V. Saritha

Learning automata as a utility for power management in smart grids

The rapid growth of smart grid systems demands efficient management of smart grid services. Smart grids are expected to enable the delivery and management of electricity in a more reliable, efficient, economical, and secured manner. Thus, the development of effective power management solutions for smart grids to meet these challenges is an important area of research in recent times. In this article, we propose using learning automata (LA), a computational learning utility, for efficient power management in smart grids (LAPM). The proposed system, LAPM, helps in identifying the electricity required for various distribution substations and controls the usage of power by various devices (i.e., preventing unauthorized use of power). The use of LA enables performing a dynamic analysis of power usage and providing decision making for its effective usage. The system is evaluated on a real-life-resembling environment, with respect to parameters such as power utilization and customer satisfaction.

Learning Automata-Based QoS Framework for Cloud IaaS

This paper presents a Learning Automata (LA)-based QoS (LAQ) framework capable of addressing some of the challenges and demands of various cloud applications. The proposed LAQ framework ensures that the computing resources are used in an efficient manner and are not over- or under-utilized by the consumer applications. Service provisioning can only be guaranteed by continuously monitoring the resource and quantifying various QoS metrics, so that services can be delivered in an on-demand basis with certain levels of guarantee. The proposed framework helps in ensuring guarantees with these metrics in order to provide QoS-enabled cloud services. The performance of the proposed system is evaluated with and without LA, and it is shown that the LA-based solution improves the performance of the system in terms of response time and speed up.

Virtual Backoff Algorithm: An Enhancement to 802.11 Medium-Access Control to Improve the Performance of Wireless Networks

This paper presents a scheme, called the virtual backoff algorithm (VBA), which is based on the sequencing technique for efficient medium-access control. The proposed method minimizes the number of collisions while reducing the delays that occur during the backoff periods. We present an analytical study on MAC-layer issues, which are very important when accessing a channel over wireless networks. The VBA scheme uses fair distributed mechanisms to access a channel. We introduce a counter at each node to maintain the discipline of the nodes. The performance of the proposed method is evaluated under various conditions, and the obtained results are very promising. The enhanced protocol improves the utilization of bandwidth by increasing the throughput up to 75%, and the amount of collisions is reduced to 65% when compared with legacy protocols. The proposed scheme shows that the energy requirements are minimum due to the limitation on the number of transmissions.

LACAV: an energy-efficient channel assignment mechanism for vehicular ad hoc networks

Designing an efficient channel assignment system for Vehicular Ad hoc Networks (VANETs), which conserves energy, is a challenging task, primarily because of the high degrees of mobility of nodes in these networks. As the high mobility of nodes in vehicular networks leads to frequent handoffs, channel assignment in VANETs becomes a tedious task. In this paper, we propose a channel assignment mechanism using the concepts of learning automata (LA) and reusability. LA is used to optimize the performance of the proposed system by selecting suitable number of reserved channels for the handoff calls and reusability allows the channel to be reused by the different base stations (BSs) based on the reuse distance. The proposed system is designed to reduce the dropping probability. The proposed system is suitable for network architectures in which it is possible to arrange the BSs with different groups of channels sequentially in a particular order that helps in conserving energy. Our experiments clearly indicate that the system reduces the dropping probability and allows a continuous communication throughout the duration of the call. The performance of proposed algorithm is compared with the Vehicular Fast Handover Scheme (VFHS), and the Cooperative scheme for service channel reservation (CRaSCH) scheme in terms of handoff latency, and it is shown that the proposed algorithm performs better than VFHS and CRaSCH.

Quality-of-service-enabled ant colony-based multipath routing for mobile ad hoc networks

Mobile ad hoc networks (MANETs) are dynamically changing and self-configuring networks. Owing to their widespread use for many applications, multipath routing in MANETs has been widely discussed for providing fault-tolerance routing, quality-of-service (QoS) and various other purposes. The authors propose a quality of service enabled ant colony-based multipath routing (QAMR) algorithm based on the foraging behaviour of ant colony for selecting path and transmitting data. In this approach, the path is selected based on the stability of the nodes and the path preference probability. The authors have considered bandwidth, delay and hop count as the QoS parameters along with the stability of node, number of hops and path preference probability factors. Simulations performed with network simulator 2 shows that the proposed algorithm is scalable and performs better at higher traffic load compared to the existing algorithms.

An efficient approach for distributed dynamic channel allocation with queues for real-time and non-real-time traffic in cellular networks

We are witnessing these days a rapid growth of mobile users. Therefore, frequency spectrum must be efficiently utilized, as available frequency spectrum is limited. This paper proposes a channel allocation scheme with efficient bandwidth reservation, which initially reserves some channels for handoff calls, and later reserves the channels dynamically, based on the user mobility. The direction of user mobility may not be straight always, but the user may also go left, right or backwards. Thus, QoS can be improved, if the channel reservation is made based upon the user mobility and the location of the user. We devise here a new algorithm that deals with multiple traffic systems by modifying the existing DDCA algorithm [Krishna, P.V., Iyengar, N.Ch.S.N., 2008. Optimal channel allocation algorithm with efficient channel reservation for cellular networks. International Journal of Communication Networks and Distributed Systems 1 (1), 33-51]. This algorithm reserves more channels for hot cells, less number of channels for cold cells and an average number of channels for the medium cells. Furthermore, we maintain queues for all types of calls. We model the system by a three-dimensional Markov Chain and compute the QoS parameters in terms of the blocking probability of originating calls and the dropping probability of handoff calls. The results indicate that the proposed channel allocation scheme exhibits better performance by considering the above mentioned user mobility, type of cells, and maintaining of the queues for various traffic sources. In addition, it can be observed that our approach reduces the dropping probability by using reservation factor.

Efficient Medium Access Control for Cyber–Physical Systems With Heterogeneous Networks

A cyber-physical system (CPS) consists of a group of interlinked networked objects. CPSs are characteristically different from the traditional internetworked systems (e.g., Internet) due to the operating environment and their applications, which impose high reliability constraints on them. One of the fundamental considerations for enabling this technology is the medium access control (MAC). The traditional IEEE 802.11-based MAC layer solutions need to be revamped. In order to increase the efficiency of data transmission, we introduce a new approach, which argues the replacement of the traditional backoff algorithm of 802.11. The proposed approach attempts to address some of the obligations posed by CPS networks. At the core of the proposed solution is the introduction of the adaptability factor to the traditional backoff procedure, which can help CPS networks operate under diverse environmental conditions. In order to survive the high degrees of dynamism of these networks, each of the nodes is equipped with a learning automaton, which adapts to the changing environment and provides the node with the most optimized value. The consistent outperformance of the proposed approach when compared with similar existing approaches under different simulation scenarios exhibits its efficacy. The critical parameters, such as packet delivery ratio and delay, are improved by up to 40% and 27%, respectively, over the traditional protocols.

An efficient approach for distributed channel allocation with learning automata-based reservation in cellular networks

Presently, mobile and wireless networks are witnessing rapid growth and the users of these networks demand many services that require unlimited frequency spectrum. Providing unlimited frequency spectrum is expensive and difficult. So,efficient use of the available frequency spectrum will greatly satisfy the demands of various services. In this paper, we propose a learning automata (LA)-based channel reservation scheme, which determines the optimal number of reserved channels for the system that is being tested. The proposed scheme is tested on four different extended models (systems) – Single Traffic No Queues (STNQ), Single Traffic with Queues (STWQ), Multi-traffic No Queues (MTNQ), and Multi-traffic with Queues (MTWQ). These four systems employ the channel allocation procedure, which is based on the distributed dynamic allocation policies. The presented systems deal with both originating calls and handoff calls. Quality of Service (QoS) may be improved further by reserving the channels for handoff calls based on the user mobility and type of cell. The performance evaluation of the systems with the proposed LA scheme shows improvement when compared with legacy systems. At a particular instant when the system load is 100, 21%, 28%, 18%, 23%, 22%, 27%, 11%, and 18% of the originating calls are blocked and only 2.4%, 3.6%, 1.9%, 2.1%, 1.9%, 2.3%, 0.4%, and 0.55% of the handoff calls are dropped in the case of the STNQ with LA, STNQ without LA, STWQ with LA, STWQ without LA, MTNQ with LA, MTNQ without LA, MTWQ with LA, and MTWQ without LA systems respectively.

Learning automata-based multi-constrained fault-tolerance approach for effective energy management in smart grid communication network

Smart grid networks aim to overcome the inadequacies of the existing electricity grids infrastructure. These networks may exhibit faults due to over-usage of data on electricity grids. Moreover, they must be configured such that energy utilization can be minimized while dealing with energy delivery networks. In order to optimize the performance of smart grids on these two issues of fault tolerance and energy management, a learning automata (LA)-based data transmission path selection algorithm with multiple constraints such as cost, delay, and energy consumption is proposed in this paper. The proposed algorithm named LAMCR is simulated for a real-time environment using NS-2 and is evaluated for QoS parameters such as packet delivery ratio, end-to-end delay, and energy consumption. LAMCR is tested and compared with the legacy systems such as OMCR (Kuipers et al., 2002) and HWMP (Zhu et al., 2011). The results show that LAMCR performs better, while exhibiting higher packet delivery ratio, lesser delay, and lower energy consumption, which improves the throughput of the system.

Learning automata-based virtual backoff algorithm for efficient medium access in vehicular ad hoc networks

In vehicular ad hoc networks (VANETs), the effect of signal distortions due to the existence of adjoining vehicles and the high degrees of mobility of the nodes affect the reliability of transmission. This paper presents a learning automata (LA)-based solution, named LAVBA, for reliable and efficient medium access control, based on virtual backoff algorithm (VBA), in VANETs. In VBA, a counter is used at each node for fair distributed channel access. The performance of VBA medium access depends on the selection of the sequence number. We use an LA-based approach for obtaining an optimal sequence number. It is observed that the performance of the proposed scheme is improved, when compared to the legacy schemes such as distributed coordination function (DCF) and VBA.