Application of Support Vector Machine and Similar Day Method for Load Forecasting

Electricity becoming more and more important for the development of a secure & sustainable energy system. Electricity Demand growth is likely to be anemic. With the rising complexity of energy systems, new ways to use engineering experience and data collecting to increase load forecasting accurately are needed. With the recent advancements in the field of machine learning to leverage big data sets and draw inferences from a vast data set. The electrical load is predicted by using a variety of research strategies, including deterministic and stochastic procedures. This manuscript intends to estimate load demand by utilizing various stochastic methods for Short-Term Load Forecasting (STLF). The dataset is trained using various regression techniques which include a Decision tree, Support Vector machines (SVM), and Ensembles. The performance of the finest regression methodology is analyzed over parameters like RMSE (root mean square error), MSE (mean square error) and, R-squared, MAE (mean absolute error) & training time. The most effective technique is determined by feeding the best machine learning algorithm to various regression learners over data cross-validation of 5 folds and 7 folds. MATLAB platforms are used to implement the methods.

An integrated genetic algorithm (GA)/fuzzy system (FS), tabu search (TS) and neural fuzzy network (NFN) method for load forecasting is presented in this paper. A fuzzy hyper-rectangular composite neural networks (FHRCNNs) was used for the initial load forecasting. Then we used CGAFS and TS to find the optimal solution of the parameters of the FHRCNNs, instead of backpropagation (BP)(including parameters such as synaptic weights, biases, membership functions, sensitivity factor in membership functions and adjustable synaptic weights). First the CGAFS generates a set of feasible solution parameters and then puts the solution into the TS. The CGAKS has good global optimal search capabilities, but poor local optimal search capabilities. The TS method on the other hand has good local optimal search capabilities. We combined both methods to try and obtain both advantages, and in doing so eliminate the drawback of the traditional ANN training by BP. Finally, we used the (GAFSTS-NFN) to see if we could improve the quality of the solution, and if we actually could reduce the error of load forecasting. The proposed CGAFS-TS load forecasting scheme was tested using data obtain from a sample study, including one year, one week and 24-hours time periods. The results demonstrated the accuracy of the proposed load forecasting scheme.

This paper aims to develop a load forecasting method for short-term load forecasting, based on an adaptive two-stage hybrid network with self-organized map (SOM) and support vector machine (SVM). In the first stage, a SOM network is applied to cluster the input data set into several subsets in an unsupervised manner. Then, groups of 24 SVMs for the next day's load profile are used to fit the training data of each subset in the second stage in a supervised way. The proposed structure is robust with different data types and can deal well with the nonstationarity of load series. In particular, our method has the ability to adapt to different models automatically for the regular days and anomalous days at the same time. With the trained network, we can straightforwardly predict the next-day hourly electricity load. To confirm the effectiveness, the proposed model has been trained and tested on the data of the historical energy load from New York Independent System Operator.

Short-term load forecasting plays a vital role for the power system’s safe operation and production arrangements. This paper regards electric load forecasting as a nonlinear time series prediction problem, and establishes the electric load autoregressive prediction model (ARX Model) based on historical load data, approaching ARX model parameters with RBF neural network, estimating model parameters with using a Structured Nonlinear Parameters Optimization Method (SNPOM), proposing cycle prediction method for short-term electric load forecasting. Experimental results show that the method has higher prediction accuracy for short-term electric load forecasting. Keywords: Short-term load forecasting; time series; RBF-ARX model; cycle forecasting; structured nonlinear parameter optimization method

A model integrating Particle Swarm Optimization (PSO) and support vector machines (SVM) is presented to forecast short-term load of electric power systems in this paper. PSO is a method for finding a solution of stochastic global optimizer based on swarm intelligence. Using the interaction of particles, PSO searches the solution space intelligently and finds out the best one. The PSO-SVM method proposed in this paper is based on the global optimization of PSO and local accurate searching of SVM. Practical example results indicate that the application of the PSO-SVM method to short term load forecasting of power systems is feasible and effective. And to prove the effectiveness of the model, other existing methods are used to compare with the result of SVM. The results show that the model is effective and highly accurate in the forecasting of short-term power load.

A new hybrid technique using support vector machines (SVM) to forecast the next `24' hours load is proposed in this paper. Four modules consisting of the basic SVM, peak and valley SVM, averager and forecaster and adaptive combiner form the integrated method for load forecasting. The proposed architecture can forecast the next `24' hours load. The basic SVM uses the historical data of load and temperature to predict the next `24' hour's load, while the peak and valley SVM uses the past peak and valley data of load and temperatures respectively. The averager captures the average variation of the load from the previous load behavior, while the adaptive combiner uses the weighted combination of outputs from the basic SVM and the forecaster, to forecast the final load. The statistical and artificial intelligence based methods are conceptually incorporated into the architecture to exploit the advantages and disadvantages of each technique.

Traditional power load or electricity forecasting methods have used only limited meteorological information. Specifically, these methods either only select one of maximal, minimal and average temperature as the influencing indicator, or only capture the very basic meteorological information, instead of exploring the nonlinear relationship between temperature and loads in depth. To overcome the shortcomings of the traditional methods, this paper proposes a new medium- and long-term load forecasting method based on sensitivity analysis of multi meteorological indicators. This method constructs the encoder and decoder between weather features and loads. Moreover, this paper combines this method with XGBoost and SVR, which can improve the accuracy of medium- and long-term forecasting algorithm in the power grid field effectively. The simulation results of this synthesized model show that average daily prediction accuracy rate of the year is 95.37% and the average monthly prediction accuracy rate of the year is 98.02%.

Efficient energy management is crucial given 2024's 4.1% worldwide electricity demand increase. This urgency emphasizes the necessity for various, sustainable energy sources in distribution grids. Short-term load prediction approaches using probabilistic power generation and energy storage are crucial for energy usage prediction. Urban energy planners use simulation, probability optimization and modelling to create sustainable energy systems. This study offers a novel hybrid model for smart grids: short-term energy load prediction using transfer learning (TL) and optimized lightGBM (OLGBM). Our two-phase solution tackles Short-term Load Forecasting complexities. First, aberrant supplements and quick deviation selection eliminate missing values and identify key features during data pre-processing. Second, TL-OLGBM learns dynamic time scales and complex data patterns with Bayesian optimization of hyperparameters to improve forecasting accuracy. Additionally, our architecture easily combines the newest Smart and Green Technology, enabling energy system innovation. Comparative performance research shows that our technique outperforms similar models in mean absolute percentage error, accuracy and root mean square error. This hybrid model is a reliable short-term energy load forecast solution that fits the dynamic terrain of smart and green technology integration in modern energy systems.

The traditional method for power load forecasting is susceptible to various factors, including holidays, seasonal variations, weather conditions, and more. These factors make it challenging to ensure the accuracy of forecasting results. Additionally, there is a limitation in extracting meaningful physical signs from power data, which ultimately reduces prediction accuracy. This paper aims to address these issues by introducing a novel approach called VCAG (Variable Mode Decomposition-Convolutional Neural Network-Attention Mechanism-Gated Recurrent Unit) for combined power load forecasting. In this approach, we integrate Variable Mode Decomposition (VMD) with Convolutional Neural Network (CNN). VMD is employed to decompose power load data, extracting valuable time-frequency features from each component. These features then serve as input for the CNN. Subsequently, an attention mechanism is applied to give importance to specific features generated by the CNN, enhancing the weight of crucial information. Finally, the weighted features are fed into a Gated Recurrent Unit (GRU) network for time series modeling, ultimately yielding accurate load forecasting results.To validate the effectiveness of our proposed model, we conducted experiments using two publicly available datasets. The results of these experiments demonstrate that our VCAG method achieves high accuracy and stability in power load forecasting, effectively overcoming the limitations associated with traditional forecasting techniques. As a result, this approach holds significant promise for broad applications in the field of power load forecasting.

The global energy issues have become increasingly prominent in recent years, photovoltaic power generation as a renewable energy use pattern is widely used, but a large number of photovoltaic power generation to the grid is a big negative impact, it is necessary to predict the output power of the photovoltaic. Power system load forecasting is the reference and safeguard of the power system operation. This article analyzes the main point of the prediction of photovoltaic power system and power load system, then introduces the support vector machine (SVM) based on quantum particle swarm optimization (QPSO) to do the prediction. And then this paper proposes a generalized system load prediction system containing the photovoltaic power system.

Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm

A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids

Short term load forecasting is essential for energy management of any power system. Over the years, a variety of methods such as exponential smoothing, autoregressive integrated moving average (ARIMA) and Artificial Neural Networks (ANNs) have been proposed in the literature. All of these methods have been used in conjunction with similar days approach to bolster the prediction accuracy. However, there is no general consensus in literature on what is the best approach to group 365 days of a year into different categories. In contrast, similar months approach to forecast electricity demand has received little attention although it alleviates many of the efforts in sorting similar days into separate groups. In this paper, we propose a similar months approach based seasonal ARIMA (SARIMA) to forecast electric demand both on a national and a household scale. Through comparison with similar days based approach on similar tasks, we demonstrate that this method is a viable method for short term electric load forecasting of power systems as well as in building energy management applications.

Pattern similarity-based methods for short-term load forecasting – Part 1: Principles

Accurate estimation of river flow can have a significant importance in water resources management. In this study, Genetic programming (GP) and Support Vector Machine (SVM) methods were used to forecast daily discharge of Barandoozchay River. The daily discharge data of Barandoozchay River measured at the Dizaj hydrometric station during 2007 to 2011 was used for modeling, which 80% of the data used for training and remaining 20% used for testing of models. The results showed that in the both of considered methods, the models including discharges of one, two and three days ago had higher accuracy in verification step and the accuracy of models decreased with increasing discharge values. Comparing the performance of GP and SVM methods indicated that, however the accuracy of the GP method with the R=0.978 and RMSE=1.66 (m3/s) was slightly more than SVM method with R=0.976 and RMSE=1.80 (m3/s), but the SVM is easier than GP method. Thus, the SVM method can be used as an alternative method in forecasting daily river discharge.