A Meta-Review on the Use of Artificial Intelligence in the Context of

Electrical Power Grid Operators

Daniel Staegemann

, Christian Haertel

, Christian Daase

, Matthias Pohl

and Klaus Turowski

Magdeburg Research and Competence Cluster VLBA, Otto-von-Guericke University Magdeburg, Magdeburg, Germany

{daniel.staegemann, christian.haertel, christian.daase, matthias.pohl, klaus.turowski }@ovgu.de

Keywords: Power Grid, Electrical Grid, Grid Operators, Artificial Intelligence, Machine Learning, Literature Review,

Meta-Review.

Abstract: With the growing energy hunger of today’s society and the ongoing transition from fossil fuels to renewable

energies, the demands on the electrical power grids are growing. Consequently, grid operators are seeking for

ways to improve their performance, flexibility, and reliability. One of these avenues is the use of artificial

intelligence. However, while there are already promising endeavors, this research stream is still far from being

mature. For this reason, in the publication at hand, a meta-review is presented that outlines important themes,

trends, and challenges to provide scientists interested in the domain with a starting point for new projects.

1 INTRODUCTION

The transition from fossil fuels to renewable energies

is one of the major topics of today’s time (Neacsa et

al. 2022) and it can be expected that its importance

will only be increasing in the future (Holechek et al.

2022). While oil and gas are (at least currently)

crucial for the creation of certain products (Allison

and Mandler 2018), in many cases at least the demand

for energy could be satisfied with electrical power

created from renewables. However, just producing

the electricity is not sufficient. Since renewable

energy sources are less consistent in their output and

a widespread power supply failure can result in

massive negative consequences (Busby et al. 2021),

it is also important to have the appropriate

infrastructure to reliably store and distribute it to its

consumers (Hossain et al. 2016; Kalair et al. 2021).

Hence, electrical grid operators play an important role

regarding the success of the transition. To facilitate

their mission and match the supply with the demand,

technological advances such as smart meters, digital

twins, and artificial intelligence play an important

role (Altenburg et al. 2023b; Bose 2017; Sifat et al.

https://orcid.org/0000-0001-9957-1003

https://orcid.org/0009-0001-4904-5643

https://orcid.org/0000-0003-4662-7055

https://orcid.org/0000-0002-6241-7675

https://orcid.org/0000-0002-4388-8914

2023). Therefore, making improvements in these

areas is an important part in propelling the transition

to renewables. However, to be able to bring about

improvements, it is at first important to understand

respective the domain. For this reason, this study aims

to explore the use of artificial intelligence in the

context of electrical power grid operators. The main

goal is to provide a general understanding of

important themes, trends, and challenges, to equip

scientists interested in the field with a starting point

and help steer upcoming research endeavors towards

a meaningful direction. For this reason, in the

publication at hand, a meta-review is conducted that

aims to answer the following research question (RQ):

RQ: What are current themes, trends, and challenges

regarding the use of artificial intelligence in the

context of electrical power grid operators?

To answer the RQ, the paper is structured as

follows. After this introduction, the conducted review

itself is described. This is followed by a discussion of

the findings. Finally, a conclusion is given that also

highlights the limitations of the current study as well

as avenues for future research.

Staegemann, D., Haertel, C., Daase, C., Pohl, M. and Turowski, K.

A Meta-Review on the Use of Artiﬁcial Intelligence in the Context of Electrical Power Grid Operators.

DOI: 10.5220/0012238500003543

In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2023) - Volume 1, pages 335-341

ISBN: 978-989-758-670-5; ISSN: 2184-2809

335

2 THE REVIEW

To provide the desired overview of the domain, a

meta-review was conducted, which means that

instead of primary works, relevant literature reviews

were gathered and analysed. This way, a high-level

picture emerges, which can be used to identify

important streams and themes and to steer future

research endeavors. For this purpose, in the following,

the applied review protocol is outlined in detail as

recommended by (Vom Brocke et al. 2009). The

protocol itself was developed based on (Levy and J.

Ellis 2006; Okoli 2015; Vom Brocke et al. 2009) as

well as this study’s particular needs.

The description of the review process is

succeeded by a brief overview of the identified papers.

Subsequently, the corresponding findings are

discussed.

2.1 Review Protocol

To find the relevant literature that provides an

overview over the use of artificial intelligence in the

context of electrical power grids, several scientific

search engines and databases have been utilized.

Namely, these are Scopus, IEEE Xplore (IEEE),

ACM Digital Library (ACM), and AIS electronic

Library (AISeL). These were chosen for the

following reasons. Scopus is arguably the biggest

abstract and citation database for scientific literature.

IEEE and ACM are highly relevant for the computer

science domain. Finally, AISeL hosts the proceedings

of some of the most important conferences in the field

of computer science and business informatics.

Therefore, by choosing this set of sources, a

comprehensive overview of the relevant literature is

assured. However, to narrow down the deluge of

available publications and to assure a certain

relevancy of those that will be further considered in

the course of the review process, suitable search terms

need to be found, which should, further, be as

consistent as possible between the different databases.

Because the paper’s regarded domain are electrical

power grids, at least one of the terms power grid,

energy grid, electricity grid, or electrical grid is

expected to appear in the title of relevant contributions.

Further, since the paper aims to explore the use of

artificial intelligence in this context, the term artificial

intelligence, its abbreviation AI, machine learning as a

commonly used and referred to subdisciplice of , or its

abbreviation ML are required to be mentioned in

title/abstract/keywords (Scopus), the metadata (ACM),

respectively anywhere (ACM), depending on the

specifics and possibilities of the search engines.

Finally, to accord for the meta-review aspect of

this study, the title also needed to contain review,

survey, overview, study, state of the art, or situation

to cover a wide variety of terms that might be used to

denote the sought after type of work. However, the

latter two parts of the search term were only used for

Scopus, IEEE, and ACM. In AISeL, the options to

finetune the search are limited. Though, the number

of search results is also manageable. Therefore, in

contrast to the other engines, here, only the first part

of the search term was applied. The used search terms

are shown in Table 1.

Table 1: The search terms.

Engine

Search Term

Scopus (TITLE ( "power grid" OR "energy grid"

OR "electricity grid" OR "electrical grid")

AND TITLE-ABS-KEY ( "machine

learning" OR "ML" OR "artificial

intelligence" OR "AI" ) AND TITLE

(review OR survey OR overview OR study

OR "state of the art" OR situation ) ) AND (

LIMIT-TO ( DOCTYPE , "cp" ) OR

LIMIT-TO ( DOCTYPE , "ar" ) )

IEEE

Xplore

("Document Title":"power grid" OR

"Document Title":"energy grid" OR

"Document Title":"electricity grid" OR

"Document Title":"electrical grid") AND

("Document Title":review OR "Document

Title":survey OR "Document

Title":overview OR "Document

Title":study OR "Document Title":"state of

the art" OR "Document Title":situation)

AND ("All Metadata":"machine learning"

OR "All Metadata":"ML" OR "All

Metadata":"artificial intelligence" OR "All

Metadata":"AI")

ACM

Digital

Library

[[Title: "power grid"] OR [Title: "energy

grid"] OR [Title: "electricity grid"] OR

[Title: "electrical grid"]] AND

[[Title: review] OR [Title: survey] OR

[Title: overview] OR [Title: study] OR

[Title: "state of the art"] OR [Title:

situation]] AND [[All: "machine learning"]

OR [All: "ml"] OR [All: "artificial

intelligence"] OR [All: "ai"]]

AIS

electronic

Library

title:( "power grid" OR "energy grid" OR

"electricity grid" OR "electrical grid" )

By applying the search terms to the databases, a total

of 18 journal articles and 44 conference papers was

identified. The distribution across the sources as well

as the overall course of the search can be seen in

Figure 1.

ICINCO 2023 - 20th International Conference on Informatics in Control, Automation and Robotics

336

Figure 1: The review protocol.

In a first filter step, duplicate papers were

removed. There were eleven papers that had

duplicates, with one even appearing across three

databases. Hence, this step led to a reduction by

twelve entries, leaving 13 and 37 contributions for

journal articles respectively conference papers.

For the purpose of further narrowing down the set

of acquired literature, some inclusion and exclusion

criteria have been defined. While the former have to

be completely fulfilled for a paper to be considered,

none of the latter must apply or a paper is rejected.

To ensure a certain quality, only peer-reviewed

conference papers and journal articles are used.

Moreover, due to the design of this study as a meta-

review, the considered contributions have to be either

a literature review or shall at least comprise a review

of the literature that constitutes an important part of

the work. Finally, a paper needs to relevantly

contribute to answering the RQ to justify its inclusion.

As a basic condition to allow the understanding of

the content, the papers have to be written in English.

Hence, papers written in other languages are excluded.

This also applies to papers whose comprehensibility

is insufficient to be deemed beneficial. Additionally,

short papers are also excluded, with the minimum

requirement being defined as a length of at least six

pages. Further, if an updated or extended version of a

paper is found, the older one is discarded.

An overview of the formulated inclusion and

exclusion criteria is given in Table 2.

Table 2: The inclusion and exclusion criteria.

Inclusion Criteria Exclusion Criteria

Paper is a conference

aper or journal article

Paper is not written in

English

Paper is either a literature-

review or contains a

literature review as an

important part of the wor

Paper is not

comprehensible enough to

be beneficial

Paper provides valuable

ut to answer the RQ

Paper has a length of less

than six

Paper has an updated

version that is part of the

literature set

Using these criteria, the identified candidate

papers were filtered by title. However, this was

handled not that strictly, meaning that whenever there

was doubt, the paper was carried over to the next

phase. In doing so, a total of 31 papers was kept.

A Meta-Review on the Use of Artiﬁcial Intelligence in the Context of Electrical Power Grid Operators

337

However, one of them was written in chinese and

was, for this reason, removed. By now, this process

was carried out, using the data exported from the

databases, without a need to actually use the actual

papers. When trying to retrieve them, this was

successful for all of them. Hence, none needed to be

excluded for availability reasons.

Now, abstract and keywords were read to

determine the suitability for answering the RQ. This

left seven papers, with one being afterwards excluded

due to its length of only four pages. Further, one paper

had six pages with the last one not being entirely filled.

However, since it was deemed relevant after reading

the abstract, it was not removed, since the criterion

was slightly vague in that regard and the more

generous interpretation was chosen. As a result, at

this point, the set of literature comprised three journal

articles and three conference papers.

In a final step, these publications were scimmed

over to determine their suitability and one, namely

„Mobile Apps Meet the Smart Energy Grid: A Survey

on Consumer Engagement and Machine Learning

Applications“ (Chadoulos et al. 2020), was excluded.

While it appeared to be relevant, it was determined

that the exploration of the use of machine learning

referred to the mobile apps and was, therefore, a bit

too far from the topical focus of this review. An

additional step to account for updated versions of

papers was not necessary, since there were none left

at this phase, even though, at an earlier point, at least

one of these pairs was noticed. However, both entries

were already removed during the title screening.

Thus, the final set comprises two journal articles

and three conference papers that will be further

described in the following sub-section. While this

number is generally rather low, the positioning of this

study as a meta-review and the comprehensive nature

of the identified publications still allows to get a

meaningful overview of the domain and, thereby,

answer the RQ.

2.2 The Identified Papers

As a result of the described search and filter process,

a final set of five publications emerged that each

contain reviews of the literature relevant to

understand the current themes, trends, and challenges

regarding the use of artificial intelligence in the

context of electrical power grid operators.

A list of these papers is given in Table 3. They

focus on aspects such as, inter alia, fault diagnosis,

risk mitigation, the handling of uncertainty, and the

harnessing of digital twins, thereby covering a rather

broad spectrum within the regarded domain. Further,

it is noticeable that they are all rather recent, with the

oldest one being from 2019.

In (Chai et al. 2019), an overview of AI approaches

for fault diagnosis of power grids is given. The authors

identified nine different methods and describe them as

well as their advantages and disadvantages. While the

paper is a review of the literature and is, therefore,

included, it is not described how the used papers were

identified. Further, the work remains rather high level

and does not go into deep detail. However, the study

provides a starting point for researchers interested in

the domain, who can then further look into the referred

to literature. Moreover, the authors describe several

research trends they expect to gain traction in the future.

The topic of ML-based contingency analysis to

prevent blackouts is focused in (Yang et al. 2020).

While the paper proposes an artifact to address the

issue and is, therefore, not a classical literature review,

it also contains a part that gives a comprehensive

overview of relevant publications in the domain. For

this reason, the respective inclusion criterion was

deemed fulfilled and the paper included. However,

due to its focus, future trends or similar aspects are

not discussed.

Supporting the integration of photovoltaic (PV)

systems with the use of AI is targeted in (Feng et al.

2021). For this purpose, supported by text mining

techniques, the authors conducted an extensive

Table 3: The final set of literature.

No. Reference Yea

Title T

e Source

1 (Chai et al.

2019

)

2019 Artificial intelligence approaches to fault diagnosis in power

rids: A review

Conference

Scopus

2 (Yang et al.

2020)

2020 Power grid contingency analysis with machine learning: A brief

survey and prospects

Conference

Pape

Scopus,

IEEE

3 (Feng et al.

2021)

2021 A taxonomical review on recent artificial intelligence

applications to PV integration into power grids

Journal

Article

Scopus

4 (Cioara et al.

2022

)

2022 An Overview of Digital Twins Application in Smart Energy

Grids

Conference

Scopus

5 (Rahim and

Siano 2022)

2022 A Survey and Comparison of Leading-Edge Uncertainty

Handling Methods for Power Grid Modernization

Journal

Article

ACM

ICINCO 2023 - 20th International Conference on Informatics in Control, Automation and Robotics

338

literature review that also contains a bibliometric

analysis. The study primarily discusses four main

application types, namely forecasting, the detection

of PV arrays as well as faults in PV systems, the

optimizitaion of PV systems‘ designs, and the

optimization of the control of PV systems, but also

dedicates a section to other (related) topics. Further,

potential avenues for future research are outlined.

The application of digital twins in the context of

smart energy grids is regarded in (Cioara et al. 2022).

While this does not necessarily fit the scope of the

study at hand at first glance, there is also a strong

focus on the use of ML in the given context.

Therefore, this publication was deemed suitable for

inclusion. The application domains of digital twins

are identified as the modeling of energy assets, the

diagnosis of faults and security, the operation and

control of grids, as well as ways to develop and

facilitate business models.

Finally, (Rahim and Siano 2022) focusses the

handling of uncertainty in the context of power grids.

For this purpose, they created a comprehensive

literature review on the corresponding state-of-the art

to determine which methods exist. Subsequently,

these were discussed and comparatively analysed. In

addition, they give separate comprehensive

overviews regarding economic operations, bidding

strategies, system expansion, electric transport, and

microgrids. Thus, they provide insights as well as

compiled lists of relevant literature for multiple facets

of the domain, and cover several aspects of the field.

Further, they also outline research gaps and give

future recommendations, thereby providing

researchers interested in the domain with a wealth of

potential avenues to start off their own research.

2.3 Findings

While the acquired papers all differ regarding their

focus and style, together they not only provide a

comprehensive overview of the regarded domain but

there are also certain themes that are somewhat

recurring. For instance, fault diagnosis (Chai et al.

2019; Cioara et al. 2022; Feng et al. 2021) as well as

contingency diagnosis (Rahim and Siano 2022; Yang

et al. 2020) are referred to in multiple papers. This

highlights their importance and is also in accordance

with other works (Altenburg et al. 2023a; Busby et al.

2021) that highlight the potential severity of disorders

of the energy supply. Moreover, the diversity and

vastness of the topic become clearly visible when

considering the high number of different methods and

techniques that are mentioned in the analyzed papers.

While this is attributable to the diversity on artificial

intelligence approaches in general and not to the

specific application domain, it still stands out

compared to many other research streams. Another

topic that is mentioned even more, emphasizing its

relevance, are time series data, their preservation,

analysis, simulation, and forecasting (Cioara et al.

2022; Feng et al. 2021; Rahim and Siano 2022). Also,

forecasting in general is prominently positioned,

appearing in all of the considered papers (Chai et al.

2019; Cioara et al. 2022; Feng et al. 2021; Rahim and

Siano 2022; Yang et al. 2020) in some capacity, yet

there is still much room for improvement.

Other directions for future research that are

identified include the creation of forecasts based on

images, the use of more sophisticated AI approaches,

and the management of uncertainties, for instance, by

providing probabilistic forecasts (Chai et al. 2019;

Feng et al. 2021; Rahim and Siano 2022). Moreover,

the combination of multiple AI technologies as well

as the fusion of multiple data sources to increase the

quality of the outputs has been suggested (Chai et al.

2019). Further, while there are already some papers

dealing with the topic of digital twins for facilitating

power grid operations, this research stream is still in

its infancy and there is much room for advances

(Cioara et al. 2022).

Another important topic is the AI support for the

planning of sizing and siting of facilities that generate

renewable energies (Feng et al. 2021). Due to the

general inconsistency of the production with its

dependence on a multitude of factors (e.g., specifics of

the respective region and its weather), sophisticated

tools can provide invaluable help to maximize the

effective output and contribution to the reliability of the

overall energy supply under consideration of all the

relevant factors and constraints.

Finally, the practical application of the developed

theories and methods was highlighted as an important

part of the overall process that is currently somewhat

lacking (Chai et al. 2019). While there are many

theoretical works, these also need to prove their

effectiveness in real-world-scenarios, which needs to

be facilitated in the future.

3 DISCUSSION

As the contributions that were identified through the

conducted review show, there are many different

directions within the general research stream

regarding the use of AI in the context of electrical

power grid operators.

Moreover, by analysing the found literature, it

became apparent that the domain is not yet matured

A Meta-Review on the Use of Artiﬁcial Intelligence in the Context of Electrical Power Grid Operators

339

and many challenges still need to be addressed.

Examples that especially stood out for their

prevalence and importance were fault diagnosis and

contingency analysis, the handling of time series data,

the fusion of varying input data, and the improvement

of AI algorithms as well as their combination. The

notion regarding the maturity gets further

substantiated by the fact that the oldest contribution

from the identified set of literature is from 2019 and,

thus, rather recent. Since literature reviews are

oftentimes used to consolidate the findings of many

scattered studies when a field otherwise gets too

incomprehensible, their emergence could also be

interpreted as a sign of growing maturity of a field

(Kraus et al. 2020).

While, despite the best efforts to achieve

comprehensiveness, the rather low number of

identified review papers might also be caused by the

choice of consulted databases, it also highlights the

necessity for the creation of more literature reviews

to further capture the domain in breadth as well as in

depth (Kraus et al. 2020).

Further, while the acquired publications already

give a broad overview of the domain, there are also

many additional aspects that can be found in the

topical literature that heavily impact the operations of

grid operators despite not necessarily always being

directly controlled by them. Examples of this are, for

instance, the use of (AI supported) apps to influence

the behavior of energy consumers (Chadoulos et al.

2020), the detection of electricity theft (Yadav and

Kumar 2021), the advancement of domain-specific

explainable AI (Machlev et al. 2022), or the advanced

automation of buildings to improve energy efficiency

(Roselyn et al. 2019). Therefore, a tighter integration

of grid operators, energy producers, and energy

consumers appears reasonable to harness synergies,

which should also be reflected in the literature.

Finally, to reiterate a point from the previous sub-

section, the exploration of real-world case studies as

well as their collection and amalgamation to gain

actionable insights should be highly prioritized.

4 CONCLUSION

While the reliable operation of energy grids was

already a demanding task before, due to the

challenges that come with the transition from fossil

fuels to renewable energies, this issue has been

further exacerbated. Consequently, adequate means

to support this cause are highly sought after. One of

the opportunities that come with the emerging

technological possibilities is the utilization of AI to

facilitate the corresponding operations. However, this

research streams still offers a lot of room for

advancements, which also implies numerous

opportunities for future research. Yet, to

meaningfully contribute, it is important to at first get

an overview of the domain to purposefully steer one’s

endeavors. For this purpose, oftentimes literature

reviews constitute a suitable starting point. However,

due to the vastness of the regarded domain, these can

also only capture certain of its aspects. Therefore, to

get a wider (though admittedly less deep) overall

picture, in the publication at hand, instead, a review

of topical literature reviews, hence a meta-review,

was conducted. In doing so, five contributions were

identified that each provide an overview of pertinent

literature and which together provide a meaningful

picture of current themes, trends, and challenges in

relation to the corresponding research. These findings

were then analysed and discussed, and promising

avenues for future research were outlined.

However, one limitation of this study certainly is

the rather low number of identified reviews. While

the results still provide valuable insights, a higher

number of relevant papers would have still improved

the significance and possibly uncovered additional

insights. Therefore, further expanding the scope by

including more databases or by adding to the search

terms could be valid approaches for the future.

Moreover, conducting a very comprehensive

literature review instead of a meta-review could also

be a promising step. However, due to the very high

number of topical publications, the scope of this

might be too large to be feasible. Besides that,

repeating the current study in several years, when

there might be more relevant reviews also appears

like a worthwhile endeavor. Besides focusing on

expansions and modifications to this study, adding to

the field by creating new literature reviews to capture

additional aspects of the domain can also advance the

corresponding research.

Finally, directly addressing the issues and

opportunities highlighted in this paper should, of

course, also be emphasized as a promising avenue for

researchers who want to comtribute to the domain.

This especially holds true when it comes to

conducting studies in real-world settings, which have

been identified as crucial but too sparse.

REFERENCES

Allison, E., and Mandler, B. (2018). “Non-Fuel Products of

Oil and Gas: Plastics, fertilizers, synthetic fibers,

pharmaceuticals, detergents, and more,”

ICINCO 2023 - 20th International Conference on Informatics in Control, Automation and Robotics

340

Altenburg, T., Staegemann, D., and Turowski, K. (2023a).

“Identifying the Economic Relevance of Smart Meter

Reliability in Germany: A Cost-Benefit Analysis,” in

Proceedings of the 20th International Conference on

Smart Business Technologies, Rome, Italy. 11.07.2023 -

13.07.2023, SCITEPRESS, pp. 203-208 (doi:

10.5220/0012124900003552).

Altenburg, T., Staegemann, D., Volk, M., and Turowski, K.

(2023b). “Reliability Estimation and Optimization of a

Smart Meter Architecture Using a Monte Carlo

Simulation,” SN Computer Science (4:5) (doi:

10.1007/s42979-023-01917-8).

Bose, B. K. (2017). “Artificial Intelligence Techniques in

Smart Grid and Renewable Energy Systems—Some

Example Applications,” Proceedings of the IEEE

(105:11), pp. 2262-2273 (doi: 10.1109/JPROC.2017.2

756596).

Busby, J. W., Baker, K., Bazilian, M. D., Gilbert, A. Q.,

Grubert, E., Rai, V., Rhodes, J. D., Shidore, S., Smith, C.

A., and Webber, M. E. (2021). “Cascading risks:

Understanding the 2021 winter blackout in Texas,”

Energy Research & Social Science (77), p. 102106 (doi:

10.1016/j.erss.2021.102106).

Chadoulos, S., Koutsopoulos, I., and Polyzos, G. C. (2020).

“Mobile Apps Meet the Smart Energy Grid: A Survey on

Consumer Engagement and Machine Learning

Applications,” IEEE Access (8), pp. 219632-219655

(doi: 10.1109/ACCESS.2020.3042758).

Chai, E., Zeng, P., Ma, S., Xing, H., and Zhao, B. (2019).

“Artificial Intelligence Approaches to Fault Diagnosis in

Power Grids: A Review,” in 2019 Chinese Control

Conference (CCC), Guangzhou, China. 27.07.2019 -

30.07.2019, IEEE, pp. 7346-7353 (doi:

10.23919/ChiCC.2019.8865533).

Cioara, T., Anghel, I., Antal, M., Antal, C., Arcas, G. I., and

Croce, V. (2022). “An Overview of Digital Twins

Application in Smart Energy Grids,” in 2022 IEEE 18th

International Conference on Intelligent Computer

Communication and Processing (ICCP), Cluj-Napoca,

Romania. 22.09.2022 - 24.09.2022, IEEE, pp. 25-30

(doi: 10.1109/ICCP56966.2022.10053945).

Feng, C., Liu, Y., and Zhang, J. (2021). “A taxonomical

review on recent artificial intelligence applications to PV

integration into power grids,” International Journal of

Electrical Power & Energy Systems (132), p. 107176

(doi: 10.1016/j.ijepes.2021.107176).

Holechek, J. L., Geli, H. M. E., Sawalhah, M. N., and Valdez,

R. (2022). “A Global Assessment: Can Renewable

Energy Replace Fossil Fuels by 2050?” Sustainability

(14:8), p. 4792 (doi: 10.3390/su14084792).

Hossain, M. S., Madlool, N. A., Rahim, N. A., Selvaraj, J.,

Pandey, A. K., and Khan, A. F. (2016). “Role of smart

grid in renewable energy: An overview,” Renewable and

Sustainable Energy Reviews (60), pp. 1168-1184 (doi:

10.1016/j.rser.2015.09.098).

Kalair, A., Abas, N., Saleem, M. S., Kalair, A. R., and Khan,

N. (2021). “Role of energy storage systems in energy

transition from fossil fuels to renewables,” Energy

Storage (3:1) (doi: 10.1002/est2.135).

Kraus, S., Breier, M., and Dasí-Rodríguez, S. (2020). “The

art of crafting a systematic literature review in

entrepreneurship research,” International

Entrepreneurship and Management Journal (16:3), pp.

1023-1042 (doi: 10.1007/s11365-020-00635-4).

Levy, Y., and J. Ellis, T. (2006). “A Systems Approach to

Conduct an Effective Literature Review in Support of

Information Systems Research,” Informing Science: The

International Journal of an Emerging Transdiscipline (9),

pp. 181-212 (doi: 10.28945/479).

Machlev, R., Heistrene, L., Perl, M., Levy, K. Y., Belikov, J.,

Mannor, S., and Levron, Y. (2022). “Explainable

Artificial Intelligence (XAI) techniques for energy and

power systems: Review, challenges and opportunities,”

Energy and AI (9), p. 100169 (doi:

10.1016/j.egyai.2022.100169).

Neacsa, A., Rehman Khan, S. A., Panait, M., and Apostu, S.

A. (2022). “The Transition to Renewable Energy—A

Sustainability Issue?” in Energy Transition, S. A. R.

Khan, M. Panait, F. Puime Guillen and L. Raimi (eds.),

Singapore: Springer Nature Singapore, pp. 29-72 (doi:

10.1007/978-981-19-3540-4_2).

Okoli, C. (2015). “A Guide to Conducting a Standalone

Systematic Literature Review,” Communications of the

Association for Information Systems (37), pp. 879-910

(doi: 10.17705/1CAIS.03743).

Rahim, S., and Siano, P. (2022). “A survey and comparison

of leading-edge uncertainty handling methods for power

grid modernization,” Expert Systems with Applications

(204), p. 117590 (doi: 10.1016/j.eswa.2022.117590).

Roselyn, J. P., Uthra, R. A., Raj, A., Devaraj, D., Bharadwaj,

P., and Krishna Kaki, S. V. D. (2019). “Development and

implementation of novel sensor fusion algorithm for

occupancy detection and automation in energy efficient

buildings,” Sustainable Cities and Society (44), pp. 85-

98 (doi: 10.1016/j.scs.2018.09.031).

Sifat, M. M. H., Choudhury, S. M., Das, S. K., Ahamed, M.

H., Muyeen, S. M., Hasan, M. M., Ali, M. F., Tasneem,

Z., Islam, M. M., Islam, M. R., Badal, M. F. R., Abhi, S.

H., Sarker, S. K., and Das, P. (2023). “Towards electric

digital twin grid: Technology and framework review,”

Energy and AI (11), p. 100213 (doi:

10.1016/j.egyai.2022.100213).

Vom Brocke, J., Simons, A., Niehaves, B., Reimer, K.,

Plattfaut, R., and Cleven, A. (2009). “Reconstructing the

Giant: On the Importance of Rigour in Documenting the

Literature Search Process,” in Proceedings of the ECIS

2009, Verona, Italy. 08.06.2009-10.06.2009.

Yadav, R., and Kumar, Y. (2021). “The detection of non-

technical losses and electricity theft by smart meter data

and Artificial Intelligence in the context of electric

distribution utilities: A comprehensive review,”

International Journal of Computing and Digital System.

Yang, S., Vaagensmith, B., and Patra, D. (2020). “Power

Grid Contingency Analysis with Machine Learning: A

Brief Survey and Prospects,” in 2020 Resilience Week

(RWS), Salt Lake City, ID, USA. 19.10.2020 -

23.10.2020, IEEE, pp. 119-125 (doi:

10.1109/RWS50334.2020.9241293).

A Meta-Review on the Use of Artiﬁcial Intelligence in the Context of Electrical Power Grid Operators

341