Approach For Short-term Load Forecasting Research Articles

Bottom-Up Short-Term Load Forecasting Considering Macro-Region and Weighting by Meteorological Region

Activities related to the planning and operation of power systems use premise load forecasting, which is responsible for providing a load estimative for a given horizon that assists mainly in the operation of an electrical system. Hierarchical short-term load forecasting (STLF) becomes an approach used for this purpose, where the overall forecast is performed through system partition in smaller macro-regions and, soon after, is aggregated to compose a global forecast. In this context, this paper presents a bottom-up STLF approach for macro-regions. The main innovation is the Average Consumption per Meteorological Region (CERM) index, used to weigh the importance of each station meteorological (EM) in total load demand. Another index, the Variation of Load and Temperature (IVCT), based on historical temperature and demand changes, is proposed. These indexes are incorporated into an ANN model of the multi-layer perceptron type (MLP). The results showed a higher average performance of the index CERM and variable IVCT in relation to the other combinations performed, and the best results were used to compose the prediction of the MTR. Finally, the proposed model presented a Mean Absolute Percentage Error lower than 1%, presenting superior performance compared to an aggregate model for MTR, which shows the efficiency and contribution of the proposed methodology.

Deep Learning-Based Short-Term Load Forecasting Approach in Smart Grid With Clustering and Consumption Pattern Recognition

Different aggregation levels of the electric grid’s big data can be helpful to develop highly accurate deep learning models for Short-term Load Forecasting (STLF) in electrical networks. Whilst different models are proposed for STLF, they are based on small historical datasets and are not scalable to process large amounts of big data as energy consumption data grow exponentially in large electric distribution networks. This paper proposes a novel hybrid clustering-based deep learning approach for STLF at the distribution transformers’ level with enhanced scalability. It investigates the gain in training time and the performance in terms of accuracy when clustering-based deep learning modeling is employed for STLF. A k-Medoid based algorithm is employed for clustering whereas the forecasting models are generated for different clusters of load profiles. The clustering of the distribution transformers is based on the similarity in energy consumption profile. This approach reduces the training time since it minimizes the number of models required for many distribution transformers. The developed deep neural network consists of six layers and employs Adam optimization using the TensorFlow framework. The STLF is a day-ahead hourly horizon forecasting. The accuracy of the proposed modeling is tested on a 1,000-transformer substation subset of the Spanish distribution electrical network data containing more than 24 million load records. The results reveal that the proposed model has superior performance when compared to the state-of-the-art STLF methodologies. The proposed approach delivers an improvement of around 44% in training time while maintaining accuracy using single-core processing as compared to non-clustering models.

A Statistical Data Selection Approach for Short-Term Load Forecasting Using Optimized ANFIS

Volume of the forecasting data and good data analysis are the key factors that influence the accuracy of forecasting algorithm because it depends on data identification and model parameters. This paper focuses on data selection approach for short-term load forecasting. It involves formulating data selection algorithm to identify factors (variables) that influence energy demand at utility level. Correlation Analysis (CA) and Hypothesis Test (HT) are used in the selection, where Wavelet Transform (WT) is applied to bridge the gap between the forecasting variables. This results to three groups of data; data without CA, HT and WT, data with CA, HT but without WT and data with CA, HT and WT. An optimized adaptive neuro-fuzzy inference system (ANFIS) using Cuckoo Search Algorithm (CS) is used to conduct the forecasting. The essence is to reduce the computational difficulty associated with the gradient descent (GD) algorithm in traditional ANFIS. With the three data groups, it is observed that CHW data can give satisfactory results more than the NCNHNW and NCNHW data. Also the numerical results shows that CHW data selection approach can give a MAPE of 0.63 against the bench-mark approach with MAPE of 3.55. This indicates that it is good practice to select the actual data and process it before the forecasting.

An ensemble method of full wavelet packet transform and neural network for short term electrical load forecasting

Due to high penetration of distributed energy resources, integration of intermittent renewable energy resources and deployment of demand-side management, highly accurate short-term load forecasting becomes increasingly important. This paper proposes a full wavelet neural network approach for short-term load forecasting, which is an ensemble method of full wavelet packet transform and neural networks. The full wavelet packet transform model is used to decompose the load profile and various features into several components with different frequencies and these components are used to train the neural networks. To perform load forecasting, the full wavelet packet transform model decomposes features into various components that are fed into the trained neural networks, and the outputs of the neural networks are constructed as the forecasted load. The proposed model is applied for load prediction in the electric market of Ontario, Canada. Simulation results show that the proposed approach reduces the mean absolute percentage error (MAPE) by 20% in comparison with the traditional neural network method. The proposed approach can be used by utilities and system operators to forecast electricity consumption with high accuracy, which is highly demanded for renewable energy integration, demand-side management and power system operation.

A Hybrid Approach to Short-Term Load Forecasting Aimed at Bad Data Detection in Secondary Substation Monitoring Equipment.

Bad data as a result of measurement errors in secondary substation (SS) monitoring equipment is difficult to detect and negatively affects power system state estimation performance by both increasing the computational burden and jeopardizing the state estimation accuracy. In this paper a short-term load forecasting (STLF) hybrid strategy based on singular spectrum analysis (SSA) in combination with artificial neural networks (ANN), is presented. This STLF approach is aimed at detecting, identifying and eliminating and/or correcting such bad data before it is provided to the state estimator. This approach is developed to improve the accuracy of the load forecasts and it is tested against real power load data provided by electricity suppliers. Depending on the week considered, mean absolute percentage error (MAPE) values which range from 1.6% to 3.4% are achieved for STLF. Different systematic errors, such as gain and offset error levels and outliers, are successfully detected with a hit rate of 98%, and the corresponding measurements are corrected before they are sent to the control center for state estimation purposes.

Lambda-Based Data Processing Architecture for Two-Level Load Forecasting in Residential Buildings

Building energy management systems (BEMS) have been intensively used to manage the electricity consumption of residential buildings more efficiently. However, the dynamic behavior of the occupants introduces uncertainty problems that affect the performance of the BEMS. To address this uncertainty problem, the BEMS may implement load forecasting as one of the BEMS modules. Load forecasting utilizes historical load data to compute model predictions for a specific time in the future. Recently, smart meters have been introduced to collect electricity consumption data. Smart meters not only capture aggregation data, but also individual data that is more frequently close to real-time. The processing of both smart meter data types for load forecasting can enhance the performance of the BEMS when confronted with uncertainty problems. The collection of smart meter data can be processed using a batch approach for short-term load forecasting, while the real-time smart meter data can be processed for very short-term load forecasting, which adjusts the short-term load forecasting to adapt to the dynamic behavior of the occupants. This approach requires different data processing techniques for aggregation and individual of smart meter data. In this paper, we propose Lambda-based data processing architecture to process the different types of smart meter data and implement the two-level load forecasting approach, which combines short-term and very short-term load forecasting techniques on top of our proposed data processing architecture. The proposed approach is expected to enhance the BEMS to address the uncertainty problem in order to process data in less time. Our experiment showed that the proposed approaches improved the accuracy by 7% compared to a typical BEMS with only one load forecasting technique, and had the lowest computation time when processing the smart meter data.

An ensemble approach for short-term load forecasting by extreme learning machine

This paper proposes a novel ensemble method for short-term load forecasting based on wavelet transform, extreme learning machine (ELM) and partial least squares regression. In order to improve forecasting performance, a wavelet-based ensemble strategy is introduced into the forecasting model. The individual forecasters are derived from different combinations of mother wavelet and number of decomposition levels. For each sub-component from the wavelet decomposition, a parallel model consisting of 24 ELMs is invoked to predict the hourly load of the next day. The individual forecasts are then combined to form the ensemble forecast using the partial least squares regression method. Numerical results show that the proposed method can significantly improve forecasting performance.

Techniques of applying wavelet de-noising into a combined model for short-term load forecasting

Electrical load time series are non-stationary and highly noisy because a variety of factors affect electrical markets. The direct forecasting of electrical load with noisy data is usually subject to large errors. This paper proposes a novel approach for short-term load forecasting (STLF) by applying wavelet de-noising in a combined model that is a hybrid of the seasonal autoregressive integrated moving average model (SARIMA) and neural networks. The process of the proposed approach first decomposes the historical data into an approximate part associated with low frequency and a detailed part associated with high frequencies via a wavelet transform. A SARIMA and a back propagation neural network (BPNN) are then established by the low-frequency signal to forecast the future value. Finally, the short-term load is forecasted by combining the prediction values of SARIMA and BPNN, and the weights of the combination are determined using a variance–covariance approach. To evaluate the performance of the proposed approach, the electricity load data in New South Wales, Australia, are used as an illustrative example. A comparison of the results with other models shows that the proposed model can effectively improve the forecasting accuracy.

Short Term Load Forecasting Using Curve Fitting Prediction Optimized By Bacterial Foraging Optimization

Short term load forecast plays an important role in electric power system planning, design and operation. Curve fitting prediction technique and time series models are used for hourly loads forecasting of the week days. In this paper a new approach for short-term load forecasting is introduced. This approach is curve fitting prediction technique combined with Bacterial Foraging optimization. BFO is used to get optimum parameters of the model describing the system with minimum error between actual and forecasted load. The suitability of the proposed approach is illustrated through an application to the actual load data of New England control area.

Short-Term Load Forecasting Using Curve Fitting Prediction Optimized by Genetic Algorithms

This paper presents a new approach for short-term load forecasting (STLF). Curve fitting prediction and time series models are used for hourly loads forecasting of the week days. The curve fitting prediction (CFP) technique combined with genetic algorithms (GAs) is used for obtaining the optimum parameters of Gaussian model to obtain a minimum error between actual and forecasted load. A new technique for selecting the training vectors is introduced. The proposed model is simple, fast, and accurate. It is shown that the proposed approach provide very accurate hourly load forecast. Also it is shown that the proposed method can provide more accurate results than the conventional techniques. The mean percent relative error of the model is less than 1 %.

A NOVEL APPROACH FOR SHORT-TERM LOAD FORECASTING USING SUPPORT VECTOR MACHINES

A support vector machine (SVM) modeling approach for short-term load forecasting is proposed. The SVM learning scheme is applied to the power load data, forcing the network to learn the inherent internal temporal property of power load sequence. We also study the performance when other related input variables such as temperature and humidity are considered. The performance of our proposed SVM modeling approach has been tested and compared with feed-forward neural network and cosine radial basis function neural network approaches. Numerical results show that the SVM approach yields better generalization capability and lower prediction error compared to those neural network approaches.