Analysis and evaluation of five short-term load forecastingtechniques

A review of five widely applied short-term (up to 24 h) load forecasting techniques is presented. These are: multiple linear regression; stochastic time series; general exponential smoothing; state space and Kalman filter; and a knowledge-based approach. A brief discussion of each of these techniques, along with the necessary equations, is presented. Algorithms implementing these forecasting techniques have been programmed and applied to the same database for direct comparison of these different techniques. A comparative summary of the results is presented to give an understanding of the inherent level of difficulty of each of these techniques and their performances     

Proportion assessment of combined PV-wind generating systems

The availability of sun and wind is often in contrast. This fact has led to the proposal of a combined generating system consisting of PV and Wind Generator. This paper introduces a method enabling the assessment of the optimal proportion of PV to wind generator capacities. The method is based on evaluation of costs and loss of load risk (LOLR). According to the Daily Electrical Energy Demand, the required generating system is designed with different alternatives: only PV, only wind generator and a combined PV and wind generator in various proportions. For each alternative, the costs and LOLR are evaluated. LOLR evaluation is performed using a probabilistic model introduced here. The alternatives are compared with each other and the optimal one is determined.