لخّصلي

1.1 General Context Massive computerization, insertion of new devices, increased data flow, and in- termittent generation have considerably increased current electrical systems' complexity.The increasing application of switching devices, nonlinear loads, rectifiers, lighting controls, protection, and relaying equipment are also the causes of the PQ disturbances (KHOKHAR et al., 2015).The AI domain, with advanced ML and cognitive computing capabilities, are a key enabler of unforeseen efficiency capabilities in the context of smart energy grids (SERBAN; LYTRAS, 2020).The new generation of AI technology represented by Big Data, Machine Learning (ML), Deep Learning (DL), Pattern Recognition, and other methods are closely related to the simulation analysis of large-scale power grids (TANG et al., 2018).Besides deteriorating grid performance, the loss of PQ also has financial implications, resulting in extra costs related to the additional power consumed (PEREIRA et al., 1998).It uses a statistical learning algorithm that automatically learns and improves without human help (SHARMA; SHARMA; JINDAL, 2021).The integration of distributed generation and renewable energies is one of the major sources of PQ disturbances.ML is an area of AI that has emerged as part of the ongoing search for build- ing intelligent machines capable of learning.One of the essential elements for a good functioning of an electrical system is Power Quality (PQ).This increase resulted in necessary changes, such as the need for more intelligent electrical networks to adapt to this different reality.Artificial Intelligence (AI) may allow that these systems can become more robust and reliable.The use of advanced techniques of AI in power systems is becoming more and more notorious in recent years.AI represents a new era in society and global development based on information and knowledge.In recent years, PQ has become a growing concern for both energy utilities and consumers of the power grid.If these disturbances are not identified and classified, they can cause severe damage to distributionWith the recent Smart Grid (SG), the use of techniques that use this type of intelligence will be even more necessary.Therefore, a high-quality diagnosis of this grid is critical to identify and solve eventual problems.It is self-learning based on algorithms that mean the system learns from its experience.

1.1 General Context
Massive computerization, insertion of new devices, increased data flow, and in-
termittent generation have considerably increased current electrical systems’ complexity.
This increase resulted in necessary changes, such as the need for more intelligent electrical
networks to adapt to this different reality. Artificial Intelligence (AI) may allow that these
systems can become more robust and reliable.
The use of advanced techniques of AI in power systems is becoming more and more
notorious in recent years. The new generation of AI technology represented by Big Data,
Machine Learning (ML), Deep Learning (DL), Pattern Recognition, and other methods
are closely related to the simulation analysis of large-scale power grids (TANG et al.,
2018).
AI represents a new era in society and global development based on information
and knowledge. With the recent Smart Grid (SG), the use of techniques that use this
type of intelligence will be even more necessary. The AI domain, with advanced ML and
cognitive computing capabilities, are a key enabler of unforeseen efficiency capabilities in
the context of smart energy grids (ŞERBAN; LYTRAS, 2020).
ML is an area of AI that has emerged as part of the ongoing search for build-
ing intelligent machines capable of learning. It is self-learning based on algorithms that
mean the system learns from its experience. It uses a statistical learning algorithm that
automatically learns and improves without human help (SHARMA; SHARMA; JINDAL,
2021).
One of the essential elements for a good functioning of an electrical system is Power
Quality (PQ). Therefore, a high-quality diagnosis of this grid is critical to identify and
solve eventual problems. Besides deteriorating grid performance, the loss of PQ also has
financial implications, resulting in extra costs related to the additional power consumed
(PEREIRA et al., 1998).
In recent years, PQ has become a growing concern for both energy utilities and
consumers of the power grid. The integration of distributed generation and renewable
energies is one of the major sources of PQ disturbances. The increasing application of
switching devices, nonlinear loads, rectifiers, lighting controls, protection, and relaying
equipment are also the causes of the PQ disturbances (KHOKHAR et al., 2015). If these
disturbances are not identified and classified, they can cause severe damage to distribution