{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:59:02Z","timestamp":1782417542822,"version":"3.54.5"},"reference-count":9,"publisher":"STEF92 Technology","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,15]]},"abstract":"<jats:p>Industrial Control Systems (ICS) are foundational to critical national infrastructure, operating vital processes in sectors such as water treatment, power generation, oil and gas, and manufacturing. As these systems become increasingly integrated with information technology through the Industrial Internet of Things (IIoT), they face growing risks from cyber threats. As Bulgaria accelerates the integration of renewable energy infrastructure, particularly solar, wind, and gas-to-power systems, the cybersecurity of these digital assets becomes a national imperative. This study presents a cybersecurity risk modeling framework for renewable energy systems, combining open-source intelligence (OSINT), port and protocol analysis, and advanced machine learning techniques. Traditional security approaches, which focus on signature-based detection, have proven inadequate in the face of sophisticated, stealthy, or zero-day attacks. To address this, our research proposes a data-driven framework for detecting anomalies in ICS environments using time-series prediction models. Specifically, we evaluate CNN-LSTM hybrids, LSTM Autoencoders, and Isolation Forests across two widely used datasets\ufffdSWaT (Secure Water Treatment) and BATADAL (Battle of the Attack Detection Algorithms). This report presents a comprehensive comparison of these techniques, analyzing their detection accuracy, cross-domain robustness, and operational feasibility. Our findings demonstrate that hybrid deep learning models can effectively identify cyber-physical anomalies in ICS telemetry data, although domain-specific calibration remains crucial for optimal performance.<\/jats:p>","DOI":"10.5593\/sgem2025\/4.1\/s16.18","type":"proceedings-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T10:08:13Z","timestamp":1763806093000},"page":"141-150","source":"Crossref","is-referenced-by-count":1,"title":["RENEWABLE ENERGY INFRASTRUCTURE: VULNERABILITY MAPPING AND PREDICTIVE RISK MODELING"],"prefix":"10.5593","volume":"25","author":[{"given":"Velizar","family":"Varbanov","sequence":"first","affiliation":[{"name":"Institute of Information and Communication Technologies \ufffd Bulgarian Academy of Sciences","place":["Bulgaria"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatiana","family":"Atanasova","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Technologies \ufffd Bulgarian Academy of Sciences","place":["Bulgaria"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3602","reference":[{"key":"ref=1","unstructured":"[1] European Union Agency for Cybersecurity, ENISA. Threat Landscape for ICS. 2024. https:\/\/www.enisa.europa.eu\/publications\/enisa-threat-landscape-2024"},{"key":"ref=2","doi-asserted-by":"crossref","unstructured":"[2] Varbanov, V. Advancing Cyber Threat Intelligence through Machine Learning Algorithms. AICCONF '24: Cognitive Models and Artificial Intelligence Conf., ACM, 2024.","DOI":"10.1145\/3660853.3660879"},{"key":"ref=3","unstructured":"[3] Goodfellow, I., Bengio, Y., & Courville, A. Deep Learning. MIT Press. 2016, www.deeplearningbook.org"},{"key":"ref=4","doi-asserted-by":"crossref","unstructured":"[4] Goh, J., Adepu, S., Junejo, K.N., Mathur, A. A Dataset to Support Research in the Design of Secure Water Treatment Systems. In: Havarneanu, G., Setola, R., Nassopoulos, H., Wolthusen, S. (eds) Critical Information Infrastructures Security. CRITIS 2016. LNCS, 10242. Springer, Cham. 2017.","DOI":"10.1007\/978-3-319-71368-7_8"},{"key":"ref=5","doi-asserted-by":"crossref","unstructured":"[5] Taormina R., Galelli, S., Tippenhauer, N.O., Salomons, E., Ostfeld, A., Eliades, D.G., Aghashahi, M., Sundararajan, R., Pourahmadi, M., Banks, M.K., Brentan, B.M., Campbell, E., Lima, G., Manzi, D., Ayala-Cabrera, D., Herrera, M., Montalvo, I., Izquierdo, J., Luvizotto E.Jr., Chandy, S.E., Rasekh, A., Barker, Z.A., Campbell, B., Shafiee, M.E., Giacomoni, M., Gatsis, N., Taha, A., Abokifa, A.A., Haddad, K., Lo C.S., Biswas, P., Pasha, Bijay Kc M.F.K., Somasundaram, S.L., Housh, M. and Ziv Ohar. Battle of the Attack Detection Algorithms: Disclosing Cyber Attacks on Water Distribution Networks, J. of Water Resources Planning and Management, 144 (8), 2018.","DOI":"10.1061\/(ASCE)WR.1943-5452.0000969"},{"key":"ref=6","doi-asserted-by":"crossref","unstructured":"[6] Saif, M., Islam, A., Rahman, M., Chakraborty, D., Kabir, S., Shufian, A. and Sheikh, P.P. Enhancing Industrial Control System Security: An Isolation Forest-Based Anomaly Detection Model for Mitigating Cyber Threats. J. of Eng. Res. and Reports 26 (3):161-73. 2024.","DOI":"10.9734\/jerr\/2024\/v26i31102"},{"key":"ref=7","doi-asserted-by":"crossref","unstructured":"[7] Dineva, K., Atanasova, T. Machine Learning Solution for IoT Big Data. 20th Int. Multidisciplinary Scientific Geoconference SGEM 2020, 18-24 Albena, Bulgaria, 2.1, 207-214, 2020.","DOI":"10.5593\/sgem2020\/2.1\/s07.027"},{"key":"ref=8","unstructured":"[8] Ngoc Le, S. Anomaly Detection with SWaT Dataset. GitHub Repository, 2023."},{"key":"ref=9","unstructured":"[9] Chen, S.Y. A Survey on BATADAL Dataset. GitHub Repository, 2023."}],"event":{"name":"25th SGEM International Multidisciplinary Scientific GeoConference 2025","theme":"Earth and Planetary Sciences","location":"Albena, Bulgaria","acronym":"SGEM2025","number":"25","sponsor":["SGEM WORLD SCIENCE (SWS) Scholarly Society, Austria"],"start":{"date-parts":[[2025,6,29]]},"end":{"date-parts":[[2025,7,6]]}},"container-title":["SGEM International Multidisciplinary Scientific GeoConference\ufffd EXPO Proceedings","25th International Multidisciplinary Scientific GeoConference Proceedings SGEM2025, Energy and Clean Technologies, Vol25, Issue 4.1"],"original-title":[],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:25:50Z","timestamp":1782415550000},"score":1,"resource":{"primary":{"URL":"https:\/\/epslibrary.at\/items\/66185f19-aee7-4539-86e3-7413f82fd5d1\/renewable-energy-infrastructure-vulnerability-mapping-and-predictive-risk-modeling"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,15]]},"references-count":9,"URL":"https:\/\/doi.org\/10.5593\/sgem2025\/4.1\/s16.18","relation":{},"ISSN":["1314-2704"],"issn-type":[{"value":"1314-2704","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8,15]]}}}