Traffic flow prediction is crucial for efficient transportation systems, allowing better traffic management and decision-making. However, it’s a complex challenge due to its intricate spatial and temporal dependencies and fine-grained variations. Various network architectures, particularly graph neural networks (GNN) and transformers, have been proposed to handle these complexities. Nevertheless, as network architectures advanced, their performance improvements started to slow down due to increased complexity. This shift in focus led to an emphasis on input embeddings, which offer a promising way to build simpler, more effective models. This work introduces the spatial–temporal long-term embedding transformer (STLTEformer) framework for precise traffic prediction. A 5, 15, and 30-min interval embedding is designed to capture short-term fluctuations, intermediate trends, and long-term patterns, respectively. These embeddings equip the STLTEformer with the ability to comprehend intricate traffic patterns. Extensive experiments were conducted on four real-world datasets. The results demonstrate that STLTEformer achieves an improvement of up to 13.6% in MAE, 9.4% in RMSE, and 14% in MAPE over popular models based on GNN, and up to a 5% improvement in MAE, 1.9% in RMSE, and 7.5% in MAPE over popular transformer-based methods with good computational efficiency.

Traffic forecasting plays an important role in minimizing travel delays and enhancing road safety by using historical and real-time data to predict future traffic conditions. However, current state-of-the-art methods using graph representational learning fail to model localized complex and dynamic spatio–temporal relationships. Also, they struggle with segmenting long, context-aware traffic sequences, which are crucial for accurate forecasting. To address these issues, this work presents a novel selective state-focused graph attention network (SSGN) for traffic forecasting. SSGN utilizes a diagonally masked multihead adaptive graph attention that allows it to attend to relevant neighboring traffic nodes and analyze complex traffic patterns dynamically. Additionally, the selective state space layer is designed and integrated to model long context-aware traffic sequences to effectively capture both short and long-term sequences in traffic data. The effectiveness of SSGN is demonstrated using the simulation of urban mobility (SUMO) simulator and popular real-world benchmark datasets, namely PEMS03, PEMS04, PEMS07, and PEMS08. As a result, SSGN improved forecasting accuracy by$\sim$8% and$\sim$6% for short and long-term traffic forecasting, respectively, in comparison to other state-of-the-art methods.

Autonomous Vehicle (AV) navigation in dynamic environments is highly complex, with overtaking maneuvers adding complexity due to multiple sub-maneuvers and limited environmental perception. Recent advancements in Deep Reinforcement Learning (DRL) and sensors address a few challenges. Yet, the high dimensional sensor data and complex maneuvers slow RL agents in effectively perceiving the environment and performing the overtaking. Furthermore, the dynamic conditions and individual sensor data limit the RL agent's ability to localize and execute the precise sub-maneuvers. Thus, in this work, we propose TDRLO, a Deep Deterministic Policy Gradient (DDPG) based semi-Markov options acquired hierarchical reinforcement learning framework for AVs overtaking with LiDAR-RADAR fusion to tackle this issue. Our approach uses the option policy to control the sub-maneuvers execution and preprocesses sensor data for extracting crucial overtaking checkpoints and low dimensional environmental perception. Temporal Difference (TD) updates in the DDPG algorithm enhance episodic learning and incremental updates, while the option policy reduces the overtaking complexity. Moreover, the preprocessing of raw data and sensor fusion provides a better environmental perception and efficient overtaking in the CARLA simulator. We evaluated our approach using the National Highway Traffic Safety Administration (NHTSA) inspired overtaking pre-crash scenarios in CARLA. The result shows an average 20-30% improvement in average peak reward with stable critic values, alongside 100% completion rate, 10-30% least collision rate, and 20-40% more average speed compared to the baseline sate-of-the-art methods.

Connected Autonomous Vehicles (CAVs) rely on software code for functioning, which requires continuous maintenance and real-time over-the-air (OTA) updates to ensure optimal performance in dynamically changing environments. However, current OTA update systems operate on pre-defined schedules or reactive diagnostics, failing to adapt deployment strategies based on contextual insights such as subsystem performance degradation and user demands. Furthermore, existing approaches lack support for on-demand decision-making across heterogeneous CAV stacks, treating vehicle software as a monolith and limiting fine-grained interventions at individual functional modules. To address these limitations, this work presents AgenticOTA, a novel agentic AI pipeline for context-aware OTA update deploy ments in CAVs. To the best of the authors' knowledge, this is the first method that enables context-aware, fine-grained, and autonomous OTA deployments in CAVs. AgenticOTA utilizes LLM-driven agent integration to autonomously select validated container images and determine deployment viability based on real-time contextual information. The pipeline implements a modular, fine-grained software management layer that enables targeted updates and the selective replacement of individual functional modules in the event of failures, through containerized microservices, without impacting the entire software system. The effectiveness of AgenticOTA is demonstrated through comprehensive experiments against the state-of-the-art baselines. Experimental results demonstrate significant improvements, including a higher update success rate with fewer failures and rollbacks, as well as an orchestration initiation latency of 0.008 seconds, with a full end-to-end latency of 2.34s, across baseline methods.

Traditional graph neural networks (GNNs) lack scalability and lose individual node characteristics due to oversmoothing, especially in the case of deeper networks. This results in sub-optimal feature representation, affecting the model's performance on tasks involving dynamically changing graphs. To address this issue, we present Graph Selective state focused Attention Networks (GSANs) based neural network architecture for graph-structured data. The GSAN incorporates multi-head masked self-attention (MHMSA) and sequential state space modeling (S3M) layers to overcome the limitations of traditional GNNs. In GSAN, the MHMSA allows GSAN to dynamically emphasize crucial node connections, particularly in evolving graph environments. The S3M layer enables the network to track and adjust dynamically in changing node states and improving predictions of node behavior in varying contexts. The S3M layer enhances the generalization of unseen graph structures and provides interpretability by analyzing how node states affect the relative importance of links within the graph. With this, GSAN effectively outperforms inductive and transductive tasks and overcomes the issues that traditional GNNs experience. To analyze the performance behavior of GSAN, a set of state-of-theart (SOTA) comparative experiments are conducted on graphs benchmark datasets, including Cora, Citeseer, Pubmed network citation, and protein-protein-interaction datasets. As an outcome, GSAN improved the classification accuracy by 0.833%, 0.5%$, 0.37%, and 1.54 % on the F1-score, respectively. The code is publicly available at https://github.com/shikharvashistha/GSAN.

Road-Side Units (RSUs) are deployed along the road to facilitate Vehicle-to-Infrastructure (V2I) communication, a critical component of Vehicle-to-Everything (V2X) services. However, the presence of rogue RSUs, which are unauthorized access points, poses significant threats to V2X communications and safety applications. These rogue RSUs, installed by adversaries, can mimic legitimate RSUs and establish connections with vehicles, enabling various attacks such as data interception, spoofing, and denial of service. Therefore, Software-defined Networking (SDN) has been leveraged to employ various traffic engineering, network management, and secure verification of RSUs and vehicle functionalities. The SDN controller (SDNC), which manages RSUs, can periodically verify their identity. This mechanism ensures the association of vehicles with legitimate RSUs and the detection of rogue RSUs. To periodically verify the RSUs' identity, a novel Fiat-Shamir Transformation-enabled Non-Interactive Zero-knowledge Proof ($\text{Z K P}$) -based identity verification mechanism has been proposed. The RSUs are initially registered with an SDNC in this protocol. Subsequently, SDNC verifies their identity periodically using a unique ZKP-based challenge-response mechanism. As per the performance and security analysis, the proposed protocol surpasses state-of-the-art authentication protocols and achieves notable improvements.

Autonomous Vehicle (AV) driving involves complex maneuvers, with Obstacle Avoidance (OA) being one of the most challenging and safety critical tasks. While Reinforcement Learning (RL) has shown promise in achieving human like driving behavior, a single RL agent struggles to manage the multiple sub-maneuvers required for OA, particularly in safety critical scenarios. To address this, we propose an Option Policy inspired Hierarchical Deep Reinforcement Learning (OPDRL) framework that divides OA into sub tasks such as left lane change, straight driving, and right lane change. Each sub task is handled by a specialized RL agent, governed by a central master policy. This approach reduces training time, simplifies validation, and seamlessly incorporates traffic safety rules to ensure robust decision making in safety critical scenarios. The proposed method is validated using scenarios inspired by the National Highway Traffic Safety Administration (NHTSA) precrash scenarios in the CARLA simulator, demonstrating its effectiveness in handling OA maneuvers efficiently.

Autonomous Vehicle (AV) driving involves complex maneuvers, often constrained by poor environmental perception. While Deep Reinforcement Learning (DRL) and advanced sensor technologies like LiDAR and RADAR have improved AV performance, high dimensional sensor data poses challenges in critical tasks like lane changes and turns. To overcome these challenges, we propose a multimodal fusion of LiDAR and RADAR sensors with the Deep Deterministic Policy Gradient (DDPG) algorithm. Our approach preprocesses sensor data into low dimensional representations, enhancing the RL agent's environmental perception and decision making. This fusion, combined with Temporal Difference (TD) updates in the actor-critic network, improves maneuvering efficiency in the CARLA simulator. Results show a 100% task completion rate with adequate speed and time, achieving a 25% higher peak reward compared to state-of-the-art methods. The simulation videos for the same are available here https://www.youtube.com/playlist?list=PLnWGKVuAZgqlrdm21CEKW-S-Nr78qmkSX.

Optimizing vehicle waiting time is essential for an intelligent intersection management system as it directly influences traffic flow, public safety, and overall network performance. Conventional emergency vehicle management methods rely on static rules that are unable to adapt to dynamic traffic conditions. This paper presents MADQL-FFC, a multi-agent deep Q-learning framework combined with federated fog computing for real-time traffic signal control at the intersection that prioritizes emergency vehicles. In this framework, deep Q-network agents are deployed at individual intersections to make localized decisions, while a federated fog computing architecture is used in information sharing among neighboring agents for coordinated decision making. This helps in decentralized, low-latency coordination across the traffic network without the need for centralized control. The proposed approach is evaluated using realistic traffic simulations based on OpenStreetMap data of Gwalior City, India, implemented in the Simulation of Urban Mobility (SUMO) simulator. Comparative results against state-of-the-art methods demonstrate that MADQL-FFC achieves reductions in waiting time for all vehicle categories. Overall, the proposed model achieves a performance improvement of 5% to 32%, 12% to 44%, 4% to 46%, and 13% to 38% in average waiting time, average vehicle speed, average queue length, and average throughput respectively, when compared to state of the art methods.

Driving an Autonomous Vehicle (AV) in dynamic traffic is a critical task, as the overtaking maneuver being considered one of the most complex due to involvement of several sub-maneuvers. Recent advances in Deep Reinforcement Learning (DRL) have resulted in AVs exhibiting exceptional performance in addressing overtaking-related challenges. However, the intricate nature of the overtaking presents difficulties for a RL agent to proficiently handle all its sub-maneuvers that include left lane change, right lane change and straight drive. Furthermore, the dynamic traffic restricts the RL agents to execute the sub-maneuvers at critical checkpoints involved in overtaking. To address this, we propose an approach inspired by semi-Markov options, called Dynamic Option Policy enabled Hierarchical Deep Reinforcement Learning (DOP-HDRL). This innovative approach allows the selection of sub-maneuver agents using a single dynamic option policy, while employing individual DRL agents specifically trained for each sub-maneuver to perform tasks during overtaking in dynamic environments. By breaking down overtaking maneuvers into several sub-maneuvers and controlling them using a single policy, the DOP-HDRL approach reduces training time and computational load compared to classical DRL agents. Moreover, DOP-HDRL easily integrates basic traffic safety rules into overtaking maneuvers to offer more robust solutions. The DOP-HDRL approach is rigorously evaluated through multiple overtaking and non-overtaking scenarios inspired by the National Highway Traffic Safety Administration (NHTSA) pre-crash scenarios in the CARLA simulator. On an average, the DOP-HDRL approach shows 100% completion rate, 14% least collision rate, 25% optimal clearance distance, and 7% more average speed compared to the state-of-the-art methods.

The Social Internet of Vehicles (SIoV) is a modern method of vehicular networking that connects specialized vehicles to share and exchange information such as traffic congestion and traffic surveillance. This study aims to establish a network of emergency SIoV (E-SIoV) vehicles that frequently communicate during their movement across intersections, reducing waiting times and average queue length. To achieve this objective, the study proposes a novel software-defined vehicular networking (SDVN) based E-SIoV framework assisted by a Smart Traffic Light Controller (STLC). In the E-SIoV network, our proposed algorithm takes centre stage, dynamically generating a lane prioritization signal, and new cycle phase duration for the smart traffic light controller, which is deployed on the SDVN-Controller (SDVNC). We also proposed maxpressure-based STLC method, which generates effective control signals following the output of the SDVNC. The proposed framework is validated using the open-source Simulation of Urban MObility (SUMO) simulator on an Indian city’s OpenStreetMap. Further, the proposed framework achieved comparative performance improvements in the interval of 26% – 37%, 11.3% – 25.2%, 36.4% – 54.2%, and 6.9% – 20.6% for various performance metrics, i.e., average waiting time, average lane speed, average queue length, and average throughput respectively.

Abstract The fog computing environment expands the capabilities of cloud computing by moving computing, storage, and networking services closer to IoT devices. These resource‐constrained IoT devices often face challenges like high task failure rates and extended execution latency due to data traffic congestion. Distributing IoT services through task offloading across different layers of computing paradigms enhances QoS (Quality of Service) parameters. This endeavor aims to allocate custom workflow‐based real‐time tasks or jobs for processing across various cloud/fog/edge layers, optimizing QoS factors like makespan, energy consumption, and cost. In the fog computing environment, challenges arise due to uncertainties related to job execution locations and the ability to predict future user requirements. Fuzzy logic offers low‐complexity solutions for handling unpredictable and rapidly changing conditions. This paper proposes a hybrid fog‐cloud‐based computing architecture and an intelligent fuzzy logic‐based computation offloading approach. This approach effectively allocates workloads among edge, fog, and cloud layers, resulting in improvements in makespan time (7.51%), energy consumption (4.63%), and cost (13.60%). The proposed method selects suitable processing units or compute nodes for job execution, utilizing heterogeneous resources. Simulation results demonstrate that the proposed methodology outperforms current state‐of‐the‐art algorithms.

Social Internet of Vehicles (SIoV) is an emerging connected vehicular networking framework among specialized social vehicles to share and disseminate important information like traffic updates, weather conditions, parking slots, so on. This study aims to form an SIoV network among emergency vehicles for their frequent communication to improve the throughput, average waiting time, queue length, and speed during vehicular movement while crossing the intersection in the city. To address this, we propose a novel Smart Traffic Light Controller (STLC)-assisted Software-Defined Vehicular Networking (SDNV)-enabled SIoV framework for emergency vehicles. Emergency vehicles form an SIoV network by utilizing SDVN architecture in vehicle-to-vehicle and vehicle-to-infrastructure communication. The SDVN module is used to offer two essential services: (1) SIoV-based road-lane prioritization and (2) congestion prevention signal generation for the STLC. An SDVN-MP algorithm is proposed to generate an effective traffic light control signal with an SDVN controller feedback signal. Furthermore, to improve the SIoV movement in the city, two levels of prioritization are done: (1) SIoV and (2) the road lane with SIoV. The first level of prioritization is to assign higher weightage to the social vehicular entities, and the second level is to prioritize the respective road lane based on SIoV quantity. The proposed framework is validated through a realistic simulation study on the Indian city OpenStreetMap utilizing the Simulation of Urban MObility simulator. The experimental findings demonstrate that the SDVN-MP model enhances (state-of-the-art) comparative performance by 22.5–55.2%, 1.2–82.7%, 1.6–38.4%, and 1.8–12.4% for average waiting time, average speed, average queue length, and average throughput metrics, respectively.

Traffic flow prediction is essential for alleviating congestion and enhancing traffic management. While previous efforts have mainly concentrated on road-level predictions, the advancement of technology and the growing presence of automated vehicles have encouraged lane-level forecasting for more efficient driving and routing decisions. Therefore, this work presents a hierarchical model using recurrent neural networks (RNNs) that takes the lane-level information as the input and makes multiscale (lane level and road level) traffic flow predictions. Initially, the lane-level predictions are made using confined attention enabled RNN (CAERNN), built using bidirection long short-term memory (Bi-LSTM) and bidirection gated recurrent unit (Bi-GRU), and separately learning the periodic and temporal characteristics. Further, the features extracted by each lane are used to predict the traffic flow on the entire road. A novel confined attention mechanism is integrated into the Bi-LSTM module to improve the model's performance by focusing on recent, more relevant information in the traffic flow sequence. It is observed that the confined attention mechanism performs better than the conventional attention mechanism. Furthermore, the external features are integrated to improve the model's performance. The proposed model is evaluated on publicly available real-world data sets (in normal and COVID-19 scenarios), and the compared results with several state-of-the-art methods are evidence for the CAERNN's effectiveness.

Traffic congestion is a pressing issue worldwide, and machine learning (ML) methods are increasingly being used in Intelligent Transportation Systems (ITS) to address this problem. Deep hybrid models, in particular, have emerged as an efficient solution for traffic flow prediction. Among these models, Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) have been widely used to capture the temporal and periodic features of traffic data. The advancements in RNNs provide an opportunity to enhance the performance of existing models. Therefore, this work proposes a BiGRU-BiGRU model with two modules to extract temporal and periodic features from traffic data. Recurrent Neural Networks (RNNs) have proven to perform well using attention mechanism. However, there is a need for attention mechanism that strictly focuses on traffic dynamics and nearby data from the prediction points. Thus, a novel confined attention mechanism is proposed and incorporated into the first module to improve the model’s performance by focusing only on the recent relevant information in the traffic flow sequence. Furthermore, the external features are integrated to improve the model’s prediction performance. The proposed model is evaluated on the publicly available real-world dataset and compared with several baseline state-of-the-art methods. As an outcome, the model offers a reduction in the average value of RMSE, MAE, and MAPE for all the prediction horizons, that is ranged from 5.1% – 20.4%, 7.3% – 27.3%, and 6.1% – 56.6%, respectively.

Existing intersection management systems, in urban cities, lack in meeting the current requirements of self-configuration, lightweight computing, and software-defined control, which are necessarily required for congested road-lane networks. To satisfy these requirements, this work proposes effective, scalable, multi-input and multi-output, and congestion prevention-enabled intersection management system utilizing a software-defined control interface that not only regularly monitors the traffic to prevent congestion for minimizing queue length and waiting time but also offers a computationally efficient solution in real-time. For effective intersection management, a modified linear-quadratic regulator, i.e., Quantized Linear Quadratic Regulator (QLQR), is designed along with Software-defined Networking (SDN)-enabled control interface to maximize throughput and vehicles speed and minimize queue length and waiting time at the intersection. Experimental results prove that the proposed SDN-QLQR improves the comparative performance in the interval of 24.94%–49.07%, 35.78%–68.86%, 36.67%–59.08%, and 29.94%–57.87% for various performance metrics, i.e., average queue length, average waiting time, throughput, and average speed, respectively.

Congestion at signalized intersections can be alleviated by improving traffic signal control system's performance. In this context, Deep Reinforcement Learning (DRL) methods are increasingly gaining attention towards collaborative traffic signal control in vehicular networks for improving the traffic-flow. However, the existing collaborative methods lack in accounting the influence of neighbouring intersections traffic while working at a particular junction as built on the top of traditional client-server architecture. To address this, a Fog integrated DRL-based Smart Traffic Light Controller (STLC) cooperative framework is proposed via TCP/IP based communication among Fog node, Road Side Cameras (RSCs) and STLCs at the edge. The significant contributions of this work are: (1) A Fog node integrated DRL agent is proposed to minimize average waiting time and queue length, at the intersection, by generating Cycle Phase Duration (CPD) for the STLC via an appropriate coordination among neighboring intersections; (2) Utilizing the Fog node generated CPD as the feedback, a max-pressure based algorithm is proposed, for the STLC at the edge to improve the congestion at the intersection; (3) The performance of the proposed framework is analyzed on Indian cities OpenStreetMap utilizing the Simulation of Urban MObility (SUMO) simulator by varying arrival rate of the vehicles. The results demonstrate the effectiveness of the method over same line state-of-the-art methods.

Virtual machines (VMs) are a crucial technology for cloud computing, permitting multiple operating systems to run on a single physical host. Here, we propose a method for analyzing the performance of virtual machines in a cloud computing environment. The current approach of tracing both the host and virtual machines can be inefficient and may not be feasible for various reasons, such as security and privacy issues. We propose a host-only kernel tracing technique that uses only trace data generated on the host system. The trace data is then analyzed using the TraceCompass tool and two algorithms: Virtual CPU State Finder (VSF) and State Time Analysis (STA). The VSF algorithm generates a graphical view of the state of each thread running inside virtual machines for the identification of latency and performance degradation. The STA algorithm calculates the amount of time each virtual CPU spends in different states, providing important insights into the resource utilization and performance of virtual resources. In addition, our usage of the Trace Compass tool and EASE scripting allows more manageable analysis and visualization of the tracing data, making it accessible to a broader range of users. This method provides cloud providers with valuable information to maintain QoS and SLA parameters and improve the overall performance of running VMs.

Internet of Vehicles (IoV), as an emerging technology, has attracted much research over the years due to rapid advancements in computing paradigms and vehicular and wireless technologies. These advancements enable vehicle-to-everything (V2X) communication to offer various services such as traffic management, data exchange, and route scheduling. However, the increase in density and the malicious behaviour of vehicle users have seriously threatened security and privacy concerns in the network. These concerns are related to anonymity, privacy, and verification of the identity of vehicle users. It is crucial to preserve users' privacy to prevent traceability and linkability, besides authentication to track malicious activities in the network. Therefore, in this paper, a novel privacy-preserving lightweight zk-SNARK of polynomial-based authentication protocol is presented. The vehicles are initially registered with a trusted authority (TA) in this protocol. After that, they are authenticated by RSUs, followed by verification of authentication during vehicle handover between RSUs. The proposed protocol is implemented using the Mininet-WiFi tool, and its performance is analyzed by comparing communication latency and computation time for variable vehicular density. An informal security analysis is also done to prove that the proposed protocol provides anonymity, privacy, user verifiability, and untraceability features.

Towards achieving the goal of green transportation, the usage of battery powered electric vehicles (BEVs) has been continuously growing across the globe. However, considering the limited number of Charging Stations (CSs) in the cities, electric vehicle charging problem has become a challenging task, especially, due to the constraints of longer waiting time and dynamic pricing at the CHs. This issue has led to the degradation in Quality of Experience (QoE) for BEV drivers. Moreover, Charging Point (CP) service providers in the cities also suffer from lack of space which causes higher congestion at the CSs. In this context, we propose ChaseMe, a heuristic scheme for optimizing CS management by scheduling BEVs based on availability and type (fast/ultra-fast) of CPs by considering delay and charging time for CPs reservation. The proposed heuristic scheme consists of two soft computing techniques i) Harris Hawk Optimization (HHO) and ii) Fuzzy Inference System (FIS). Former technique is used to map the CP reservation requests to the best-suited CS by considering Quality of Service (QoS) parameters and acting as a global optimizer. FIS locally manages CPs at a particular CS in coordination with proposed meta-heuristic technique. The experimental results prove the benefits of the proposed ChaseMe framework as compared to the state-of-the-art techniques considering various charging metrics for BEVs.

This work proposes a traffic-light scheduling framework using the deep reinforcement learning technique to balance the traffic flow and to prevent congestion in the dense regions of the city via a software-defined control interface. A software-defined control enabled architecture is proposed to monitor the traffic conditions and it generates the traffic light control signal (Red/Yellow/Green) accordingly. For an intelligent traffic light control signal, a Deep Reinforcement Learning (DRL) model is proposed which takes vehicular dynamics as inputs from the real-time traffic environment such as heterogeneous vehicles count, speed, traffic density etc. To determine the congestion, a threshold policy is proposed and deployed on control server which generates the congestion prevention signal. A DRL agent operates in the coordination of congestion prevention signal and generates an effective traffic light control signal. The proposed model is evaluated through a realistic simulation on Indian city OpenStreetMap by using a well-known open-source simulator (SUMO). The comparative results show that the proposed solution improves several performance metrics such as average waiting time, throughput, average queue length, and average speed in the interval of 28.34% – 66.62%, 24.76% – 66.60%, 30.89% – 69.80%, and 16.62% – 43.67% respectively over other states of the art approaches.

Due to rapid increment in the number of vehicles but limited physical transport infrastructure, cities are crowded with vehicles which led to high congestion. The congestion in cities causes many environmental issues such as noise pollution, air pollution, carbon emissions, etc. This work proposes a Software Defined-Control enabled Traffic Light Control System (SDTLCS), which detects congestion in the city and generates traffic light control signals to minimize congestion. SDTLCS is utilized to generate the congestion control signals at the traffic light junctions considering the several vehicular dynamics of the current traffic state. This model assigns weights to the different types of vehicles, and it considers the cumulative sum of the weights corresponding to vehicles on the road lanes to determine the time duration for each phase. The proposed architecture consists of control nodes as the traffic light controllers and the normal sensor nodes lying on the data plane, i.e., roadside units/other sensors, to collect the traffic data. This proposed architecture has been assessed by running the simulation over a map of the Gwalior district using the well-known simulation tool, i.e., Simulation of Urban MObility (SUMO). The results showed that the proposed architectural model was successful in order to improve several performance metrics, i.e., average waiting time, average speed, etc in comparison to other state-of-the-art methods.

Social Internet of Vehicles (SIoV) is an evolving vehicular networking framework integrating the next generation smart devices with vehicular communications. Green computing and communication under disruptive vehicular environment is one of the challenging tasks for enabling SIoV. In this context, green traffic data dissemination in SIoV environments is modelled as an NP-hard problem focusing on heterogeneous traffic data, transmission distance from next generation smart devices and probabilistic delay in transmissions due to disruptive vehicular environment. An adopted meta-heuristic solution namely Two-Way Particle Swarm Optimization (TWPSO) is developed for the green traffic data dissemination problem in SIoV considering software defined vehicular network architecture. Extensive simulation experiments were performed to assess the performance of TWPSO as compared to the state-of-the-art techniques. The critical analysis of the comparative results attest the green computing oriented benefits of TWPSO under real SIoV environments.

Intelligent Transportation System (ITS) has been emerged an important component and widely adopted for the smart city as it overcomes the limitations of the traditional transportation system. Existing fixed traffic light control systems split the traffic light signal into fixed duration and run in an inefficient way, therefore, it suffers from many weaknesses such as long waiting time, waste of fuel and increase in carbon emission. To tackle these issues and increase efficiency of the traffic light control system, in this work, a Dynamic and Intelligent Traffic Light Control System (DITLCS) is proposed which takes real-time traffic information as the input and dynamically adjusts the traffic light duration. Further, the proposed DITLCS runs in three modes namely Fair Mode (FM), Priority Mode (PM) and Emergency Mode (EM) where all the vehicles are considered with equal priority, vehicles of different categories are given different level of priority and emergency vehicles are given at most priority respectively. Furthermore, a deep reinforcement learning model is also proposed to switch the traffic lights in different phases (Red, Green and Yellow), and fuzzy inference system selects one mode among three modes i.e., FM, PM and EM according to the traffic information. We have evaluated DITLCS via realistic simulation on Gwalior city map of India using an open-source simulator i.e., Simulation of Urban MObility (SUMO). The simulation results prove the efficiency of DITLCS in comparison to other state of the art algorithms on various performance parameters.

Load-balanced scheduling deals with the uniform allocation of workload to a set of computational resources in order to optimize some characteristic metrics such as makespan, resource utilization and relative load imbalance. As such, the load balancing is an NP-hard problem which becomes more complex when heterogeneity in the workload and the computing resources are introduced. Workload heterogeneity is defined by the types of the workload whereas CPU resources can be heterogeneous in terms of memory/cache hierarchy, clock speed, etc. For load balancing in a truly heterogeneous multicore system, this work proposes a model by incorporating a related heuristic into Genetic Algorithm (GA) to generate the priorities of the workload and the computing resources by exploiting their heterogeneity characteristics. The priorities play a significant role in the effective mapping of the workload on the computing resources. A good number of simulation experiments are carried out to study the performance of the proposed model besides comparing it with some contemporary GA-based models. Results indicate that incorporating the relevant heuristic into GA makes a significant load-balanced scheduling, especially for heavy workload applications.