Zeyar Aung

Securing advanced metering infrastructure using intrusion detection system with data stream mining

Advanced metering infrastructure (AMI) is an imperative component of the smart grid, as it is responsible for collecting, measuring, analyzing energy usage data, and transmitting these data to the data concentrator and then to a central system in the utility side. Therefore, the security of AMI is one of the most demanding issues in the smart grid implementation. In this paper, we propose an intrusion detection system (IDS) architecture for AMI which will act as a complimentary with other security measures. This IDS architecture consists of three local IDSs placed in smart meters, data concentrators, and central system (AMI headend). For detecting anomaly, we use data stream mining approach on the public KDD CUP 1999 data set for analysis the requirement of the three components in AMI. From our result and analysis, it shows stream data mining technique shows promising potential for solving security issues in AMI.

An efficient index-based protein structure database searching method

In this paper, we present a novel indexing method called ProtDex to facilitate fast searching in 3-dimensional protein structure database. In ProtDex, we first build an index on the representative properties of all proteins in the database. When evaluating a query, with the help of the index, we filter out a small candidate list of proteins. Then, we can either directly report them, with their respective rankings, to the user, or do the expensive actual alignments on them upon users request. Preliminary experimental results show that our solution is up to 16 times faster than the popular DALI method for database searching task (without actual alignments), while its overall accuracy is only slightly inferior to that of DALI. The software is available upon request by sending emails to the authors.

An ensemble model for day-ahead electricity demand time series forecasting

In this work, we try to solve the problem of day-ahead prediction of electricity demand using an ensemble forecasting model. Based on the Pattern Sequence Similarity (PSF) algorithm, we implemented five forecasting models using different clustering techniques: K-means model (as in original PSF), Self-Organizing Map model, Hierarchical Clustering model, K-medoids model, and Fuzzy C-means model. By incorporating these five models, we then proposed an ensemble model, named Pattern Forecasting Ensemble Model (PFEM), with iterative prediction procedure. We evaluated its performance on three real-world electricity demand datasets and compared it with those of the five forecasting models individually. Experimental results show that PFEM outperforms all those five individual models in terms of Mean Error Relative and Mean Absolute Error.

Discovering Correlated Subspace Clusters in 3D Continuous-Valued Data

Subspace clusters represent useful information in high-dimensional data. However, mining significant subspace clusters in continuous-valued 3D data such as stock-financial ratio-year data, or gene-sample-time data, is difficult. Firstly, typical metrics either find subspaces with very few objects, or they find too many insignificant subspaces – those which exist by chance. Besides, typical 3D subspace clustering approaches abound with parameters, which are usually set under biased assumptions, making the mining process a ‘guessing game’. We address these concerns by proposing an information theoretic measure, which allows us to identify 3D subspace clusters that stand out from the data. We also develop a highly effective, efficient and parameter-robust algorithm, which is a hybrid of information theoretical and statistical techniques, to mine these clusters. From extensive experimentations, we show that our approach can discover significant 3D subspace clusters embedded in 110 synthetic datasets of varying conditions. We also perform a case study on real-world stock datasets, which shows that our clusters can generate higher profits compared to those mined by other approaches.

Artificial Neural Network-based electricity price forecasting for smart grid deployment

A deregulated electricity market is one of the keystones of up-and-coming smart grid deployments. In such a market, forecasting electricity prices is essential to helping stakeholders with the decision making process. Electricity price forecasting is an inherently difficult problem due to its special characteristics of dynamicity and nonstationarity. In our research, we use an Artificial Neural Network (ANN) model on carefully crafted input features for forecasting hourly electricity prices for the next 24 hours. The input features are selected from a pool of features derived from information such as past electricity price data, weather data, and calendar data. A wrapper method for feature selection is used in which the ANN model is continuously trained and updated in order to select the best feature set. The performance of the proposed method is evaluated and compared with the published results of the state-of-the-art Pattern Sequence-based Forecasting (PSF) method on the same data sets and our method is observed to provide superior results.

Automatic 3D Protein Structure Classification without Structural Alignment

In this paper, we present a new scheme named ProtClass for automatic classification of three-dimensional (3D) protein structures. It is a dedicated and unified multiclass classification scheme. Neither detailed structural alignment nor multiple binary classifications are required in this scheme. We adopt a nearest neighbor-based classification strategy. We use a filter-and-refine scheme. In the first step, we filter out the improbable answers using the precalculated parameters from the training data. In the second, we perform a relatively more detailed nearest neighbor search on the remaining answers. We use very concise and effective encoding schemes of the 3D protein structures in both steps. We compare our proposed method against two other dedicated protein structure classification schemes, namely SGM and CPMine. The experimental results show that ProtClass is slightly better in accuracy than SGM and much faster. In comparison with CPMine, ProtClass is much more accurate, while their running times are about the same. We also compare ProtClass against a structural alignment-based classification scheme named DALI, which is found to be more accurate, but extremely slow. The software is available upon request from the authors. The supplementary information on ProtClass method can be found at: http://xena1.ddns.comp.nus.edu.sg/ approximately genesis/PClass.htm.

Database Systems for the Smart Grid

In this chapter, two aspects of database systems, namely database management and data mining, for the smart grid are covered. The uses of database management and data mining for the electrical power grid comprising of the interrelated subsystems of power generation, transmission, distribution, and utilization are discussed.

Probabilistic Forecasting of Solar Power: An Ensemble Learning Approach

Probabilistic forecasts account for the uncertainty in the prediction helping the decision makers take optimal decisions. With the emergence of renewable technologies and the uncertainties involved with the power generated through them, probabilistic forecasts can come to the rescue. Wind power is a mature technology and is in place for decades now, various probabilistic forecasting techniques are used here. On the other hand solar power is an emerging technology and as the technology matures there will be a need for forecasting the power generated days ahead. In this study, we utilize some of the probabilistic forecasting techniques in the field of solar power forecasting. An ensemble approach is used with different machine learning algorithms and different initial settings assuming normal distribution for the forecasts. It is observed that having multiple models with different initial settings gives exceedingly better results when compared to individual models. Getting accurate forecasts will be of great help where the large scale solar farms are integrated into the power grid.

SLiM on Diet

MOTIVATION An important class of protein interactions involves the binding of a proteins domain to a short linear motif (SLiM) on its interacting partner. Extracting such motifs, either experimentally or computationally, is challenging because of their weak binding and high degree of degeneracy. Recent rapid increase of available protein structures provides an excellent opportunity to study SLiMs directly from their 3D structures. RESULTS Using domain interface extraction (Diet), we characterized 452 distinct SLiMs from the Protein Data Bank (PDB), of which 155 are validated in varying degrees-40 have literature validation, 54 are supported by at least one domain-peptide structural instance, and another 61 have overrepresentation in high-throughput PPI data. We further observed that the lacklustre coverage of existing computational SLiM detection methods could be due to the common assumption that most SLiMs occur outside globular domain regions. 198 of 452 SLiM that we reported are actually found on domain-domain interface; some of them are implicated in autoimmune and neurodegenerative diseases. We suggest that these SLiMs would be useful for designing inhibitors against the pathogenic protein complexes underlying these diseases. Our findings show that 3D structure-based SLiM detection algorithms can provide a more complete coverage of SLiM-mediated protein interactions than current sequence-based approaches.

Machine learning techniques for supporting renewable energy generation and integration: a survey

The extraction of energy from renewable sources is rapidly growing. The current pace of technological development makes it commercially viable to harness energy from sun, wind, geothermal and many other renewable sources. Because of the negative effects on the environment and the economy, conventional energy sources like natural gas, crude oil and coal are coming under political and economic pressure. Thus, they require a better mix of energy sources with a higher percentage of renewable energy sources. Harnessing energy from renewable sources range from small scale (e.g., a single household) to large scale (e.g., power plants producing several MWs to a few GWs providing energy to an entire city). An inherent characteristic common to all renewable power plants is that power generation is dependent on environmental parameters and thus cannot be fully controlled or planned for in advance. In a power grid, it is necessary to predict the amount of power that will be generated in the future, including those from the renewable sources, as fluctuations in capacity and/or quality can have negative impacts on the physical health of the entire grid as well as the quality of life of its users. As renewable power plants continue to expand, it will also be necessary to determine their optimal sizes, locations and configurations. In addition, management of the smart grid, in which the renewable energy plants are integrated, is also a challenging problem. In this paper we provide a survey on different machine learning techniques used to address the above issues related to renewable energy generation and integration.