O. Mirabella

Stochastic analysis of periodic real-time systems

This paper describes a stochastic analysis method for general periodic real-time systems. The proposed method accurately computes the response time distribution of each task in the system, thus making it possible to determine the deadline miss probability of individual tasks, even for systems with maximum utilization factor greater than one. The method uniformly covers both fixed-priority scheduling (such as rate monotonic) as well as dynamic-priority scheduling (such as earliest deadline first) and can handle arbitrary relative deadlines and execution time distributions. The accuracy of the method is proven by comparing the results from the analysis with those obtained from simulations, as well as other methodologies in the literature.

Improving the real-time behavior of ethernet networks using traffic smoothing

In modern process control systems, Ethernet is achieving a leading position, proposing itself as a network capable of supporting all communication needs at all levels in the Computer Integrated Manufacturing hierarchy. The main obstacle to using Ethernet at the Field level is the nondeterminism of the Ethernet MAC protocol, which cannot provide real-time traffic with bounded channel access times. This paper focuses on industrial applications featuring soft real-time constraints, such as periodic control or industrial multimedia, which do not require deterministic guarantees on deadline meeting. To cope with this class of applications, Ethernet should be able to guarantee the timely delivery of real-time packets in statistical terms. The paper presents fuzzy traffic smoothing, a technique to perform adaptive traffic smoothing over Ethernet networks at the Field level thus enabling them to provide a statistical bound on packet delivery time. Previous work showed that the fuzzy smoother outperforms other adaptive smoothers proposed in the literature. This paper addresses fuzzy smoother optimization through genetic algorithms. The proposed optimization is applied to tune the inference engine membership functions. The results obtained show the effectiveness of the approach.

A Hybrid Wired/Wireless Networking Infrastructure for Greenhouse Management

In this paper, the problems related to the management of a farm made up of several greenhouses are discussed. The management of this kind of farms requires data acquisition in each greenhouse and their transfer to a control unit which is usually located in a control room, separated from the production area. At present, the data transfer between the greenhouses and the control system is mainly provided by a suitable wired communication system, such as a fieldbus. In such contexts, even though the replacement of the wired system with a fully wireless one can appear very attractive, a fully wireless system can introduce some disadvantages. A solution based on a hybrid wired/wireless network, where Controller Area Network and ZigBee protocols are used, is presented along with all the related problems that this integration involves. In particular, in order to integrate at the Data Link Layer the wireless section with the wired one, a suitable multiprotocol bridge has been implemented. Moreover, at the Application Layer, porting of Smart Distributed System services on ZigBee, called ZSDS, allows one to access the network resources independently from the network segment they are connected to.

A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks

The paper deals with the problem of fault tolerance in a multilayer perceptron network. Although it already possesses a reasonable fault tolerance capability, it may be insufficient in particularly critical applications. Studies carried out by the authors have shown that the traditional backpropagation learning algorithm may entail the presence of a certain number of weights with a much higher absolute value than the others. Further studies have shown that faults in these weights is the main cause of deterioration in the performance of the neural network. In other words, the main cause of incorrect network functioning on the occurrence of a fault is the non-uniform distribution of absolute values of weights in each layer. The paper proposes a learning algorithm which updates the weights, distributing their absolute values as uniformly as possible in each layer. Tests performed on benchmark test sets have shown the considerable increase in fault tolerance obtainable with the proposed approach as compared with the traditional backpropagation algorithm and with some of the most efficient fault tolerance approaches to be found in literature.

Design and Implementation of an Educational Testbed for Experiencing With Industrial Communication Networks

This paper presents the design and implementation of an educational testbed developed for a course on industrial communication networks at the Engineering Faculty, University of Catania. The aim is to realize a platform capable of emulating various network configurations, thus enabling students to find out by themselves through practical experiments how different design choices, parameter settings, network configurations, and algorithms impact on the overall network performance. The testbed comprises a number of basic components (hosts, routers, and access points) implemented on nodes equipped with operating systems and open source software, which together make up a modular system. Each router can be loaded with data flows and monitored over preestablished time windows so as to evaluate its performance in a wide range of operating conditions. The wireless part makes it possible to configure environments with different levels of noise and bandwidth utilization so as to emulate a broad spectrum of real operating environments. The testbed can be used via remote access through a web interface that not only allows the operating conditions to be configured but also permits real-time monitoring. Students can configure the testbed on the basis of the network they are studying and can measure its performance for evaluation purposes.

Optimization of acyclic bandwidth allocation exploiting the priority mechanism in the FieldBus data link layer

In process control applications, the bandwidth assigned to acyclic traffic is oversized in order to ensure that the time constraints of control traffic are met. In the FieldBus, a protocol designed to support the exchange of information between sensors/actuators and regulating elements in an automation environment, this means allocating an excessive portion of the macrocycle to acyclic traffic. The use of traffic management based on priority can allow more efficient management of the available bandwidth. The authors analyze the priority mechanism provided for in the FieldBus data link layer and assess various strategies for management of aperiodic traffic and different application scenarios. >

Fuzzy traffic smoothing: an approach for real-time communication over Ethernet networks

The paper presents an improvement on existing dynamic traffic smoothing techniques in two respects. Firstly, here the input parameters for the smoother are both the overall throughput and the number of collisions observed over an interval. Together, these two parameters represent a more complete indicator of the actual network workload. Secondly, here the smoothing action is dynamically gauged according to the actual workload by using a fuzzy controller. Experimental results in a real environment, comprising 11 workstations running the Linux OS and connected via a IOBASE-T Ethernet, are presented, together with a performance comparison with a dynamic smoother in the literature.

Pre-run-time scheduling to reduce schedule length in the FieldBus environment

The paper deals with the problem of scheduling the transmission of periodic processes in a distributed FieldBus system, defining the conditions guaranteeing correct transmission. The scheduling of periodic processes fixes the transmission times for each process in a table, whose length is equal to the Least Common Multiple (LCM) of all the periods. This involves great memorization problems when some periods are relatively prime. The authors identify the theoretical conditions which allow the length of the scheduling table to be drastically reduced, but still guarantee correct transmission. On the basis of the theoretical conditions given, the authors present a pre-run-time scheduling algorithm which determines a transmission sequence for each producing process within the desired scheduling interval. An online scheduling algorithm is also proposed to schedule new transmission requests which are made while the system is functioning. The reduction in the schedule length may increase the number of transmissions, thus reducing the effective bandwidth and increasing the communication overload. In order to make as complete an analysis as possible of the scheduling solution, the authors also present an analysis of both the computational complexity of the algorithms proposed and the communication overload introduced. >

Evaluating the field bus data link layer by a Petri net-based simulation

The performance of the data link layer of the field bus, an emerging LAN architecture for control systems presently under standardization, is discussed and evaluated. Some aspects of the communication mechanism are presented, referring to the use of the two kinds of tokens of the protocol and pointing out their main features and the advantages and disadvantages offered by each one. The protocol was specified by extended timed Petri-nets and was evaluated by a suitable simulation tool. The results provide some criteria according to which the designer can choose, among the various mechanisms made available by the standard proposal, those which provide the most efficient solution for the scenario being considered. >

Optimal path determination in a graph by Hopfield neural network

Abstract Recurrent stable neural networks seems to represent an interesting alternative to classical algorithms for the search for optimal paths in a graph. In this paper a Hopfield neural network is adopted to solve the problem of finding the shortest path between two nodes of a graph. The results obtained point out the validity of the solution proposed and its capability to adapt itself dynamically to the variations in the costs of the graph, acquiring an “awareness” of its structure.