<!DOCTYPE html>
<html>
  <head>

    <meta http-equiv="content-type" content="text/html; charset=UTF-8">
  </head>
  <body text="#000000" bgcolor="#FFFFFF">
    <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"
            moz-do-not-send="true">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 moz-do-not-send="true"
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 moz-do-not-send="true"
            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>
  </body>
</html>