00626919

Component

http://onlinepubs.trb.org...trr/1992/1364/1364-005.pdf

https://scholar.google.co...ider&publication_year=1992

Currently available algorithms for finding optimal solutions to the discrete transportation network design problem are deficient in two ways. First, their computing time requirements are very large, which makes them infeasible for processing large networks. Second, they cannot process multiple criteria simultaneously--that is, only one objective value can be optimized in one run and, therefore, only one final solution can be obtained. A neural network in the optimal solution search process to replace the trip assignment algorithm for the computation of total travel time is employed. Before a neural network is used, it must be trained and tested with solutions obtained from a user-equilibrium trip assignment model. Experiments show that the trained neural network can predict total travel times quickly and accurately. Next, this neural network is used in combination with a genetic algorithm to search for optimal network designs. The original genetic algorithm did not work well for the problem. However, an analysis of its results suggested improvements that led to the creation of a very powerful search algorithm: the cumulative genetic algorithm. Experiments show that the cumulative genetic algorithm can seek and find system optimal designs extremely fast, using two criteria simultaneously. A full set of optimal solutions can be obtained to construct a trade-off curve for the two criteria. This trade-off curve, composed of optimal solutions, is the boundary of one side of the entire solution space.

This paper appears in Transportation Research Record No. 1364, Transportation Planning, Programming, Land Use, and Applications of Geographic Information Systems. Distribution, posting, or copying of this PDF is strictly prohibited without written permission of the Transportation Research Board of the National Academy of Sciences. Unless otherwise indicated, all materials in this PDF are copyrighted by the National Academy of Sciences. Copyright © National Academy of Sciences. All rights reserved

01404948

English

p. 37-44

1992

Transportation Research Record

0309054036

Figures (9) ; References (12) ; Tables (2)

Accuracy; Algorithms; Calculation; Design; Networks; Neural networks; Optimization; Transportation; Travel time

Transportation networks

Design; Planning and Forecasting; Transportation (General); I72: Traffic and Transport Planning

TRIS, TRB

Feb 22 1993 12:00AM

• ANALYSIS OF TRANSIT SERVICE AREAS USING GEOGRAPHIC INFORMATION SYSTEMS
• APPLICATIONS OF GEOGRAPHIC INFORMATION SYSTEM-TRANSPORTATION ANALYSIS PACKAGES IN SUPERREGIONAL TRANSPORTATION MODELING
• APPLICATIONS OF WEIGH-IN-MOTION DATA IN TRANSPORTATION PLANNING
• AREAWIDE ESTIMATION OF VEHICLE TRIP GENERATION RATES FOR ROUTE 9A RECONSTRUCTION ON MANHATTAN'S WEST SIDE
• CALIBRATION AND ADJUSTMENT OF WEIGH-IN-MOTION DATA
• CHALLENGES CONFRONTING METROPOLITAN PORTLAND'S TRANSPORTATION DECISION SYSTEM
• CREATING A MUNICIPAL GEOGRAPHIC INFORMATION SYSTEM FOR TRANSPORTATION: CASE STUDY OF NEWTON, MASSACHUSETTS
• DECENTRALIZATION OF JOBS AND EMERGING SUBURBAN COMMUTE
• DIFFUSION OF TRANSPORTATION PLANNING APPLICATIONS IN METROPOLITAN PLANNING ORGANIZATIONS: RESULTS OF NATIONAL SURVEY
• FACTORS AFFECTING AUTOMOBILE OWNERSHIP AND USE
• GEOGRAPHIC INFORMATION SYSTEM-BASED TRANSPORTATION PROGRAM MANAGEMENT SYSTEM FOR COUNTY TRANSPORTATION AGENCY
• HIGHWAY PERFORMANCE MONITORING SYSTEM ANALYTICAL PROCESS APPLICATION TO KENTUCKY'S ADEQUACY PROGRAM
• LOCATION PLANNING FOR COMPANIES AND PUBLIC FACILITIES: A PROMISING POLICY TO REDUCE CAR USE
• MATCHING PLANNING STYLES AND ROLES IN TRANSPORTATION TO CONDITIONS OF UNCERTAINTY AND STATE TECHNOLOGICAL KNOW-HOW
• PHOENIX COMMERCIAL VEHICLE SURVEY AND TRAVEL MODELS
• PLANNING FOR TEXAS' NEEDS USING HIGHWAY PERFORMANCE MONITORING SYSTEM ANALYTICAL PROCESS
• PROPOSED METHOD FOR CALIBRATING WEIGH-IN-MOTION SYSTEMS AND FOR MONITORING THAT CALIBRATION OVER TIME
• ROADWAY LEVELS OF SERVICE IN AN ERA OF GROWTH MANAGEMENT
• STARTING A REGIONAL TRANSPORTATION PLANNING ORGANIZATION
• TRIAL IMPLEMENTATION OF A PHOTOELECTRIC SENSOR SYSTEM TO CLASSIFY VEHICLES
• USE OF HIGHWAY PERFORMANCE MONITORING SYSTEM AND BRIDGE NEEDS AND INVESTMENT PROCESS FOR REPORTING CONDITIONS, NEEDS, AND PERFORMANCE TRENDS
• USE OF HIGHWAY PERFORMANCE MONITORING SYSTEM IN RECLASSIFYING RURAL HIGHWAYS IN SUPPORT OF NATIONAL HIGHWAY SYSTEM IN KANSAS