Download presentation
Presentation is loading. Please wait.
Published byClara Henderson Modified over 9 years ago
1
Ephemeral Network Broker to Facilitate Future Mobility Business Models/Transactions A collaboration between Ford University Research Program and University of Minnesota University PI: Shashi Shekhar Ford PI: Shounak Athavale
2
Outline High-level Problem Description Challenges Related Work Possible Problem Formulations/Examples Synthetic Data Generation Discussion
3
Basic Concepts Ephemeral Networks: Groups of people, good and services that encounter each other in the physical world –are in close geographic proximity –during routine activities such as commute, shopping, entertainment Goal: Investigate ephemeral network broker that can identify novel opportunities for Mobile Commerce in Ephemeral Networks (MCEN).
4
High-level Problem Description Input: –Historical trajectories and real-time locations of consumers and service providers (producers) –Consumer Calendars, wish lists, gift-registries, shopping lists –Historical mobile commerce transactions Output: –Near-future or real-time mobile commerce opportunities in the ephemeral network by matching producers and consumers Constraints: –Physical World: Human life (set of activities) → Activities generate trips which generate commerce opportunities (supply and demand) –Activities are not random/independent: Routine/Periodic activity, routine patterns of life, routine demands/commerce needs
5
Challenges Scaling to Big Spatio-temporal Data (megacities) Modeling of socio-economic semantics (e.g. supply, demand, trust) Choice of interest measure (tradeoff)
6
Related Work Social network analysis for long term social relationships Ephemeral Social networks Sharing economy: –(Online) Ride sharing, Uber (Yan Huang et al., VLDB 2014), (Blerim Cici, et al. SIGSPATIAL 2015) –hotel rooms (Airbnb), Meal sharing, favor networks for sharing chores Trajectory Pattern mining (e.g. flock, meeting patterns) –Does not consider real-time demand, road network
7
Real-time/Online Ridesharing Systems (1/2) Passenger constraints: (src, dst, earliest departure time, latest arrival time) Driver constraints: (src, dst, departure time, deviation distance tolerance) Pairs only (2 sec/query)
8
Real-time/Online Ridesharing Systems (2/2) Passenger constraints: (src, dst, maximum waiting time, % of extra acceptable detour) Driver constraints: only satisfying all current passengers constraints –A vehicle can group multiple passengers Problem : Given a set of vehicles and a new passenger request, find the vehicle that minimizes the overall trip cost for the augmented trip schedule. Approach: materializing and pruning valid trip schedules (4 to 12 ms/query)
9
Limitation of Online Ridesharing Literature Assumes fixed users and moving servers as opposed to fixed servers and moving users. Does not handle commerce opportunities arising between pairs of moving objects → Ephemeral network –Fixed passenger location at time of request Does not make use of historical trajectories (aside from driver ratings) of producers and consumers (recurring events)
10
Problem Formulation 1: Fixed Servers, Moving Consumers Input: –A set of servers (i.e. service providers). Each server is defined using: Location coordinates service types (e.g. food options, clothing) A time series of supply over the day (e.g. 20 meals/hour) –A consumer request: (current location, destination, service type, max. service waiting time, max. distance detour) Output: –A server recommendation for the incoming request + estimated service time Objective: –computational efficiency/scalability –Minimizing consumer waiting time and distance detour –Matching the max. number of requests for multiple simultaneous requests? Constraints: –Accepted requests by a server should not exceed server supply at service time –Recommended server should meet max. service waiting time and max. distance detours for each request
11
Example 1: Fixed Servers, Moving Consumers c1c1 c2c2 L1L1 L2L2 S1S1 ServersConsumers L 1, L 2 : 11-1pm: 10 req/hour otherwise: 20 req/hour C 1 : Lunch, max waiting time =1 min, max detour = 10% C 1 can be matched to L 1 or L 2 But L 1 not ready! C 1 Max. waiting time will be exceeded Match to L 2 and Detour S 1 : rush hours: 4 req/hour otherwise: 8 req/hour C 2 : Shopping, max waiting time =2min, max detour = 20%
12
Grouping consumers for the same server: –e.g. If server announces a groupon, consumers may go to further servers or wait more. (money constraint, ranking constraints) Should we assume that supply can change at real-time? –e.g. based on restaurant occupancy –But has to at least satisfy already accepted requests What about recommending multiple services for a single user along his route? Problem Formulation 1: Fixed Servers, Moving Consumers (cont’d)
13
Problem Formulation 2: Moving Servers and Moving Consumers Input: –A set of servers (e.g. food trucks). Each server is defined using: Current location coordinates service types (e.g. food options) Total supply –A consumer request: (current location, destination, service type, max. service waiting time, max. distance detour??) Output: –A recommended server + service time and location (+ estimated cost?) Objective: –Recommended server is the one that minimizes total server trip cost including previously accepted consumers –Computational efficiency/scalability –Minimizing consumer waiting time and distance detour?? –Matching the max. number of requests for multiple simultaneous requests?? Constraints: –Accepted requests by a server should not exceed server supply –Recommended server must meet max. service waiting time and distance detour for each request
14
Example 2: Moving Servers and Moving Consumers C1C1 L1L1 C2C2 ServersConsumers L 1 : 100 mealsC 1 : Lunch, max waiting time =1 min, max detour = 10% C 2 : Lunch, max waiting time =1 min, max detour = 10% L2L2 What if L 2 will travel a longer distance towards C 2 (than L 1 ) but can meet C 2 earlier on the road?
15
Comparing Different Formulations Problem Fixed Servers and Moving Consumers Moving Servers and Moving Consumers ImportanceMobile commerce for many service providers (e.g. food, retail stores, malls, etc) Food trucks schedules, sales representatives schedules Related WorkShelter/resource allocation: But with real-time requests and variable supplier capacity Operations Research/Optimization Trip Planning, but site locations are also moving (i.e. moving consumers) Operations Research/Optimization ChallengesScalability, real-time response, supply generation, Scalability, real-time response, supply generation Validation% of accepted requests Average query response time Average waiting time per request Average distance detour per request % of accepted requests Average query response time Average waiting time per request Average distance detour per request
16
Synthetic Data Generation (Supply/Demand) (1/2) Users mobility patterns are derived by their needs (Maslow’s hierarchy of needs). These needs can be used to model the users demand and generate trips: –Physiological (Food, clothing, shelter): trips for grocery shopping and restaurants Trips to shopping malls – Safety (financial, health): Home/work or school trips Trips to clinics/hospitals –Love/belonging/socialization: Trips to parks, cinemas, POIs Maslow’s Hierarchy of Needs
17
Synthetic Data Generation (Supply/Demand) (2/2) Possible generation model (based on BerlinMod): –Generate work/home trips per user –Generate additional trips in spare-time blocks under a given probability –Regular shopping trips –Occasional recreational/clinic trips
18
Discussion How can we make use historical trajectories? Why not just match real-time locations? (recurring vs. non-recurring rendezvous)
20
Synthetic Data Generation (1/3) Brinkhoff: –Trip-based short term observations Vehicles disappear at destination –Speed affected if number of moving objects on edge > threshold –Starting node: randomly –Destination node: depends on preferred route length (i.e. time, vehicle) –External events: weather, traffic jams (external objects) May lead to re-computation of route Limitations: –Does not account for real-world traffic flow and population (in implementation) –Does not model multiple trips for the same object (historical data)
21
Synthetic Data Generation (2/3) BerlinMod: –Object-based simulation for long-term observations/multiple days –Each object has home node and work node and neighborhood (3 km) –Work/Home nodes: random or using region probability –Trips: Home/work: 8 pm + t 1 → 4 pm + t 2 0.4 probability for trips in each spare time block (1 to 3 stops) »4 hour after work »2 five-hour blocks on a weekend –Simulates speed changes: Accelerate: automatically to reach max speed Deceleration/Stop: road crossings, curved edges Limitations: –Does not consider edge load (e.g. congestion) and external factors (e.g. weather effect). –Generation of home and work nodes are independent
22
Synthetic Data Generation (3/3) DYNASMART: –Dynamic Network Assignment-Simulation Model for Advanced Road Telematics –Designed to model traffic pattern and evaluate network performance under real-time information systems (e.g. reconstructions). –Uses OD Matrix to model simulated trips. –Trip Simulation: Assign vehicles initially to (one of k) shortest path (s). Recompute path cost –Congested edges are penalized Re-assign vehicles (switching occurs) Continue until wardrop equilibrium is reached –Advanced capabilities: Models signalized intersections, ramp entry/exit etc. Models driver’s behaviors –infrequent updates of network route info, fraction of info-equipped drivers
23
Relation to Colocation/Co-occurrence Mining Problem Sub-time-series Co-occurrence Patterns Periodic Sub-trajectory Co-location Patterns ProblemGiven historical trajectory data, identify the (multi-dimensional) sub- time-series that correlates with non- compliant windows (e.g. of emissions) Given historical trajectory data, identify (Producer, Consumer) pairs that periodically co-locate Interest measure What patterns have a distribution that is NOT independent from non- compliant events? Should capture: duration/length of encounter Periodicity/Return period Historical Success rate? ApproachEnumeration of temporal patterns in a set of time series Enumeration on a spatio- temporal network
24
Return Period A estimate of the likelihood of an event (e.g. earthquake, flood) to occur. Return Period = Example: –If a flood has a return period of 10 years. Then, its probability of occurring in any one year is 1/100 or 1% –Could happen more than once in 100 years (independent of when last event occurred) Producer/consumer pairs with small return periods are more promising.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.