جستجوی مقالات مرتبط با کلیدواژه « short-term load forecasting » در نشریات گروه « برق »

To maintain supply-demand balance, it is crucial to design a method to provide prior knowledge on load consumption in look-ahead time with high level of accuracy and reliability. The load prediction problem is becoming more and more challenging due to emerging new concepts in the electrical grids and reconstruction of the power networks. This paper develops a residual neural network to predict the electrical loads with high level of accuracy. In the designed network with combining two powerful deep residual network, a new residual deep network is proposed to improve the learning ability as well as prevent problems like overfitting and gradient reduction/explosion. Furthermore, to fully understand the spatial-temporal features, convolutional neural network (CNN) and gated recurrent unit (GRU) are combined and integrated into the designed multi-level deep network. The seasonal analysis and investigating several cases using actual electrical load consumption in Shiraz, Iran verifies the effectiveness of the proposed method and higher accuracy of the proposed deep network in comparison with other methods demonstrate the superiority of the proposed method.

The aim of the short term load forecasting is to forecast the electric power load for unit commitment, evaluating the reliability of the system, economic dispatch, and so on. Short term load forecasting obviously plays an important role in traditional non-cooperative power systems. Moreover, in a restructured power system a generator company (GENCO) should predict the system demand and its corresponding price for efficient decision making.
The task of a forecasting engine is to find the relation of the inputs and outputs of the system and also predicts the outputs for a given inputs. Therefore, the accuracy of forecasting is highly affected by the inputs of the forecasting engine. This effect can be studied from two points of view; First, extracting the more informative inputs and second, reducing the dimension of input space, both make it possible to learn the forecasting network via more simple models with more generalization. As a result, a reduced informative input space leads to lower prediction error. In many previous load forecasting methods, the inputs have been selected empirically. In this manner, the more correlative factors with the load in the forecasting day have been chosen as the inputs. They are generally a combination of load history and weather conditions. Several researches are focused on mathematical approaches of the input selection which are mainly based on principal component analysis (PCA) method as well as some intelligent algorithms.
In this paper, a manifold learning method namely Locally Linear Embedding (LLE) is proposed, aiming to extract more informative inputs and to reduce the dimension of input space for short term load forecasting. Among all methods based on manifold learning, it can be seen that LLE performs very well in extracting the electric load curve features. The aim of this paper is to analyze the features of the load curve for estimating this curve in future. The extensive computational experiments show that the extracted features by LLE results in less prediction error than two other methods. Furthermore, LLE acts faster and makes input dimension lower than the two other methods. In the following section we will discuss the LLE method. The LLE method finds the nonlinear relationships among features by mapping a locally linear manifold in the feature space. Extracting the more informative inputs by extracting the combinational features by finding the nonlinear dependences of the features, results in reducing the dimension of input space. The resulted inputs from feature extraction and dimension reduction are utilized for load forecasting.
To examine the effect of the proposed feature extraction method on load prediction error, a hybrid prediction system is proposed which is a combination of a radial basis function (RBF) network and a fuzzy system. The RBF network is the core of the prediction engine and works with historical load data as its inputs. The fuzzy inference system is combined with the RBF network to incorporate the impact of temperature on load. The case studies are carried out on the real data of electric power load of Mazandaran area in Iran. The efficiency of the proposed forecasting engine is compared with three benchmarks, the artificial neural network, time series and neuro-fuzzy methods. Furthermore, the proposed input selection method (LLE) is compared with principal component analysis (PCA) and empirical selection of inputs. Simulation results with statistical significance analysis show that the LLE method with the proposed forecasting engine is superior to other input selection methods and forecasting engines in sense of lower input dimension and lower prediction error.

Regarding to increase electric power demand consumption, identification of its change circumstances is an important issue in electric networks. From this point of view, short-term load forecasting is vital problem in technical and economic management of the power industry to ensure supply demand and network security. So far numerous methods with different accuracy have been proposed to model and forecast electric load in short-term. Most of them utilize large amounts of data and other parameters of the predictor variable. In this paper, grey model )GM(1,1)) and rolling grey model (RGM) can model and forecast time series by using low number of data and high accuracy improved. Fourier residual correction grey model (FGM) has been employed to increase the accuracy of proposed methods. In addition, the proposed methods performances have been compared with four other methods by applying them on Iran and New England networks. Several error definitions have been adopted as ability and accuracy criteria. Also, the sensitivity of the proposed methods to the number of required data and prediction step size has been investigated. Simulation results show high performance and accuracy of the proposed methods in the modeling and load forecasting.

In this paper the modified grey models are proposed for short-term load forecasting in presence of demand response. The demand response is a valuable element of the smart grids. On the other hand, short-term load forecasting is very important for energy purchase planning and optimal operating of restructured power systems. Since the consumer participation is undetermined and inherently uncertain, the load forecasting will be a difficult task in presence of demand response. Numerous methods have been proposed to the load forecasting, which they have little ability to track demand side reaction. Therefore, requirement of a high precision method to model and predict the electric load in presence of demand response is appreciable. In this paper, grey models, which utilize low number of data to high precision prediction, have been modified by an iterative strategy to short-term load forecasting in presence of demand response. Since grey models are local predictors, they show better ability in modeling and forecasting of the load profiles with the unexpected and sudden changes. After applying demand response scenarios on Iran consumption load data, they have been utilized to verify the proposed method. Simulation results show high performance and accuracy of the proposed methods.

Short term load forecasting (STLF) is one of the important issues in the energy management of power systems. Increasing the accuracy of STLF results leads to improving the energy system scheduling and decreasing the operating costs. Different methods have been proposed and applied in the STLF problem such as neural network, fuzzy system, regression-based and neuro-fuzzy methods. This paper investigates the knowledge-based method because of its less computation time and memory compared with other methods. The accuracy of knowledge-based STLF method is improved by proposing a novel priority index for selection of similar days. In this index, temperature similarity and date proximity are simultaneously considered. In order to consider the effect of temperature in STLF more efficiently, the system is partitioned into the smaller regions and the STLF of the whole system is calculated by gathering the STLF of all regions. The proposed method is implemented on a sample real data, Iran’s national power network, to show the advantages of the proposed method compared with Bayesian neural network and locally linear neuro-fuzzy methods in aspects of accuracy and computation time. It is shown that the proposed method decreases yearly mean absolute percentage error (MAPE), and generates more reliable load forecasting.