Negotiating the value of gas priceAgendaSlide 3MotivationsObjectivesRelated WorksAssumptionsSlide 8No Existent FrameworkThe negotiation setReal-life ScenariosNearby Gas StationsSlide 13The ModelEventsScenario GenerationScenario Generation (cont.)ExampleServer LogicSlide 20Types of ServersBaseline SimulationSimple SimulationFuzzy SimulationPNN SimulationResultsResults (cont.)Slide 28ObservationsFuture WorkReferencesQuestionsNegotiating the value of gas priceBy: Hector M Lugo-Cordero, MSSaad A Khan, MSEEL 67881Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions2Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions3Motivations•Gas prices change with some deviation over regions•How can we know which is the cheapest station?•Lets say we know it, how can we benefit others and ourselves from it?•Can there be an intelligent entity that negotiates with users providing them with the best options according to distance, time, and money?4Objectives•To provide a basic framework for researchers to study gas prices negotiation•To incorporate urban computing in the gas price problem in order to solve the lack of information on client’s side•To provide a possible new income source•To develop smart agents that can negotiate gas prices with uses successfully5Related Works•Automatic collection of fuel prices from a network of mobile camera•A service-oriented negotiation model between autonomous agents•Modeling Agents Behavior in Automated Negotiation•Netflix game6Assumptions •Users have the money and the will to participate on sharing the information•Users work on the weekdays and during the weekends may go shopping or stay at home7Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions8No Existent Framework•Usage of software engineering to create an easy to use framework•Design patterns for code reusability9The negotiation setUtility for agent iUtility for agent jAEBCDPareto optimalThis circle delimits the space of all possible dealsConflict dealUtility of conflict deal for iUtility of conflict deal for j10Real-life Scenarios•In order to obtain real results real data was needed•Certain locations were selected for source and destinations•Gas stations data abstracted from real observations, i.e. personal and http://www.gasbuddy.com11Nearby Gas Stations•Distance estimation to avoid using Google maps queries•Great circle distance equation–R*deltaSigma–Phi are longitude, Lambda are latitude–Subscripts s and f stand for the start and final locations respectively•Afterwards Google maps may be used to reach the destination12Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions13The Model•Server interacts with14Events•Basic simulation component used to generate messages for communication (negotiation) between server and client•Primary event types:–SEES, ARRIVES, DEPARTS, and NEEDS GAS•Stucture:–User, location, distance, timestamp15Scenario Generation•Selection of random locations to generate three sets–R: residential, W: work, S: shop•Usage of a transition matrix A(L, d, t) to decide the paths–L is current location–d is current day–t is current time16Scenario Generation (cont.)•Consult Google to find out the distance, time, and stations on the way of the path•Merge different users according to timestamp17Example•USER20DEPARTS R11 ON 2010-03-22 13:53 0•USER1 DEPARTS R10 ON 2010-03-22 13:54 0•USER20SEES STATION40 ON 2010-03-22 13:54 1.1•USER1 DEPARTS R10 ON 2010-03-22 13:54 0•USER9 DEPARTS R9 ON 2010-03-22 13:54 0•USER20SEES STATION9 ON 2010-03-22 13:55 1.2•USER1 SEES STATION40 ON 2010-03-22 13:55 0.9•USER9 SEES STATION10 ON 2010-03-22 14:03 1.8•USER1 SEES STATION59 ON 2010-03-22 14:04 1.1•USER8 DEPARTS R11 ON 2010-03-22 14:04 0•USER20SEES STATION11 ON 2010-03-22 14:04 1.2•USER1 SEES STATION59 ON 2010-03-22 14:04 1.1•USER8 SEES STATION40 ON 2010-03-22 14:05 1.1•USER9 SEES STATION20 ON 2010-03-22 14:17 6.3•USER1 SEES STATION18 ON 2010-03-22 14:18 1.1•USER8 SEES STATION12 ON 2010-03-22 14:18 3.2•USER20SEES STATION38 ON 2010-03-22 14:18 1.2•USER1 SEES STATION18 ON 2010-03-22 14:18 1.1•USER9 ARRIVES W6 ON 2010-03-22 14:18 6.3•USER1 SEES STATION15 ON 2010-03-22 14:19 1.1•USER8 SEES STATION6 ON 2010-03-22 14:19 3.4•USER20ARRIVES W1 ON 2010-03-22 14:19 1.218Server Logic•Interest in mainly two events, i.e. SEES and NEEDS GAS•Receive request from client•Analyze for acceptance•Calculate new value if necessary•Post result to client•Client decides based on a probability, i.e. no intelligent agent acts on its behalf19Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions20Types of Servers•Baseline•Simple•Fuzzy Logic•Probabilistic Neural Network21Baseline Simulation•Its serves as a based for additional simulations•No server exists•Users get gas from the next station they see when needed•Event is triggered when less than 2 gallons remain22Simple Simulation•Both server and users accept offer with a probability of p•Concept of entropy–minp(-plog(p))•Values of probabilities represent interest and affect the outcome of the negotiations, i.e. earnings23Fuzzy Simulation•Tries to model the partial agreements using fuzzy sets•Price its changed according to how good or bad was the offer•Acceptance its done through a threshold of agreement•Conditions adapt to a variety of values24PNN Simulation•An approximation of the Bayesian networks•Takes into account the history (statistics) of data•Intelligence its done by layers–Input: one neuron for each controlling parameter (i.e. {buy price, sell price} = 2)–Hidden: one neuron for each training sample, uses radial basis functions–Classifier: one neuron for output class (i.e. {reject, accept} = 2)–Output: the class with the highest contribution is the winner25Results26Results (cont.)27Agenda•Problem statement•Challenges•Design•Evaluation•Conclusions28Observations•The ideal case it’s an easy to convince user with a good negotiator server•PNN its reliable for the server side since it considers the whole history•Fuzzy logic did not performed well for the server because sets are static and don’t have memory–Maybe using adaptation processes like genetic algorithms to adjust the sets could improve this•Negotiation of gas prices can help users to spend less money while servers gain
View Full Document