Claudio Balducelli’s research while affiliated with ENEA and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (29)


Safeguarding information intensive critical infrastructures against novel types of emerging failures
  • Article

September 2007

·

26 Reads

·

35 Citations

Reliability Engineering & System Safety

C. Balducelli

·

·

·

The complexity of information intensive critical infrastructures, like electricity networks, telecommunication networks and public transportation networks is today augmented much more than in the past: such complexity augments the number of possible failures and anomalous working conditions and consequently decreases the survivability of the infrastructures.In this paper, the possibility is investigated to detect early anomalies and failures inside information intensive critical infrastructures by the introduction of anomaly detectors being “self-aware” about the normal working conditions of the infrastructure itself. This approach has the objective to improve the performance of the most popular signature-based algorithms for intrusion detection, and makes use of different classes of time-oriented algorithms based on artificial intelligence paradigm. It has the advantage to work also in presence of unknown and unexpected types of attacks or failures.The tests, to evaluate the performance of the utilised detectors, are executed inside an emulated supervisory control and data acquisition (SCADA) system of an electrical power transmission grid, and a proposal for the future integration inside real SCADA systems is also reported.


A Middleware Improved Technology (MIT) to Mitigate Interdependencies between Critical Infrastructures

January 2007

·

44 Reads

·

8 Citations

Lecture Notes in Computer Science

Public life, economy and society as a whole depend to a very large extend on the proper functioning of critical infrastructures (CIs) like energy supply or telecommunication. The extensive use of information and communication technologies (ICT) has pervaded the critical infrastructures, rendering them more intelligent but even increasingly interconnected, complex, interdependent, and therefore more vulnerable. In this paper a new technology (MIT - Middleware Improvement Technology) is proposed: it is based on a collection of software components aiming at enhancing the dependability, the survivability and the resilience of LCCIs (Large Complex Critical Infrastructures) by mitigating dependency and interdependency effects. It should prevent and limit cascading effects and/or support automated (if possible) recovery and service continuity in critical situations. The research activities and results described in the paper have been developed inside EU/FP6 Integrated Project IRRIIS - Integrated Risk Reduction of Information-based Infrastructure Systems.


Novelty detection and management to safeguard information-intensive critical infrastructures

January 2007

·

40 Reads

·

9 Citations

International Journal of Emergency Management

When the complexity of a system increases, the number of possible faults and anomalous working conditions becomes very high; on the contrary, the number of 'normal' behaviours is generally low and often well determined by rules and constraints defined by the characteristics of the furnished services. In this paper, after a general overview of the SAFEGUARD system, a more detailed description of the agents, dedicated to early detection of anomalies and failures inside a Supervisory and Control and Data Acquisition (SCADA) system of an electricity transmission network is given. The paper also describes how it is possible to correlate the detected novelty events and to decide the right recovery policies avoiding inappropriate reactions caused by false alarms. A test benchmark of the novelty detection agents will be executed inside a simulated SCADA electricity transmission system and the layout of the utilised testing environment is described in the paper.


Analysing interdependencies of critical infrastructures using agent discrete event simulation

January 2005

·

82 Reads

·

23 Citations

International Journal of Emergency Management

The paper explores the possibility of using interacting agents for modelling and discrete event simulation as a tool to approach interdependencies analysis and evaluation for critical infrastructures. A discrete event simulation system was developed, using agent-oriented programming, considering the following limited sets of critical infrastructures: a great hospital infrastructure, a railway transportation infrastructure and other public transportation infrastructures. Faults inside the electricity distribution system are simulated, producing electrical power outages whose duration could be variable with respect to time and space, and generating consequences inside the transportation infrastructures. The hospital infrastructure users, such as different types of physicians, nurses, subsidiary personnel, students and patients are also modelled using agent oriented architectures. The objective of the simulations is to study and analyse the interdependencies of the considered infrastructures. Many typologies of test scenarios are also executed and the severity of the generated consequences are analysed in the paper.


Electric Power System Anomaly Detection Using Neural Networks

September 2004

·

321 Reads

·

41 Citations

Lecture Notes in Computer Science

The aim of this work is to propose an approach to monitor and protect Electric Power System by learning normal system behaviour at substations level, and raising an alarm signal when an abnormal status is detected; the problem is addressed by the use of autoassociative neural networks, reading substation measures. Experimental results show that, through the proposed approach, neural networks can be used to learn parameters underlaying system behaviour, and their output processed to detecting anomalies due to hijacking of measures, changes in the power network topology (i.e. transmission lines breaking) and unexpected power demand trend.


TIEMS98: Disaster and Emergency Management: International Challenges for the Next Decade. The Fifth Annual

April 2004

·

15 Reads

The paper presents on-going ENEA's results in the development of active/intelligent DSSs (IDSS) for emergency managers. The emergency management problem is initially analyzed top-down, from the perspective of the general functional requirements of IDSSs, and integrated with the bottom-up perspective of incremental prototyping. Independently developed autonomous agents support higher, 'mental' functions of IDSS. Such parallel bottom-up and top-down development of a generic IDSS kernel, supported by intelligent multi-agent architecture, enables: - various real-time specialization of the system on the level of tools, - strong reduction of the design time by parallel execution of project phases - easier the verification and validation of the system as independent tasks .


Dependability and Survivability of Large Complex Critical Infrastructures

September 2003

·

25 Reads

·

10 Citations

Lecture Notes in Computer Science

This paper refers to research activities related to SAFEGUARD project (IST Project Number: IST-2001-32685). The aims of the project is to examine LCCI’s in terms of nature of different facets in each infrastructure: organizational, computational (cyber) and physical layers. Critical inter-dependencies among layers can thus be analyzed. Possible impact of bad events, early classified in attack scenarios with and without SAFEGUARD, will be coped with countermeasures to maintain at acceptable level system’s operability. SAFEGUARD, an agent-based middleware, is conceived to operate embedded inside of the cyber-layers, the more sensitive part to malicious attacks and anomalies, and is designed to enhance dependability and survivability of a LCCI. Self-healing mechanism of SAFEGUARD agents will start with the trouble diagnosis and classification using Hybrid Intrusion Detection techniques (software instrumentation, novelty detection, etc.). Once the problem has been diagnosed, a number of techniques will be used to solve and repair the fault (i.e.: adaptive middleware technology, backup, hot standby and so on). More self-healing mechanisms will have to be combined and coordinated to with an attempt to deal with the source of the problem.


Figure 1. Guided training in a 47kV system.
Virtual reality tools for emergency operation support and training
  • Conference Paper
  • Full-text available

June 2001

·

581 Reads

·

38 Citations

This paper discusses the current state of the art of virtual reality (VR) technology within the context emergency operation support and training. Recent widely reported fatal road and railway tunnel accidents (e.g. Mont Blanc, Kaprun) have highlighted the problems that arise when evacuating people to safety in the event of a fire in a confined space with limited exit possibilities. Similar problems arise in the evacuation of aircraft and high-speed trains or subways. In order to improve preparedness plans, it is necessary to develop rescue scenarios to ascertain the fire safety and to train rescue personnel by simulation of fire emergencies. The integration of VR technology with traditional geographical information systems and tools for managing emergency procedures is particularly interesting from both a decision support and training perspective. A VR interface could either replace a conventional 2D interface or complement it, depending on user requirements. This paper proposes VR methodologies as the only feasible alternative to full-scale fire tests inside tunnels. In a computer simulation-based virtual environment, all data about infrastructure, safety equipment, ventilation resources, fire and smoke propagation, and vehicle/passengers involvement could be managed by a single database. Fire and smoke simulation tools as well as computerised emergency procedures, acting on the virtual data, could also be integrated in such a system and utilised for training support by the emergency operators.

Download

Genetic agents in an EDSS system to optimize resources management and risk object evacuation

June 2000

·

22 Reads

·

17 Citations

Safety Science

Emerging efficient and intelligent behaviors from co-operative activities of many autonomous agents comprise unexpected events that often take place inside animal social organizations. This type of evidence induced artificial intelligence researchers to re-design the artificial computing system architectures, from monolithic and hierarchical structures toward networked and component distributed environments. In this work the co-operative capacity of three different software agents is experimented to front the management problem, emerging during fires emergencies, relative to fire-proof resources optimization and dangerous products evacuation inside large oil storage and production plants. The three software components include, respectively, a repository or memory of past solutions (managed by case-based reasoning methods), the capacity to discover new solutions (using evolutionary algorithms), and the capacity to verify solutions (using numerical simulation models). The main result of the work was that, from the co-operative activities of these three software components, together with the human agent, the capacity to learn and adapt solutions for the current problem arises as a proper and additional feature of such hybrid system. The general problem of anti-fire resources optimization and evacuation of risk products, during fire emergencies, inside a petrol-chemical plant, is firstly described. Then, the models and the software algorithms, implemented in the three mentioned components, are illustrated in the central part of the work. Finally, a set of test cases are reported, for different scenarios in the physical domain, experimented and analyzed.


Fig. 2. Bottom-up development of active DSS.
Fig. 4 Application of neuro-fuzzy and genetic algorithms inside GEO system [Balducelli at al.,97]
Fig. 5 Schema of functions allocation among active DSS and its user [Balducelli,Gadomski,97].
Fig. 6 An example of IDSS with one decision-support intelligent agent.
Integrated Parallel Bottom-up and Top-down Approach to the Development of Agent-based Intelligent DSSs for Emergency Management

April 1999

·

700 Reads

·

19 Citations

The paper presents on-going ENEA's results in the development of active/intelligent DSSs (IDSS) for emergency managers. The emergency management problem is initially analyzed top-down, from the perspective of the general functional requirements of IDSSs, and integrated with the bottom-up perspective of incremental prototyping. Independently developed autonomous agents support higher, 'mental' functions of IDSS. Such parallel bottom-up and top-down development of a generic IDSS kernel, supported by intelligent multi-agent architecture, enables: - various real-time specialization of the system on the level of tools, - strong reduction of the design time by parallel execution of project phases - easier the verification and validation of the system as independent tasks . The advantages of this methodology are illustrated by the current ENEA's results related to the project GEO. 1. Introduction The current paper is a continuation of the ENEA's studies related to the development of a multip...


Citations (17)


... In the figure is showed part of a Case Base relative to diagnostic Knowledge about a Turbine faults detection (Balducelli and Gallanti 1987). At the top of the panel is possible to see the identification of a selected Case to be edit; in the scrollable window are showed all the questions contained in the Case Base and the questions pertinent to the selected Case are evidenced by a blue circle at left ...

Reference:

A CBR Shell to Implement and Test Case Based Diagnostic Models
Developing an Expert System for Fault Diagnosis of a Turbo Generator Group Using an OPS5 Production Rules Programming Environment
  • Citing Chapter
  • January 1988

... Lo scopo del nostro lavoro è di dare un contributo concreto allo sviluppo di un sistema che, integrando nuove tecnologie informatiche come gli Agenti Intelligenti [5] [8] [12] [15] [16], il Ragionamento su Basi di Casi [7][13] e sistemi GIS [6] [11], e applicando tali tecnologie alla progettazione e sviluppo di un sistema di Supporto Decisionale che sia usabile durante incidenti industriali su vasta scala territoriale. ...

Case Base Reasoning Approach in Industrial Emergency Assessment and Management.
  • Citing Article
  • January 1996

C. Balducelli

·

·

G. Di Constanzo

·

[...]

·

... The first prototype of an Intelligent Decision Advisor (IDA) for Emergency Management has been the objective of the MICA R&D project 2.8.3.1.F focused on the development of an active computer support for large scale industrial and territorial emergencies. The project has been realized under the umbrella of the ENEA's long term strategic MINDES Program synchronized with the worldwide GEMINI (Global Emergency Management Information Network Initiative) of the G7 Committee [18], [21]. The main objective of MINDES is to develop an intelligent decision-support kernel for the computerized nodes of an Emergency Management Network. ...

MINDES: Managerial Intelligent Node for Decisional Emergency Support.
  • Citing Article
  • January 1998

... For detecting anomalous behaviour in SCADA systems, there have been several works that are based on network traffic inspection [4], analyzing data readings [5] and validating protocol specifications [6]. However, process-related attacks typically cannot be detected by observing protocol specifications or network traffic. ...

Novelty detection and management to safeguard information-intensive critical infrastructures
  • Citing Article
  • January 2007

International Journal of Emergency Management

... Methods to quantify the economic damage that can result from interdependencies among sectors include agent-based models [33,34], dynamic general equilibrium models [35], hierarchical holographic modeling [36], high-level architecture [37], and input-output models [38], among others [39]. Agent-based models are based on a group of dynamic, rule-based interacting agents. ...

Analysing interdependencies of critical infrastructures using agent discrete event simulation
  • Citing Article
  • January 2005

International Journal of Emergency Management

... SCADA systems are publicly known to have been subject to attacks incorporating the use of concealment techniques with the capability to manipulate process signals on control units (Chen and Abu-Nimeh, 2011), or communication routes (Verba and Milvich, 2008) on a long term basis. Such attacks have been discussed extensively (Verba and Milvich, 2008;Gamez et al., 2000;McEvoy and Wolthusen, 2009). Detective strategies based on protocol analysis, or statistical signal analysis by themselves can be shown to have weaknesses in uncovering such attacks (Svendsen and Wolthusen, 2009), particularly in the face of an adversary with the ability to subvert network nodes in the system (McEvoy and Wolthusen, 2010b). ...

Safeguarding Critical Infrastructures

... It can provide operative information on damage and casualties due to strong earthquakes all over the world. Balducelli et al. (2000) adopted a decision support system call the intelligent decision assistant (IDA), which can play an important role in emergency management of a large area based on agent technology. The system consists of three software agents: a direct advisor, automatic planner, and information provider. ...

A Prototype of an Active Decision Support System for Automatic Planning Support in Emergency Management

... Keke et al., 2020;ZZhu et al., 2016) and autonomous vehicles performance estimation in search and rescue operations (Auslander et al., 2015). With regard to CBR-based diagnosis systems, they were modelled to diagnose failure situations (Assali et al., 2012;Balducelli et al., 2007) or characterising an occurred disaster (Li et al., 2017;Peng et al., 2019). All of the abovementioned systems were used to solve emergency management issues in different emergency contexts such as natural disasters (e.g., typhoon) and man-made disasters (e.g., terrorism). ...

Safeguarding information intensive critical infrastructures against novel types of emerging failures
  • Citing Article
  • September 2007

Reliability Engineering & System Safety