What is inventory :Inventory is the stock of any item or resource used in an organization.

An inventory system is the set of policies and controls that monitor levels of inventory and determine what levels should be maintained, when stock should be replenished, and how large orders should be. By convention, manufacturing inventory generally refers to items that contribute to or become part of a firms product output. Manufacturing inventory is typically classified into raw materials, finished products, component parts, supplies , and work-in-process. In distribution, inventory is classified as in-transit , meaning that it is being moved in the system, and warehouse, which is inventory in a warehouse or distribution center. Retail sites carry inventory for immediate sale to customers. In services, inventory generally refers to the tangible goods to be sold and the supplies necessary to administer the service.

Purposes of inventory :All firms (including JIT operations) keep a supply of inventory for the following reasons: 1. To maintain independence of operations. A supply of materials at a work center allows that center fl exibility in operations. For example, because there are costs for making each new production setup, this inventory allows management to reduce the number of setups. Independence of workstations is desirable on assembly lines as well. The time that it takes to do identical operations will naturally vary from one unit to the next. Therefore, it is desirable to have a cushion of several parts within the workstation so that shorter performance times can compensate for longer performance times. This way the average output can be fairly stable.

2. To meet variation in product demand. If the demand for the product is known precisely, it may be possible (though not necessarily economical) to produce the product to exactly meet the demand. Usually, however, demand is not completely known, and a safety or buffer stock must be maintained to absorb variation. 3. To allow flexibility in production scheduling. A stock of inventory relieves the pressure on the production system to get the goods out. This causes longer lead times, which permit production planning for smoother fl ow and lower-cost operation through larger lot-size production. High setup costs, for example, favor producing a larger number of units once the setup has been made. 4. To provide a safeguard for variation in raw material delivery time. When material is ordered from a vendor, delays can occur for a variety of reasons: a normal variation in shipping time, a shortage of material at the vendors plant causing backlogs, an unexpected strike at the vendors plant or at one of the shipping companies, a lost order, or a shipment of incorrect or defective material 5. To take advantage of economic purchase order size. There are costs to place an order: labor, phone calls, typing, postage, and so on. Therefore, the larger each order is, the fewer the orders that need be written. Also, shipping costs favor larger ordersthe larger the shipment, the lower the per-unit cost 6. Many other domain-specific reasons. Depending on the situation, inventory may need to be carried. For example, in-transit inventory is material being moved from the suppliers to customers and depends on the order quantity and the transit lead time. Another example is inventory that is bought in anticipation of price changes such as fuel for jet planes or semiconductors for computers. There are many other examples

Inventory costs:In making any decision that affects inventory size, the following costs must be considered: 1. Holding (or carrying) costs. This broad category includes the costs for storage facilities, handling, insurance, pilferage, breakage, obsolescence, depreciation, taxes, and the opportunity cost of capital. Obviously, high holding costs tend to favor low inventory levels and frequent replenishment. 2. Setup costs. To make each different product involves obtaining the necessary materials, arranging specific equipment setups, filling out the required papers, appropriately charging time and materials, and moving out the previous stock of material. If there were no costs or loss of time in changing from one product to another, many small lots would be produced. This would reduce inventory levels, with a resulting savings in cost. One challenge today is to try to reduce these setup costs to permit smaller lot sizes. (This is the goal of a JIT system.) 3. Ordering costs. These costs refer to the managerial and clerical costs to prepare the purchase or production order. Ordering costs include all the details, such as counting items and calculating order quantities. The costs associated with maintaining the system needed to track orders are also included in ordering costs. 4. Unit production cost of a single speaker (excluding the setup cost) is $10, independent of the batch size produced. (In general, however, the unit production cost need not be constant and may decrease with batch size.)

The Basic EOQ Model To summarize, in addition to the costs specified above, the basic EOQ model makes the following assumptions. Assumptions (Basic EOQ Model). 1. The ordering cost is constant. 2. The rate of demand is known, and spread evenly throughout the year. 3. The lead time is fixed. 4. The purchase price of the item is constant i.e. no discount is available 5. The replenishment is made instantaneously, the whole batch is delivered at once. 6. Only one product is involved. Variables :

C = purchase price, unit production cost Q = order quantity Q* = optimal order quantity D = annual demand quantity K = fixed cost per order, setup cost (not per unit, typically cost of ordering and shipping and handling. This is not the cost of goods) h = annual holding cost per unit, also known as carrying cost or storage cost (capital cost, warehouse space, refrigeration, insurance, etc. usually not (but sometimes) related to the unit production cost)

Total cost function :The single-item EOQ formula finds the minimum point of the following cost function: Total Cost = purchase cost or production cost + ordering cost + holding cost - Purchase cost: This is the variable cost of goods: purchase unit price annual demand quantity. This is cD - Ordering cost: This is the cost of placing orders: each order has a fixed cost K, and we need to order D/Q times per year. This is K D/Q

- Holding cost: the average quantity in stock (between fully replenished and empty) is Q/2, so this cost is h Q/2 . To determine the minimum point of the total cost curve, partially differentiate the total cost with respect to Q (assume all other variables are constant) and set to 0:

Solving for Q gives Q* (the optimal order quantity):

Therefore: Therefore:

. .

Q* is independent of c; it is a function of only K, D, h. The optimal value Q* may also be found by recognising that[3]

where the non-negative quadratic term disappears for provides the cost minimum which

Class of heuristics
There are many kinds of heuristics developed for the ELSP, mainly dating from late 1960s to early 1980s (Simpson, 2001). The class of heuristics we will be focusing on in this report is the same class of on-line heuristics as de_ned in Van den Heuvel and Wagelmans (2009a). definition :The on-line lot-sizing heuristics make setup decisions period by period (so previously made decisions are xed and cannot be changed) and setup decisions do not depend on future demand. Silver meal heuristic :The SilverMeal heuristic is a forward method that requires determining the average cost per period as a function of the number of periods the current order is to span and stopping the computation when this function first increases. Define : K: the setup cost per lot produced. h: holding cost per unit per period. C(T) : the average holding and setup cost per period if the current order spans the next T periods. Let (r1, r2, r3, .,rn) be the requirements over the n-period horizon. To satisfy the demand for period 1

C(1) = K

The average cost = only the setup cost and there is no inventory holding cost. To satisfy the demand for period 1, 2 Producing lot 1 and 2 in one setup give us an average cost:

C(2) = (K + (h*r2))/2

The average cost = (the setup cost + the inventory holding cost of the lot required in period 2.) divided by 2 periods. To satisfy the demand for period 1, 2, 3 Producing lot 1, 2 and 3 in one setup give us an average cost:

C(3) = (K + (h*r2)+(2hr3))/3

The average cost =( the setup cost + the inventory holding cost of the lot required in period 2+ the inventory holding cost of the lot required in period 3) divided by 3 periods. In general,

C(j) = (K + hr2 + 2hr3 + ... + (j 1)hrj) / j

The search for the optimal T continues until C(T) > C(T 1). Once C(j) > C(j 1), stop and produce r1 + r2 + r3 + ... + rj 1 And, begin the process again starting from period j. 2. Least cost method :As it is discussed before, least unit cost heuristic chooses a lot size that equals the demand of some K periods in future, where K>0. The average holding and ordering cost per unit is computed for each K=1, 2, 3, etc. starting from K=1 and increasing K by 1 until the average cost per unit starts increasing. The best K is the last one up to which the average cost per unit decreases. Observe how similar is Silver-Meal heuristic and least unit cost heuristic. The only difference is that Silver-Meal heuristic chooses K on the basis of average cost per period and least unit cost on average cost per unit.