Multinodal load forecasting deals with the loads of several interest nodes in an electrical network system, which is also known as bus load forecasting. To perform this demand, a technique that is precise, reliable, and has short-time processing is necessary. This paper uses two methodologies for short-term multinodal load forecasting. The first individually forecasts the local loads and the second forecasts the global load and individually forecasts the load participation factors to estimate the local loads. For the forecasts, a modified general regression neural network and a procedure to automatically reduce the number of inputs of the artificial neural networks are proposed. To design the forecasters, the previous study of the local loads was not necessary, thus reducing the complexity of the multinodal load forecasting. Tests were carried out by using a New Zealand distribution subsystem and the results obtained were found to be compatible with those available in the specialized literature.

Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

A Hybrid ART-GRNN Online Learning Neural Network With a $\varepsilon$ -Insensitive Loss Function

Traditionally, load forecasting models are trained offline and generate predictions online. However, the pure batch learning approach fails to incorporate new load information available in real-time. Conversely, online learning allows for efficient adaptation of newly incoming information. This letter advocates a novel online ensemble learning approach for load forecasting by combining batch and online learning. While the individual batch models provide an appropriate forecast basis, the online ensemble combines their predictions and ensures adaptivity for online application. In that respect, we propose a modified Passive Aggressive Regression (PAR) model to implement the online ensemble forecasting. Case studies on a real-world load dataset show that the proposed method can improve the forecasting accuracy significantly compared to a pure batch learning approach.

Online Ensemble Learning for Load Forecasting

Designers are required to plan for future expansion and also to estimate the grid’s future utilization. This means that an effective modeling and forecasting technique, which will use efficiently the information contained in the available data, is required, so that important data properties can be extracted and projected into the future. This study proposes an adaptive method based on the multi-model partitioning algorithm (MMPA), for short-term electricity load forecasting using real data. The grid’s utilization is initially modeled using a multiplicative seasonal ARIMA (autoregressive integrated moving average) model. The proposed method uses past data to learn and model the normal periodic behavior of the electric grid. Either ARMA (autoregressive moving average) or state-space models can be used for the load pattern modeling. Load anomalies such as unexpected peaks that may appear during the summer or unexpected faults (blackouts) are also modeled. If the load pattern does not match the normal behavior of the load, an anomaly is detected and, furthermore, when the pattern matches a known case of anomaly, the type of anomaly is identified. Real data were used and real cases were tested based on the measurement loads of the Hellenic Public Power Cooperation S.A., Athens, Greece. The applied adaptive multi-model filtering algorithm identifies successfully both normal periodic behavior and any unusual activity of the electric grid. The performance of the proposed method is also compared to that produced by the ARIMA model.

Adaptive load forecasting of the Hellenic electric grid

The main purpose of this paper is to achieve a comparative analysis among Autoregressive Integrated Moving Average model, Artificial Neural Networks and Adaptive Neuro- Fuzzy System techniques for load demand forecasting in distribution substations. The system inputs are three load demand time series, which are composed by data measured at intervals of five minutes each, during seven days, from substations located at Andradina, Ubatuba and Votuporanga. Autoregressive Integrated Moving Average models with suitable results have been analyzed, whereas several input configurations and different architectures have been investigated for Artificial Neural Networks and Adaptive Neuro-Fuzzy System techniques aiming the forecasting of twelve further steps. The results showed the Artificial Neural Network based technique superiority for such forecasting, followed by Autoregressive Integrated Moving Average model and Adaptive Neuro-Fuzzy approach. The load demand forecasting can minimize costs of energy generation as well as improve the electric power system safety.

Very Short-Term Load Forecasting Based on ARIMA Model and Intelligent Systems

Short term load forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian adaptive resonance theory (GA) and the generalized regression neural network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the support vector regression.

Mohd Suhairi Shah

Papers

Short Term Load Forecasting Using a Hybrid Neural Network