Abstract The network security analyzers use intrusion detection systems (IDSes) to distinguish malicious traffic from benign ones. The deep learning-based (DL-based) IDSes are proposed to auto-extract high-level features and eliminate the time-consuming and costly signature extraction process. However, this new generation of IDSes still needs to overcome a number of challenges to be employed in practical environments. One of the main issues of an applicable IDS is facing traffic concept drift, which manifests itself as new (i.e. , zero-day) attacks, in addition to the changing behavior of benign users/applications. Furthermore, a practical DL-based IDS needs to be conformed to a distributed (i.e. , multi-sensor) architecture in order to yield more accurate detections, create a collective attack knowledge based on the observations of different sensors, and also handle big data challenges for supporting high throughput networks. This paper proposes a novel multi-agent network intrusion detection framework to address the above shortcomings, considering a more practical scenario (i.e., online adaptable IDSes). This framework employs continual deep anomaly detectors for adapting each agent to the changing attack/benign patterns in its local traffic. In addition, a federated learning approach is proposed for sharing and exchanging local knowledge between different agents. Furthermore, the proposed framework implements sequential packet labeling for each flow, which provides an attack probability score for the flow by gradually observing each flow packet and updating its estimation. We evaluate the proposed framework by employing different deep models (including CNN-based and LSTM-based) over the CIC-IDS2017 and CSE-CIC-IDS2018 datasets. Through extensive evaluations and experiments, we show that the proposed distributed framework is well adapted to the traffic concept drift. More precisely, our results indicate that the CNN-based models are well suited for continually adapting to the traffic concept drift (i.e. , achieving an average detection rate of above 95% while needing just 128 new flows for the updating phase), and the LSTM-based models are a good candidate for sequential packet labeling in practical online IDSes (i.e. , detecting intrusions by just observing their first 15 packets).

The penetration of renewable energy sources (RES) has caused some challenges for grid operation, including frequency variation, low power quality, and reliability issues. These challenges can be mitigated with the help of battery energy storage systems (BESS) which are characterized by long lifetime and high-power capability. Among the different types of high-power storage devices, lithium titanate oxide (LTO) batteries and lithium-ion capacitor (LIC) cells attract more attention. The performance behavior, the total cost of the battery system, and the system’s size are some other criteria for cell selection. This research compares the performance behavior of an LTO battery type for this application with two LIC type storage system at positive and negative temperatures and also considers the system size, cost, and lifetime of the BESS. The result proves that LICs are better candidates for low and high temperature applications in terms of energy efficiency and capacity drop. However, in terms of cost and size, the high energy LTO cells are a better selection.

Research progress on the optimization in order to obtain the value of material constants for a set of creep damage constitutive equations was presented, including (1) a brief review of continuum creep damage modeling and the designs of objective functions; (2) case study reporting the influence of the initial start points on the final results; and (3) discussion and conclusion. As far as the authors know, there is no any published paper addressing specifically on the influence of starting values on the final results. In order to overcome the difficulty or inaccuracy it is suggested in this paper to (1) check the accuracy of a particular set of experimental data, (2) review the method to depict the relationship between the stress level and minimum strain rate, (3) to design a better objective functions so that the convergence is ensured to all the stress levels. Proceedings 28th European Conference on Modelling and Simulation