Artificial Immune System-Based Mobile Node MovementMotivationTwo Desirable TraitsRelevant Adaptive Immune System BasicsArtificial Immune SystemsArtificial Immune System Basis of The Presented SystemNode StateIf Node Sensor Detects an EventIf Node Receives Event MessageResult of Node-Event InteractionNode-Node Stimulation EffectsResult of Node-Node InteractionBeaconNode MovementSimulation ParametersDemonstrationResults: Random Node Placement, Waypoint Event Mobility ModelResults: Random Node Placement, Blocked Event Mobility ModelResults: Grid Node Placement, Waypoint Event Mobility ModelResults: Grid Node Placement, Blocked Event Mobility ModelConclusionsFuture WorkArtificial Immune System-Based Mobile Node MovementPeter MatthewsMotivationMobile NodesDesirable for manyapplicationsAllows dynamic node topology configurationTopology reconfigures in response to perceived conditions, internal and externalGoal: Adaptively cover a large area with a small # of nodes, high sensing fidelity, and high reliabilityDifficult balance of area coverage and local specializationTwo Desirable TraitsDecentralized OperationMore scalable in terms of communication, and thus requires much less powerAllows more immediate response to changing conditionsBoth external perceptions and node status changesMore robust to node / link failuresSimplicityMust be designed in a fashion mindful of limited sensor node computational abilities, memory, and powerOne way of accomplishing this is via a form of self-organization or “distributed intelligence”Biological inspiration: Swarm Behavior, Ant Behavior, Artificial Immune Systems, and the likeRelevant Adaptive Immune System BasicsNatural defense mechanism. Able to discriminate between self and non-self and respond accordingly to foreign invaders.Ability to learn about pathogens and respond to them by producing antibodies that attack antigens associated with the pathogenPathogen: Foreign substanceAntigen: Molecule (protein) associated with pathogenAntibody: Protein that allows B-cell to bind to antigen and destroy itAntibodies have differing affinity to specific antigensB-cell surface has many antibodies and when one of these antibodies binds to an antigen the B-cell becomes stimulatedLevel of stimulation depends onHow well it matches the antigenHow well it matches other B-cells in the immune networksSuppression factor from other B-cells with small affinityB-Cell: Lymphocyte (white blood cell)Stimulation leads to antibody production / cloningArtificial Immune SystemsThe immune system is a self-organizing system that has the ability to process information, to learn and memorize, to create a diverse population of well adapted individuals, to discriminate between self and non-self, and respond to changing conditions in a decentralized fashionAIS attempt to apply the principles and mechanisms of immune system operation to a variety of problemsExamples: They have been found well suited to anomaly detection, pattern recognition, data clustering, multi-modal optimization, etc.Artificial Immune System Basis of The Presented SystemWhen immune system encounters a pathogen, some B-cells are stimulated and secrete antibodies in order to destroy the antigens.Likewise, when an event occurs in sensor range some sensor nodes are stimulated and move in order to minimize distance and more accurately monitor the eventB-Cells : Sensor NodesPathogens : Events of InterestAntigen : Distance to EventAntibody : MovementAntibody Density : SpeedNode State2 Indexes of Node StimulationX-Stimulation, Y-Stimulation[-Max, +Max]Short-lived buffer of received event messagesFor discriminating whether the event report has already been processed by this nodeTimer for last beacon message received from sinkUsed to avoid node disconnection from sinkCount of number of neighbors at last time quantumUpdated via regular probing / taking note when overhearing other nodes’ transmissionsIf Node Sensor Detects an EventNode estimates XDistance, YDistance, TotalDistance.XDistance, YDistance may be negativeX-Stimulation, Y-Stimulation are suppressed by Observation_Suppression_Factor ( < 1)Discounts previous stimulation stateX-Stimulation += xDistance / SensorRange * Max_Detection_StimulationY-Stimulation updated likewiseTransmit message to any nodes in range containingEstimated location of eventTimestamp# Hops (= 0)# En route neighbors = # Neighbors of this nodeIf (# neighbors > Cluster_Size AND totalDistance / SensorRange < restrictionRange)Stimulation = Max_Event_Stimulation / (# neighbors - Cluster_Size )ElseStimulation = Max_Event_StimulationIf Node Receives Event MessageIf already processed copy of same message or if already processed a report of event with same timestamp and within a small estimated distance of each other, ignoreCalculate distance to event locationIf distance < Max_Distance and #EnRouteNeighbors > Max_NeighborstotalStimulation = stimulationIntensity * (.5 * (1 – distance / Max_Distance) + .5 * (1 - #EnRouteNeighbors/Max_Neighbors))X-Stimulation += xDistance / totalDistance * totalStimulationY-Stimulation likewiseIf Estimated # Neighbors < Cluster_Sizeand distance < Max_DistanceRetransmit message withOriginal location and timestampStimulation = original stimulationIntensity#Hops += 1# En route neighbors += # Neighbors of this nodeResult of Node-Event InteractionNode is stimulated to move towards the location of an event of interestStimulation falls off as a factor of distance and # neighbor nodes along route# neighbor nodes some indication of how crowded is route from event to nodeIf area becomes too crowded, node does not transmitThis avoids node “implosion” effects. Tunable to specify how large of a cluster is appropriate for a given application.Node-Node Stimulation EffectsVia regular probing and overhearing of transmissions, each node keeps a list of neighbors within transmission range and estimated distanceFor each neighboring nodeX-Stimulus += (-xDistance / Distance) * (1 – (Distance / TransmissionRange - α)^2) * Neighbor_Stimulation_RateY-Stimulus likewiseResult of Node-Node InteractionIf a node is within transmission range - α of another sensor node, where α is very small, then this node receives a repulsive stimulation
View Full Document