With the high wind penetration in the power system, accurate and reliable probabilistic wind power forecasting has become even more significant for the reliability of the power system. In this paper, an instance-based transfer learning method combined with gradient boosting decision trees (GBDT) is proposed to develop a wind power quantile regression model. Based on the spatial cross-correlation characteristic of wind power generations in different zones, the proposed model utilizes wind power generations in correlated zones as the source problems of instance-based transfer learning. By incorporating the training data of source problems into the training process, the proposed model successfully reduces the prediction error of wind power generation in the target zone. To prevent negative transfer, this paper proposes a method that properly assigns weights to data from different source problems in the training process, whereby the weights of related source problems are increased, while those of unrelated ones are reduced. Case studies are developed based on the dataset from the Global Energy Forecasting Competition 2014 (GEFCom2014). The results confirm that the proposed model successfully improves the prediction accuracy compared to GBDT-based benchmark models, especially when the target problem has a small training set while resourceful source problems are available.

No abstract

No abstract

Abstract:The strength of time series modeling is generally not used in almost all current intrusion detection and prevention systems. By having time series models, system administrators will be able to better plan resource allocation and system readiness to defend against malicious activities. In this paper, we address the knowledge gap by investigating the possible inclusion of a statistical based time series modeling that can be seamlessly integrated into existing cyber defense system. Cyber-attack processes exhibit long range dependence and in order to investigate such properties a new class of Generalized Autoregressive Moving Average (GARMA) can be used. In this paper, GARMA (1, 1; 1, ±) model is fitted to cyber-attack data sets. Two different estimation methods are used. Point forecasts to predict the attack rate possibly hours ahead of time also has been done and the performance of the models and estimation methods are discussed. The investigation of the case-study will confirm that by exploiting the statistical properties, it is possible to predict cyber-attacks (at least in terms of attack rate) with good accuracy. This kind of forecasting capability would provide sufficient early-warning time for defenders to adjust their defense configurations or resource allocations.

No abstract