**2. Artificial Intelligence and Electric Power Systems**

Artificial intelligence techniques have become necessary to procedures of monitoring, man‐ agement and control of electric power systems. The current expansion of electric power sys‐ tems is physically verified by the increase of branches and by the way distribution lines are installed: generators and loads are interconnected with the distribution lines through multi‐ ple paths (radial form) and in ring among them. This technique increases the confidence in‐ dex on the system because the failure of one line does not cause a total failure of the system and can provide the transmission of electric power from other of its branches. Every new technique offers certain advantages, however when a new technique is implemented, there is an increase of the complexity of the electric power system. Because of that there is the need of an efficient protection in which the sector responsible for the energy transmission and distribution as well as the generating sector are controlled in a quick and efficient way in order to keep the power generated according to the charges required. That said so, energy generation must be kept according to the conditions established by the load and comply with the conditions in which the protection systems are capable of prevent failures of the generation equipment due to possible overloads [3][7].

Recently, new techniques from artificial intelligence (AI) made possible to connect multiple generating sources of electric power as well as loads to the transmission system. However, although all these new factors make access easier, they may cause problems by destabilizing the system, which requires a sophisticated AI based control to assure capable and efficient control of the generation according to the demand. These actions which modify the opera‐ tional state of the electric power systems at any time must be controlled in order to provide power transference in a safe and coordinated way.

Nowadays, the software SCADA is installed in the electric power systems. SCADA stands for Supervisory Control and Data Acquisition and provides in real-time large amounts of in‐ formation about values related to electric quantities of the electric power system which can be obtained from points of the transmission network. Such quantities are, for example, volt‐ age, current and potency. The information obtained by the SCADA system are used as input for the analysis systems and decision-making [1][8][9]. However, due to the large amount of information received by the control centers, interference and natural failures in the synchro‐ nization of the transmission, it is not always that the information brought for analysis by SCADA are complete. Because of that, a databank is created and contains ambiguous, vague and contradicting data. Due to the nature of these data a human operator could be led to make false interpretations or even make wrong decisions which could lead to huge losses and delay of the system restoring [1] with damage to the quality index desired. That being so, it became very urgent to have computational treatment with expert systems dedicated to interpretation, data analysis and the presentation of suggestions as a way of supporting the operation of electric power systems.

#### **2.1. Expert Systems structured in non-classical logics**

**1.3. The voltage variation and Overcurrent as Overload Risk Factors**

32 Advances in Expert Systems

nection of the electric power system will be higher.

generation equipment due to possible overloads [3][7].

**2. Artificial Intelligence and Electric Power Systems**

According to what was seen, in an electric power system the loads represented by the elec‐ tric power consumers, such as electric machines of industries, lighting systems, heating de‐ vices of residences and refrigeration systems of businesses, are not static. They are constantly changing, being turned on and off with value variations which may lead to over‐ load. The overloads are outage risks for the whole system because it increases the intensity of the electric current (overcurrent) in the lines and can heat the conductors, increasing their temperature and causing permanent damage with the interruption of energy transmission.

The existence of load variations requires precise equipments which adjust the voltage in the line, because the overload causes the voltage outage. The voltage variation can aggravate the electric power system state with emergence of large intensities in distribution branches. Because of that, the decrease value or the voltage outage (under-voltage) and the intensity value of the electric current (overcurrent) are two important risk factors to the monitoring of transmission lines of electric power. That being so, the monitoring of the ranges of voltage outage and of maximum current of an electric power system are used as a diagnosis of over‐ loads. In order to increase the quality index these two factors must be constantly monitored because if they both are out of the ranges specified in their projects the possibility of discon‐

Artificial intelligence techniques have become necessary to procedures of monitoring, man‐ agement and control of electric power systems. The current expansion of electric power sys‐ tems is physically verified by the increase of branches and by the way distribution lines are installed: generators and loads are interconnected with the distribution lines through multi‐ ple paths (radial form) and in ring among them. This technique increases the confidence in‐ dex on the system because the failure of one line does not cause a total failure of the system and can provide the transmission of electric power from other of its branches. Every new technique offers certain advantages, however when a new technique is implemented, there is an increase of the complexity of the electric power system. Because of that there is the need of an efficient protection in which the sector responsible for the energy transmission and distribution as well as the generating sector are controlled in a quick and efficient way in order to keep the power generated according to the charges required. That said so, energy generation must be kept according to the conditions established by the load and comply with the conditions in which the protection systems are capable of prevent failures of the

Recently, new techniques from artificial intelligence (AI) made possible to connect multiple generating sources of electric power as well as loads to the transmission system. However, although all these new factors make access easier, they may cause problems by destabilizing Artificial Intelligence research oriented to electric power systems has as its goal to find ways of designing new computational tools for the support of decision-making of the team re‐ sponsible for the correct operational action. However, due to the large number of electric keys (breakers that modify the system's topology), to variations on the values of loads and to other several factors inherent to an electric power system, there are many difficulties to find efficient ways. The methods which use conventional binary classical logics to analyze data from the electric power system with the capability of offering suggestions for the opti‐ mized restoring after a failure has not provide good results. One of the difficulties found in the design of models based in classic logics is its condition of being defined by rigid binary laws which lead to equations which are extremely complex to reproduce models. Besides, these equations almost always lead to a combinatorial explosion. Due to this aspect, in this area of artificial intelligence, projects designed with the goal of analysis and decision-mak‐ ing based in classic logics has found many difficulties. It is verified that the low efficiency showed by these projects which use classic logics comes up when a large amount of data has to be computed. These data almost always have redundancies which bring up incomplete‐ ness and contradiction invalidating important information for the analysis. Some classic works use complex algorithms with good results but the computation time is very high making the response time long which is unfeasible in real conditions where an electric pow‐ er system always demands quick and direct actions in order to avoid bigger damages.

#### **2.2. Expert Systems Based on Paraconsistent logics**

These problems found in classical projects lead to the conclusion that the algorithms based on the concepts of non-classic logics may show a better efficiency in the design of expert sys‐ tems dedicated to the analysis and treatment of uncertain data originated in complex data‐ banks such as the one of an electric power system.

**3.1. Paraconsistent Annotated logics - PAL**

dence degrees as follows:

**3.3. The Equations of PAL2v**

**Figure 2.** Lattice of four Vertexes.

lattice similar to the one associated with the PAL2v.

which is unfavorable to proposition *P*.

Among the several families of paraconsistent logics there is the logics called paraconsistent annotated logics (PAL) [5] which belongs to the class of evidential logics and allows analysis of signals represented by annotations [5][9][11]. In its representation each annotation µ be‐ longs to a finite lattice τ which assigns values to its corresponding propositional formula *P*.

Electric Power System Operation Decision Support by Expert System Built with Paraconsistent Annotated Logic

http://dx.doi.org/10.5772/51379

35

For the PAL each evidence degree µ from its representing lattice, whose value varies from 0 and 1 in a closed interval of real numbers, assigned to the proposition *P* a logical state repre‐ sented on the vertexes. By means of a special logical operator, the interpretations on the lat‐ tice of the PAL allow the creation of equations which provide algorithms for the

The paraconsistent annotated logics with annotation of two values (PAL2v) is an extension of the PAL and to each propositional formula *P* is assigned an annotation given by two evi‐

An evidence degree (µ) which is favorable to proposition *P* and an evidence degree (λ)

The annotation composed by two evidence degrees (µ,λ) gives proposition *P* a connotation of paraconsistent logical state ετ which can be identified on the extreme vertices of the lattice: in‐ consistent (⊤), true (t), false (F) or indeterminate (⊥ ) [9]. That being so, in the representation of the PAL2v, a paraconsistent logical signal is represented by proposition *P* and its annotation,

The PAL2v can be studied with the unitary square of the Cartesian plane (USCP) as shown in Figure 2 where, through linear transformations, values on the two representing axes of a

which is composed by two evidence degrees, such that: *P*(µ,λ) with µ, λ ⊂ [0,1] ∈ℜ.

paraconsistent analysis with evidence degrees extracted from real physical systems.

**3.2. Paraconsistent Annotated logics with Annotation of two values - PAL2v**

Based on these considerations we introduce in this paper a paraconsistent expert system (PES) with algorithms based on the theoretical concepts of the Paraconsistent logics (PL) which is a non-classic logics whose main basic theoretical features is, under certain condi‐ tions, to accept contradicting values so that the conflict does not invalidate the conclusions [5][9][10].

The paraconsistent expert system (PES) introduced in this work has the role of performing the analysis of the information coming from the electric power system in the sector of ener‐ gy sub-transmission treating possible contradictions in the information signals. Through the analysis of values of voltage and electric current and the consideration of the states of con‐ nection or disconnection of the electric keys in the substations, PES informs about the risk conditions of overload and about the different configuration topologies of the electric power system.

When a failure, that triggers the interruption of the transmission of energy, happens, PES informs the operators of the sub-transmission system how to proceed with the actions for the restoring in an optimized way. Given the real-time monitoring, the analysis that PES performs is based on data before the occurrence of the failure, which allows PES to indicate the best and most efficient sequence of connecting electric keys in the interrupted section. The actions indicated by PES take into consideration the restrictions of load, technical and safety norms due to the conditions imposed to that particular situation.
