Routing Decisions Research Articles

Towards Robust Routing: Enabling Long-Range Perception with the Power of Graph Transformers and Deep Reinforcement Learning in Software-Defined Networks

Deep Reinforcement Learning (DRL) has demonstrated promising capabilities for routing optimization in Software-Defined Networks (SDNs). However, existing DRL-based routing algorithms are struggling to extract graph-structured information and constrained to a fixed topology, suffering from the lack of robustness. In this paper, we strengthen the advantages of Graph Neural Networks (GNNs) for DRL-based routing optimization and propose a novel algorithm named Graph Transformer Star Routing (GTSR) to enhance robustness against topology changes. GTSR utilizes the multi-agent architecture to enable each node to make routing decisions independently, and introduces a Graph Transformer to equip agents with the capabilities of handling topology changes. Furthermore, we carefully design a global message-passing mechanism with a virtual star node and a path-based readout method, enhancing the long-range perception of traffic and the detection of potential congestion for routing decision-making. Moreover, we construct a multi-agent cooperation mechanism to facilitate the learning of universal perceptual strategies and reduce the amount of computation. Extensive experiments on multiple real-world network topologies demonstrate that GTSR is capable of adapting to unseen topology changes without retraining and decreases end-to-end latency by at least 47% and packet loss rate by at least 10% compared to all baselines, highlighting strong robustness.

An Intelligent Fuzzy-Based Routing Protocol for Vehicular Opportunistic Networks

Opportunistic networks are characterized by intermittent connectivity and dynamic topologies, which pose significant challenges for efficient message delivery, resource management, and routing decision-making. This paper introduces the Fuzzy Control Routing Protocol, a novel approach designed to address these challenges by leveraging fuzzy logic to enhance routing decisions and improve overall network performance. The protocol considers buffer occupancy, angle to destination, and the number of unique connections of the target nodes to make context-aware routing decisions. It was implemented and evaluated using the FuzzyC framework for simulations and the opportunistic network environment simulator for realistic network scenarios. Simulation results demonstrate that the Fuzzy Control Routing Protocol achieves competitive delivery probability, efficient resource utilization, and low overhead compared to the Epidemic and MaxProp protocols. Notably, it consistently outperformed the Epidemic protocol across all metrics and exhibited comparable delivery probability to MaxProp while maintaining significantly lower overhead, particularly in low-density scenarios. The results demonstrate the protocol’s ability to adapt to varying network conditions, effectively balance forwarding and resource management, and maintain robust performance in dynamic vehicular environments.

LIA: Latency-Improved Adaptive routing for Dragonfly networks

Low-diameter network topologies require non-minimal routing, such as Valiant routing, to avoid network congestion under challenging traffic patterns like the so-called adversarial. However, this mechanism tends to increase the average path length, base latency, and network load. The use of shorter non-minimal paths has the potential to enhance performance, but it may also introduce congestion depending on the traffic patterns. This paper introduces LIA (Latency-Improved Adaptive), a routing mechanism for Dragonfly networks which dynamically exploits minimal and non-minimal paths. LIA harnesses the traffic counters already present in contemporary switches to determine when it is safe to shorten non-minimal paths and to adjust routing decisions based on their information about the network conditions. Evaluations reveal that LIA achieves nearly optimal latency, outperforming state-of-the-art adaptive routing mechanisms by reducing latency by up to 30% while maintaining stable throughput and fairness.

MODRS: A Multi-Objective Deep Learning Algorithm for Optimizing Routing and Scheduling in LEO Satellite Networks

The demand for high-quality Direct-to-Home (D2H) television broadcasting services delivered via Low Earth Orbit (LEO) satellite constellations has surged in recent years. To address the growing needs of viewers, satellite communication must optimize the scheduling and routing of signals while balancing conflicting objectives. This research presents a novel approach named as Multi-Objective Deep Routing and Scheduling (MODRS) algorithm that is designed to tackle the challenges of signal latency minimization, bandwidth utilization maximization, and viewer demand satisfaction. The Multi-Objective Deep Neural Network (MODNN) is implemented in this paper to make intelligent routing and scheduling decisions for balancing multiple objectives. To enhance the learning process and provide training stability, the experience replay is used and the epsilon-greedy strategy is included to balance exploitation and exploration strategies. The Pareto-front concept is used for efficient D2H television broadcasting in the LEO satellite constellation. The experimental validation is conducted based on low-latency broadcasting, high-bandwidth utilization, viewer demand flexibility, adaptive signal strength and resource allocation efficiency. Using a series of simulated scenarios, this paper explores the versatility and robustness of MODRS, showcasing its exceptional performance in real-time, resource-efficient, disaster recovery, and rural broadcasting contexts. The findings indicate that MODRS is well-suited for a wide range of real-world applications, from low-latency broadcasting and disaster recovery to cost-effective rural expansion, enhancing the quality and accessibility of D2H television services. The MODRS algorithm emerges as a transformative solution for satellite communication optimization, ensuring viewer satisfaction and operational efficiency.

The vehicle routing problem as applied to residential solid waste collection operations: Systematic literature review

The accelerated growth of cities, population increase and economic development have leveraged waste generation globally. This trend is expected to continue, with a significant increase projected in the coming years. Therefore, efficient waste management has become a crucial concern for local, national and international authorities. Transportation plays a key role in waste collection and disposal, being directly related to traffic congestion, fuel consumption and environmental pollution. Despite the existing studies on household waste collection, there is a gap in the literature regarding routing for residential waste collection in medium-sized cities, especially in emerging and frontier developing countries. Therefore, this study seeks through the science tree metaphor and PRISMA methodology, to find studies focused on the vehicle routing problem in waste collection operations, considering aspects such as Modeling approaches and solution techniques, applied Vehicle Routing Problems variants, objective functions, decision variables and constraints, applications in real environments, applied algorithms, and studies considering uncertainty and real conditions. A methodological outline of Vehicle Routing Problems in waste collection operations is presented, where central research topics are identified such as processes developed with Geographic Information System and their integration with exact methods, time windows, multi-objective capacitated vehicle routing problems, the application of stochastic models consider the uncertainty in waste collection, which has allowed including future prediction and optimization as prediction models, based on neural networks, to foresee uncertain conditions of the operations. This article analyzes the evolution in the optimization of municipal solid waste collection routes since 1964, highlighting the transition from iterative models to advanced technologies and multi-objective approaches. The importance of tools such as 3D Geographic Information System and heuristic/metaheuristic algorithms in improving planning and efficiency, despite limitations in the face of uncertainty, is emphasized. The systematic review shows a trend towards sustainable and efficient solutions, indicating future directions for research in urban waste management.

On the Concept of Opportunity Cost in Integrated Demand Management and Vehicle Routing

Integrated demand management and vehicle routing problems are characterized by a stream of customers arriving dynamically over a booking horizon and requesting logistical services, fulfilled by a given fleet of vehicles during a service horizon. Prominent examples are attended home delivery and same-day delivery problems, where customers commonly have heterogeneous preferences regarding service fulfillment and requests differ in profitability. Thus, demand management methods are applied to steer the booking process to maximize total profit considering the cost of the routing decisions for the resulting orders. To measure the requests’ profitability for any demand management method, it is common to estimate their opportunity cost. In the context of integrated demand management and vehicle routing problems, this estimation differs substantially from the estimation in the well-examined demand management problems of traditional revenue management applications as, for example, found in the airline or car rental industry. This is because of the unique interrelation of demand control decisions and vehicle routing decisions as it inhibits a clear quantification and attribution of cost, and of displaced revenue, to certain customer requests. In this paper, we extend the theoretical foundation of opportunity cost in integrated demand management and vehicle routing problems. By defining and analyzing a generic Markov decision process model, we formally derive a definition of opportunity cost and prove opportunity cost properties on a general level. Hence, our findings are valid for a wide range of specific problems. Further, based on these theoretical findings, we propose approximation approaches that have not yet been applied in the existing literature, and evaluate their potential in a computational study. Thereby, we provide evidence that the theoretical results can be practically exploited in the development of solution algorithms. Funding: This work was supported by the University of the Bundeswehr Munich. Supplemental Material: The online appendices are available at https://doi.org/10.1287/trsc.2024.0644 .

Enhancing CNN Weights for Improved Routing in UAV Networks for Catastrophe Relief with MSBO Algorithm

UAVs have become key in various applications lately, from catastrophe relief to environmental monitoring. The plan of powerful and reliable directing protocols in UAV networks is seriously hampered by the dynamic and habitually eccentric mobility patterns of UAVs. This study proposes a novel technique to beat these challenges by utilizing the Modified Smell Bees Optimization (MSBO) algorithm to upgrade the weights of CNNs. This study’s principal objective is to further develop UAV network routing decisions by using CNNs’ ability for design recognition and the Modified SBO’s optimization abilities. Our methodology comprises of randomly relegating CNN weights to a populace of bees at start, evaluating their wellness by fitness of directing performance, and iteratively fine-tuning these weights utilizing local and global search procedures got from bee searching. Broad simulations and performance evaluations show that our recommended approach incredibly expands the general dependability of UAV’s, brings down communication latency, and improves directing productivity. Future exploration in UAV network improvement gives off an impression of being going in a promising direction with the integration of CNNs for pattern recognition and the Modified SBO for weight enhancement. In addition to progressing UAV routing conventions, this work sets out new open doors for machine learning applications of bio-inspired optimization algorithms.

Modeling and generating user‐centered contrastive explanations for the workforce scheduling and routing problem

AbstractIn the last decade, explainability has been attracting much attention in the machine learning community. However, this research topic extends beyond this field to encompass others such as operations research and combinatorial optimization (CO). This paper addresses this issue in the case of the workforce scheduling and routing problem (WSRP), a CO problem involving human resource allocation and routing decisions. We first introduce a novel mathematical framework that models the process of explaining solutions to the end‐users of a WSRP‐solving system. Then, we present original algorithmic methods to generate explanation texts employing a high‐level vocabulary adapted to such end‐users. Explanations are user‐centered, local, and contrastive. They are triggered by end‐user questions about various topics regarding a solution of a WSRP instance. Both questions and explanations are expressed as texts thanks to templates. Numerical experiments show that the algorithms generating explanation texts have execution times that are mostly compatible with the online use of explanations in an interactive system.

Dynamic open time‐dependent traveling salesman problem with speed optimization

AbstractIncreased awareness of people of the problems caused by CO2 emissions brings companies to consider environmental issues in their distribution systems. The rapid advance in technology allows logistics companies to tackle with dynamic nature of distribution networks (e.g., a change in the vehicle speed due to unexpected events). The planned routes at the beginning of the time horizon could be subject to modification at any point in time to account for the recent traffic information. This study addresses a dynamic open time‐dependent traveling salesman problem. The problem also involves speed optimization that aims to find optimal vehicle speed in a dynamic setting by respecting real‐time traffic conditions. We develop a mixed integer linear programming (MILP) formulation for the addressed problem to determine routing and vehicle speed decisions. Furthermore, a MILP‐based myopic‐clustering decomposition heuristic algorithm has been introduced to solve large‐sized instances within reasonable solution times. The use of the heuristic algorithm provides decision‐makers with a responsiveness capacity by enabling fast incorporation of dynamically observed data during operations. The numerical analyses demonstrate the potential benefits of employing the proposed tools.

Fuzzy‐Markov Routing Policy and Priority‐Based Load Balancing for Cognitive Radio Ad Hoc Networks

ABSTRACTA cognitive radio ad hoc network (CRAHNs) is an infrastructure‐free network containing a cognitive radio, which can use the spectrum resources effectively through an adaptive change of parameter settings and decision‐making. Hence, it enhances the spectrum efficacy for satisfying the growing mobile traffic requests. In multihop CRAHNs, in order to ensure a reliable transmission and energy efficiency, the routing protocol should consider the metrics of channel quality, link stability, and energy consumption. In this paper, a Fuzzy‐Markov routing policy and priority‐based load balancing algorithm (FMRP‐PLB) for CRAHNs is designed. In this protocol, a combined routing metric is derived using delay, energy rate, and link expiration time metrics. For modeling the channel state, a Fuzzy‐Markov decision model is designed, in which the channel states and spectrum availabilities of SU are modeled as state transition matrices. Then, optimum routing decisions are made using the combined routing metric and the predicted transmission success probability. A load balancing metric (LBM) is derived in terms of available link capacity, remaining buffer size of node, and back‐off delay. During data transmission, based on the traffic priority and measured levels of LBM, the optimum paths are selected. Simulation results using NS2 suggest that FMRP‐PLB attains an increased packet delivery ratio with reduced delay and energy consumption.

Energy-based approach to the assessment of traffic flow

This article focuses on modeling vehicle acceleration noise in different road conditions, emphasizing urban, highway, and rural roads in Ukraine. Acceleration noise, which refers to the fluctuations in a vehicle's acceleration, is a critical factor in vehicle safety, fuel efficiency, and driving comfort. The research aims to improve current vehicle dynamics models by integrating multi-body dynamics and machine learning algorithms, allowing for more precise predictions of acceleration variability in real-time. The study is based on the existing literature, showing that road surface quality significantly affects acceleration noise. With frequent stop-and-go traffic, urban roads produce moderate but irregular noise patterns. Highways show stable acceleration noise at moderate speeds, but noise increases sharply as vehicles approach higher speeds due to aerodynamic forces. Rural roads, especially those in poor condition, exhibit the highest variability in acceleration noise, even at low speeds. The proposed model has been validated using real-world data. It demonstrates a strong correlation between the predictions and actual vehicle behavior on various road types. One of the key innovations in this research is the use of machine learning to adjust model parameters in real-time dynamically. This adaptive approach enhances the model’s accuracy and applicability, especially in intelligent transport systems. The model can inform traffic management strategies, allowing for real-time adjustments to speed limits, traffic signals, and routing decisions based on road conditions. This contributes to safer, more efficient, and sustainable transport systems, particularly in regions with inconsistent road infrastructure. The research concludes that integrating acceleration noise modeling into intelligent transport systems can significantly improve traffic flow and vehicle safety. Future research will expand the dataset to include a broader range of vehicle types and road conditions, further refining the model's predictive capabilities.

A Hybrid Caching Scheme with Dynamic Forwarding Strategy in Information‐Centric Network

In this era of huge data traffic, the information‐centric network (ICN) is a switching strategy from conventional host‐centric communication to a new data‐centric one. In‐network caching an integral part of ICN can reduce the shortcomings of today's location‐based internet paradigm. As ICN has limited caching capability, the decision of optimal routing and content placement are the major challenges. In this study, we suggest a hybrid caching with a dynamic forwarding (HCDF) strategy which takes advantage of the off‐path hash routing scheme and on‐path caching scheme. To facilitate both caching schemes, a fraction of the caching space is allotted in each cache node for local caching. At the user‐end segment, an estimation‐based content placement (ECP) policy is designed using content popularity state and cache node position. This policy helps to cache popular content near the consumer's location using the shared cache space. At the server‐end segment, the HCDF scheme dynamically selects the most appropriate routing strategy among three strategies (symmetric, asymmetric, and multicast) based on hop count and path stretch. To demonstrate the effectiveness of HCDF, extensive simulation on real‐world internet topologies has been carried out. From our investigation, it is observed that the suggested approach exhibits an impressive performance in terms of cache hit, latency, and average link load compared to other standard hash routing and well‐known on‐path caching schemes. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Stochastic scheduling and routing decisions in online meal delivery platforms with mixed force

This paper investigates stochastic scheduling and routing problems in the online meal delivery (OMD) service. The huge increase in meal delivery demand requires the service providers to construct a highly efficient logistics network to deal with a large-volume of time-sensitive and fluctuating fulfillment, often using inhouse and crowdsourced drivers to secure the ambitious service quality. We aim to address the problem of developping an effective scheduling and routing policy that can handle real-life situations. To this end, we first model the dynamic problem as a Markov Decision Process (MDP) and analyze the structural properties of the optimal policy. Then we propose four integrated approaches to solve the operational level scheduling and routing problem. In addition, we provide a continuous approximation formula to estimate the bounds of required fleet size for the inhouse drivers. Numerical experiments based on a real dataset show the effectiveness of the proposed solution approaches. We also obtain several managerial insights that can help decision makers in solving similar resource allocation problems in real-time.

A reinforcement learning approach for the online dynamic home health care scheduling problem.

Over recent years, home health care has gained significant attention as an efficient solution to the increasing demand for healthcare services. Home health care scheduling is a challenging problem involving multiple complicated assignments and routing decisions subject to various constraints. The problem becomes even more challenging when considered on a rolling horizon with stochastic patient requests. This paper discusses the Online Dynamic Home Health Care Scheduling Problem (ODHHCSP), in which a home health care agency has to decide whether to accept or reject a patient request and determine the visit schedule and routes in case of acceptance. The objective of the problem is to maximize the number of patients served, given the limited resources. When the agency receives a patient's request, a decision must be made on the spot, which poses many challenges, such as stochastic future requests or a limited time budget for decision-making. In this paper, we model the problem as a Markov decision process and propose a reinforcement learning (RL) approach. The experimental results show that the proposed approach outperforms other algorithms in the literature in terms of solution quality. In addition, a constant runtime of less than 0.001 seconds for each decision makes the approach especially suitable for an online setting like our problem.

Research on High-Efficiency Routing Protocols for HWSNs Based on Deep Reinforcement Learning

In heterogeneous wireless sensor networks (HWSNs), optimizing energy efficiency presents significant challenges due to variations in node energy levels and the complexity of the network environment. This paper introduces an energy efficiency optimization algorithm for HWSNs based on the Deep Q-Network (HDQN). The algorithm aims to address these challenges by selecting the optimal information transmission path. The HDQN leverages energy differences between nodes and real-time environmental data to enhance network efficiency. Its reward function takes into account node distance, remaining energy, and relay node count to balance node participation and minimize overall energy consumption. The Deep Q-Network (DQN) uses the mean squared error for precise reward estimation, and an improved packet header structure supports effective routing decisions. Simulation results show that the HDQN significantly outperforms existing algorithms—EEHCHR, 2L-HMGEAR, NCOGA, DEEC, and SEP—in terms of energy efficiency, network lifetime, and robustness, demonstrating its potential to advance the performance of HWSNs. The research results of the paper provide a theoretical basis for future energy efficiency research in wireless communication and contribute to the study of the new generation of wireless networks.

Performance evaluation for Q-learning based anycast routing protocol in unmanned aerial vehicle networks with multiple base stations

Unmanned Aerial Vehicle (UAV) networks can be used for data transmission in emergency scenarios, relaying data from ground users to base stations (BSs). While UAV networks collaborating with multi-BSs can significantly enhance performance, existing UAV routing protocols predominantly focus on unicast routing and often neglect critical aspects such as base station discovery. In addition, the high mobility of UAVs and rapid changes in network topology also pose great challenges for existing multi-BS routing protocols to maintain efficient data transmission. Aiming at the above problems, this paper abstracts the routing of multi-base station UAV networks as anycast routing for dynamic networks and proposes a distributed anycast routing protocol called QARP to improve the data transmission performance. In QARP, base stations can be discovered automatically and parameters of Q-learning are dynamically adjusted to improve the efficiency of data transmission. The Link Duration Estimation is used to influence routing decision and dynamically adjust the hello message interval. A multiple base stations transmission value function is designed to indicate the performance of data transmission and is used to calculate the reward and update Q-table. The experimental results show that the QARP proposed in this paper outperforms existing multi-BS routing and Q-learning based routing protocols in terms of delay, packet delivery ratio and throughput in single base station and multiple base stations scenarios.

Development of HTC-DBSCAN: A Hierarchical Trajectory Clustering Algorithm with Automated Parameter Tuning

Existing route-clustering methods often fail to identify abnormal sections or similarities between routes, mainly when working with large or long datasets. While sub-route clustering can detect regional patterns, it struggles to accurately capture the overall route structure. The present study proposes a new ship route-clustering method that enhances computational efficiency and noise recognition while addressing these limitations. We refined Automatic Identification System data via four data-cleaning processes and applied a statistical distance measurement to assess ship trajectory similarity. Dimensionality reduction was then used to facilitate clustering. The clustering of ship route similarities is non-parametric and can be applied to datasets not separated based on density to find clusters of various densities. Density-Based Spatial Clustering of Applications (DBSCA) applies to many research fields; using the DBSCA with Noise (DBSCAN) algorithm, we propose an improved DBSCAN algorithm that automatically determines the parameters Epsilon and MinPts. In this study, as a core ship route-clustering process, we propose a sub-route clustering process by setting the distance and density of data points to clear standards for re-analysis and completion. The proposed approach demonstrates markedly enhanced clustering performance, offering a more sophisticated and efficient basis for ship route decision-making.

GSADDQN: Combining GraphSAGE and reinforcement learning for routing optimization in software-defined optical transport network

As a result of rapid development of network communication technology, optical transport network (OTN) traffic has also experienced rapid growth in terms of information volume scale, traffic complexity, and spatiotemporal distribution dynamics. Because the OTN traffic demand has complex spatiotemporal fluctuations, the traditional deep reinforcement learning (DRL) algorithm has been applied to the routing optimization of software-defined OTNs. However, the traditional DRL algorithm has problems such as slow convergence, weak generalization ability, and load imbalance when performing routine tasks. To address these issues, we propose a graph sampling and aggregation (GraphSAGE)-based dueling deep Q-network (GSADDQN) algorithm for software-defined OTN routing optimization. First, we design a DRL-based routing decision model to find the best routing strategy for each optical network’s source–destination traffic demand. Second, considering the sparse connection characteristics of optical network nodes, we use sampling neighbors and a deep aggregation mechanism as the neural network model of the Dueling Deep Q-Network (Dueling DQN) algorithm so that the reinforcement learning agent can consciously aggregate important network information and improve the model’s convergence performance and generalization ability. Finally, we design simulation routing experiments based on Gym and evaluate the algorithm’s load balancing and generalization capabilities for different network topologies. The experimental results show that the GSADDQN algorithm has good convergence performance and load balancing ability in routing optimization of optical transmission networks and can generalize new network structures, maintaining good decision-making ability even during network node failures.

Web-based spatial decision support system for optimum route to forest fires: A case of Viphya plantations

Efficient access to fire incidents is crucial for successful firefighting operations. This study aimed at developing a web-based spatial decision support system (SDSS) to determine optimal routes to forest fires and risk zones in the Viphya Plantations, Malawi. The system integrates remote sensing analysis to identify fire risk zones and a web-based SDSS to suggest optimal response routes. Remote sensing data was used to map areas prone to forest fires based on factors such as land use/cover type, terrain, and anthropogenic activities. These risk zones were incorporated into the GIS routing decision support system, enabling the generation of optimal routes from fire stations to fire risk zones and reported fire cases. System testing demonstrated the SDSS's capability to provide optimum routing options targeting fire risk hotspots and reported incidents within the plantations. The SDSS facilitated the identification of optimal routes to mitigate transportation costs and provided insights into spatial patterns of fire vulnerability, revealing areas that may be inaccessible within the optimal timeframe. This highlighted the necessity of establishing additional fire stations in high-risk regions to enhance rapid response times. The web-based SDSS proved to be an effective decision support tool for optimizing resource allocation and improving emergency response coordination for fighting forest fires in the Viphya Plantations.

Distance and energy aware DEAODV routing protocol in disastrous situation

In the disastrous or emergency situation a reliable and robust ad hoc mobile network communication is important. The natural disaster when occurs in the urban populated areas which damage Information technology infrastructure and other valuable assets within a movement. In such emergency situation when the disaster victims stuck in debris, lifesaving of people are important. The purpose of this study is to enhance lifetime and improve network performance when the lives of disaster victims are matters. Distance and Energy aware AODV (DEAODV) reactive routing protocol enhance the network performance and ensure the reliable data transmission during crisis situation. The DEAODV reactive routing protocol considered node Energy and shortest distance as a routing metrics during route decision process. DEAODV routing protocol is compared with traditional AODV routing protocol to evaluate the performance of network. The proposed routing protocol is more efficient in emergency situation than AODV in terms of Packet Delivery Ratio, End to End Delay and Consumed Energy.