ARTIFICIAL INTELLIGENCE IN POWER SYSTEM

Ganesh BhandariHimal Chaulagain

Paras SubediPankaj Sah

IntroductionPower SystemNetwork of electrical components used to

generate, transmit and use electric powerMain components: generating station transmission lines distribution system

Artificial IntelligenceFounded at conference on

the campus of Dartmouth College in 1956

AI is the ability of a computer to act like human beings.

Intelligence exhibited by machines and software such as robots and computer programs

Used to the project of developing systems equipped with the intellectual processes features and characteristics of human

Need for A.I. in power system

Power system analysis by conventional technique becomes more difficult because of `(i) Complex, versatile and large amount of

information which is used in calculation, diagnosis and learning.

(ii) Increase in the computational time period (iii) Extensive and vast system data handling

Artificial intelligence techniquesThree major families of AI techniques (i) Expert System Technique (ii) Artificial Neural Network (iii) Fuzzy Logic

Expert system techniquesSet of computer

programs that manipulates knowledge to solve problem in specified area

Obtain the knowledge of human expert in a narrow specified domain into a machine implementable form

Use interface mechanism and knowledge to solve the problem

Writing code is better and simpler than actually calculating and estimating value of power system network parameter

Tested by being placed in the same real world problem solving situation

AdvantagesPermanent and consistentEasily documentedEasily transferred or reproduced

DisadvantagesUnable to learn or adapt to new problems or

situations

Artificial Neural NetworkDerived from biological neuronCovert a set of input into a set of output by a

network of neuronsEach neuron produces one output as a

function of inputsNeurons are treat like a processor which

make simple non-linear operation of its input producing a single output

Working of neurons and pattern of their interconnection can be used to construct computers for solving real world problems

Architecture: Three layers (i) Input layer (ii) Hidden layer (iii) Output layerProblems in generation, transmission and

distribution of electric energy is fed to the ANNs so that a suitable solution can be obtained

Line parameter can be numerically calculated by ANNs taking various factor like environmental factors, unbalancing conditions

Architecture of ANN of Architecture of a ANN

Typical structure of an ANN

Advantages: Speed of processing Ability to handle situations of incomplete data and

information, corrupt data Fault tolerant Capability to generalize

Disadvantages: Large dimensionality. Results are always generated even if the input data are

unreasonable. They are not scalable i.e. once an ANN is trained to do

certain task, it is difficult to extend for other tasks without retraining the neural network

Fuzzy logic

First proposed in early 1990’s by Zadeh

Form of knowledge representation suitable for notations that cannot be defined precisely, distinctly or clearly

Similar to human decision making with ability to produce exact and accurate solution from certain approximate information and data

Works like human brain and can be implement this technology in machines

Use for desigining the physical components of power system

As most of the data used in power system analysis are approximate values and assumption, Fuzzy logic can be of greatly use to derive a stable, exact and ambiguity-free output

Benefits of using fuzzy logic

Application of AI in power system

Operation of power system like hydro-thermal coordination, maintenance scheduling, load and power flow.

Planning of power system like generation expansion planning, power system reliability, transmission expansion planning, reactive power planning.

Control of power system like voltage control, stability control, power flow control, load frequency control.

Automation of power system like restoration, management, fault diagnosis, network security

Applications of distribution system like planning and operation of distribution system, demand side response and demand side management, operation and control of smart grids, network reconfiguration

Applications of distributed generation like distributed generation planning, solar photovoltaic power plant control, wind turbine plant control and renewable energy resources

Forecasting application like short term and long term load forecasting, electricity market forecasting

ResultReplacing human workers for dangerous

and highly specialized operations

Operation in hazardous environments, such as radioactive locations in nuclear plants

Fuzzification provides superior expressive power, higher generality and an improved capability to model complex problems at low or moderate solution cost.

Stability analysis and enhancement.

Power system control, fault diagnosis and load forecasting

Reactive power planning and its control

Automation of power system like restoration management, fault diagnosis, network security

Can be used in anything from small circuits to large mainframes

Can be used to increase the efficiency of the components used in power systems

Conclusion The main feature of power system design and planning is

reliability. Conventional techniques don't fulfill the probabilistic essence of power systems.This leads to increase in operating and maintenance costs.Plenty of research is performed to utilize the current interest on Artificial Intelligence for power system applications.

A lot of research is yet to be performed to perceive full advantages of this upcoming technology for improving the efficiency of electricity market investment, distributed control and monitoring, efficient system analysis, particularly power systems which use renewable energy resources for operation

Any queries???

THANK YOU!!!