<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div class="moz-text-html" lang="x-unicode">
<p> </p>
<div class="moz-text-html" lang="x-unicode">
<div class="moz-forward-container">
<div class="moz-forward-container">
<p>Dear Colleagues,<br>
<br>
We invite submissions to the special issue of the
Performance Evaluation Journal by Elsevier, on the theme:<br>
<br>
<b>"Artificial Intelligence for Performance and
Reliability Evaluation of Software Systems"<br>
</b> <br>
The deadline for paper submission is May 15th, 2026.<br>
<br>
Details can be found below and at the following link:<br>
<a class="moz-txt-link-freetext"
href="https://www.sciencedirect.com/special-issue/329639/artificial-intelligence-for-performance-and-reliability-evaluation-of-software-systems">https://www.sciencedirect.com/special-issue/329639/artificial-intelligence-for-performance-and-reliability-evaluation-of-software-systems</a></p>
<p>Kind regards,<br>
<br>
Laura Carnevali<br>
Pengfei Chen<br>
Evgenia Smirni<br>
<br>
---------------------</p>
<p><b>CALL FOR PAPERS</b></p>
<p>Nowadays software systems have become deeply pervasive,
with a wide variety of applications (e.g., enterprise
architectures, web services, artificial intelligence,
mobile app) in several domains (e.g., IoT systems,
cyber-physical systems, cloud systems, automotive driving
systems). By leveraging technological advancements in
hardware and communication, software systems have grown in
scale, complexity, and inter-dependence, thus introducing
new challenges in performance and reliability evaluation.
In fact, in distributed and heterogeneous environments,
performance and reliability may be affected by many
different factors (e.g., software architecture, hardware
infrastructure, network communication, runtime
environment).<br>
<br>
Although lots of effort has been contributed to
performance and reliability evaluation of software
systems, challenges still exist. Recently, Artificial
Intelligence (AI) and Machine Learning (ML) methods
provide powerful tools to develop descriptive, predictive,
and prescriptive analytics, being able to learn the system
behavior from observed data, detect anomalies at run time,
and then trigger proactive remediation. At the same time,
notable challenges are introduced as well, e.g., concerned
with availability and quality of data, cost of
re-training, and interpretability of results.<br>
<br>
<br>
This special issue solicits unpublished works on novel
solutions that leverage AI, and in particular ML, to
assess and improve performance and reliability of software
systems. It is intended for researchers, engineers, and
practitioners who study and work on AI/ML methods for
software engineering as well as those interested in
performance and reliability engineering in general. Works
solely focused on improving classification or regression
performance of AI/ML models (e.g., in terms of metrics
such as accuracy, recall, F1 score) are outside the scope
of this special issue. Papers are expected to demonstrate
advances to performance and/or reliability evaluation
methods.<br>
<br>
This special issue seeks submissions of full-length
original research articles. Short communications and
surveys are not in the scope of this special issue.<br>
<br>
Topics of interest for this special issue include, but are
not limited to, the following:</p>
<p><b>AI/ML for performance evaluation of software systems</b></p>
<ul>
<li>Deep learning for performance anomaly detection</li>
<li>Explainable AI for performance diagnosis and
prediction</li>
<li>Forecasting approaches for workload characterization
and prediction</li>
<li>Data-driven performance profiling, benchmarking, and
testing</li>
</ul>
<p><b>AI/ML for reliability evaluation of software systems</b>
</p>
<ul>
<li>Neuro-symbolic approaches for reliability engineering</li>
<li>LLMs for fault localization and root-cause analysis</li>
<li>Generative AI for fault injection</li>
<li>Clustering techniques for alert grouping and
attribution</li>
<li>Time-series analysis for predictive maintenance</li>
</ul>
<b>Applications in cutting-edge software domains</b>
<ul>
<li>Edge-to-cloud computing systems</li>
<li>Microservices architectures</li>
<li>Cyber-physical systems and real-time systems</li>
<li>Software-defined networks</li>
<li>LLM systems</li>
</ul>
<p><b><br>
</b></p>
<p><b>MANUSCRIPT SUBMISSION INFORMATION</b><br>
</p>
<p>General information for submitting papers to PEVA can be
found at <a
href="https://www.sciencedirect.com/journal/performance-evaluation/publish/guide-for-authors">Guide
for Authors - Performance Evaluation</a>. <br>
<br>
Authors should submit their manuscripts to the Performance
Evaluation Editorial System (EM) at <a
href="https://www.editorialmanager.com/peva/default2.aspx">Submission
site for Performance Evaluation</a>, and <b>select
"VSI:AI for PRE of SW" when they reach the \u201cArticle
Type\u201d step in the submission process.</b><br>
</p>
<p><b>EXPECTED TIMELINE</b></p>
<ul>
<li>Manuscript submission deadline: May 15th, 2026</li>
<li>First review round completed: September 15th, 2026</li>
<li>Revised manuscripts due: December 15th, 2026</li>
<li>Final notification: February 15th, 2027</li>
<li>Publication: June 1st, 2027</li>
</ul>
<p><br>
</p>
</div>
</div>
</div>
<p><br>
</p>
<p><br>
</p>
<div class="moz-signature">-- <br>
<p><a
href="https://www.unifi.it/p-doc2-2022-0-A-2c2a3a2c3a27-1.html"><font
color="blue"><strong>Laura Carnevali</strong></font></a> <br>
<strong>Associate Professor</strong> <br>
055 2758519</p>
<p>UNIVERSITĄ DEGLI STUDI DI FIRENZE <br>
<strong>Dipartimento di Ingegneria dell'Informazione (DINFO)</strong></p>
<p>--</p>
</div>
</div>
<br>
</body>
</html>