Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- LEMMAS: a secured and trusted Local Energy Market simulation systemPublication . Andrade, Rui; Vitorino, João; Wannous, Sinan; Maia, Eva; Praça, IsabelThe ever changing nature of the energy grid and the addition of novel systems such as the Local Energy Market (LEM) drastically increase its complexity, thus making the management harder and with increased importance at local level. Providing innovative and advanced management solutions is fundamental for the success of this new distributed energy grid paradigm. In this paper we extend Multi-Agent System (MAS) based simulation tool for LEMs called LEMMAS. A cyberattack detection model is developed and integrated in LEMMAS with the objective of preventing cyber-attacks from affecting the negotiations. This model is compared with the previous version which only analysed the trustworthiness of participants. The results show that the cyber-attack detection model drastically increases the security capabilities of LEMMAS.
- A Comparative Analysis of Machine Learning Techniques for IoT Intrusion DetectionPublication . Vitorino, João; Andrade, Rui; Praça, Isabel; Sousa, Orlando Jorge Coelho Moura; Maia, EvaThe digital transformation faces tremendous security challenges. In particular, the growing number of cyber-attacks targeting Internet of Things (IoT) systems restates the need for a reliable detection of malicious network activity. This paper presents a comparative analysis of supervised, unsupervised and reinforcement learning techniques on nine malware captures of the IoT-23 dataset, considering both binary and multi-class classification scenarios. The developed models consisted of Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Isolation Forest (iForest), Local Outlier Factor (LOF) and a Deep Reinforcement Learning (DRL) model based on a Double Deep Q-Network (DDQIN), adapted to the intrusion detection context. The most reliable performance was achieved by LightGBM. Nonetheless, iForest displayed good anomaly detection results and the DRL model demonstrated the possible benefits of employing this methodology to continuously improve the detection. Overall, the obtained results indicate that the analyzed techniques are well suited for IoT intrusion detection.
- A Two Tier Architecture for Local Energy Market Simulation and ControlPublication . Andrade, Rui; Garcia-Rodriguez, Sandra; Praça, Isabel; Vale, ZitaThis paper addresses energy management and security having as basis sensing and monitoring of cyber-physical infrastructure of consumers and prosumers, and their participation in the Local Energy Market (LEM). The vision is to create a layered multi-agent framework that brings a complete view of the cyber-physical system of LEM participants, and provides optimization and control of energy for said participants. The proposed system is separated into a Market layer and a Cyber-Physical layer, each of them providing different services. The cyber-physical layer, represented by SMARTERCtrol system, provides Data Monitoring and Optimized Energy Control of individual building resources. The Market layer, represented by LEM Multi-Agent System, provides Negotiation, Forecasting, and Trust Evaluation. Both systems work together to provide and integrate a tool for simulation and control of LEM.
- UCB1 Based Reinforcement Learning Model for Adaptive Energy Management in BuildingsPublication . Andrade, Rui; Pinto, Tiago; Praça, Isabel; Vale, ZitaThis paper proposes a reinforcement learning model for intelligent energy management in buildings, using a UCB1 based approach. Energy management in buildings has become a critical task in recent years, due to the incentives to the increase of energy efficiency and renewable energy sources penetration. Managing the energy consumption, generation and storage in this domain, becomes, however, an arduous task, due to the large uncertainty of the different resources, adjacent to the dynamic characteristics of this environment. In this scope, reinforcement learning is a promising solution to provide adaptiveness to the energy management methods, by learning with the on-going changes in the environment. The model proposed in this paper aims at supporting decisions on the best actions to take in each moment, regarding buildings energy management. A UCB1 based algorithm is applied, and the results are compared to those of an EXP3 approach and a simple reinforcement learning algorithm. Results show that the proposed approach is able to achieve a higher quality of results, by reaching a higher rate of successful actions identification, when compared to the other considered reference approaches.