Efficiently computing weighted proximity relationships in spatial databases

Spatial data mining recently emerges from a number of real applications, such as real-estate marketing, urban planning, weather forecasting, medical image analysis, road traffic accident analysis, etc. It demands for efficient solutions for many new, expensive, and complicated problems. In this paper, we investigate the problem of evaluating the top k distinguished “features” for a “cluster” based on weighted proximity relationships between the cluster and features. We measure proximity in an average fashion to address possible nonuniform data distribution in a cluster. Combining a standard multi-step paradigm with new lower and upper proximity bounds, we presented an efficient algorithm to solve the problem. The algorithm is implemented in several different modes. Our experiment results not only give a comparison among them but also illustrate the efficiency of the algorithm.

Impact of weather dependency on planning decisions in the australian national electricity market

A long-term planning method for the electricity market is to simulate market operation into the future. Outputs from market simulation include indicators for transmission augmentation and new generation investment. A key input to market simulations is demand forecasts. For market simulation purposes, regional demand forecasts for each half-hour interval of the forecasting horizon are required, and they must accurately represent realistic demand profiles and interregional demand relationships. In this paper, a demand model is developed to accurately model these relationships. The effects of uncertainty in weather patterns and inherent correlations between regional demands on market simulation results are presented. This work signifies the advantages of probabilistic modeling of demand levels when making market-based planning decisions.

Short-term electricity price forecasting using wavelet and SVM techniques

In deregulated electricity market, modeling and forecasting the spot price present a number of challenges. By applying wavelet and support vector machine techniques, a new time series model for short term electricity price forecasting has been developed in this paper. The model employs both historical price and other important information, such as load capacity and weather (temperature), to forecast the price of one or more time steps ahead. The developed model has been evaluated with the actual data from Australian National Electricity Market. The simulation results demonstrated that the forecast model is capable of forecasting the electricity price with a reasonable forecasting accuracy.