Traffic safety at road–rail level crossings using a driving simulator and traffic simulation

Several intelligent transportation systems (ITS) were used with an advanced driving simulator to assess its influence on driving behavior. Three types of ITS interventions were tested: video in vehicle, audio in vehicle, and on-road flashing marker. The results from the driving simulator were inputs for a developed model that used traffic microsimulation (VISSIM 5.4) to assess the safety interventions. Using a driving simulator, 58 participants were required to drive through active and passive crossings with and without an ITS device and in the presence or absence of an approaching train. The effect of changes in driver speed and compliance rate was greater at passive crossings than at active crossings. The slight difference in speed of drivers approaching ITS devices indicated that ITS helped drivers encounter crossings in a safer way. Since the traffic simulation was not able to replicate a dynamic speed change or a probability of stopping that varied depending on ITS safety devices, some modifications were made to the traffic simulation. The results showed that exposure to ITS devices at active crossings did not influence drivers’ behavior significantly according to the traffic performance indicator, such as delay time, number of stops, speed, and stopped delay. However, the results of traffic simulation for passive crossings, where low traffic volumes and low train headway normally occur, showed that ITS devices improved overall traffic performance.

Optimisation techniques for planning automatic under frequency load shedding in New Zealand’s power system

Electricity generation is vital in developed countries to power the many mechanical and electrical devices that people require. Unfortunately electricity generation is costly. Though electricity can be generated it cannot be stored efficiently. Electricity generation is also difficult to manage because exact demand is unknown from one instant to the next. A number of services are required to manage fluctuations in electricity demand, and to protect the system when frequency falls too low. A current approach is called automatic under frequency load shedding (AUFLS). This article proposes new methods for optimising AUFLS in New Zealand’s power system. The core ideas were developed during the 2015 Maths and Industry Study Group (MISG) in Brisbane, Australia. The problem has been motivated by Transpower Limited, a company that manages New Zealand’s power system and transports bulk electricity from where it is generated to where it is needed. The approaches developed in this article can be used in electrical power systems anywhere in the world.

Reinforcement Learning With Function Approximation for Traffic Signal Control

We propose, for the first time, a reinforcement learning (RL) algorithm with function approximation for traffic signal control. Our algorithm incorporates state-action features and is easily implementable in high-dimensional settings. Prior work, e. g., the work of Abdulhai et al., on the application of RL to traffic signal control requires full-state representations and cannot be implemented, even in moderate-sized road networks, because the computational complexity exponentially grows in the numbers of lanes and junctions. We tackle this problem of the curse of dimensionality by effectively using feature-based state representations that use a broad characterization of the level of congestion as low, medium, or high. One advantage of our algorithm is that, unlike prior work based on RL, it does not require precise information on queue lengths and elapsed times at each lane but instead works with the aforementioned described features. The number of features that our algorithm requires is linear to the number of signaled lanes, thereby leading to several orders of magnitude reduction in the computational complexity. We perform implementations of our algorithm on various settings and show performance comparisons with other algorithms in the literature, including the works of Abdulhai et al. and Cools et al., as well as the fixed-timing and the longest queue algorithms. For comparison, we also develop an RL algorithm that uses full-state representation and incorporates prioritization of traffic, unlike the work of Abdulhai et al. We observe that our algorithm outperforms all the other algorithms on all the road network settings that we consider.

Reinforcement learning with average cost for adaptive control of traffic lights at intersections

We propose for the first time two reinforcement learning algorithms with function approximation for average cost adaptive control of traffic lights. One of these algorithms is a version of Q-learning with function approximation while the other is a policy gradient actor-critic algorithm that incorporates multi-timescale stochastic approximation. We show performance comparisons on various network settings of these algorithms with a range of fixed timing algorithms, as well as a Q-learning algorithm with full state representation that we also implement. We observe that whereas (as expected) on a two-junction corridor, the full state representation algorithm shows the best results, this algorithm is not implementable on larger road networks. The algorithm PG-AC-TLC that we propose is seen to show the best overall performance.

Network pricing for QoS: A 'Regulation' approach

V. S. Borkar’s work was supported in part by grant number III.5(157)/99-ET from the Department of Science and Technology, Government of India. D. Manjunath’s work was supported in part by grant number 1(1)/2004-E-Infra from the Ministry of Information Technology, Government of India.

A neural network based automatic generation control design through reinforcement learning

This paper presents the design and implementation of a learning controller for the Automatic Generation Control (AGC) in power systems based on a reinforcement learning (RL) framework. In contrast to the recent RL scheme for AGC proposed by us, the present method permits handling of power system variables such as Area Control Error (ACE) and deviations from scheduled frequency and tie-line flows as continuous variables. (In the earlier scheme, these variables have to be quantized into finitely many levels). The optimal control law is arrived at in the RL framework by making use of Q-learning strategy. Since the state variables are continuous, we propose the use of Radial Basis Function (RBF) neural networks to compute the Q-values for a given input state. Since, in this application we cannot provide training data appropriate for the standard supervised learning framework, a reinforcement learning algorithm is employed to train the RBF network. We also employ a novel exploration strategy, based on a Learning Automata algorithm,for generating training samples during Q-learning. The proposed scheme, in addition to being simple to implement, inherits all the attractive features of an RL scheme such as model independent design, flexibility in control objective specification, robustness etc. Two implementations of the proposed approach are presented. Through simulation studies the attractiveness of this approach is demonstrated.

Experimental Investigation on Switching Characteristics of High-Current Insulated Gate Bipolar Transistors at Low Currents

Insulated gate bipolar transistors (IGBTs) are used in high-power voltage-source converters rated up to hundreds of kilowatts or even a few megawatts. Knowledge of device switching characteristics is required for reliable design and operation of the converters. Switching characteristics are studied widely at high current levels, and corresponding data are available in datasheets. But the devices in a converter also switch low currents close to the zero crossings of the line currents. Further, the switching behaviour under these conditions could significantly influence the output waveform quality including zero crossover distortion. Hence, the switching characteristics of high-current IGBTs (300-A and 75-A IGBT modules) at low load current magnitudes are investigated experimentally in this paper. The collector current, gate-emitter voltage and collector-emitter voltage are measured at various low values of current (less than 10% of the device rated current). A specially designed in-house constructed coaxial current transformer (CCT) is used for device current measurement without increasing the loop inductance in the power circuit. Experimental results show that the device voltage rise time increases significantly during turn-off transitions at low currents.

Experimental Investigation on Switching Characteristics of High-Current Insulated Gate Bipolar Transistors at Low Currents

Insulated gate bipolar transistors (IGBTs) are used in high-power voltage-source converters rated up to hundreds of kilowatts or even a few megawatts. Knowledge of device switching characteristics is required for reliable design and operation of the converters. Switching characteristics are studied widely at high current levels, and corresponding data are available in datasheets. But the devices in a converter also switch low currents close to the zero crossings of the line currents. Further, the switching behaviour under these conditions could significantly influence the output waveform quality including zero crossover distortion. Hence, the switching characteristics of high-current IGBTs (300-A and 75-A IGBT modules) at low load current magnitudes are investigated experimentally in this paper. The collector current, gate-emitter voltage and collector-emitter voltage are measured at various low values of current (less than 10% of the device rated current). A specially designed in-house constructed coaxial current transformer (CCT) is used for device current measurement without increasing the loop inductance in the power circuit. Experimental results show that the device voltage rise time increases significantly during turn-off transitions at low currents.

Experimental results on low cost microcontroller based DC drive implementation

This paper presents the experimental results for an attractive control scheme implementation using an 8 bit microcontroller. The power converter involved is a 3 phase full controlled bridge rectifier. A single quadrant DC drive has been realized and results have been presented for both open and closed loop implementations.

Experimental Study on Switching Characteristics of an Inverter Leg Consisting of IGBTs of Dissimilar Makes

Usually the top and bottom IGBT devices in an inverter leg are of the same make (i.e. from same manufacturer). At low power level, these two devices even may be contained in the same module. However at high power levels the top and bottom devices are in separate modules. Sometimes, in the event of device failure, device of particular make may be replaced by one of another make, but of same ratings (on account of non-availability of the original make). This paper investigates the effect of such intermixing of two different makes of high power IGBTs in an inverter leg on the switching characteristics. The switching transitions between IGBT and diode of similar make and those of IGBT and diode of dissimilar make are compared experimentally at various DC link voltages and currents. The comparisons are made in terms of, IGBT peak turn-on di/dt, IGBT peak turn-off di/dt, peak diode reverse recovery current (I-rr), peak IGBT voltage overshoot and switching energy losses.

Study of Multilevel Sinusoidal PWM methods for Cascaded H-Bridge Multilevel Inverters

This paper is a study of Multilevel Sinusoidal Pulse Width Modulation (MSPWM) methods; Phase Disposition (PD), Alternate Phase Opposition Disposition (APOD), Phase Opposition Disposition (POD) on a single phase Cascaded H-Bridge Multilevel inverter. Various factors such as amplitude modulation index (Ma), frequency modulation index (M-f), phase angle between carrier and reference modulating wave (phi) have been considered for simulation. Variation in these factors and their effect on inverter performance is evaluated. Factors such as DC bus utilization, output r.m.s voltage, total harmonic distortion (%THD), dominant harmonic order, switching losses are evaluated based on simulation results.

Multi-agent Reinforcement Learning for Traffic Signal Control

Optimal control of traffic lights at junctions or traffic signal control (TSC) is essential for reducing the average delay experienced by the road users amidst the rapid increase in the usage of vehicles. In this paper, we formulate the TSC problem as a discounted cost Markov decision process (MDP) and apply multi-agent reinforcement learning (MARL) algorithms to obtain dynamic TSC policies. We model each traffic signal junction as an independent agent. An agent decides the signal duration of its phases in a round-robin (RR) manner using multi-agent Q-learning with either is an element of-greedy or UCB 3] based exploration strategies. It updates its Q-factors based on the cost feedback signal received from its neighbouring agents. This feedback signal can be easily constructed and is shown to be effective in minimizing the average delay of the vehicles in the network. We show through simulations over VISSIM that our algorithms perform significantly better than both the standard fixed signal timing (FST) algorithm and the saturation balancing (SAT) algorithm 15] over two real road networks.

Prognosis of underground structures deterioration based on in-situ measurements

The stability of the underground structure is very important not only from the point of view of the structure itself, but also from the point of view of other structures. Therefore, the evaluation of the process of deterioration can help us very much. In the first part of the paper the ageing of the structures in the scope of their life cycle will be described. The whole process of deterioration is important but limited to certain time intervals and is able to give signals about changes in macro-scale. The second part of the paper is focused on the adaptation of new methods: micro technology of monitoring - such as MEMS (Micro Electrical Mechanical Systems) and wireless technologies for data transfer. It is obvious that such new technologies have to be assessed for the ability to deliver data continuously and for their safety and solidity. At the end of the paper the application of the measurements on the Prague metro's lining is mentioned. © 2007 Taylor & Francis Group.

Tomorrow's cities - a framework for building resilience

Urbanisation is the great driving force of the twenty-first century. Cities are associated with both productivity and creativity, and the benefits offered by closely connected and high density living and working contribute to sustainability. At the same time, cities need extensive infrastructure – like water, power, sanitation and transportation systems – to operate effectively. Cities therefore comprise multiple components, forming both static and dynamic systems that are interconnected directly and indirectly on a number of levels, all forming the backdrop for the interaction of people and processes. Bringing together large numbers of people and complex products in rich interactions can lead to vulnerability from hazards, threats and even trends, whether natural hazards, epidemics, political upheaval, demographic changes, economic instability and/or mechanical failures; The key to countering vulnerability is the identification of critical systems and clear understanding of their interactions and dependencies. Critical systems can be assessed methodically to determine the implications of their failure and their interconnectivities with other systems to identify options. The overriding need is to support resilience – defined here as the degree to which a system or systems can continue to function effectively in a changing environment. Cities need to recognise the significance of devising adaptation strategies and processes to address a multitude of uncertainties relating to climate, economy, growth and demography. In this paper we put forward a framework to support cities in understanding the hazards, threats and trends that can make them vulnerable to unexpected changes and unpredictable shocks. The framework draws on an asset model of the city, in which components that contribute to resilience include social capital, economic assets, manufactured assets, and governance. The paper reviews the field, and draws together an overarching framework intended to help cities plan a robust trajectory towards increased resilience through flexibility, resourcefulness and responsiveness. It presents some brief case studies demonstrating the applicability of the proposed framework to a wide variety of circumstances.