Recently there has been a significant proliferation in the use of forecasting techniques, mainly due to the increased availability and power of computation systems and, in particular, to the usage of ...personal computers. This is also true for power network systems, where energy demand forecasting has been an important field in order to allow generation planning and adaptation. Apart from the quantitative progression, there has also been a change in the type of models proposed and used. In the `70s, the usage of non-linear techniques was generally not popular among scientists and engineers. However, in the last two decades they have become very important techniques in solving complex problems which would be very difficult to tackle otherwise. With the recent emergence of smart grids, new environments have appeared capable of integrating demand, generation, and storage. These employ intelligent and adaptive elements that require more advanced techniques for accurate and precise demand and generation forecasting in order to work optimally. This review discusses the most relevant studies on electric demand prediction over the last 40 years, and presents the different models used as well as the future trends. Additionally, it analyzes the latest studies on demand forecasting in the future environments that emerge from the usage of smart grids.
•Novel application of Reinforcement Learning (RL) to network intrusion detection.•Novel application of RL to a labeled dataset.•Detailed comparison of results with the most common machine learning ...models.•The resulting detector is based on an extremely simple and fast policy network.•The study includes 4 variants of RL algorithms and 2 intrusion detection datasets.
The application of new techniques to increase the performance of intrusion detection systems is crucial in modern data networks with a growing threat of cyber-attacks. These attacks impose a greater risk on network services that are increasingly important from a social end economical point of view. In this work we present a novel application of several deep reinforcement learning (DRL) algorithms to intrusion detection using a labeled dataset. We present how to perform supervised learning based on a DRL framework.
The implementation of a reward function aligned with the detection of intrusions is extremely difficult for Intrusion Detection Systems (IDS) since there is no automatic way to identify intrusions. Usually the identification is performed manually and stored in datasets of network features associated with intrusion events. These datasets are used to train supervised machine learning algorithms for classifying intrusion events. In this paper we apply DRL using two of these datasets: NSL-KDD and AWID datasets. As a novel approach, we have made a conceptual modification of the classic DRL paradigm (based on interaction with a live environment), replacing the environment with a sampling function of recorded training intrusions. This new pseudo-environment, in addition to sampling the training dataset, generates rewards based on detection errors found during training.
We present the results of applying our technique to four of the most relevant DRL models: Deep Q-Network (DQN), Double Deep Q-Network (DDQN), Policy Gradient (PG) and Actor-Critic (AC). The best results are obtained for the DDQN algorithm.
We show that DRL, with our model and some parameter adjustments, can improve the results of intrusion detection in comparison with current machine learning techniques. Besides, the classifier obtained with DRL is faster than alternative models. A comprehensive comparison of the results obtained with other machine learning models is provided for the AWID and NSL-KDD datasets, together with the lessons learned from the application of several design alternatives to the four DRL models.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The purpose of a Network Intrusion Detection System is to detect intrusive, malicious activities or policy violations in a host or host's network. In current networks, such systems are becoming more ...important as the number and variety of attacks increase along with the volume and sensitiveness of the information exchanged. This is of particular interest to Internet of Things networks, where an intrusion detection system will be critical as its economic importance continues to grow, making it the focus of future intrusion attacks. In this work, we propose a new network intrusion detection method that is appropriate for an Internet of Things network. The proposed method is based on a conditional variational autoencoder with a specific architecture that integrates the intrusion labels inside the decoder layers. The proposed method is less complex than other unsupervised methods based on a variational autoencoder and it provides better classification results than other familiar classifiers. More important, the method can perform feature reconstruction, that is, it is able to recover missing features from incomplete training datasets. We demonstrate that the reconstruction accuracy is very high, even for categorical features with a high number of distinct values. This work is unique in the network intrusion detection field, presenting the first application of a conditional variational autoencoder and providing the first algorithm to perform feature recovery.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
The adaptation of energy production to demand has been traditionally very important for utilities in order to optimize resource consumption. This is especially true also in microgrids where many ...intelligent elements have to adapt their behaviour depending on the future generation and consumption conditions. However, traditional forecasting has been performed only for extremely large areas, such as nations and regions. This work aims at presenting a solution for short-term load forecasting (STLF) in microgrids, based on a three-stage architecture which starts with pattern recognition by a self-organizing map (SOM), a clustering of the previous partition via k-means algorithm, and finally demand forecasting for each cluster with a multilayer perceptron. Model validation was performed with data from a microgrid-sized environment provided by the Spanish company Iberdrola.
•We present a solution for short-term load forecasting (STLF) in microgrids.•The system includes pattern recognition, a k-means clustering algorithm, and demand forecasting.•The model is validated using microgrid-sized environment provided by the Spanish company Iberdrola.•The model produces low errors compared to other simple models.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
A network traffic classifier (NTC) is an important part of current network monitoring systems, being its task to infer the network service that is currently used by a communication flow (e.g., HTTP ...and SIP). The detection is based on a number of features associated with the communication flow, for example, source and destination ports and bytes transmitted per packet. NTC is important, because much information about a current network flow can be learned and anticipated just by knowing its network service (required latency, traffic volume, and possible duration). This is of particular interest for the management and monitoring of Internet of Things (IoT) networks, where NTC will help to segregate traffic and behavior of heterogeneous devices and services. In this paper, we present a new technique for NTC based on a combination of deep learning models that can be used for IoT traffic. We show that a recurrent neural network (RNN) combined with a convolutional neural network (CNN) provides best detection results. The natural domain for a CNN, which is image processing, has been extended to NTC in an easy and natural way. We show that the proposed method provides better detection results than alternative algorithms without requiring any feature engineering, which is usual when applying other models. A complete study is presented on several architectures that integrate a CNN and an RNN, including the impact of the features chosen and the length of the network flows used for training.
This work proposes a quantile regression neural network based on a novel constrained weighted quantile loss (CWQLoss) and its application to probabilistic short and medium-term electric-load ...forecasting of special interest for smart grids operations. The method allows any point forecast neural network based on a multivariate multi-output regression model to be expanded to become a quantile regression model. CWQLoss extends the pinball loss to more than one quantile by creating a weighted average for all predictions in the forecast window and across all quantiles. The pinball loss for each quantile is evaluated separately. The proposed method imposes additional constraints on the quantile values and their associated weights. It is shown that these restrictions are important to have a stable and efficient model. Quantile weights are learned end-to-end by gradient descent along with the network weights. The proposed model achieves two objectives: (a) produce probabilistic (quantile and interval) forecasts with an associated probability for the predicted target values. (b) generate point forecasts by adopting the forecast for the median (0.5 quantiles). We provide specific metrics for point and probabilistic forecasts to evaluate the results considering both objectives. A comprehensive comparison is performed between a selection of classic and advanced forecasting models with the proposed quantile forecasting model. We consider different scenarios for the duration of the forecast window (1 h, 1-day, 1-week, and 1-month), with the proposed model achieving the best results in almost all scenarios. Additionally, we show that the proposed method obtains the best results when an additive ensemble neural network is used as the base model. The experimental results are drawn from real loads of a medium-sized city in Spain.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Network Traffic Classification (NTC) is a key piece for network monitoring, Quality-of-Service management and network security. Machine Learning algorithms have drawn the attention of many ...researchers during the last few years as a promising solution for network traffic classification. In Machine Learning, ensemble algorithms are classifiers formed by a set of base estimators that cooperate to build more complex models according to given training and classification strategies. Resulting models normally exhibit significant accuracy improvements compared to single estimators, but also extra time cost, which may obstruct the application of these methods to online NTC. This paper studies and compares the performance of seven popular ensemble algorithms based on Decision Trees, focusing on model accuracy, byte accuracy, and latency to determine whether ensemble learning can be properly applied to this modeling task. We show that some of the studied algorithms overcome single Decision Tree in terms of model accuracy and byte accuracy. However, the notable latency increase hinders the application of these methods in real time contexts. Additionally, we introduce a novel ensemble classifier that exploits the imbalanced populations presented in traffic networks datasets to achieve faster classifications. The experimental results show that our scheme retains the accuracy improvements of ensemble methods but with low latency punishment, enhancing the prospect of ensembles methods for online network traffic classification.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Electricity is indispensable and of strategic importance to national economies. Consequently, electric utilities make an effort to balance power generation and demand in order to offer a good service ...at a competitive price. For this purpose, these utilities need electric load forecasts to be as accurate as possible. However, electric load depends on many factors (day of the week, month of the year, etc.), which makes load forecasting quite a complex process requiring something other than statistical methods. This study presents an electric load forecast architectural model based on an Artificial Neural Network (ANN) that performs Short-Term Load Forecasting (STLF). In this study, we present the excellent results obtained, and highlight the simplicity of the proposed model. Load forecasting was performed in a geographic location of the size of a potential microgrid, as microgrids appear to be the future of electric power supply.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Network Traffic Classification is a fundamental component in network management, and the fast-paced advances in Machine Learning have motivated the application of learning techniques to identify ...network traffic. The intrinsic features of Internet networks lead to imbalanced class distributions when datasets are conformed, phenomena called Class Imbalance and that is attaching an increasing attention in many research fields. In spite of performance losses due to Class Imbalance, this issue has not been thoroughly studied in Network Traffic Classification and some previous works are limited to few solutions and/or assumed misleading methodological approaches. In this article, we deal with Class Imbalance in Network Traffic Classification, studying the presence of this phenomenon and analyzing a wide number of solutions in two different Internet environments: a lab network and a high-speed backbone. Namely, we experimented with 21 data-level algorithms, six ensemble methods and one cost-level approach. Throughout the experiments performed, we have applied the most recent methodological aspects for imbalanced problems, such as: DOB-SCV validation approach or the performance metrics assumed. And last but not least, the strategies to tune parameters and our algorithm implementations to adapt binary methods to multiclass problems are presented and shared with the research community, including two ensemble techniques used for the first time in Machine Learning to the best of our knowledge. Our experimental results reveal that some techniques mitigated Class Imbalance with interesting benefit for traffic classification models. More specifically, some algorithms reached increases greater than 8% in overall accuracy and greater than 4% in AUC-ROC for the most challenging network scenario.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
One of the main challenges of today’s society is the need to fulfill at the same time the two sides of the dichotomy between the growing energy demand and the need to look after the environment. ...Smart Grids are one of the answers: intelligent energy grids which retrieve data about the environment through extensive sensor networks and react accordingly to optimize resource consumption. In order to do this, the Smart Grids need to understand the existing relationship between energy demand and a set of relevant climatic variables. All smart “systems” (buildings, cities, homes, consumers, etc.) have the potential to employ their intelligence for self-adaptation to climate conditions. After introducing the Smart World, a global framework for the collaboration of these smart systems, this paper presents the relationship found at experimental level between a range of relevant weather variables and electric power demand patterns, presenting a case study using an agent-based system, and emphasizing the need to consider this relationship in certain Smart World (and specifically Smart Grid and microgrid) applications.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
PDF
