Hybrid short term load forecasting using ARIMA-SVM

Karthika, S.; Margaret, Vijaya; Balaraman, K.

doi:10.1109/ipact.2017.8245060

Cited by 48 publications

(24 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the introduction of random and intermittent energy sources in the grid, the traditional statistical approach does not work for the complex load curve. The use of machine learning models that overcame the shortcoming of statistical methods in STLF models were widely implemented for this class of problems, including support vector machine (SVM) [12], [13], light gradient boosting machine (LightGBM) [14] and artificial neural network(ANN) [15]- [17]. SVM's primary methodology is based on the principle of structural risk minimization.…”

Section: Related Workmentioning

confidence: 99%

Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Goh

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Load forecasting is critical for power system operation and market planning. With the increased penetration of renewable energy and the massive consumption of electric energy, improving load forecasting accuracy has become a difficult task. Recently, it was demonstrated that deep learning models perform well for short-term load forecasting (STLF). However, prior research has demonstrated that the hybrid deep learning model outperforms the single model. We propose a hybrid neural network in this article that combines elements of a convolutional neural network (1D-CNN) and a long short memory network (LSTM) in novel ways. Multiple independent 1D-CNNs are used to extract load, calendar, and weather features from the proposed hybrid model, while LSTM is used to learn time patterns. This architecture is referred to as a CNN-LSTM network with multiple heads (MCNN-LSTM). To demonstrate the proposed hybrid deep learning model's superior performance, the proposed method is applied to Ireland's load data for single-step and multi-step load forecasting. In comparison to the widely used CNN-LSTM hybrid model, the proposed model improved single-step prediction by 16.73% and 24-step load prediction by 20.33%. Additionally, we use the Maine dataset to verify the proposed model's generalizability.INDEX TERMS short-term load forecast, deep learning, multi-head CNN-LSTM, multi-step load prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Goh

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Currently, Iraq is revamping its power generating capacity and the transmission system, for which a significant investment is being made. The country is also working on its security mechanisms to ensure a safe oil supply to revamp its energy sector [13][14][15][16][17][18][19][20][21].…”

Section: Indirect Factorsmentioning

confidence: 99%

“…The literature that has been reviewed suggested a hybrid load forecasting model by applying historical data analytics and/or clustering such as Nepal et al, Japan [17] and Sulandari et al, Indonesia [18], or historical data with/without combination with external factors such weather conditions, such as He, F. et al, China [3] and S. Karthika et al, India [19]. Our research proposes a novel hybrid load forecasting model combining fuzzy C-means for data clustering and auto-regressive integrated moving average (ARI'MA) for historical load data analytics.…”

mentioning

confidence: 99%

Smart Grid Data Management in a Heterogeneous Environment with a Hybrid Load Forecasting Model

et al. 2021

View full text Add to dashboard Cite

The power consumption model can be represented in multiple dimensions, and it is proliferating to include structured and unstructured data. Dealing with such heterogeneous data and analyzing it in real-time is an ongoing challenge in the energy sector. Moreover, converting these data into useful information remains an open research area. This study focuses on modeling realistic and efficient power consumption data management in the heterogeneous environment for the Iraq energy sector and suggested a novel hybrid load forecasting model. The proposed system is named the Power Consumption Information and Analytics System (PIAS), which can perform various roles such as data acquisition from mechanical and smart meters, data federation, data management, data visualization, data analysis, and load forecasting. The proposed system has a four-tier framework (Data, Analytics, Application, and Presentation). Each layer is discussed in detail in this study to overcome the anticipated challenges. Furthermore, this study discusses the proposed system by applying two case studies. The first case study discusses power consumption data management, while the second introduces a novel hybrid load forecasting model using Fuzzy C-Means clustering, Auto Regressive Integrated Moving Average (ARIMA), and Gradient Boosted Tree Learner. The dataset used in this forecasting is based on a 1-year duration dated 1st January 2019 to 31st December 2019, on an hourly basis (365 * 24) for the Baghdad governorate. The results showed high accuracy in load forecasting with improved error rates (MAPE, MAE, and RMSE) achievements in comparison with other evaluated models such as standalone ARIMA and Gradient Boosted Trees methods.

show abstract

“…This section focuses the techniques for STLF. STLF is essentially a time series problem, and thus many traditional time series prediction techniques have been used to solve this problem, e.g., ARMA [23], ARIMA [24], and a hybrid of ARIMA and SVM [25]. Under normal conditions, these statistical techniques deliver good prediction results.…”

Section: Related Work On Short-term Load Forecastingmentioning

confidence: 99%

Integrating Long Short-Term Memory and Genetic Algorithm for Short-Term Load Forecasting

Santra

Lin

2019

Energies

View full text Add to dashboard Cite

Electricity load forecasting is an important task for enhancing energy efficiency and operation reliability of the power system. Forecasting the hourly electricity load of the next day assists in optimizing the resources and minimizing the energy wastage. The main motivation of this study was to improve the robustness of short-term load forecasting (STLF) by utilizing long shortterm memory (LSTM) and genetic algorithm (GA). The proposed method is novel: LSTM networks are designed to avoid the problem of long-term dependencies, and GA is used to obtain the optimal LSTM's parameters, which are then applied to predict the hourly electricity load for the next day. The proposed method was trained using actual load and weather data, and the performance results showed that it yielded small mean absolute percentage error on the test data.With the advance of computing power, deep neural network (DNN) has gained much popularity and been applied to STLF in recent years [36]. LSTM is a special type of DNN that is suitable for time series prediction due to its capability of remembering both the short-term and the long-term behavior in time series data. In Reference [37], two types of LSTM were compared against other deep learning techniques for predicting electricity load of every hour or every minute. Their results showed that LSTM outperformed the other techniques. However, all of the neural network approaches above require setting up the initial weightings of the links in the network, but poorly chosen weightings could lead the searching process trapped in the local optimum. A hybrid of LSTM and GA is proposed in Section 4 to resolve this problem.Prior to presenting our approach in Section 4, this section gives a detailed description of LSTM. LSTM is an augmented recurrent neural network model. It learns sequential information with long term dependencies, and preserves information for a long period of time. Traditional recurrent neural network suffers from the vanishing gradient problem. That is, as the number of layers using the same activation function increases, the gradients of the loss function approaches zero, making it difficult to train the network through backpropagation of errors. To prevent the vanishing gradient problem, LSTM utilizes memory cells, where each cell maintains a cell state and a hidden cell state, and uses three gates (namely, input gate, output gate, and forget gate) to control the flow of information into or out of the cell. A formal explanation of the LSTM model is given below.LSTM is for time series modeling, which maps an input sequence x = {x 1 , x 2 , . . . , x n } to an output sequence y = y 1 , y 2 , . . . , y n . For the STLF problem under study, each x i represents the hourly electricity load and the weather data of day i, and each y i represents the hourly electricity load of day i + 1, indicating a look-ahead parameter of value one. The LSTM contains layers of memory cells, where the interaction between the LSTM layers is shown in Figure 1, and the architecture of a LSTM cell is shown...

show abstract

Hybrid short term load forecasting using ARIMA-SVM

Cited by 48 publications

References 15 publications

Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Smart Grid Data Management in a Heterogeneous Environment with a Hybrid Load Forecasting Model

Integrating Long Short-Term Memory and Genetic Algorithm for Short-Term Load Forecasting

Contact Info

Product

Resources

About