Intelligent Modeling for Decision Making

Intelligent Modeling For Decision Making-ppt Download

  • Date:19 Jul 2020
  • Views:30
  • Downloads:0
  • Size:6.78 MB

Share Presentation : Intelligent Modeling For Decision Making

Download and Preview : Intelligent Modeling For Decision Making

Report CopyRight/DMCA Form For : Intelligent Modeling For Decision Making


Transcription:

Intelligent Modelingfor Decision MakingKatta G MurtyIndustrial and Operations EngineeringUniversity of Michigan.
Ann Arbor Michigan 48109 2117 USAmurty umich edu Operations Research OR Deals WithMaking Optimal DecisionsMain strategy Construct math model for decision.
List all relevant decision variables bounds andconstraints on them from the way the systemoperates objective function s to optimize Solve model using efficient algorithm to findoptimal solutions.
Make necessary changes and implement Math Modeling OR theory developed efficient algorithms to solve several singleobjective decision models But practitioners find no model in OR theory fits their problem well.
Real world problems usually multi objective and lack nice structure ofmodels discussed in theory there is a big gap between theory andThe gap between practice and theory and its bridge 3 Math Modeling continued To get good results essential to model.
intelligently using heuristic modifications approximations relaxations hierarchicaldecomposition Will illustrate this using work done atHong Kong Container Port and a bus.
rental company in Seoul Achieving Elastic CapacityThrough Data intensiveDecision Support System DSS Professor Katta G Murty.
Industrial and Operations EngineeringUniversity of Michigan Ann ArborHong Kong University of Science TechnologyWork done at Hong Kong Container Port Hong Kong.
International Terminals The largest privately ownedterminal in the world s busiestcontainer port Operating under extremely.
limited space and the highestyard density yet achieving one ofhighest productivity amongst Key FacilitiesQuay Crane 41.
Yard Crane 116Internal Trucks 400Yard Stacking Capacity 80 000 boxes 111football stadiums .
The ContainerStorage YardStorage yard SY Containersin stacks 4 6.
high RTGCs Rubber TiredGantry Cranes containers SYdivided into.
rectangular Storage Blockits legs 6 QCs on DockQCs unload.
containers place themon ITs ITspicks them containers.
from SY toQCs to loadinto vessel The flow of outboundcontainers.
SY Storage YardUnderneath each location or operation we list theequipment that handles the containers thereArrival at terminal Retrieval andand storage loading into vessel.
Terminal StorageCustomer Yard Quayside VesselExternal Gate External Internal QuayTractor Tractor Yard Tractor Crane Documentation Crane.
Inspection Storage spaceassignment Arrival Storage and Retrieval ofImport Containers.
Retrieval pickup Unloading by customer storageTerminal StorageCustomer Quayside VesselExternal Gate External Yard Internal Quay.
Tractor Tractor Yard Tractor CraneFlow of inbound containers Top View of a Block B1 BeingServed by an RTGCStorage lanes.
Truck The RTGCTruck lane Land Scarcity for TerminalDevelopment in Hong Kong The Highest Land Utilization.
Terminal in the WorldCTB HIT Pier THamburg Hong Kong Long BeachLand Area Number of Berth.
39 5 acre 25 1 acre 72 0 acreThroughput2 3m TEU 6 4m TEU 1 2m TEUHK handles more throughput with less land 14 Key Service.
Quality MetricsTurnaroundTurnaround Objectives of the Study Minimize congestion on terminal road.
Reduce internal truck cycle time Increase yard crane productivity Minimize reshuffling Improve quay crane rate Enhance vessel operating rate.
Decision Problem SolvedD1 Route trucks and allocate storage spaces to arrivingcontainers to minimize congestion and reshufflingGate Container Yard Berth Decision Problem Solved.
D2 Optimize trucks allocation quay crane tominimize quay crane truck waiting time numberof trucks used and number of trucks in yard Decision Problem SolvedD3 Develop procedure to estimate truck requirement.
profile and optimum truck driver hiring schemeNo of Trucks Required Decision Problem SolvedD4 Optimize yard crane deployment to blocks to minimizecrane time spent on the terminal road network.
Decision Problem Solved Under StudyD5 Allocate appointment times to external trucksto minimize turnaround time and theirnumber in yard during peak time and level Expected Number of Containers in Planning Period at.
Each Node to Go to Various Destination NodesD1 Data for flow model to route trucksBlock 1 Block 2Export ExportHIT HIT Berth 1.
Import ImportBlock 3 Block 4Block 5 Block 6 Berth 2Container Yard BerthData on Blocks Data on Berths.
Data 400 ExportB1 40 Export Containers to Berth 1 Berth 1 180 ImportContainers10 Export Containers to Berth 4 Containers to go forto go for Storage.
20 Import Containers to Gate Storage Decision Variables in Multi Commodity FlowModel for Routing Trucks fij total no container turns flowingon arc i j in planning period.
max fij over all arcs i j min fij over all arcs i j Variation in Workload Over TimeNo Effective Movesover a Typical Day.
Number of MovesTime hr quarter Three Separate Policies Equalize fill ratios in blocks Truck dispatching policy.
Storage space assignment in a block Numerical Example forFill Ratio Equalization 9 blocks each with 600 spaces ai No Containers in Block i at period end if no new containers sent.
xi Decision Variables no new containers sent to Block i during the LP Model to Determine Container QuotaNumbers for Blocks Min i ai xi 400 Linear Programming formulation is .
Min i ui ui Subject toai xi ui ui 400 all i x i 1040xi ui ui 0 all i.
Numerical ExampleAverage stored containers block 2570 1040 9 400i ai xi Remaining7 100 300 7403 120 280 460.
2 150 250 2106 300 100 1108 325 75 355 350 50 04 375 25 0.
Total 2570 1040 31 Innovations in Work on D1 First paper to study congestion inside container terminals Controlling congestion by equalization fill ratios and truckdispatching.
LP model for fill ratio equalization its combinatorial solution First paper to relate container stacking to bin packing Hardware Developed for real time monitoring andcommunication OR Techniques LP IP Combinatorial Optimization.
Decision Frequency Container quota numbers for 95 blockseach four hours take few seconds D2 Result from a Simulation Runn number Trucks Quay Craneh number Containers to process in hatch 30.
Innovations in Work on D2 Recognize importance of reducing number of trucks toreduce congestion Internal trucks pooling system adopted worldwide OR Techniques Estimation Queuing theory simulation.
Decision Frequency One time decision D3 Truck Requirement Profile h number of containers unloaded loaded in a hatch h average time minutes 8 28 1 79 h h standard deviation 1 31 0 019 h.
Time allotted h h Benefits from Work on D3 Estimate hourly truck requirements for planning OR Techniques Estimation simulation linearregression.
Decision frequency Daily takes few minutes D4 Crane Movement Between BlocksCrane minutes to moveFrom Block To blockB6 B7 B8 B9.
B1 20 25 35 30B2 25 10 20 15B3 30 25 10 20B4 35 15 25 10B5 30 20 10 25.
Solved as transportation model about once per two hours typically size 15x 15 takes few seconds D5 Appointment Times for External Trucksto Pickup During Peak Hours Optimal quota number for external trucks to pick up in.
each 30 minute interval determined by simulation Appointment time booking system is automatedtelephone based system Benefits from Work on D5 Quota for half hour determined by simulation.
Innovation First terminal to introduce booking to reducenumber of external trucks in peak hours their turnaround time Hardware Developed Automated telephone based booking OR Techniques Used Estimating probability distributions queuing theory and simulation.
Decision Frequency One time decision Summary of Techniques UsedProblem Techniques Size Frequency Comp TimeLP combinatorialRoute trucks optimization Quota for.
D1 Every 4 hours Few secondsallocate storage integer 95 blocksprogrammingD1 Truck dispatch Heuristic rule Each truck Real time Real timeTruck Crane.
D2 estimation and One time allocationsimulationProcedure to Estimation D3 estimate truck simulation and One time .
requirements linear regressionEstimate truck 15 vesselD3 Planning Once a day Few minutesrequirement profile schedulesEstimation and Once about 2.
D4 Crane movement 15 x 15 Few secondsnetwork flows hoursEstimation D5 Booking system queuing and One time 40simulation.
Improvement in Key Quality Service MetricsInternal Truck Turnaround TimeExternal Truck Turnaround Time 30 Quay Crane Rate 45 Vessel Turnaround Time 30 .
Vessel Operating Rate 47 More BenefitsCustomers Staff Social Catch Up Port in Reduce workload Avoid the.
Shipping lines with increased construction ofsavings amount to productivity new berths whichUS 65 million per Boost to staff results in lessyear morale pollution and Enhance overall.
adverse effects tosatisfaction and the society Business Benefits to HPH and CustomersFinancial Benefits SummarySavings Key Improvement Areas.
US 54 million Improvement of internal tractor utilization Handling cost reductionUS 100 million Avoidance of building new facilitiesUS 65 million Vessel turnaround time improvementTotal Annual.
Annual SavingSaving US 219US 219 million References1 Katta G Murty Yat Wah Wan Jiyin Liu Mitchell M .
Tseng Edmond Leung Kam Keung Lai Herman W C Chiu Hong Kong International Terminals Gains ElasticCapacity Using a Data Intensive Decision SupportSystem 2004 Edelman Contest Finalist Paper toappear in Interfaces January February 2005 .
2 Katta G Murty Jiyin Liu Yat Wah Wan Richard Linn A decision support system for operations in a containerterminal to appear in Decision Support Systems 2005 available online at www sciencedirect com3 Katta G Murty Woo Je Kim Intelligent DMSS for.
Chartered Bus Allocation in Seoul South Korea November 2004 Intelligent Modeling for Decision Making Katta G. Murty Industrial and Operations Engineering ... Storage and Retrieval of Import Containers Top View of a Block B1 Being Served by an RTGC Land Scarcity for Terminal Development in Hong Kong The Highest Land Utilization Terminal in the World Key Service Quality Metrics Objectives of the Study ...

Related Presentations

Modeling Consumer Decision Making and Discrete Choice Behavior

Classical Inference. Population. Measurement. Characteristics. Behavior Patterns. Choices. Imprecise inference about the entire population – sampling theory and asymptotics

28 Views0 Downloads

Chapter 2 Decision Making Systems Modeling and Support

In a DSS the what-if and the goal-seeking options must be easy to perform 2.10 The Implementation Phase There is nothing more difficult to carry out, nor more doubtful of success, nor more dangerous to handle, than to initiate a new order of things (Machiavelli [1500s]) *** The Introduction of a Change *** Important Issues Resistance to change ...

26 Views0 Downloads

Modeling Organizational Decision Making in Military

Outline Outline III Corps battle management organizational structure Summarize Army frustration with measuring the ROI of digitization Review of C2 decision modeling paradigms The multi-tiered decision process within a battle staff Coping with situational ignorance: the need for sensemaking System performance measurement: the need for a ...

71 Views4 Downloads

Decision Making Manual A Toolkit for Making Moral Decisions

Syllabus as Social Contract. Consent (free and informed) Quid Pro Quo (mutually beneficial exchange) Safe Exit. FIC (free and informed consent)—The right of a risk bearer to participate in the public decision as to the acceptability of that risk.

24 Views0 Downloads

Making Sense Making Numbers Making Significance

Asymptotic Theory 3 Lecture notes 3 Logit and Probit Regression 3 Compendium: Logistic Regression 4 Logit and Probit Regression 3 Compendium: Logistic Regression 5 Exercises 2 6 Panel Models 3 Book chapter (14): Analyzing Panel Data: Fixed – and Random-Effects Models 7 Panel Models 3 Book chapter (14): Analyzing Panel Data: Fixed – and ...

35 Views0 Downloads

Decision Support and Intelligent Systems Home IOE Notes

Decision Support System. A decision support system is an integrated set of computer tool that allows a decision maker to interact directly with computers to create information and it useful in making semi-structured and unstructured decisions.. The software components for decision-support systems are a language system which enables the user to interact with the decision-support system, a ...

1 Views0 Downloads

MULTI CRITERIA DECISION ANALYSIS AND DECISION SUPPORT SYSTEMS

Quantify uncertainty. Quantify preferences. Combine uncertainty and preferences . Choice of A Decision Rule Depends On. Importance of decision consequences. Complexity of decision task. Time pressure. Similarity of alternatives. Rating on twodimensions: Value ofconsequences. Probabilityoftheiroccurence.

19 Views0 Downloads

Medical Decision Modeling Inc MBSW Online

Types of Modeling Methods Types of modeling methods frequently used in health technology assessment: Decision trees Markov Cohort Monte Carlo Microsimulation Fixed-time advance Discrete-event, Time-to-event (without and with queuing for resources) Agent-based Decision Trees A decision tree is a diagrammatic representation of the possible ...

16 Views0 Downloads

Chapter 1 Introduction to Managerial Decision Modeling

Types of Decision Models Quantitative vs. Qualitative Data Spreadsheets in Decision Making Steps in Decision Modeling Steps in Modeling Example Model: Tax Computation Tax Brackets Percent of Taxable Income Taxable Income up to $14,600 10% $14,601 to $59,400 15% $59,401 to $119,950 25% Example Model: Break-Even Analysis Slide 11 Possible ...

28 Views0 Downloads

Spreadsheet Modeling amp Decision Analysis

Introduction to Mathematical Programming MA/OR 504 Chapter 7 Machine Learning: Discriminant Analysis Neural Networks 6-*

18 Views0 Downloads

Decision Trees and Modeling Approach Federico Girosi RAND

then the main points could come up one at a time in "build" fashion. Can we streamline the verbiage on this chart--maybe even make it into a kind of table with adult and child across the top and the important factors down the side? then the main points could come up one at a time in "build" fashion.

12 Views0 Downloads

How Book Sharing May Impact Vaccine Decision Making Is

It helps them to see what the consequences could be without vaccinating.” “Starts conversations and makes parents think.” “True stories about families of all back grounds.” “This book put real patients with the diseases in front of the parents.” “Compelling.”

23 Views0 Downloads