision Support for Management Unit 8

    ABC Analysis

    38

    ABC Analysis:Analysis of a range of items, from inventory levels to

    customers and sales territories, into three groups:

    A= very important

    B= important

    C= marginal significance.

    The goal is to categorize items which would be prioritized, managed, orcontrolled in different ways.

    ABC analysis is also called usage-value analysis.

    Details of ABC classifications will be discussed in Unit 11.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    20/23 2

    ABC classification:

    Applications in Inventory Control

    39

    ABC classification could be used to determine the importance rating fordifferent items and help the Stores in better inventory control. We could

    have the following objectives for classifications:

    Purchasing and Finance may want to classify the items in three

    classes, i.e.A, Band Cbased upon last years consumption value.

    Stores may want to classify the items in class High, Medium, and

    Lowbased upon on-hand quantities for the purpose of doing a better

    store space planning.

    Inventory Controller may want to classify the items inHigh

    movement, Medium movements and Low movements for

    analysing the Min-Max Levels of different items.

    CISM02 Decision Support for Management Unit 8

    Inventory Control: an Example (1)

    40

    A product is manufactured to meet the demand over the nextn periods.

    At periodi, the demandri (units) may be filled from the productionxi

    (units) in this period and/or the inventory carried forward from previous

    periods. This means it is possible to produce more thanriunits in period

    i, with the surplus being used to fill (some of) the demand for one or

    more succeeding periods.

    No shortages are allowed in any period so that the demand for all

    periods must be filled. If the level of production in periodi is increased

    over that in period (i-1), that is,xi> xi-1, a costaipounds per excess unitis incurred.

    On the other hand, ifxi< xi-1, a costbipounds per decreased unit is

    added for decreasing the level of production.

    An inventory holding costci pounds is incurred for every unit held over to

    the next period.

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    21/23 2

    Inventory Control: an Example (2)

    41

    The objective of the modelis to determine the optimal production

    schedule such that the total cost of the production-inventory system isminimised.

    The balance equation at periodi is:

    Ii+1= xi+ Iiri, I = 1,2,,n

    whereI1is the initial inventory at the beginning of period1and In+1is

    the final inventory at the end of periodn; the demandri (units); the

    productionxi (units).

    Generally,I1>=0, whileIn+1must be zero in any optimal solution. In

    order to guarantee that the demand is satisfied in every period (no

    shortage), Ii>=0, I = 1,2,, n-1.

    Naturally, production quantities must be nonnegative so that

    xi>= 0, i=1,2,,n

    CISM02 Decision Support for Management Unit 8

    Inventory Control: an Example (3)

    1 1

    1 1

    1

    ( ), if

    ( ), if

    0, if =

    i i i i i

    i i i i i i

    i i

    a x x x x

    y b x x x x

    x x

    42

    The above restrictions define all the constraints of the problem. The

    objective function includes three components:cost of holding inventory,

    cost of increasing production, andcost of decreasing production.

    The holding cost is the simplest, and it is given directly for period i by

    ci Ii+1(notice the inventory holding cost is charged on units left at the

    end of the period). The cost of increasing and decreasing production in

    periodi is given by

    CISM02 Decision Support for Management Unit 8

  • 7/25/2019 Inventory control in Operation Research

    22/23 2

    Inventory Control: an Example (4)

    1 1max{ ( ), ( )}i i i i i i iy a x x b x x

    43

    Equivalently,yimay be written as

    This follows since if production is increased,xi-1xi< 0so that

    bi(xi-1xi)0. Thusbi (xi-1xi)

  • 7/25/2019 Inventory control in Operation Research

    23/23

    Inventory Control: an Example (6)

    1

    1

    1

    0

    0

    , , 0, 1,2,...,i

    i i i i i

    i i i i i

    i i i i

    i i

    a x a x y

    b x b x y

    x I I r

    I x y i n

    0 1

    1

    minimise ( )n

    i i i

    i

    x c I y

    45

    The linear programming model of the production-inventory problem maybe summarised as

    subject to

    whereIn+1=0. The variableyiis nonnegative because it represents thecost of increasing or reducing production.

    CISM02 Decision Support for Management Unit 8