ANALYSING AND IMPROVING OPERATIONS AT AN OPTICAL COMPANY

1
 Table of Contents
Abstract.................................................................................................................................................3
Introduction...........................................................................................................................................3
FORECASTING, INVENTORY CONTROL AND TRANPORTATION..............................................................3
Forecasting and Its Role.....................................................................................................................3
Inventory Control..............................................................................................................................4
Transportation...................................................................................................................................6
LINEAR PROGRAMMING AND ITS ROLE IN TRANSPORTATION PROBLEM.............................................6
Linear Programming & Its Role..........................................................................................................6
SIMULATION- ADVANTAGES AND DISADVANTAGES.............................................................................7
Simulation..........................................................................................................................................7
Advantages....................................................................................................................................7
Disadvantages................................................................................................................................8
Monte Carlo Simulation.....................................................................................................................9
Forecasting by Monte Carlo Simulation.........................................................................................9
Inventory Control by Monte Carlo Simulation.............................................................................10
Conclusion...........................................................................................................................................10
References...........................................................................................................................................11

2
 Abstract
This paper is about assessing and enhancing a company's operations. Forecasting is a tool for

determining possible consequences. Inventory control and transportation management system

can help improve the company's performance. In addition, this study discusses alternative

forecasting and inventory control approaches that can be used. It is also mentioned how linear

programming is implemented to solve transport difficulties. Furthermore, the paper discusses

how simulations are used to examine product models. Monte Carlo Simulation, a forecasting

and stock control simulator, is also covered.

Introduction
The report entails a thorough discussion of the functions of forecasting, inventory control and

transportation in an organization. Alongside this, it also discusses the advantages and

disadvantages of simulation and how monte carlo simulation may be performed for

forecasting and inventory control, the report also discusses linear programming and how it

can be solved in solving transportation problems.

FORECASTING, INVENTORY CONTROL AND

TRANPORTATION
Forecasting and Its Role
The top management must establish some assumptions of what is probable to occur in the

future while formulating specific aspirations. Forecasting gives them this information. (Yuan

et al., 2018) So, forecasting can be described as the practice of estimating the upcoming via

statistics and predictions that take into account past data, latest developments, and expected

changes in the immediate future.

Because management concerns the forthcoming, no useful plan can be created unless the

manager is sufficient to deal for all potential future occurrences. Which is why forecasting is

3
such an important part of the planning procedure. In reality, forecasting underpins all

decisions made within the company.

Various companies make use of various of forecasting techniques. The following is a list of

some of them -

 Historical Analogy Technique: In this procedure, a prognosis for a specific

circumstance is based on similar events that occurred in the past.

 Survey Method: Surveying can be used to obtain information mostly on objectives of

those who are involved.  The survey technique can also be used to make forecasts

both for current and new products.

 Opinion Poll: An opinion poll is done to evaluate the viewpoints of experienced

professionals and practitioners in a specific field whose opinions are held in high

regard. If opinion polls suggest vastly conflicting viewpoints, professionals may be

summoned in for a discussion and reflection of their ideas.

 Input-Output Analysis: If the connection between outputs and inputs is defined, this

approach forecasts output based on supplied input. Likewise, with a given input-

output connection, input requirements can be forecasted based on ultimate output.

 Barometers for Business: A barometer is a device that measures air pressure.

Similarly, index numbers are used to compare the status of an economy over different

time periods. Patterns, seasonal variations, rhythmic shifts, and random variability are

all studied using these index values. Yet, it is important to remember that business

barometers have their own restrictions and are not a guarantee of success.

Inventory Control
Inventory control, frequently known as stock control is the practice of ensuring that the

company has the correct number of supplies on store. The approach guarantees that

organisation can satisfy customer requirements and offers economic flexibility by providing

4
quality management as well as operational standards. (Wang et al., 2019) Additional

situations where stock control policies and approaches could help firms save money or make

more sales involve - expired goods, excess storage expenses, reduced sales, losing potential

customer, excess storage, losing inventory tracking.

In several material requirement planning systems, the Order Up To (OUT) policy is a typical

ordering approach for assessing the service to customers, stock, and throughput trade-offs.

This approach is frequently implemented by businesses in order to synchronize orders for

many commodities from the same provider, where installation expenses can be overlooked

(Ignaciuk, P., & Wieczorek, Ł., 2017). The OUT strategy is simple to comprehend on a

theoretical level. The company check their stock levels on a regular basis and make an

"order" to move it "-up-to" a certain level.

The following are some of the best stock control methods:

 Pick a good Management Improvement Methodology: Inventory control is only one

benefit of quality management techniques. With a management approach that people

stick to, they can enhance their business from floor to ceiling. Kaizen, Lean, and Six

Sigma are just a few choices.

 Optimize Purchasing Procedures: Using statistics and forecasts to regulate the

purchasing procedures is among the trademarks of good inventory management.

Screening things by assessing consumers' needs, eliminating excessive inventory,

changing stock levels and reordering levels are all part of this process.

 Manage Supplier Relationships: It's vital to manage relationships with suppliers well

since interacting directly with suppliers can sometimes prevent and resolve issues.

 Perform a Risk Evaluation: If there is an unanticipated sales increase, a financial

deficit, insufficient storage space, a stock mismanagement, slow-moving

5
 commodities, or expired merchandise, complications will inevitably arise in the

company. Making a risk assessment matrix can help figure out what the biggest

threats are and how to deal with them if they arise.

Transportation
Transportation management includes transferring products from one destination to another

using any means of transportation available. Transportation management ensures that a

corporation's complete distribution network functions efficiently. Stock can be maintained

compact and transported in and out of a facility swiftly and effectively with proper

transportation management. This increases inventory levels, shortens overall lead times, and

lowers storage costs (Shi et al., 2019). High delivery efficiency and persistent consumer

satisfaction can be ensured with efficient transport operations. As a result, it's difficult to

overstate the significance of transportation systems.

LINEAR PROGRAMMING AND ITS ROLE IN

TRANSPORTATION PROBLEM
Linear Programming & Its Role
Linear programming is a broad term encompassing number of mathematical strategies

designed to optimize results in terms of resource utilization.

Distribution or transport costs issues can be handled more readily using a linear programming

approach if both the target function and the binding conditions or limitations can be

expressed as linear equations (Jia, 2020). In basic illustrations, the ideal solution will be on

the practicable area's margin, or, more precisely, at the edge of the polyhedral feasible region.

Complicated linear programming issues, on the other hand, cannot be represented on a two-

dimensional graphic, alternative methodologies, such as the "simplex method," are capable of

solving such issues. The linear programming strategy is used by manufacturing and sales

management as the optimum alternative for transporting finished items or products to their

storehouse. Production and distribution managers also use linear programming to assist them

6
with daily chores like production mix, staffing and planning, work assignments and

allocations, market analysis, product mix, financial portfolios, and so forth.

The Transportation Method of linear programming is used to solve issues involving the

analysis of effective transportation networks, that is, how quickly products from various

sources of production are carried to multiple locations with the lowest overall transport costs

(Roy et al., 2018). The following actions should be taken in order to solve the transportation

problem:

 Finding the first practicable strategy, which entails selecting a solution that meets the

production and consumption criteria.

 The initial reasonable alternative is put into practice to see if it is effective. After

obtaining a workable alternative, the next task is to decide if it is perfect. The

effectiveness is tested using two different methods: the Stepping-stone Method and

the Modified Distribution Method (MODI)

 The final stage is to improve the approach till the best one is found.

SIMULATION- ADVANTAGES AND DISADVANTAGES

Simulation
An interactive modelling that duplicates the functioning of a current or potential system is

referred to as a simulation. By employing a simulated environment to examine the effect of

new processes and 'but if' situations, one can identify a method that produces the greatest

outcomes (Gunal, 2019). Simulation helps to compare several designs under identical

conditions. Users get to choose the technique that will deliver the best performances for key

considerations in the procedure by experimenting with alternative concepts.

Advantages
Simulation models have the ability to give designers with realistic information when creating

real-world systems, which is one of their major advantages. This enables the developers to

7
assess the validity and effectiveness of a design prior to its implementation. As a result, the

user can investigate the pros and cons of different models without having to create the

systems practically. The total costs of developing the system are greatly reduced by assessing

the effects of individual design choices during the design process instead of the construction

stage (Cs.mun.ca, 2021). Furthermore, by using a simulation, the users can compare the

potential quality of each model without having to build the circuitry. The circuit simulation

can provide feedback to the developer on the effectiveness and precision of other

configurations by simulating the performance of the systems. The optimum circuit can then

be built after closely examining the implications of each model.

Another advantage of simulations is that they allow project managers to investigate an issue

through several dimensions. By addressing a system at a greater level of error, the developer

is more capable of understanding the actions and interactions of all of the system's high-level

constituents, and is thus better prepared to deal with the entire system's complication. If the

issue had been handled from a reduced level, these complexities could easily overwhelm the

developer. The lower-level parts can then be modelled and implemented for validation and

performance assessment as the developer gains a better understanding of the behaviour of the

higher tier parts through the use of the simulation.

Disadvantages
Despite the potential benefits of simulation as described previously, simulations, like any

technologies, have disadvantages. Most of these issues can be traced back to the

computationally complex processing that some simulators demand. As a corollary, the

simulation's results may not be instantly accessible after it has begun.  The latencies could be

caused by a high number of systems being simulated or by the intricate interactions that take

place among the components in the simulation environment. As a result, these simulations are

constrained by hardware platforms that cannot match the simulator's computing requirements.

8
This difficulty is now becoming less of an issue as more modern approaches and better

simulation approaches become accessible.

Introducing simplified assertions or strategies into the simulation system is one technique to

counteract the aforementioned complexities (Cs.mun.ca, 2021). While this strategy might

drastically cut simulation time, this can also offer users a false perception of assurance about

the simulation findings' quality. Even when a simulation revealed no defects in a layout, the

circuit can still be flawed. Another solution to cope with computational complexity is to use a

multilayer modelling and prototyping technique, which allows the developer to work at a

higher stage of design. But this method may present its own set of issues. When working at a

higher level of abstraction, the developer may mischaracterize or even remove some of the

system's lower-level elements. Given the lack of adequate precise information in the model, if

the level of complexity is too excessive, it may be difficult to actually create the equipment.

Monte Carlo Simulation

Monte Carlo simulation is a computer-assisted numerical approach for incorporating risk into

statistical analysis and decision-making. For each given course of action, Monte Carlo

simulation provides the decision-maker with a spectrum of potential outcomes as well as the

possibilities that they will happen. It depicts the extreme outcomes, the implications of going

for broke and the most progressive decision as well as all potential consequences for

intermediate selections (Arend & Schäfer, 2019).

Forecasting by Monte Carlo Simulation

A Monte Carlo-based forecasting, unlike a standard forecast, will not create a single value but

rather a set of future possibilities depending on a probability distribution. Also, because input

is data range rather than pieces of data, a Monte Carlo simulation generates output range. The

simulator aggregates range values rather than point values to produce an output spectrum,

taking into consideration of essential aspects.

9
Forecasts are almost generally little inaccurate, and this is most often due to inaccuracies or

uncertainty in the data input. As a result, it is preferable to compensate for them directly. In

reality, Monte Carlo-based forecasts is a better way to deal with unpredictability since it

provides a framework for thinking about what volatility looks like (Fünfgeld et al., 2017). It

accomplishes this by enabling us to adjust the form of the range's allocation.

Inventory Control by Monte Carlo Simulation

Monte Carlo Simulation, which generates a huge set of random numbers to acquire

simulation solutions, is frequently used for inventory control. The idea of simulation is to

continue random sampling several times until the variation is as small as possible. In average,

a company's ability to estimate future supply requests is limited since the quantity of requests

in the prospective cannot be forecasted with accuracy (Wulandari et al., 2021). Hence, one of

the most widely applied forecasting methods is Monte Carlo (MC) simulation. We can assess

or anticipate how much output we need to make using this MC simulation.

Conclusion
Forecasting, stock control, and transportation are all important aspects of evaluating and

enhancing a company's operations. For predicting the company's future, there are numerous

forecasting approaches. Inventory control and transportation which is efficient improves the

business growth while also attracting new customers. Linear programming can be used to

tackle transportation issues. Additionally, simulation may assist a corporation in developing

better products, as well as improving forecasting and inventory management through the use

of Monte Carlo Simulation.

10
 References
Arend, M. G., & Schäfer, T. (2019). Statistical power in two-level models: A tutorial based

on Monte Carlo simulation. Psychological methods, 24(1), 1.

Cs.mun.ca. (2021). Advantages of Simulation. Retrieved 6 August 2021, from

http://www.cs.mun.ca/~donald/msc/node6.html

Cs.mun.ca. (2021). Disadvantages of Simulation. Retrieved 6 August 2021, from

http://www.cs.mun.ca/~donald/msc/node7.html

Fünfgeld, S., Holzäpfel, M., Frey, M., & Gauterin, F. (2017). Stochastic forecasting of

vehicle dynamics using sequential monte carlo simulation. IEEE Transactions on

Intelligent Vehicles, 2(2), 111-122.

Gunal, M. M. (2019). Simulation for Industry 4.0. Past, Present, and Future. Springer.

Ignaciuk, P., & Wieczorek, Ł. (2017, September). Optimization of mesh-type logistic

networks for achieving max service rate under order-up-to inventory policy.

In International Conference on Information Systems Architecture and

Technology (pp. 118-127). Springer, Cham.

Jia, Y. B. (2020). Linear programming.

Roy, S. K., Ebrahimnejad, A., Verdegay, J. L., & Das, S. (2018). New approach for solving

intuitionistic fuzzy multi-objective transportation problem. Sādhanā, 43(1), 1-12.

Shi, Y., Arthanari, T., Liu, X., & Yang, B. (2019). Sustainable transportation management:

Integrated modeling and support. Journal of Cleaner Production, 212, 1381-1395.

Wang, Q., Wu, J., Zhao, N., & Zhu, Q. (2019). Inventory control and supply chain

management: A green growth perspective. Resources, Conservation and

Recycling, 145, 78-85.
11
Wulandari, L. M. C., & Putri, L. D. I. (2021). Inventory Control Analysis of Plastic Raw

Materials Using Monte Carlo Simulation Approach. OPSI, 14(1), 104-114.

Yuan, X., Chen, C., Lei, X., Yuan, Y., & Adnan, R. M. (2018). Monthly runoff forecasting

based on LSTM–ALO model. Stochastic environmental research and risk

assessment, 32(8), 2199-2212.

12