| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Merjenje in upravljanje trajnostnega delovanja pri zunanjih izvajalcih logističnih storitev v realnem času
Authors:ID Oršič, Jerko (Author)
ID Obrecht, Matevž (Mentor) More about this mentor... New window
ID Jereb, Borut (Comentor)
Files:.pdf DOK_Orsic_Jerko_2024.pdf (2,85 MB)
MD5: 1D8241F193B27093DA7A5266D064DD70
 
Language:Slovenian
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FL - Faculty of Logistic
Abstract:Zaradi novih trendov digitalne logistike, smo nadgradili obstoječe prakse za spremljanje in upravljanje aktivnosti logističnih podjetij z razvojem modela, ki omogoča sprotno izboljševanje trajnostnega izvajanja logističnih dogodkov v realnem času. Zahteve digitalne logistike se osredotočajo na hitrost, učinkovitost in izvajanje logističnih storitev v realnem času s poudarkom na optimizaciji delovanja ter zmanjšanju trajnostnih obremenitev. Kompleksnost teh zahtev se kaže predvsem pri vodilnem poslovnem modelu e-trgovine, pri dostavah na dom s prisotnostjo prejemnika. Takšno poslovanje je potrebno obvladovati v omejenih dogovorjenih časovnih okvirih, po možnosti še isti dan, kar predstavlja enega najdražjih in trajnostno najbolj obremenjenih področij logistike. Predvidevanje, kdaj bo določena dostava možna, je odvisno tudi od prometnih, vremenskih in drugih okoliščin, ki se stalno spreminjajo ter tako predstavljajo velik izziv za uspešno in trajnostno izvedbo dostav. Za podporo reševanju teh izzivov, v doktorski disertaciji predstavljamo model RELSIF, ki je osnovan na treh segmentih, in sicer: napovedi kapacitet možnih dostav v določenem geografskem in časovnem okviru, načrtovanju optimalnih dostav s točno prostorsko ter časovno definiranimi procesi, in nadzorom izvedbe načrtovanih dostav. Prvi segment se osredotoča na predvidevanje možnih dostav na določeno območje tako, da se lahko kupcu v fazi odločanja o nakupu ponudi možne izvedljive dostave v različnih časovnih okvirih. Poleg tega je prikazana trajnostna obremenitev posameznih dostav, kjer smo predvidevali, da se bo kupec odločil za bolj trajnostno dostavo. V naslednjem segmentu modela se z optimizacijo načrtovanja dostav omogočijo skrajšan čas dostave in dolžina dostavnih poti, dostave pa se izvedejo v dogovorjenih časovnih okvirih. To smo dosegli z upoštevanjem podatkov, ki se obravnavajo v realnem času v namene načrtovanja najustreznejšega zaporedja postankov, ob izogibu predvidenim zastojem, z večjo izkoriščenostjo prevoznih kapacitet, kar ima za posledico zmanjšanje trajnostnih obremenitev. Pri tretjem segmentu se stalno spremljajo vsi logistični dogodki, kjer se inteligentno reagira na možna odstopanja pri izvedbi dostav. V vsakem segmentu za razreševanje izzivov je predstavljena uporaba različnih algoritmov, temelječih na umetni inteligenci, z namenom pridobivanja podatkov iz različnih virov, prepoznavanju vzorcev v podatkih in stalnem učenju v povratni zanki. Uspešnost delovanja modela RELSIF temelji na zajemanju logističnih dogodkov v realnem času, upoštevanju različnih območij dostave, razpoložljivih virov, obsegov naročil za dostavo in ostalih zahtevah kupcev. Model je vpet v dejanski svet dogodkov, katere spremlja in se uči iz njih, vključno z vremenskimi razmerami in prometnimi posebnostmi. Poleg tega lahko model na osnovi podatkov, pridobljenih v realnem času, izbira bolj trajnostne rešitve, (pričakovano) tudi s pomočjo ozaveščenih kupcev. Tako smo ustvarili model, ki je sposoben dovolj točno napovedovati realne časovne okvire in hkrati izračunati trajnostne obremenitve posamezne dostave. Omogoča celovito spremljanje ter zmanjšanje vplivov na okolje in družbo, ter monitoring in izboljšave transparentnosti delovanja.
Keywords:oskrbovalne verige, logistika zadnje milje, 3PL, trajnost, umetna inteligenca, dogodki v realnem času, masivni podatki
Place of publishing:Celje
Publisher:[J. Oršič]
Year of publishing:2023
PID:20.500.12556/DKUM-86362 New window
UDC:656.073:502.131.1(043.3)
COBISS.SI-ID:192606723 New window
Publication date in DKUM:06.05.2024
Views:419
Downloads:93
Metadata:XML DC-XML DC-RDF
Categories:FL
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:17.11.2023

Secondary language

Language:English
Title:Real-Time monitoring and management of sustainable performance at logistics service providers
Abstract:Due to new trends in digital logistics, we have upgraded existing practices for monitoring and managing the activities of logistics companies by developing a model that allows for real-time improvement of the sustainable execution of logistics events. The requirements of digital logistics focus on speed, efficiency, and real-time execution of logistics services, emphasizing optimizing operations and reducing sustainability burdens. The complexity of these requirements is particularly evident in the leading e-commerce business model, specifically in attended home deliveries. Managing such operations within limited agreed-upon time frames, preferably on the same day, represents one of the costliest and most sustainability-challenged areas of logistics. Predicting when a specific delivery will be feasible depends on various factors, such as traffic conditions, weather, and other constantly changing circumstances, posing a significant challenge to successful and sustainable delivery execution. To address these challenges, we present the RELSIF model in the doctoral dissertation, which is based on three segments: forecasting the capacities of feasible deliveries within a specific geographical and time frame, planning optimal deliveries with precisely defined spatial and temporal processes, and monitoring the execution of planned deliveries. The first segment focuses on predicting feasible deliveries to a specific area so that the customer is offered feasible delivery options in various time frames during the purchase decision phase. Additionally, the sustainability burden of individual de-liveries is displayed, assuming that the customer opts for a more sustainable delivery. In the next segment of the model, optimizing delivery planning enables shorter delivery times and distances, with deliveries executed within agreed-upon time frames. This is achieved by considering real-time data for planning the most appropriate sequence of stops, avoiding anticipated delays, and making more efficient use of transport capacities, resulting in reduced sustainability burdens. In the third segment, all logistics events are continuously monitored, and intelligent responses are made to possible deviations during delivery execution. Each segment employs various artificial intelligence-based algorithms to acquire data from different sources, identify data patterns, and continuously learn in a feedback loop. The success of the RELSIF model relies on real-time capture of logistics events, consideration of various delivery areas, available resources, order volumes, and customer requirements. The model is embedded in actual world events; it monitors and learns from them, including weather conditions and traffic specifics. Furthermore, based on real-time data, the model can select more sustainable solutions, potentially with the assistance of environmentally conscious customers. Thus, we have created a model capable of accurately predicting real-time frames while calculating the sustainability bur-dens of individual deliveries, enabling comprehensive monitoring and reduction of environmental and societal impacts, and enhancing transparency in operations.
Keywords:Keywords: supply chain, last mile logistics, 3PL, sustainability, artificial intelligence, real-time events, big data


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica