Load profile generator and load forecasting for a renewable based microgrid using Self Organizing Maps and neural networks

Application of artificial neural networks (ANNs) to forecast the hourly loads of an electrical power system is examined in this chapter. Two types of ANN’s, i.e., the Kohonen’s self-organising feature maps and the feedforward multilayer neural networks, are employed for load forecasting. Kohonen’s self-organising feature map, which is a kind of ANN with unsupervised learning scheme, is first used to identify those days with similar hourly load patterns. These days with similar load patterns are said to be of the same day type. The load pattern of the day under study is obtained by averaging the load patterns of several days in the past which are of the same day type as the given day. After the hourly load pattern has been reached, a multilayer feedforward neural network is designed to predict daily peak load and valley load. Once the peak load and valley load and the hourly load pattern are available, the desired hourly loads can be readily computed. The effectiveness of the proposed neural network is demonstrated by the short-term load forecasting of Taiwan power system.

The CENIT research project GAD (Demand Active Management), partly supported by the Spanish government, has as its objective the demand side management (DSM) of domestic end-users, smoothing the peaks of energy demand, therefore enhancing the conditions of transport and distribution networks and the quality of energy delivery and service. One of the objectives in the development of the project is the classification of users according to their patterns of daily energy load profiles. Based on daily hour measures from a sample of residential users, a self-organizing map (SOM) has been trained to classify users according to a specific number of resulting patterns of daily load profiles, attached to a number of indices that define the users' energy consumption. The so-trained SOM classifier allows the characterization of future users based on their load profiles, thus estimating their energy consumption habits and potentially manageable energy.

EV charging stations (EVCS) are expected to be deployed at business premises such as universities, hospitals, shopping malls and other office buildings in the future. Their impact on electric grids depends on their combined daily load profile and proportions of its constant current (CC) and constant voltage (CV) load. The daily load profile and the proportion of its CC and CV are different for different factors. The factors include penetration, market share of different EVs, state of charge (SOC) after the last charging, driving distance, number of EVs present at EVCS, rate of arrival and departure of EVs, charging rate, duration of charging etc. Therefore, the aim of this paper is to develop a model that will help forecasting the daily load profile and the proportions of its CC and CV for given stochastic distributions of various factors.

Forecasting the electricity demand for individual households is important for both consumers and utilities due to the increasing decentralized nature of the electricity system. Particularly, utilities often have very little information about their consumers except for aggregate building level loads, without knowledge of interior details about the household appliance sets or occupants. In this paper, we explore the possibility of enhancing the day-ahead load forecasts for hundreds of individual households by clustering their daily load profile history to obtain each consumer's specific typical consumption patterns. The clustering method is based on load profile shape using the Earth Mover's Distance metric to calculate similarity between load profiles. The forecasting methods then predict the next day shape from the empirical probability of previous cluster transitions in the consumer's load history and estimate the magnitude either by using historical load relationships with temperature and forecast temperatures or previous day consumption levels. The generated forecasts are compared to a benchmark Multiple Linear Regression (MLR) day-ahead forecast and persistence forecasts for all individuals. While at the aggregate level the MLR method represents a significant improvement over persistence forecasts, on an individual level we find that the best forecasting model is specific to the individual. In particular, we find that the MLR model produces lower errors when consumers have a consistent daily temperature response and the cluster model with previous day magnitude produces lower errors for consumers whose consumption changes abruptly in magnitude for several days at a time. Our work adds to the state of knowledge surrounding individual household load forecasting and demonstrates the potential for cluster-based methodologies to enhance short term load forecasts.

Forecasting daily urban electric load profiles using artificial neural networks

With an onset of social network amount of data is increasing day by day. In order to analyze the data and extract useful information, the data mining technology can be used. Clustering is one of the popular method of data mining. Clustering can be used for visualizing and analyzing of data. We are discussing Kohonen SOM. We are using neural networks, as a data mining tool which provides statistical observation and layout from big data-sets. We determine how Self-Organizing Kohonen Maps, can be efficiently used for data mining purposes. The Self Organizing Map (SOM) unsupervised learning is an effective computational tool in data mining processes. Self-Organizing Maps (SOMs) used to visualize social network dataset. We used Self-Organizing Map for clustering and analyzing high-dimensional and complex social network datasets. This paper also visualizes SOM neighbor connection, SOM neighbor weight distance, SOM weight position. We perform self organizing map algorithm for social network dataset in matlab.

We have been working on the application of Machining Learning in Metabolomics, Drug-Drug Interaction Discovery and Human Gait Recognition [1-5], profiling large data sets. Extraction of vital information about 1) plant metabolomics that can improve the environment and food quality, 2) in vitro neuronal network behavior patterns for various drugs that can be used to characterize drugs for brain deceases and 3) human gait patterns that can reveal various diseases were among these applications. We have demonstrated with considerable success in using unsupervised clustering techniques to analyze genetic and metabolomic data. This includes analysis of drought resistance in wheat [4] and microbial metagenomes [5].We introduced two methods: Near Unsupervised Learning (NUL) and Sub-sample Error Graphs (SEGs) [5] to analyze large amount of data. Self Organizing Map (SOM), which is one of the widely used Unsupervised Neural Networks, has been used as a data-mining tool due to its ability to map high dimensional data into a two dimensional feature map, which is expected to be topology preserving allowing users to visually identify clusters by their topological relationships in terms of their proximity on the map. The Growing Self Organizing Maps (GSOM) further allows the map size to be determined by the algorithm, which relies upon a user set parameter called Spread Factor (SF) [6]. The wide availability of GPUs for affordable prices allows faster comparison of various SOMs with different maps sizes taking away some of the advantages GSOM claimed. Further development of GSOM into a Dynamic SOM Tree exploits the possibility of varying SF to obtain multiple GSOMs from a small number of compact clusters to a large number of sparse clusters [7]. NUL methods can be applied on GSOM using a small number of labels that should be available for every class. This is however not realistic in some applications where the number of classes cannot be explicitly known. We propose a new method call Deep Near Unsupervised Learning (D-NUL), where Dynamic SOM tree is used instead of GSOM and the number of classes are not assumed to be known. The implementation of Dynamic SOM tree methods with varying SF on GPUs will make the computation with D-NUL possible for many problems in big data analytics.

In this paper, we cluster and analyze data from the past embedded software development projects using self-organizing maps (SOMs)[9] that are a type of artificial neural networks that rely on unsupervised learning. The purpose of the clustering and analysis is to improve the accuracy of predicting the number of errors. A SOMproduces a low-dimensional, discretized representation of the input space of training samples; these representations are called maps. SOMs are useful for visualizing low-dimensional views of high-dimensional data, a multidimensional scaling technique. The advantages of SOMs for statistical applications are as follows: (1) data visualization, (2) information processing on association and recollection, (3) summarizing large-scale data, and (4) creating nonlinear models. To verify our approach, we perform an evaluation experiment that compares SOM classification to product type classification using Welch’s t-test for Akaike’s Information Criterion (AIC). The results indicate that the SOM classification method is more contributive than product type classification in creating estimation models, because the mean AIC of SOM classification is statistically significantly lower.KeywordsSelf-organizing mapsclusteringembedded software development

Self organized mapping of data clusters to neuron groups

The article presents neural network for recognition of driving strategies based on interactions between drivers in road traffic. It analyzes the architecture of the model implemented as a self-organizing map (SOM), consisting of a group of neural networks based on radial basis functions (RBF). It is a training model grounded in the biological foundations of artificial neural networks, in which the training set should consist exclusively of input vectors; wherein the network training algorithm adjusts itself the network's weights to obtain consistent output vectors (i.e. to make presenting sufficiently close input vectors result into the same outputs).\nThe article presents the results of using a new generation of the neural network developed by us, which includes an adaptive learning algorithm to reduce the effect of re-training (overfitting) and false recognition, as well as to improve the determination of the boundaries between clusters.\nThe aim of the research is to outline architecture and structure of the neural network model that allows recognizing strategical characteristics of driving and can identify strategies of interactions between vehicles (their drivers) in road traffic as well as identify behavioral patterns This paper considers driving strategies that characterize the interaction of dyads of vehicles (drivers) moving in road traffic. The research results show that the SOM RBF neural networks can recognize and classify types of interactions in road traffic based on modelling of the analysis of vehicle movement trajectories. Experimental results demonstrate the neural networks architecture and networks learning involving 400 iterations of streaming the training data representing 500 possible simulated interaction situations. This paper presents a novel neural network model for recognition of drivers' behaviour patterns and for classification of driving strategies into five general classes: (1) competition strategy, (2) contest strategy, (3) evasion strategy, (4) compromise strategy, and (5) active confrontation strategy. This neural network has demonstrated a high rate of recognition and concise clusterization of similar driving strategies. The key contribution of this paper: it proposes a neural network model based on Kohonen's Self-Organizing Map (SOM) for detecting drivers' behaviours from vehicle movement patterns - driving strategies - instead of monitoring driver's specific activities.

Application of Self Organizing Map and SRTM data to characterize yardangs in the Lut desert, Iran

A fault detection and diagnosis method for the hydraulic servo system based on adaptive threshold and self-organizing map (SOM) neural network is proposed in this study. The nonlinear, time-varying, fluid-solid coupling properties of the hydraulic servo system are considered. Fault detection is realized based on a two-stage radial basis function (RBF) neural network model. The first-stage RBF neural network is adopted as a fault observer for the hydraulic servo system; the residual error signal is generated by comparing the estimated observer output with the actual measurements. To overcome the drawback of false alarms when the traditional fixed fault threshold is used, an adaptive threshold producer is established by the second-stage RBF neural network. Fault occurrence is detected by comparing the residual error signal with the adaptive threshold. When a system fault is detected, the SOM neural network is employed to implement fault classification and isolation by analyzing the features of the residual error signal. Three types of common faults are simulated to verify the performance and effectiveness of the proposed method. Experimental results demonstrate that the proposed method based on adaptive threshold and SOM neural network is effective in detecting and isolating the failure of the hydraulic servo system.

Indonesia merupakan negara yang mengandalkan hasil dari sektor pertanian dan sektor perkebunan sebagai sumber mata pencaharian dan penopang pembangunan. Peningkatan dan pemeliharaan produktivitas serta efisiensi sektor perkebunan di suatu wilayah dapat dilakukan apabila pemerintah daerah dapat mengetahui potensi daerahnya tersebut. Untuk mengetahui potensi komoditas sektor perkebunan di Indonesia, perlu diketahui hasil clustering dengan algoritma Self Organizing Map (SOM). SOM merupakan algoritma yang melakukan pemetaan dari data yang ada di ruang vektor berdimensi tinggi ke ruang vektor dua dimensi yang terletak pada lokasi yang berdekatan. Selama proses, neuron yang paling cocok dengan pola input dipilih sebagai winner neuron. Analisis clustering akan menggunakan data produksi perkebunan di Indonesia tahun 2020. Pembentukan cluster diawali dengan normalisasi data, kemudian melakukan proses iterasi untuk mendapatkan neuron. Selanjutnya dapat menetukan inter-cluster dan menentukan yang terkecil. Hasil cluster yang terbentuk dilakukan proses validasi menggunakan DBI. Hasil penelitian menghasilkan 5 cluster dengan nilai DBI 0,2039. Setiap cluster yang terbentuk memiliki karakteristik tersendiri diantaranya cluster 1 memiliki hasil produksi perkebunan kakao tertinggi, cluster 2 memiliki nilai tertinggi pada hasil produksi perkebunan kelapa, tebu, dan tembakau, cluster 3 memiliki nilai tertinggi pada hasil produksi perkebunan karet dan kopi, cluster 4 memiliki hasil produksi perkebunan kelapa sawit tertinggi, dan cluster 5 hasil produksi perkebunan teh tertinggi.Kata kunci: perkebunan, Self Organizing Map, clustering¸ Davies Bouldin Index.

ICSSSS: An intelligent channel selection scheme for cognitive radio ad hoc networks using a self organized map followed by simple segregation

Ability to organize data spatially while conserving the topological relation between data features makes the Self Organizing Map (SOM) a very useful tool for analysis and visualization of high dimensional data such as a power transformer's Dissolved Gas Analysis (DGA). Past SOM application required large historical data for its training and has limited fault detection sensitivity. In this paper, the effects of input features and data normalization are studied to enhance SOM's clustering. SOM is trained using DGA results extracted from actual faulted transformers. Combination of input features and data normalization methods are tested on SOM before the best SOM is identified. Validation is conducted using several datasets i.e. the IEC Technical Committee 10 database. Compared with past SOM applications, the proposed SOM required lesser training data, improved SOM's sensitivity in incipient fault detection and has good diagnosis accuracy. The proposed SOM is also compared with other AI-based DGA interpretation method i.e. Support Vector Machine (SVM) for benchmarking.