10023 research outputs found
Sort by
Adaptive Cooling System Control in Data Center with Reinforcement Learning
Get PDFData center cooling system is consuming large amounts of power, which requires effective control to reduce operational costs and deliver optimal server performance. The high power consumption occurs because traditional cooling methods struggle to adapt dynamically to workloads, causing wasteful power consumption. Therefore, this study aimed to explore the use of machine learning methods to improve energy efficiency for data center cooling system. For the experiment, an RL (Reinforcement Learning) model was designed to adjust cooling parameters with dynamic environmental changes. The method focused on optimizing energy efficiency while maintaining stable temperature and humidity control. By applying RL-based control method to PAC system, this study contributed original results that validated the effectiveness of RL-simulated data center environments. Specifically, the stages included developing system model, creating simulations using the PAC control system, and training an RL model with environmental conditions. Data were collected from simulations and analyzed to test the model performance, and the outcomes were presented using a real-time monitoring interface with Flask. The results showed that the RL model achieved an average reward of 4.76 (between -5 and 5), a convergence rate 13.2, a sampling efficiency 10.15, and a stability score 2.6. The model effectively reduced temperature and increased humidity during stressed data center operations. When compared with a fixed cooling system, RL showed superior adaptability to workload variations and reduced unnecessary energy consumption. However, scalability to real data center remained an issue, which required more than simulation validation. In conclusion, the RL-based method optimized efficiency of cooling system, showing the potential to improve energy savings and operational resilience in data center environments
Quantitative Assessment of Blacklist-Based Malicious Domain Filtering for ISP Security: Balancing Protection and Performance
Get PDFThe growing dependence on internet connectivity has heightened cybersecurity threats through malicious domains that facilitate malware, phishing, and botnet operations. These threats significantly impact individuals and organizations, particularly in Internet Service Provider (ISP) settings. Domain filtering on firewalls is a common defensive strategy, yet its effectiveness remains underestimated in large-scale ISP settings. Previous studies have not focused specifically on security systems commonly employed by ISPs, impeding practical adoption. The research contributions are: (1) developing a cost-effective malicious domain filtering approach specifically designed for ISP environments requiring minimal infrastructure investment, and (2) providing quantitative evidence of how blacklist-based filtering impacts both security effectiveness and network performance. The methodology employs alternating firewall states over four time periods to collect metrics including connection flow, bandwidth utilization, and packet rate. Results demonstrate that malicious domain filtering improves security while causing a 2.49% increase in total connection flow due to retry mechanisms. This process yields a 24.5% reduction in total bytes transferred, 10.5% decrease in packets sent, 22.58% reduction in bandwidth, and 8.81% decrease in packet rate. The study identified 1,919 malicious IP addresses blocked from 1,090 user attempts to access harmful domains. These findings confirm blacklist-based domain filtering strengthens security and enhances bandwidth efficiency by mitigating unwanted traffic. This approach is particularly relevant for ISPs, providing a cost-effective solution that balances cybersecurity with optimized network performance, allowing organizations to protect users while maintaining operational effectiveness
Mobil Listrik Sebagai Media Pembelajaran
Get PDFInvensi ini mengenai mobil listrik sebagai media pembelajaran. Invensi ini dapat digunakan dalam pembelajaran praktik bagi peserta
pendidikan/pelatihan kompetensi keahlian otomotif. Bagian mobil listrik sebagai media pembelajaran terdiri dari baterai, pedal gas, kontroler, sistem manajemen baterai (SMB), motor listrik, diferensial, layar indikator, saklar maju-mundur, saklar kecepatan, roda depan, roda belakang, poros roda belakang, kemudi, kartu Radio Frequency Identification/RFID, dan kontaktor, yang dicirikan dimana, mobil listrik sebagai media pembelajaran tersebut menggunakan kartu RFID untuk menentukan apakah sesuai atau tidaknya, jika sesuai maka akan mengaktifkan kontraktor dan juga mengaktifkan kontroler, jika kontroler sudah diaktifkan maka akan mengaktifkan layar indikator, mengaktifkan saklar maju atau mundur, mengaktifkan saklar kecepatan, mengaktifkan pedal gas dan juga mengaktifkan motor listrik sehingga mobil listrik dapat berjalan
