Prediction-based Routing Research Articles

The Co-Production of Service: Modeling Services in Contact Centers Using Hawkes Processes

In customer support contact centers, every service interaction involves a messaging dialogue between a customer and an agent; together, they exchange information, solve problems, and collectively co-produce the service. Because the service progression is shaped by the history of conversation thus far, we propose a bivariate marked Hawkes process cluster model of the customer-agent interaction. To evaluate our stochastic model of service, we apply it to an industry contact center data set containing nearly 5 million messages. Through both a novel residual analysis comparison and several Monte Carlo goodness-of-fit tests, we show that the Hawkes cluster model indeed captures dynamics at the heart of the service and surpasses classic models that do not incorporate the service history. Furthermore, in an entirely data-driven simulation, we demonstrate how this history-dependent model can be leveraged operationally to inform a prediction-based routing policy. We show that widely used and well-studied customer routing policies can be outperformed with simple modifications according to the Hawkes model. Through analysis of a stylized model proposed in the contact center literature, we prove that service heterogeneity can cause this underperformance and, moreover, that such heterogeneity will occur if service closures are not carefully managed. This paper was accepted by Elena Katok, operations management. Funding: The authors are grateful for the generous support of this work by the National Science Foundation Division of Graduate Education [Grant DGE-1650441] (A. Daw), the Israel Science Foundation [Grant 336/19] (G. B. Yom-Tov), and the United States-Israel Binational Science Foundation [Grant 2022095] (A. Daw, G. B. Yom-Tov). Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.04060 .

Collaborative Intelligence Enabled Routing in Green IoV: A Grid and Vehicle Density Prediction-Based Protocol

Green Internet of Vehicles (IoV) is a newly-emerged research area which focuses on reducing networking overhead and improving communication efficiency in future vehicular cyber-physical systems (VCPS). A critical requirement to realize such tasks in Green IoV is the achievement of effective routing protocols for data dissemination. However, maintaining end-to-end communication and reducing the communication overhead at the same time is quite challenging due to high vehicle dynamics and complex traffic environments. In this paper, we propose a vehicle density prediction-based routing protocol called VDPGrid. Firstly, we introduce a vehicle density prediction model according to the spatio-temporal features of vehicle trajectories. Then, to reduce the communication overhead and improve communication efficiency, we divide the map into grids and present a routing path evaluation scheme that jointly considers the vehicle density, link quality, and routing length. Moreover, a grid-based routing method is proposed to select the optimal relay node according to real-time traffic information. Finally, extensive experiments using real-world vehicle trajectories are conducted to validate the effectiveness of our method.

Grey Prediction-based Energy-Aware Opportunistic Routing in WSN

Grey Prediction-based Energy-Aware Opportunistic Routing in WSN

A Human Location Prediction-Based Routing Protocol in Mobile Crowdsensing-Based Urban Sensor Networks

Mobile crowdsensing (MCS) has recently emerged as an urban-sensing paradigm that takes advantage of smartphone sensing capabilities and user mobility. A major challenge in mobile crowdsensing-based urban sensor networks is how to efficiently transfer data from sensors to the sink (e.g., the server center). Therefore, this study proposes a human location prediction-based routing protocol (HLPRP) in such networks. Specifically, a human location prediction (HLP) model is designed to estimate the location of mobile nodes. The proposed HLP model is based on a recurrent neural network with long short-term memory cells. The movement history of each person is used in the HLP model to predict their future locations. Experimental results on real traces are used to validate the proposed HLP model. Then, using predicted location information from the HLP model, packet delivery predictability is obtained. Packet delivery predictability represents the possibility that a node will deliver a packet to its destination and is used to select optimal relay nodes to maximize the packet delivery ratio, minimize the packet delivery cost, and reduce delivery latency. In addition, the proposed routing protocol considers social strength for relay selection. To evaluate the HLPRP, we conduct simulations and compare results with other routing protocols, showing that the HLPRP can outperform existing protocols.

An adaptive routing protocol in flying ad hoc networks

Nowadays, ad hoc networks play a vital role in wireless communication. It is a temporary network to relay the data between nodes. Ad hoc network is divided into different types such as MANET, VANET & FANET. FANET is a combination of MANET and VANET. In FANET, routing is a big challenging issue due to unique characteristics like dynamic topology, frequent changes of link quality, mobility of UAV nodes, etc. Reliability of routes is also a real challenge due to the very high mobility in FANET. In this research work, we have introduced an adaptive routing protocol, PF-WGTR - A predicted future weight-based routing scheme for FANETs that considers the node’s existing and upcoming values of assured parameters to determine the reliable routing path. This proposed routing protocol assigns weight to every node in the network by calculating the node’s future. Depending on the predicted future weight of every node in a network, the communicating nodes can establish a reliable path that persists for a long time. This adaptive, future prediction-based routing scheme ensures better data delivery with minimum overhead and optimized energy consumption in all conditions compared with the existing routing protocols. The NS-2 simulator is used to compare the proposed routing protocol with previous protocols in terms of FANET parameters. Finally, the simulation results show better performance than the existing works.

HMMR: Hidden Markov Model Prediction-Based Routing in Opportunistic IoT Scenario

HMMR: Hidden Markov Model Prediction-Based Routing in Opportunistic IoT Scenario

PREDICTION BASED ENERGY EFFICIENT OPPORTUNISTIC ROUTING PROTOCOL IN WIRELESS SENSOR NETWORKS

Opportunistic routing is a most promising routing method for improving the network lifetime and throughput of wireless sensor networks (WSN). It utilises the broadcast nature of WSN, that allows to select and prioritise a node from the potential forwarder set as next-hop forwarder. The design of energy efficient routing protocol becomes one of the major concern in WSN, due to limited battery power of a sensor node. The common energy loss reasons of existing routing protocols are: 1) packets may travel through a specific set of sensor nodes will drain out a battery energy very soon; 2) packets discard will create a packet retransmission. Opportunistic routing broadcast nature will avoid packet retransmission. The proposed energy efficient Markov prediction-based opportunistic routing (EEMPOR) protocol uses the following metrics to select and prioritise the energy efficient nodes namely, number of transactions of a node and residual energy of a node. Then proposed protocol shows that Markov prediction-based opportunistic routing protocol provides better network performance than non-prediction-based method. Simulation results show, that the proposed protocol outperforms the existing OR in terms of consumed energy, residual energy, network lifetime, and throughput.

Travel Time Prediction-Based Routing Algorithms for Automated Highway Systems

Travel Time Prediction-Based Routing Algorithms for Automated Highway Systems

A Performance Evaluation of Location Prediction Position-Based Routing Using Real GPS Traces for VANET

Vehicular ad-hoc network (VANET) is an emerging paradigm for road transportation which minimizes traffic, accidents and improves fuel efficiency. VANET uses the position of the vehicle obtained from satellite system such as global positioning system (GPS), global navigation satellite system, Compass and Galileo as a location id in position-based routing protocol. The position obtained from the satellite system is likely to have an error due to environmental and technical issues which effect the routing performance. Thus, this paper proposes a position-based routing protocol which uses Kalman filter based location prediction technique to improve routing performance by minimizing location error. The routing protocol performance is evaluated on NS-3.23 simulator with real time GPS traces and simulator generated mobility on Two-ray ground and Winner-II propagation model for 500 m transmission range. Further, performance is compared with other prediction-based routing protocol on the metrics of packet delivery ratio, average delay and throughput.

Resource prediction-based routing using agents in mobile ad hoc networks

Resource prediction-based routing using agents in mobile ad hoc networks

Resource prediction-based routing using agents in mobile ad hoc networks

QoS outing in multimedia applications over MANET is affected by limited resources, shared channel, unpredictable mobility, improper load balancing, and variation in signal strength. Existing works on MANET QoS routing focuses on only one of the factor such as bandwidth, mobility or energy neglecting dependent behaviour. In this paper, resource prediction-based routing is proposed wherein intelligent agents identify routes for communication with adequate future availability of buffer-space, energy and bandwidth resources considering mobile nodes. It has four steps of execution: resource prediction, resource prediction factor computation, route establishment, and route maintenance. Resources are predicted to compute resource prediction factors for reliable route establishment and route maintenance against link and node failure. Simulation results show an improvement in terms of packet delivery ratio, packet delivery latency, memory overhead and energy consumption.

Adaptive Message Routing and Replication in Mobile Opportunistic Networks for Connected Communities

Mobile opportunistic networking is a promising technology that can supplement existing cellular and WiFi networks to provide desirable services for smart and connected communities. Message routing is the most compelling challenge in mobile opportunistic networks due to the lack of contemporaneous end-to-end paths and the resource constraints at mobile devices. To improve the probability of successful message delivery, most existing routing schemes use the past contact history to predict future contacts for message forwarding, and exploit message replication and redundancy for multicopy routing. However, most existing prediction-based routing schemes simply use the average pairwise contact probability as the routing metric and neglect the benefits of exploring fine-grained contact information such as pairwise repeated contact patterns to improve the accuracy of predicting future contacts. Moreover, there is no efficient mechanism that can adaptively control message replication in a decentralized manner to achieve both high probability of successful message delivery and low message overhead. To address these problems, we present FGAR, a routing protocol designed for mobile opportunistic networks by leveraging fine-grained contact characterization and adaptive message replication. In FGAR, contact history is characterized in a fine-grained manner with timing information using a sliding window mechanism, and future contacts are predicted based on the fine-grained contact information, thereby improving the accuracy of contact prediction. We further design an efficient message replication scheme in which message replication is controlled in a fully decentralized manner by taking into account the expected message delivery probability, the replication history, and the quality of the encountered device. A replica is generated only when it is necessary to fulfill the expected message delivery probability. We evaluate our scheme through trace-driven simulations, and the simulation results show that FGAR outperforms existing schemes. In comparison with PRoPHET, FGAR can achieve more than 20% improvement on average on successful message delivery, whereas the message overhead has been reduced by a factor up to 15.

A location Prediction-based routing scheme for opportunistic networks in an IoT scenario

Opportunistic Internet of Things (OppIoT) is a paradigm, technology, and system that promotes the opportunistic exploitation of interactions between IoT devices to achieve increased connectivity, reliability, network capacity, and overall network lifetime. The increased demand for identifying such opportunistic exploitation is illustrated by IoT scenarios, where the goal is to recognize when an opportunity for communication is possible, thereby allowing for data forwarding and routing. In an OppIoT system, devising a routing scheme is a challenging task due to the difficulty in guaranteeing the existence of connectivity between devices (nodes) and in identifying an intermediate node as a packet forwarder towards its destination. Considering that opportunistic networks (oppNets) are a subclass of OppIoT and considering IoT scenarios where the opportunistic exploitation of IoT devices is possible even in case the device’s presence is uncertain or may change over time, this paper proposes a novel routing scheme for OppNets (called Location Prediction-based Forwarding for Routing using Markov Chain (LPFR-MC)) that can also be used in IoT scenarios. The proposed LPFR-MC scheme considers the node’s present location and the angle formed by it and the corresponding source (resp. destination) to predict the node’s next location or region using a Markov chain and to determine the probability of a node moving towards the destination. Simulation results are provided, showing that the proposed LPFR-MC outperforms the existing traditional protocols in terms of message delivery probability, hop count, number of messages dropped, message overhead ratio, and average buffer time.

4PR: Privacy preserving routing in mobile delay tolerant networks

Message routing is one of the major challenges in Mobile Delay Tolerant Networks (MDTNs) due to frequent and long-term network partitions. A number of routing protocols for MDTNs belong to the category of prediction-based routing protocols, which utilize the social encounter probability of nodes to guide message forwarding. However, these prediction-based routing protocols compromise the privacy of the nodes by revealing their mobility patterns. In this paper, we propose the Privacy Preserving Probabilistic Prediction-based Routing (4PR) protocol that forwards messages by comparing aggregated information about communities instead of individual nodes. Specifically, it compares the probability that at least one node in a community will encounter the destination node. We present theoretical security analyses as well as practical performance evaluations. Our simulations on a well established community-based mobility model demonstrate that our routing protocol has comparable performance to existing prediction-based protocols. Additionally, the community information is computed efficiently and independently of the routing protocol.

Prediction-Based Routing Methods in Opportunistic Networks

The dynamic nature of opportunistic networks results in long delays, low rates of success for deliveries, etc. As such user experience is limited, and the further development of opportunistic networks is constrained. This paper proposes a prediction-based routing method for opportunistic networks (PB-OppNet). Firstly, using an ARIMA model, PB-OppNet describes the historical contact information between a node pair as a time series to predict the average encounter time interval of the node pair. Secondly, using an optimal stopping rule, PB-OppNet obtains a threshold for encounter time intervals as forwarding utility. Based on this threshold, a node can easily make decisions of stopping observing, or delivering messages when potential forwarding nodes enter its communication range. It can also report different encounter time intervals to the destination node. With the threshold, PB-OppNet can achieve a better compromise of forwarding utility and waiting delay, so that delivery delay is minimized. The simulation experiment result presented here shows that PB-OppNet is better than existing methods in prediction accuracy for links, delivery delays, delivery success rates, etc.

Mobility-aware routing in delay tolerant networks

Delay tolerant networks (DTNs) make use of opportunistic encounters of nodes for communication. The characteristics of high mobility of nodes, frequent link variation and long communication delays in DTNs result in an absence of an instantaneous end-to-end path from any source to a destination, making routing a challenge in DTNs. To deal with this issue, a lot of routing schemes have been proposed, in which future contacts of nodes are predicted based on node mobility traces and contact information. However, the previous works did not consider the spatial information of nodes, such as dwelling time at a location, and the transitivity of contacts in the prediction process of future encounter opportunities of nodes. In this paper, a novel mobility prediction-based routing (MPR) scheme is proposed for DTNs, in which the spatial information of nodes and contact transitivity are both taken into account. Specifically, a time-homogeneous semi-Markov process model is proposed to describe node mobility. By employing the semi-Markov model, we formulate the probability of a node destined to an area subject to the remaining time period constraint. The simulation results show that the proposed MPR scheme substantially improves delivery ratio and reduces delivery latency compared with traditional DTN routing schemes.

Mobility Prediction-Based Link Stability Routing Protocol for MANET

In mobile ad hoc networks, node mobility causes frequent link failures, thus invalidating the routes containing those links. Once a link is detected broken, an alternate route has to be discovered. That will impose significant affect on the route stability and the overall performance of the network. We suggest discovering contained stable links routes based on fuzzy control. When mobile node S wishes to send a packet to a destination mobile node D, node S transmits a ROUTE REQUEST (RREQ) message which contains its velocity and direction as a single local broadcast packet. When one mobile node i (it is not D) receiving RREQ, it first gets the velocity and direction of previous node, then estimates the link stability between two nodes based on fuzzy logic. When the link stability come up to a certain standard, node i adds its address to RREQ and forward it, otherwise, discard it. Simulations show that the proposed PLSR (Mobility Prediction-based Link Stability Routing Protocol) outperforms DVMP (Distance Vector protocol with Mobility Prediction that uses GPS) [8].

A Link Stability Prediction-Based Multicast Routing Protocol in Mobile Ad Hoc Networks

Mobile Ad Hoc networks have dynamic topology since all nodes have a random mobility behavior which increases rerouting frequency and degrades network communication performance.A more stable route can reduce rerouting frequency and prolong route lifetime.In this paper,we propose a novel link stability prediction model,via sampling the signal strength of the received data packets,and integrate the proposed prediction model into the traditional multicast routing protocol.Simulation results have been conducted to verify the efficiency of the proposed prediction scheme.Moreover,with a lower control overhead,this extended protocol LSPMR(Link Stability Prediction-based Multicast Routing Protocol) achieves a remarkable improvement in the packet delivery ratio,and decreases the average end-to-end delay.

Prediction-based routing as RWA in multilayer traffic engineering

Multilayer traffic engineering (MLTE) allows coping with ever-increasing and varying traffic demands in IP-over-Optical multilayer networks. It utilizes cross-layer TE (Traffic Engineering) techniques to provision optical lightpath capacity to the IP/MPLS (Internet Protocol/ Multi-Protocol Label Switching) logical topology on-demand. Such provisioning however causes optical connection arrival rates that pose strong performance requirements to Routing and Wavelength Assignment (RWA) strategies. Collecting up-to-date network information for the RWA with rapidly changing network states can be quite difficult. Exposing optical layer state information to the IP layer in the overlay model, or transforming this optical layer information in a workable representation in an integrated control plane is similarly problematic. Prediction-Based Routing (PBR) has been proposed as a RWA mechanism for optical transport networks; it bases routing not on possibly inaccurate or outdated network state, but instead on previous connections set-up. In this article, we propose to implement PBR as the RWA mechanism in the optical layer of a multilayer network, and use the predictive capabilities of PBR to expose dynamic optical network information into the multilayer traffic engineering algorithm with minimal control plane overhead. Some simulations show the benefits of using the PBR in the optical layer for MLTE purposes.

Traffic prediction-based routing algorithm over structured P2P networks

Routing has always been a great challenge for structured Peer-to-Peer (P2P) networks. There are a lot of representative structured routing algorithms for P2P networks, but these algorithms do not guarantee the quality of service (QoS) for real-time P2P applications. Addressing this challenge, a traffic prediction-based structured routing algorithm over P2P networks (TPSR) is proposed. Our contributions are described as below. We firstly analyze P2P traffic features and then build a wavelet neural-network predicting model. Secondly, we employ the traffic prediction model to predict the future state of each peer, such as normal or congestion, and let each peer update its routing table. In this way the requesting peers always get a resource list which contains the best resource peers. Simulation results demonstrate that TPSR has higher transmission success rate and lower end to end delay than other structured routing algorithms. Thus, TPSR can guarantee the QoS for real-time P2P applications.