Agent-based modelling of paratransit as an intelligent complex adaptive system to improve efficiency

Ndibatya, Innocent (2021-03)

Thesis (PhD)--Stellenbosch University, 2021.

Thesis

ENGLISH ABSTRACT: Urban residents in Sub-Saharan Africa (SSA) face mobility challenges that limit theiraccess to jobs, services, markets, and socioeconomic opportunities. In most SSA cities,public transport is predominantly provided by the inefficient paratransit system – a flex-ible mode of passenger transport consisting of privately-owned, low-capacity unscheduledminibuses and motorcycle taxis. There is growing interest among city authorities andurban transport researchers in addressing the inefficiency problem associated with para-transit. Several approaches, such as complete overhaul to bus rapid transit (BRT), andphased banning of paratransit from the cities have previously been proposed and con-comitant implementation projects started. However, most of such projects have eitherfailed to take off, or they have stalled. This is likely because of the huge capital invest-ment required, the unique social and cultural dynamics associated with “third world”countries, and urban sprawl due to poor city planning. This study departs from the com-mon perspective held by several researchers and city authorities who view paratransit as“chaotic”, thus, the justification for its total overhaul and banning. Instead, this studyaims to leverage the beneficial aspects of existing paratransit – such as flexibility, demand-responsiveness and near-ubiquitous coverage – with the elusive objective of achieving amore efficient paratransit state as a result.Through theoretical modelling, field study and experimental approaches, this studyaimed to improve the efficiency of minibus taxis paratransit systems. The theoretical mod-elling work involved modelling paratransit systems as complex adaptive systems (CAS)and developing an agent-based model (ABM) for minibus taxi operations in an organically-evolved paratransit setting. The field study involved an in-depth investigation of minibustaxi operations in Kampala’s paratransit system, and collection and analysis of minibustaxi movement data that was used to validate the agent-based model. The experimen-tal approaches involved three separate simulation experiments, simulating the minibustaxi transportation dynamics with varying levels of agents’ intelligence and situational awareness. Machine learning methods, such as random forests and convolutional neuralnetworks were used to train agents in the subsequent simulation experiment to improvetheir intelligence during decision making. At each stage, several efficiency metrics’ valuessuch as passenger waiting time and minibus taxi occupancy were collected. The resultsfrom the experiments showed that there was an improvement in the overall efficiency ofthe minibus taxi paratransit system. For instance, the average passenger waiting time re-duced from 1.2 hours to 30 minutes, indicating a 55% improvement. Whereas the averageminibus taxi occupancy increased from 42% to 51%, indicating a 21% improvement. Ac-cordingly, we concluded that improving the micro-level agents’ intelligence and situationalawareness, results in an overall increase in the efficiency of the paratransit system.To the transportation researchers, we recommend further work on using ABM toinclude other modes of paratransit transport such as the three-wheeled rickshaws andmotorcycle taxis (boda bodas). To the city authorities, we recommend the integration ofsmart mobility and ICT applications into the paratransit ecosystem to support journeyplanning, booking, scheduling, and fare collection.

AFRIKAANSE OPSOMMING: Stedelike inwoners in Afrika Suid van die Sahara (SSA) word gekonfronteer met mo-biliteitsuitdagings wat hul toegang tot werk, dienste, markte en sosio-ekonomiese geleen-thede beperk. In die meeste SSA-stede word openbare vervoer oorheersend aangebieddeur die ondoeltreffende paratransit-stelsel -’n buigsame manier van passasiersvervoerwat bestaan uit private lae-volume busse en huur-motorfietse. Daar is toenemende be-langstelling onder stadsowerhede en navorsers van stedelike vervoer om die ondoeltref-fendheidsprobleem so eie aan paratransit. Verskeie benaderings, soos byvoorbeeld dievolledige opknapping van busvervoer (BRT) en ’n gefaseerde verbod op paratransit instede, is voorheen voorgestel en verwante implementeringsprojekte is van stapel gestuur.Die meeste van hierdie projekte het egter nie daarin geslaag om te begin nie, of hulleis gestaak. Dit is waarskynlik as gevolg van die groot kapitaalinvestering wat benodigword, die unieke sosiale en kulturele dinamika wat verband hou met lande van die ”derdewˆereld” en stedelike uitbreiding as gevolg van swak stadsbeplanning.Hierdie studie wyk af van die algemene perspektief wat deur verskeie navorsers en stad-sowerhede gehou word, wat paratransit as “chaoties” beskou, en dus van die regverdigingvir die totale opknapping en verbod daarvan. In plaas daarvan beoog hierdie studie omdie voordelige aspekte van paratransit te versterk - soos buigsaamheid, aanvraagresponsi-witeit en byna alomteenwoordige dekking - met die hoop om ’n doeltreffender paratransit-staat as gevolg daarvan te bewerkstellig.Deur middel van teoretiese modellering, veldstudies? en eksperimentele benaderings,het hierdie studie ten doel gehad om die doeltreffendheid van minibustaxi-paratransitstelselste verbeter. Die teoretiese modelleringswerk behels die modellering van paratransitstelselsas komplekse aanpasbare stelsels (CAS) en die ontwikkeling van ’n agent-gebaseerde model(ABM) vir minibustaxibedrywighede in ’n organies-ontwikkelde paratransit-omgewing.Die veldstudie behels ’n diepgaande ondersoek na minibustaxibedrywighede in Kampala se paratransit-stelsel, en versameling en ontleding van minibustaxibewegingsdata wat ge-bruik is om die agent-gebaseerde model te bekragtig. Die eksperimentele benaderings hetdrie afsonderlike simulasie-eksperimente behels, wat die minibustaxi-vervoerdinamika metverskillende vlakke van agente se intelligensie en situasiebewustheid simuleer. Masjienleer-metodes soos ewekansige woude en evolusionˆere neurale netwerke is gebruik om agente indie daaropvolgende simulasie-eksperiment op te lei om hul intelligensie tydens besluitnem-ing te verbeter. In elke stadium is verskeie waardes vir doeltreffendheid soos die passasier-swagtyd en die besetting van minibustaxi’s versamel. Die resultate van die eksperimentehet getoon dat die algehele doeltreffendheid van die minibus-paratransitstelsel verbeterhet. Byvoorbeeld, die gemiddelde passasierwagtyd verminder van 1,2 uur tot 30 minute,wat dui op ’n 55% verbetering. Terwyl die gemiddelde besetting van minibustaxi van 42%tot 51% gestyg het, wat dui op ’n verbetering van 21%.Gevolglik het ons tot die gevolgtrekking gekom dat die verbetering van die intelligensieen situasiebewustheid van die mikrovlakagente tot ’n algehele toename in die doeltreffend-heid van die paratransitstelsel lei.Vir die vervoernavorser beveel ons verdere ABM-werk aan om ander maniere vanparatransit-vervoer soos die driewiel-riksja’s en motorfiets-taxi’s (boda bodas) in te sluit.Aan die stadsowerhede beveel ons die integrasie van slim mobiliteit- en IKT-toepassingsaan in die paratransit-ekosisteem om reisbeplanning, bespreking, skedulering en tariefin-vordering te ondersteun.

Please refer to this item in SUNScholar by using the following persistent URL: http://hdl.handle.net/10019.1/109824
This item appears in the following collections: