This paper collects the SoC (State-of-Charge) changes of electric vehicles and analyzes the battery consumption behavior. For multiple SoC streams generated on the same road, a Hadoop Pig script filters essential information fields out of the vast amount of SoC records, while its user-defined function adds the distance and the time taken from the start point. Next, neural networks are built to trace the SoC dynamics according to both spatial and temporal aspects of SoC records using the R statistics package. A time-combined model reduces the fitting error by 50 %, compared with the distance-only model. The ongoing project keeps accumulating SoC streams and our model will investigate the effect of other parameters and correlate different streams. An accurate model for major roads taken by most trips, will lead to a more efficient estimation of battery consumption for any point-to-point routes.

This paper presents a technique to integrate energy efficient ubiquitous sensors to work in a network for optimum control. This optimization technique can reduce power consumption by using wireless communicating sensors with a supervisor control. This supervisory control of the sensors gives it an advantage of being controllable from any embedded, desktop or Internet platform. Sensors for different purposes can work together to form a network which can be implemented in many environment like homes, city, hospitals and remote locations like mountains, forests etc. We employed an optimized sensing system and algorithm which reduced the number of sensors and power consumption.

In anomaly intrusion detection, how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior as a profile, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes a new clustering algorithm, which continuously models a data stream. A set of features is used to represent the characteristics of an activity. For each feature, the clusters of feature values corresponding to activities observed so far in an audit data stream are identified by the proposed clustering algorithm for data streams. As a result, without maintaining any historical activity of a user physically, new activities of the user can be continuously reflected to the on-going result of clustering.

While various checkpointing schemes have been widely used to reduce the recovery time when a fault occurs, the problem of evaluating the optimal checkpoint interval that maximizes the availability of the system has been a critical research issue for decades. The evaluation can be done by developing analytical models with restrict assumptions. However, the analytical model has reached its limitations as the checkpointing schemes become complicated. This paper proposes to use stochastic Petri net model for the evaluation and shows the effectiveness of the approach using case studies. The paper develops stochastic Petri net models and shows how to obtain the optimal checkpoint intervals for systems employing two widely used checkpointing schemes: Checkpoint with Rollback Recovery scheme for uniprocessor systems and Primary Site Approach for multiprocessor systems.

The task scheduling policy and the processor allocation scheme affect the system performance significantly. In this paper, we propose an efficient processor allocation scheme for 3D mesh interconnection network with a simple FIFO scheduling policy. Complexity analysis shows that the allocation and deallocation of the scheme are O(LWH/sup 2/) and O(LH), respectively, which are better than earlier schemes. Comprehensive computer simulation shows that the average allocation time of the proposed scheme is improved up to about 85% compared to the best earlier 3D approach.

Scheduling parallel tasks represented as a Directed Acyclic Graph (DAG), on a multiprocessor system has been an important research area in the past decades. One of the critical aspects of a class of scheduling algorithms, called "List Scheduling", is how to decide which task is to be scheduled next. This is achieved by assigning priorities to the nodes or the edges of the input DAG, and thus the task with the highest priority will be scheduled next. This paper proposes a low complexity scheduling algorithm to improve the priority node selection criteria in list scheduling algorithms. The worst case performance of the proposed algorithm is analyzed for general input DAGs. Also, the worst case performance and the optimality conditions are obtained for free structured input DAGs. The performance comparison study shows that the proposed algorithm outperforms existing scheduling algorithms especially for input DAGs with high communication overheads. The performance improvement over existing algorithms becomes larger as the input DAG becomes more dense and the level of parallelism in the DAG is increased.