AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’

TRAINING IN POWER SYSTEM CONTROL CENTRES

Luiz Faria, António Silva, Zita Vale, Carlos Ramos

Knowledge Engineering and Decision Support Research Centre, Institute of Engineering – Polytechnic of Porto, Portugal

Albino Marques

REN – Energy Networks of Portugal, Porto, Portugal

Keywords: Intelligent Tutoring Systems, Intelligent Alarm Processing, Diagnosis, Restoration, Control Centres, Power

Systems.

Abstract: The activity of Control Center operators is important to guarantee the effective performance of Power

Systems. Operators’ actions are crucial to deal with incidents, especially severe faults, like blackouts. In this

paper we present an Intelligent Tutoring approach for training Portuguese Control Centre operators in tasks

like incident analysis and diagnosis, and service restoration of Power Systems. Intelligent Tutoring System

(ITS) approach is used in the training of the operators, taking into account context awareness and the

unobtrusive integration in the working environment.

1 INTRODUCTION

Current Power Systems are highly complex and

require sophisticated and precise operation and

control. The most important real-time decisions

concerning Power System operation are taken in

Control Centres where human operators are the final

link of a complex chain. Although Power System

reliability has been increasing, incidents with more

or less severe consequences still occur. In some

cases, this can result in blackout situations, leading

to consumer lack of supply, for which the economic

and social impact can be dramatically high. Figure 1

shows the impact of the 14th August 2003 blackout

in the Northeast part of USA.

Blackouts have been a major concern in Power

Systems mainly since the occurrence of the 9th

November 1965 Northeast Blackout in USA. In

recent years, several blackouts caused major

concerns making the need to keep lights on more

important than ever. IEEE Power & Energy

magazine edited a special issue titled “Shedding

light on blackouts – From prevention through

restoration” (vol.4, no. 5, September/October 2006).

On the 4th October 2006, a Saturday, some minutes

after 10 p.m., the UCTE (Union for the Coordination

of Transmission of Electricity) European Network

experienced a quasi blackout situation affecting 9

European countries and North Africa and about 10

million consumers, originated from a switching-off

of the 380 kV double circuit line Conneforde-Diele

in Germany.

Figure 1: Northeast USA before and after the 14th August

2003 Blackout (Source: NOAA – National Oceanic &

Atmospheric Administration).

Control Center operators’ performance is

determinant to minimize the incident consequences.

The need of a good response of Control Centres to

severe faults, like blackouts, is even more important

nowadays, due to the generalization of the

Electricity Markets (Praça, Ramos, Vale, and

Cordeiro 2003). As Power Systems reliability

increased, the number of incidents offering occasion

for operator on-the-job training has decreased. The

consequences of incorrect operator behaviour are all

more severe during a serious incident (Vale et all

Faria L., Silva A., Vale Z., Ramos C. and Marques A. (2009).

AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’ TRAINING IN POWER SYSTEM CONTROL CENTRES.

In Proceedings of the International Conference on Agents and Artiﬁcial Intelligence, pages 37-44

DOI: 10.5220/0001656200370044

 SciTePress

1997). Operator training is vital for overcoming

these problems, as well as the availability of

decision support tools.

Intelligent Tutoring Systems (ITS) has been the

main approach selected to deal with the operators’

training in diagnosis and restoration tasks, namely

because:

1. They represent domain knowledge in a

structured way, allowing the inference of new

knowledge (access to the essential knowledge).

2. They model the trainee, allowing action in a

non-monotonous way, adapting better to the

trainee’s characteristics and evolution (awareness of

the needs of people).

3. With the right didactic knowledge they allow

the system to choose different pedagogical

approaches in the different phases of the learning

process (requirements customization).

4. They are able to constantly monitor the

trainee’s performance and evolution, gathering

information to guide the system's adaptation (context

awareness).

5. They typically require very little intervention

from the training staff, and can be used in the

working environment without disturbing the normal

working routines (unobtrusivity).

Figure 2: Tutoring Environment Architecture.

In this paper we present an Intelligent Tutoring

System used for training Control Centre operators in

fault diagnosis and power restoration. Several

Artificial Intelligence techniques are used to make

this system able to minimize network experts need

in training preparation and to enable on the job and

cooperative effective training.

The Intelligent Tutoring System that has been

developed for the Control Centre operators involves

two main areas: one devoted to the training of fault

diagnosis skills and another dedicated to the training

of power system restoration techniques. Figure 2

shows this tutoring environment architecture.

2 TUTORING MODULE FOR

FAULT DIAGNOSIS TRAINING

In order to illustrate how a training session is

conducted and the interaction between the operator

and the tutor, this section presents a very simplified

diagnosis problem containing a DmR (monophase

tripping with reclosure) incident, occurred in panel

204 of Ermesinde substation (SED). The relevant

SCADA messages related to this incident are

depicted in Table 1. These SCADA messages

correspond to the following events: breaker tripping,

breaker moving and breaker closing (Vale et all

1997). In a real training scenario the operator is

faced with a huge amount of messages, typically

several hundreds.

Table 1: Incident in panel 204 of SED substation.

14-DEC-2003 04:24:45.200 SED 204 CCL,2 >>>TRIPPING 0 1

14-DEC-2003 04:24:45.240 SED 204 CCL,2 -BK BREAKER 0 0

14-DEC-2003 04:24:45.860 SED 204 CCL,2 -BK BREAKER 0 1

2.1 Reasoning about Operator Answers

The interaction between the trainee and the tutor is

performed through prediction tables (Figure 3)

where the operator selects a set of premises and the

corresponding conclusion. The premises represent

events (SCADA messages), temporal constraints

between events or previous conclusions (Faria, Vale,

and Ramos, 2005).

Figure 3: Prediction Table.

ICAART 2009 - International Conference on Agents and Artificial Intelligence

DiagTutor does not require the operator’s

reasoning to follow a predefined set of steps, as in

other implementations of the model tracing

technique (Anderson et al., 1995). In order to

evaluate this reasoning, the tutor will compare the

prediction tables’ content with the specific situation

model. This model is obtained by matching the

domain model with the inference undertaken by

SPARSE expert system (Vale et al., 1997). This

process is used to: identify the errors revealing

operator’s misconceptions; provide assistance on

each problem solving action, if needed; monitor the

trainee knowledge evolution; and provide learning

opportunities for the trainee to reach mastery.

The identified errors are used as opportunities to

correct the faults in the operator’s reasoning. The

operator’s entries in prediction tables cause

immediate responses from the tutor. In case of error,

the operator can ask for help which is supplied as

hints. Hinting is a tactic that encourages active

thinking structured within guidelines dictated by the

tutor. The first hints are generic, becoming more

detailed if the help requests are repeated.

ce1

ce4

ct1

ce2

ct4

cc2

cs11

ce1 ce4 ct1

cs6 ce2 ct4

cc2

cs8

TRIPPING / T1 BREAKER 00 / T2

BREAKER 01 / T3

|T1-T2|<=30

|T2-T3|<=100

Mono-phase tripping

of unknown type / T1

Mono-phase

re-closure / T3

Mono-phase tripping

with successful re-

closure (DmR) / T3

1 line-end DmR / T3

Higher granularity level Lower granularity level

Figure 4: Higher and lower granularity levels of the

situation specific model.

The situation specific model generated by the

tutoring system for the problem presented is shown

in the left frame of Figure 4. It presents high

granularity since it includes all the elementary steps

used to get the problem solution. The tutor uses this

model to detect errors in the operator reasoning by

comparing the situation specific model with the set

of steps used by the operator. This model’s

granularity level is adequate to a novice trainee but

not to an expert operator. The right frame of Figure

4 represents a model used by an expert operator,

including only concepts representing events (ce

temporal constraints between events (ct

) and the

intermediate (cs

) and final conclusions (cc

). Any

reasoning model between the higher and lower

granularity level models is admissible since it does

not include any violation to the domain model.

These two levels are used as boundaries of a

continuous cognitive space.

2.2 Adapting the Curriculum to the

Operator

The main goal of the Curriculum Planning module is

to select, from a library, a problem fitting the trainee

needs.

The preparation of the tutoring sessions’

learning material is a time-consuming task. In the

industrial environment, there is not usually a staff

exclusively dedicated to training tasks. Specifically,

in the electrical sector, the preparation of training

sessions is done by the most experienced operators

which are often overloaded with power system

operation tasks (Faria, Vale and Ramos 2000). In

order to overcome this difficulty, we developed two

tools. The first one generates and classifies training

scenarios from real cases previously stored. As these

may not cover all the situations that control centre

operators must be prepared to face, another tool is

used to create new training scenarios or to edit

already existing ones (Faria, Vale and Ramos 2000).

The process used by the Curriculum Planning

module to define the problems’ features involves

two phases. First, the tutor must define the difficulty

level of the problem, using heuristic rules. These

rules relate parameters like the trainee’s

performance in previous problems and his overall

level of knowledge. In the second phase, the tutor

uses the user model’s contents to choose the type of

the most suitable incidents to be included in the

problem, taking into account the domain concepts

involved in each type of incident and the

corresponding trainee’s expertise.

2.3 Difficulty Level Selection

To evaluate the problems’ difficulty level, we need

to identify the cases’ characteristics that increase

their complexity, namely by the: number of

incidents involved in the case; variety of incident

types; number of involved plants; and existence of

chronological inversion in SCADA messages.

The choice of the difficulty level depends on two

factors contained in the trainee’s model: the trainee’s

global knowledge and a global acquisition factor.

AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’ TRAINING IN POWER SYSTEM CONTROL

CENTRES

The first parameter is a measure of the trainee’

knowledge level in the whole range of domain

concepts and is calculated using the mean of his

knowledge level in each domain concept. The

Curriculum Planning Module needs appropriate

thresholds for deciding on the next problem

difficulty level. The opinion of the trainees,

regarding their personal evolution as the problems

difficulty level is changed, can be used to tune these

thresholds.

The acquisition factors record how well trainees

learn new concepts. When a new concept is

introduced, the tutor monitors the trainee

performance on the first few problems, namely how

well and how quickly he solves them. This analysis

determines the trainee’s acquisition factor. The

procedure used to determine the trainee’s acquisition

in each domain concept is based on the number of

times the trainee’s knowledge level about the

concept increased, considering the three first

applications of the concept.

The mechanism used to define the difficulty

level of the problems is based on the following rule:

If the global knowledge level and the global

acquisition factor change in opposite directions

Then the problem difficulty level does not change

Else the problem difficulty level changes in the same

direction of the global knowledge level.

2.4 Problem Type Adequacy to the

Trainee Cognitive Status

The mechanism used to classify each kind of

incident in terms of adequacy to the trainee is based

on a neural network (Fig. 5). The nodes belonging to

the input layer correspond to the concepts included

in the domain’s knowledge base (to be assimilated

by the trainees). Each node represents the

application of a concept in a specific context. For

instance, the nodes ce1/T1 and ce1/T5 represents

two instances of the same concept and characterize

the application of the concept of breaker tripping in

the situations of first tripping and tripping after an

automatic reclosure. The input vector contains an

estimate of the trainee’s expertise level for each

concept or its application and is obtained from the

user model. Therefore, this vector represents an

estimate of the trainee’s domain knowledge.

The output layer units represent the adequacy of

an incident type to the current learner’s knowledge

status. The number of units corresponds to the

number of incident types of the following types: DS

(single tripping); DtR (three-phase tripping with

reclosure); DmR (monophase tripping with

reclosure); DtD (three-phase tripping with reclosure

at both ends of the line); and DmD (monophase

tripping with reclosure at both ends of the line).

Each output layer’s node, representing a type of

incident, is connected only to the input nodes

corresponding to concepts involved with that

incident type. These connections are done with links

of weight wij.

The values used as weights are wij={1, 0, –}

where ‘–‘ is used to indicate that there is no

connection between node i of the output layer and

the input node j. This means that concept j is not

involved in an incident type i.

0,10

0,26

0,42

0,58

0,74

0,90

ce1/T1 ce1/T5 ce2/T4 ce3/T3 ce3/T7 ce4/T2

ce4/T6 ct1/T1/T2 ct1/T5/T6 ct2/T1/T3 ct2/T5/T7 ct3/T3/T4

ct4/T2/T4 ct5/T4/T5 cs5/T1 cs5/T5 cs6/T1 cs7/T4

cs8/T4 cs9/T1 cs10/T4 c s 11/ T 4 cs12/T5 cs13/T5

DmD

DtR

DmR

DtD

Incident

types

Operator’s

knowledge

level

Activation

level

Figure 5: Classification mechanism.

Each output neuron activation level is computed

using the input vector and its weight vector. The

activation is defined by the Euclidean distance,

given by (1).

∑

⎟

⎠

⎞

⎜

⎝

⎛

−=

(1)

We can see that a neuron with a weight vector

(w) similar to the activation level vector of the input

nodes (x) will have a low activation level and vice

versa. The output layer’s node with the lowest

activation will be the winner.

ICAART 2009 - International Conference on Agents and Artificial Intelligence

In Figure 5 we illustrate a situation where all the

model variables are set to their minimum value (0.1)

and achieve a maximum value of 0.9. It is also

assumed that the ideal operator applies correctly all

the domain concepts involved in the problem and

that the updating rate is constant.

It can be observed that, after the third iteration,

the concepts used in DS incident type overcome the

medium level (0.5), leading to a new type of incident

(DtR) in the next iteration. After the fourth iteration,

some concepts that are not used in DS but are

involved in DtR incident overtake the minimum

level for the first time.

We observed that an early introduction of new

concepts can contribute to increase the instructional

process efficiency. The problem selection

mechanism ensures that the problem sequence is not

monotonous, tending to stimulate the operator’s

performance with new kinds of incidents.

3 TUTORING MODULE FOR

RESTORATION TRAINING

3.1 Restoration Training Issues

The management of a power system involves several

distinct entities, responsible for different parts of the

network. The power system restoration needs a close

coordination between generation, transmission and

distribution personnel and their actions should be

based on a careful planning and guided by adequate

strategies (Sforna and Bertanza, 2002).

In the specific case of the Portuguese

transmission network, four main entities can be

identified: the National Dispatch Centre (CC); the

Operational Centre (CO); the Hydroelectric Control

Centres (CTCH); and the Distribution Dispatch

(EDIS).

The power restoration process is conducted by

these entities in such a way that the parts of the grid

they are responsible for will be slowly led to their

normal state, by performing the actions specified in

detailed operating procedures and fulfilling the

requirements defined in previously established

protocols. This process requires frequent negotiation

between entities, agreement on common goals, and

synchronization.

The purpose of the training tutor is to allow the

training of the established restoration procedures and

the drilling of some basic techniques. Power system

utilities have built detailed plans containing the

actions to execute and the procedures to follow in

case of incident. In the case of the Portuguese

network, there are specific plans for the system

restoration following several cases of sectorial

blackouts as well as national blackouts, with or

without loss of interconnection with the Spanish

network. Table 2 illustrates a service restoration

plan.

Table 2: Restoration Plan example.

Step

No.

PLAN STEP

0 Notify Distribution Dispatch Center about the

incident and expected restoration time. Wait for

150 kV to be available in SRA bus

1 Feed the 150kV to SRA bus using 400/150 kV

autotransformers

2 Switch SVI substation to manual

3 Energize the lines fed by the 150 kV bus of

SRA with priority to lines connected to

substations SOR and SRU and to power plants

CCD and CVN

4 Contact the Hydroelectric Power Plants’ CC,

asking for the restoration of their lines with

priority for the ones between CCD and CAR

and between CCD and SVI/CVF

5 Wait for the automatic operators of SCV and

SGR substations to restore the 150/60 kV

transformers, if no voltage is available in 60 kV

buses

6 Wait for SOR substation automatic operator to

restore the service, including the line to SVI

7 Finish the restoration of 150 kV line between

substations SRA and SED

8 Check if the automatic operators’ work is

concluded and finish the restoration if it has not

been done automatically

9 Notify Distribution Dispatch Center about the

end of the restoration process

Our Restoration training system use the concept

of agents (Jennings and Wooldridge, 1995), that can

be seen as virtual entities that possess knowledge

about the domain. As real operators, they have tasks

assigned to them, goals to be achieved and beliefs

about the network status and others agents’ activity.

They work asynchronously, performing their duties

simultaneously and synchronizing their activities

only when this need arises. Therefore, the system

needs a facilitator (simulator in Figure 2) that

supervises the process, ensuring that the simulation

is coherent and convincing.

In our system, the trainee can choose to play any

of the available roles, namely the CO and the CC

ones, leaving to the tutor the responsibility of

simulating the other participants.

AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’ TRAINING IN POWER SYSTEM CONTROL

CENTRES

3.2 Trainee’s Model

The representation method used to model the

trainee’s knowledge about the domain knowledge is

a variation of the Constraint-Based Modelling

(CBM) technique (Ohlsson, 1993). This student

model representation technique is based on the

assumption that diagnostic information is not

extracted from the sequence of student’s actions but

rather from the situation, also described as problem

state, that the student arrived at. Hence, the student

model should not represent the student’s actions but

the effects of these actions. Because the space of

false knowledge is much greater than the one for the

correct one, it was suggested the use of an

abstraction mechanism based on constraints. In this

representation, a state constraint is an ordered pair

(Cr,Cs) where Cr stands for relevance condition, and

Cs for satisfaction condition. Cr identifies the class

of problem states in which this condition is relevant

and Cs identifies the class of relevant states that

satisfy Cs. Under these assumptions, domain

knowledge can be represented as a set of state

constraints. Any correct solution for a problem

cannot violate any of the constraints. A violation

indicates incomplete or incorrect knowledge and

constitutes the basic piece of information that allows

the Student Model to be built on.

This CBM technique does not require an expert

module and is computationally undemanding

because it reduces student modelling processing to a

basic pattern matching mechanism. One example of

a state constraint can be found below:

If there is a request to CTCH to restore the lines

under its responsibility

Then the lines that connect to the hydroelectric

power plants must already have been restored

Otherwise an error has occurred

Each violation to a state constraint like the one

above enables the tutor to intervene both

immediately or at a later stage, depending on the

seriousness of the error or the pedagogical approach

that was chosen.

This technique has allowed us to give the tutor

the flexibility needed to address trainees with a wide

range of experience and knowledge, tailoring, in a

much finer way, the degree and type of support

given, and, at the same time, spared us the

exhaustive monitoring and interpretation of student’s

errors during an extended period, which would be

required by alternative methods.

Nevertheless, it was found the need for a

metaknowledge layer in order to adapt the CBM

method to an essentially procedural, time-dependent

domain like the power system restoration field. This

layer is composed of rules that control the

constraints’ application, depending on several

issues: the phase of the restoration process in which

the trainee is; the constraints previously satisfied;

and the set of constraints triggered simultaneously.

These rules establish a dependency network

between constraints that can be represented by a

graph (Figure 6) (Silva, Vale, and Ramos, 1995).

The relationships between constraints expressed by

this graph can be of precedence, mutual exclusion or

priority.

Figure 6: Constraint Dependency Graph.

3.3 The Cooperative Learning

Environment

This tutor is able to train individual operators as if

they were in a team, surrounded by virtual

“operators”, but is also capable of dealing with the

interaction between several trainees engaged in a

cooperative process. It provides specialized agents to

fulfil the roles of the missing operators and, at the

same time, monitors the cooperative work, stepping

in when a serious imbalance is detected. The tutor

can be used as a distance learning tool, with several

operators being trained at different locations.

To support the tutor monitoring activities of the

cooperative discussion and decision processes,

several provisions were made in order to be able to

accurately model the interactions between trainees.

The core data contained in the student model has

been complemented with information concerning the

quantity and characteristics of the interactions

detected between trainees. This data is gathered by

the tutor by means of a loose monitoring of the

interaction patterns coupled with a surface level

analysis of the messages contents.

ICAART 2009 - International Conference on Agents and Artificial Intelligence

The tutor will be active by its own initiative only

if it detects a clear imbalance in the discussion

process. It may be called to step in though by the

trainees themselves, if they agree on a course of

action or if they find themselves in an impasse

situation. In the first case, the tutor will use the

knowledge contained in the CBM module to

evaluate the divergent proposals. In the later case, it

will combine the constraint satisfaction data

previously gathered with procedural knowledge

containing the sequence of the specific restoration

plan, in order to issue recommendations about the

next step to fulfil.

Figure 7: CoopTutor Interface.

The general aspect of the ITS interface is shown

in Figure 7.

4 CONCLUSIONS

This paper described how an Intelligent Tutoring

System can be used for the training of Power

Systems Control Centre operators in two main tasks:

Incident Analysis and Diagnosis; and Service

Restoration. Several Artificial Intelligence (AI)

techniques were joined to obtain an effective

Intelligent Tutoring environment, namely: Multi-

Agent Systems, Neural Networks, Constraint-based

Modelling, Intelligent Planning, Knowledge

Representation, Expert Systems, User Modelling,

and Intelligent User Interfaces.

The developed system is used in the training of

Electrical Engineering BSc students, since the

selection of new operators is done from this kind of

students. It is also important to notice that this

environment has been selected as one of the most

important systems combining AI techniques to be

available in the “AI-50 years” Exhibition in Portugal

(Ramos, 2006), being experimented by many

undergraduate students, motivating them for the

Electrical Engineering and Computer Science fields.

Concerning the operators’ training, the most

interesting features of this environment are:

1. The connection with SPARSE, a legacy

Expert System used for Intelligent Alarm Processing

(Vale et al, 1997).

2. The use of prediction tables and different

granularity levels for fault diagnosis training.

3. The use of the model tracing technique to

capture the operator’s reasoning.

4. The development of two tools to help the

adaptation of the curriculum to the operator - one

that generates training scenarios from real cases and

another that assists in creating new scenarios.

5. The automatic assignment of the difficulty

level to the problems.

6. The identification of the operators’

knowledge acquisition factors.

7. The automatic selection of the next problem

to be presented, using Neural Networks.

8. The use of Multi-Agent Systems paradigm to

model the interaction of several operators during

system restoration.

9. The use of the Constraint-based Modelling

technique in restoration training.

10. The availability of an Intelligent User

Interface in the interaction with the operator.

ACKNOWLEDGEMENTS

The authors would like to thank FCT foundation and

FEDER, PEDIP, POSI, POSC, and PTDC

programmes for their support in several research

projects leading to the development of the work

described here.

REFERENCES

Anderson, J., Corbett, A., Koedinger, K., and Pelletier, R.,

“Cognitive Tutors: Lessons Learned”, The Journal of

the Learning Sciences, v. 4, no. 2, pp. 167-207, 1995

Faria, L., Vale, Z., Ramos, C., Silva, A, and Marques, A.,

“Training Scenarios Generation Tools for an ITS to

Control Center Operators”, Proc. Intelligent Tutoring

Systems Conf. (ITS’2000).

Faria, L., Vale, Z., Ramos, C., “Diagnostic Tasks Training

Based on a Model Tracing Approach”, International

Journal of Engineering Intelligent Systems for

Electrical Engineering & Communications (CRL), v.

13, no. 4, pp. 223-230, 2005.

AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’ TRAINING IN POWER SYSTEM CONTROL

CENTRES

Jennings, N., and Wooldridge, M., “Applying agent

technology”, Applied Artificial Intelligence: An

International Journal, Taylor & Francis London, 9 (4)

1995, 351-361

Ohlsson, S., “Constraint-Based Student Modeling”,

Student Modeling: the Key to Individualized

Knowledge-based Instruction, Greer and McCalla,

Editors, Springer-Verlag, 1993, 167-189.

Praça, I., Ramos, C., Vale, Z., and Cordeiro, M.,

“MASCEM: A Multiagent System That Simulates

Competitive Electricity Markets”, IEEE Intelligent

Systems- Special Issue on Agents and Markets, 18(6),

pp. 54-60, 2003.

Ramos, C., “How Portugal Celebrated AI’s 50th

Anniversary”, IEEE Intelligent Systems, 21(4), pp. 86-

88, 2006.

Sforna, M., Bertanza, V., “Restoration Testing and

Training in Italian ISO”, IEEE Transactions on Power

Systems, November 2002, vol 17, No 4

Silva, A., Vale, Z., Ramos, C., "Cooperative Training of

Power Systems Restoration Techniques", 13rd

International Conference on Intelligent Systems

Applications to Power Systems, Washington,

November 2005.

Vale, Z., Moura, A., Fernandes, M., Marques, A., Rosado,

A. and Ramos, C., “SPARSE: An Intelligent Alarm

Processor and Operator Assistant”, IEEE Expert-

Special Track on AI Applications in the Electric

Power Industry, 12(3), pp. 86- 93, 1997.

ICAART 2009 - International Conference on Agents and Artificial Intelligence