Generalized stochastic Petri nets based models for performance analysis of communication networks of IEC61850 system

In this paper, data streams are classified into four types conforming to a standardized infrastructure of communication networks for a substation automation system （SAS） based on IEC61850 system. The data exchanged on the net are demonstrated to be stochastic according to investigation on the Ethemet communication principles. Four generalized stochastic Petri nets （GSPN） based models for performance analysis of communication networks of IEC61850 system are developed based on the three-level structure of SAS, different time requirements of the four data streams and different networks topology for different voltage level. The GSPN-based model associated with immediate and exponential transitions is proven to be theoretically isomorphic with Markov chain; hence we apply the mathematic methods of performance evaluation contained in Markov chain to the GSPN models proposed. The computer simulation of the model including only sample value data streams shows that it can meet performance evaluation needs of communication networks of IEC61850 system. Further researches should be focused on the pe^ormance of the other three models to explain clear how those different data streams are interrelated to and interact on each other.

Performability analysis of avionics system with multilayer HM/FM using stochastic Petri nets

The integrated modular avionics （IMA） architecture is an open standard in avionics industry, in which the number of functionalities implemented by software is greater than ever before. In the IMA architecture, the reliability of the avionics system is highly affected by the software applications. In order to enhance the fault tolerance feature with regard to software application failures, many industrial standards propose a layered health monitoring/fault management （HM/FM） scheme to periodically check the health status of software application processes and recover the malfunctioning software process whenever an error is located. In this paper, we make an analytical study of the HM/FM system for avionics application software. We use the stochastic Petri nets （SPN） to build a formal model of each component and present a method to combine the components together to form a complete system model with respect to three interlayer query strategies. We further investigate the effectiveness of these strategies in an illustrative system.

STOCHASTIC OBJECT-ORIENTED PETRI NETS (SOPNS) AND ITS APPLICATION IN MODELING OF MANUFACTURING SYSTEM RELIABILITY

Object-oriented Petri nets (OPNs) is extended into stochastic object-oriented Petri nets (SOPNs) by associating the OPN of an object with stochastic transitions and introducing stochastic places. The stochastic transition of the SOPNs of a production resources can be used to model its reliability, while the SOPN of a production resource can describe its performance with reliability considered. The SOPN model of a case production system is built to illustrate the relationship between the system's performances and the failures of individual production resources.

Survivability analysis of wireless Ad hoc network using stochastic reward nets

To provide services in presence of failures or attacks in a timely manner, the network survivability was analyzed. Based on stochastic Petri nets, we put forward an effective model for ad hoe network and adopt a two-phase approach consisting of the steady-state availability analysis and the system transient performance analysis, then provide a quantitative approach for analysis of the network survivability. The results show that the proposed model is useful for the design and evaluation of the wireless ad hoc network.

An SPN analysis method for parallel scheduling in Ad Hoc networks

In this paper, a new analytic method for modeling and evaluating mobile ad hoc networks (MANET) is proposed. Petri nets technique is introduced into MANET and a packet-flow parallel scheduling scheme is presented using Stochastic Petri Nets (SPN). The flowing of tokens is used in graphics mode to characterize dynamical features of sharing a single wireless channel. Through SPN reachability analysis and isomorphic continuous time Markov process equations, some network parameters, such as channel efficiency, one-hop transmission delay etc., can be obtained. Compared with conventional performance evaluation methods, the above parameters are mathematical expressions instead of test results from a simulator.

Stochastic individual predicate/transition nets

We analyze the drawbacks of generally distributed time transition stochastic Petri nets(GDTT_SPN) in evaluating the performance of parallel systems,and propose a more general model,stochastic individual predicate/transition nets(SIPTN). SIPTN has higher modeling power and could provide more realistic models compared to GDTT_SPN,because in SIPTN the sojourn time distribution is determined not only by the transition,but also by the individuals. It is further proved that GDTT_SPN is a subset of SIPTN. As SIPTN introduces folding techniques from predicate/transition nets,SIPTN models have simpler and more intuitive graphic notations and accordingly higher usability,and thus are suitable for constructing simulation models for parallel systems.

An SPN-Based Integrated Model for Web Prefetching and Caching

The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the primary approaches to reducing the user perceived access latency and improving the quality of services. In this paper, a Stochastic Petri Nets （SPN） based integrated web prefetching and caching model （IWPCM） is presented and the performance evaluation of IWPCM is made. The performance metrics, access latency, throughput, HR （hit ratio） and BHR （byte hit ratio） are analyzed and discussed. Simulations show that compared with caching only model （CM）, IWPCM can further improve the throughput, HR and BHR efficiently and reduce the access latency. The performance evaluation based on the SPN model can provide a basis for implementation of web prefetching and caching and the combination of web prefetching and caching holds the promise of improving the QoS of web systems.

Performance Evaluation and Dynamic Optimization of Speed Scaling on Web Servers in Cloud Computing

The energy consumption in large-scale data centers is attracting more and more attention today with the increasing data center energy costs making the enhanced performance very expensive. This is becoming a bottleneck to further developments in terms of both scale and performance of cloud computing. Thus, the reduction of the energy consumption by data centers is becoming a key research topic in green IT and green computing. The web servers providing cloud service computing run at various speeds for different scenarios. By shifting among these states using speed scaling, the energy consumption is proportional to the workload, which is termed energy-proportionality. This study uses stochastic service decision nets to investigate energy-efficient speed scaling on web servers. This model combines stochastic Petri nets with Markov decision process models. This enables the model to dynamically optimize the speed scaling strategy and make performance evaluations. The model is graphical and intuitive enough to characterize complicated system behavior and decisions. The model is service-oriented using the typical service patterns to reduce the complex model to a simple model with a smaller state space. Performance and reward equivalent analyse substantially reduces the system behavior sub-net. The model gives the optimal strategy and evaluates performance and energy metrics more concisely.

Electricity Services Based Dependability Model of Power Grid Communication Networking

The technology of Ultra-High Voltage （UHV） transmission requires higher dependability for electric power grid. Power Grid Communication Networking （PGCN）, the fundamental information infrastructure, severs data transmission including control signal, protection signal, and common data services. Dependability is the necessary requirement to ensure services timely and accurately. Dependability analysis aims to predicate operation status and provide suitable strategies getting rid of the potential dangers. Due to the dependability of PGCN may be affected by external environment, devices quality, implementation strategies, and so on, the scale explosion and the structure complexity make the PGCN＇s dependability much challenging. In this paper, with the observation of interdependency between power grid and PGCN, we propose an electricity services based dependability analysis model of PGCN. The model includes methods of analyzing its dependability and procedures of designing the dependable strategies. We respectively discuss the deterministic analysis method based on matrix analysis and stochastic analysis model based on stochastic Petri nets.

FLUID-BASED SIMULATION APPROACH FOR HIGH VOLUME CONVEYOR TRANSPORTATION SYSTEMS

High volume conveyor systems in distribution centers have very large footprint and can handlelarge volumes and hold thousands of items.Traditional discrete-event cell-based approach to simulatesuch networks becomes computationally challenging.An alternative approach,in which the traffic isrepresented by segments of fluid flow of different density instead of individual packages,is presentedin this paper to address this challenge.The proposed fluid-based simulation approach is developedusing a Hybrid Petri Nets framework.The underlying model is a combination of an extension of aBatches Petri Nets(BPN)and a Stochastic Petri Nets(SPN).The extensions are in the inclusion ofrandom elements and relaxation of certain structural constraints.Some adaptations are also made to fitthe target system modeling.The approach is presented with an example.

Evaluation Method of Software Reliability Based on SPN Model

As a significant measure of software security evaluation, software reliability evaluation is also the basis of software safe operation. Traditional software system security evaluation methods are qualitative evaluation based on the functional and structural measurements, and it often ignores quantitative research based on invalidity and fault. This paper propose a stochastic transition function as a measure parameters of the reliability of stochastic Petri nets （SPN） theory. By calculating the probability of stability of the system, failure and mean time to first failure, it establishes an evaluation and measurement method for software reliability. With example analysis, the method can conduct effective evaluation on the software reliability index quickly and accurately, and meanwhile provides a new method for the software security evaluation.