Search

Forecasting the electrical load is essential in power system design and growth. It is critical from both a technical and a financial standpoint as it improves the power system performance, reliability, safety, and stability as well as lowers operating costs. The main aim of this paper is to make forecasting models to accurately estimate the electrical load based on the measurements of current electrical loads of the electricity company. The importance of having forecasting models is in predicting the future electrical loads, which will lead to reducing costs and resources, as well as better electric load distribution for electric companies. In this paper, deep learning algorithms are used to forecast the electrical loads; namely: (1) Long Short-Term Memory (LSTM), (2) Gated Recurrent Units (GRU), and (3) Recurrent Neural Networks (RNN). The models were tested, and the GRU model achieved the best performance in terms of accuracy and the lowest error. Results show that the GRU model achieved an R-squared of 90.228%, Mean Square Error (MSE) of 0.00215, and Mean Absolute Error (MAE) of 0.03266. [ABSTRACT FROM AUTHOR]

Smart meters and the advanced metering infrastructure facilitate distribution system operators (DSOs) to gather information on energy consumption at the customer level. With the increasing penetration of building-level intermittent distributed energy resources (DERs) behind the meter, DER information is not available to DSOs. At the same time, the smart meter enables users to participate in grid, with real-time information. Information for behind the meter is needed by the user to coordinate building-level assets for maximum benefits. The concept of unbundled smart meter (USM) needs agents to decompose smart meter measurements to provide service to DSOs as well as customers. In this article, we propose a spatiotemporal decomposition agent (STDA) for the USM based on artificial intelligence. The STDA can help users optimize their energy usage and help DSOs to utilize building assets for the grid operation. The energy usage strategy developed by the STDA is suitable for different users and can be customized by deep learning (DL) models according to the different energy consumption habits of each user. The power prediction performance results of various DL models and evaluation using a set of data from a Hawaii utility is presented. Also, STDA integration with home energy management systems to manage resources is presented and validated. STDA preprocesses the measurements before model training and provides the spatiotemporal decomposed forecasting. [ABSTRACT FROM AUTHOR]

Forecasting the electrical load is essential in power system design and growth. It is critical from both a technical and a financial standpoint as it improves the power system performance, reliability, safety, and stability as well as lowers operating costs. The main aim of this paper is to make forecasting models to accurately estimate the electrical load based on the measurements of current electrical loads of the electricity company. The importance of having forecasting models is in predicting the future electrical loads, which will lead to reducing costs and resources, as well as better electric load distribution for electric companies. In this paper, deep learning algorithms are used to forecast the electrical loads; namely: (1) Long Short-Term Memory (LSTM), (2) Gated Recurrent Units (GRU), and (3) Recurrent Neural Networks (RNN). The models were tested, and the GRU model achieved the best performance in terms of accuracy and the lowest error. Results show that the GRU model achieved an R-squared of 90.228%, Mean Square Error (MSE) of 0.00215, and Mean Absolute Error (MAE) of 0.03266.

Accurate and rapid load forecasting for industrial customers has been playing a crucial role in modern power systems. Due to the variability of industrial customers’ activities, individual industrial loads are usually too volatile to forecast accurately. In this paper, a short-term load forecasting model for industrial customers based on the Temporal Convolutional Network (TCN) and Light Gradient Boosting Machine (LightGBM) is proposed. Firstly, a fixed-length sliding time window method is adopted to reconstruct the electrical features. Next, the TCN is utilized to extract the hidden information and long-term temporal relationships in the input features including electrical features, a meteorological feature and date features. Further, a state-of-the-art LightGBM capable of forecasting industrial customers’ loads is adopted. The effectiveness of the proposed model is demonstrated by using datasets from different industries in China, Australia and Ireland. Multiple experiments and comparisons with existing models show that the proposed model provides accurate load forecasting results. [ABSTRACT FROM AUTHOR]

To support daily operation of smart grid, the stochastic load behavior is analyzed by a day-ahead prediction interval (PI) which is built from predictor’s probability density function, computed in statistical mean-variance, and achieves a symmetrical PI. However, this approach lacks for intended risk information on the predictors’ uncertainty, e.g., weather condition and load variation. This article proposes a novel statistical load forecasting (SLF) using quantile regression random forest (QRRF), probability map, and risk assessment index (RAI) to obtain the actual pictorial of the outcome risk of load demand profile. To know the actual load condition, the proposed SLF is built considering accurate point forecasting results, and the QRRF establishes the PI from various quantiles. To correlate the uncertainty of external factors to the actual load, the probability map computes the most probable quantile happening in the training horizon. Based on the current inputs, the RAI calculates the PI’s intended risk. The proposed SLF is verified by Independent System Operator–New England data, compared to benchmark algorithms and Winkler score. The results show that the proposed method can model a more precise load PI along with the risk evaluation, as compared to results of the existing benchmark models. [ABSTRACT FROM AUTHOR]

Power demand forecasting with high accuracy is a guarantee to keep the balance between power supply and demand. Due to strong volatility of industrial power load, ultra-short-term power demand is difficult to forecast accurately and robustly. To solve this problem, this article proposes a Long Short-Term Memory (LSTM) network based hybrid ensemble learning forecasting model. A hybrid ensemble strategy—which consists of Bagging, Random Subspace, and Boosting with ensemble pruning—is designed to extract the deep features from multivariate data, and a new loss function that integrates peak demand forecasting error is proposed according to bias-variance tradeoff. Experimental results on open dataset and practical dataset show that the proposed model outperforms several state-of-the-art time series forecasting models, and obtains higher accuracy and robustness to forecast peak demand. [ABSTRACT FROM AUTHOR]

This article proposes a network reconfiguration methodology using repository-based constrained nondominated sorting genetic algorithm with preference order ranking for an unbalanced distribution system. The algorithm can accommodate the variable nature of load demand and distributed generator output. A mathematical multiobjective model is formulated to obtain the optimal topology for a whole day considering minimization of daily energy loss, energy not supplied, and cumulative current unbalance factor under the constraint of minimum switching action. A wavelet transform-based ARIMA model is used for wind speed forecasting and is proposed for solar irradiance and load forecasting as well. Hourly network reconfiguration (NR) is also performed, and a comparison is performed between hourly and whole-day NR. The proposed approach has been implemented on IEEE 34-bus and IEEE 123-bus systems to evaluate the effectiveness of the developed methodologies. [ABSTRACT FROM AUTHOR]

The development of smart grid and new advanced metering infrastructures induces new opportunities and challenges for utilities. Exploiting smart meters information for forecasting stands as a key point for energy providers who have to deal with time varying portfolio of customers as well as grid managers who needs to improve accuracy of local forecasts to face with distributed renewable energy generation development. We propose a new machine learning approach to forecast the system load of a group of customers exploiting individual load measurements in real time and/or exogenous information like weather and survey data. Our approach consists in building experts using random forests trained on some subsets of customers then normalise their predictions and aggregate them with a convex expert aggregation algorithm to forecast the system load. We propose new aggregation methods and compare two strategies for building subsets of customers: 1) hierarchical clustering based on survey data and/or load features and 2) random clustering strategy. These approaches are evaluated on a real data set of residential Irish customers load at a half hourly resolution. We show that our approaches achieve a significant gain in short term load forecasting accuracy of around 25 percent of RMSE. [ABSTRACT FROM AUTHOR]

Demand-side management (DSM) increases the complexity of forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from the data set. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to convert the continuity feature of input data into binomial distribution feature. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on the genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods. [ABSTRACT FROM AUTHOR]

Accurate renewable energy generation and electricity demand forecasting tools constitute an essential part of the energy management system functions in microgrids. This study proposes a hybrid approach for short‐term load forecasting in microgrids, which integrates empirical mode decomposition (EMD), particle swarm optimisation (PSO) and adaptive network‐based fuzzy inference systems (ANFISs). The proposed technique first employs EMD to decompose the complicated load data series into a set of several intrinsic mode functions (IMFs) and a residue, and PSO algorithm is then used to optimise an ANFIS model for each IMF component and the residue. The final short‐term electric load forecast value could be obtained by summing up the prediction results from each component model. The performance of the proposed model is examined using load demand dataset of a case study microgrid in Beijing and is compared with four other forecasting methods using the same dataset. The results show that the proposed approach yielded superior performance for short‐term forecasting of microgrid load demand compared with the other methods. [ABSTRACT FROM AUTHOR]

We present in this paper a model for forecasting short-term electric load based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers’ understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated to improve the forecast results. Further, a two-stage ensemble strategy is used to enhance the generalization capability of the proposed model. We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model. Multiple test cases and comparison with existing models show that the proposed model provides accurate load forecasting results and has high generalization capability. [ABSTRACT FROM AUTHOR]

The optimal operation planning (OOP) of electrical distribution systems (EDS) is very sensible to the quality of the short-term load forecasts. Assuming aggregated demands in EDS as univariate non-stationary seasonal time series, and based on historical measurements gathered by smart meters, this paper presents a parsimonious short-term load forecasting method to estimate the expected outcomes of future demands, and the standard deviations of forecast errors. The chosen short-term load forecasting method is an adaptation of the multiplicative autoregressive integrated moving average (ARIMA) models. Seasonal ARIMA models are parsimonious forecasting techniques because they require very few parameters and low computational resources to provide an adequate representation of stochastic time series. Two approaches are used in this paper to estimate the parameters that constitute the proposed multiplicative ARIMA model: a frequentist and a Bayesian approach. Advantages and disadvantages of both methods are compared by simulating a centralized self-healing scheme of a real EDS that uses the forecasts to deploy a robust restoration plan. Results show that the proposed seasonal ARIMA model is a fast, precise, straightforward, and adaptable load forecasting method, suitable for OOP of highly supervised EDS. [ABSTRACT FROM AUTHOR]

As the power system is facing a transition toward a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation, load forecasting, especially short-term load forecasting for individual electric customers plays an increasingly essential role in the future grid planning and operation. Other than aggregated residential load in a large scale, forecasting an electric load of a single energy user is fairly challenging due to the high volatility and uncertainty involved. In this paper, we propose a long short-term memory (LSTM) recurrent neural network-based framework, which is the latest and one of the most popular techniques of deep learning, to tackle this tricky issue. The proposed framework is tested on a publicly available set of real residential smart meter data, of which the performance is comprehensively compared to various benchmarks including the state-of-the-arts in the field of load forecasting. As a result, the proposed LSTM approach outperforms the other listed rival algorithms in the task of short-term load forecasting for individual residential households. [ABSTRACT FROM AUTHOR]

In this paper, we newly propose a holographic ensemble forecasting method (HEFM). First, we use the mutual information and statistical method to select feature variables, which is an ensemble of information about the cross-border multi-source data at the dataset level. Then, we generate multiple training sets by performing diversity sampling with bootstrap, which is an ensemble of information about multiple sample sets at the sampling space level. Next, we construct a multi-model using different artificial intelligence and machine-learning algorithms, which is an ensemble of information about multiple nonlinear heterogeneous models at the forecasting model level. Finally, we use the original features, the forecasting load which is output of the multiple heterogeneous models trained in the first learning, and the actual load of the recent period before each forecasted time to generate a new training set, which is used for the online second learning and final forecasting. This is an ensemble of information about online second learning at the decision level. The ensemble of multi-category multi-state information for four levels (dataset, sampling space, forecasting model, and decision) constitutes the framework of HEFM, whose essence is a forecasting method with comprehensive information integration for the whole life cycle of the forecasting process. We study the load in Guangzhou, China, and New England, USA. Compared to the state-of-the-art forecasting methods, the MAPE of HEFM is reduced by 7.69%–65.77%. The results demonstrate that the forecasting performance may not be improved with the number of algorithms, and that there is a need to understand the positive and negative fusion effect between different algorithms and data characteristics. [ABSTRACT FROM AUTHOR]

Short-term load forecasting at the distribution level predicts the load of substations, feeders, transformers, and possibly customers from half an hour to one week ahead. Effective forecasting is important for the planning and operation of distribution systems. The problem, however, is difficult in view of complicated load features, the large number of distribution-level nodes, and possible switching operations. In this paper, a new forecasting approach within the hierarchical structure is presented to solve these difficulties. Load of the root node at any user-defined subtree is first forecast by a wavelet neural network with appropriate inputs. Child nodes categorized as “regular” and “irregular” based on load pattern similarities are then forecast separately. Load of a regular child node is simply forecast as the proportion from the parent node load forecast while the load of an irregular child node is forecast by an individual neural network model. Switching operation detection and follow-up adjustments are also performed to capture abnormal changes and improve the forecasting accuracy. This new approach captures load characteristics of nodes at different levels, takes advantage of pattern similarities between a parent node and its child nodes, detects abnormalities, and provides high quality forecasts as demonstrated by two practical datasets. [ABSTRACT FROM PUBLISHER]

This study presents a non‐linear ensemble of partially connected neural networks for short‐term load forecasting. Partially connected neural networks are chosen as individual predictors due to their good generalisation capability. A group‐based chaos genetic algorithm is developed to generate diverse and effective neural networks. A novel pruning method is employed to develop partially connected neural networks. To further enhance prediction accuracy, an artificial neural network‐based non‐linear ensemble of partially connected neural network predictors is developed. The proposed non‐linear ensemble neural network is evaluated on a PJM market dataset and an ISO New England dataset with promising results of 1.76 and 1.29% error, respectively, demonstrating its capability as a promising predictor. [ABSTRACT FROM AUTHOR]

The abundance of energy consumption data collected by smart meters has inspired researchers to employ deep neural networks to solve the existing problems in the power industry, such as Short-Term Load Forecasting (STLF). Most studies addressing the STLF problem, focus on historical load data and to achieve higher performance, they supplement costly accessible environmental and calendar variables with data. This approach ignores the existing spatial information among the consumers which subsequently might lead into the emergence of similar consumption patterns. In this paper, we present a Graph Convolutional Recurrent Neural Network, a novel neural architecture, for STLF problem that combines Graph Convolutional Networks and Long Short-Term Memory networks to simultaneously extract spatial and temporal information from users with similar consumption patterns. Our model captures spatial information from users without prior knowledge of their geographic location and does not rely on additional environmental variables. We compared our model to traditional baseline models for STLF using two real-world electricity consumption datasets. The empirical results demonstrate a significant improvement in prediction compared with the baseline models, exhibiting a 9.5% and an 8% improvement in terms of Mean Absolute Percentage Error, in the Customer Behavior Trials and Low Carbon London datasets, respectively. [ABSTRACT FROM AUTHOR]

It is very helpful for power system operation to assess and forecast the uncertainty of the load forecasting. The improved credibility assessment index of the short‐term load forecasting results is presented to assess the uncertainty in this study. The forecasting method for credibility of short‐term load forecasting is also proposed by adopting genetic algorithm‐based back propagation neural network. In the case study, it is proved that the improved credibility assessment can evaluate the short‐term load forecasting results and the forecasting methods. Meanwhile, the credibility forecasting can contribute to optimise reserve capacity in power system scheduling. [ABSTRACT FROM AUTHOR]

Because of their excellent scheduling capabilities, artificial neural networks (ANNs) are becoming popular in short-term electric power system forecasting, which is essential for ensuring both efficient and reliable operations and full exploitation of electrical energy trading as well. For such a reason, this paper investigates the effectiveness of some of the newest designed algorithms in machine learning to train typical radial basis function (RBF) networks for 24-h electric load forecasting: support vector regression (SVR), extreme learning machines (ELMs), decay RBF neural networks (DRNNs), improves second order, and error correction, drawing some conclusions useful for practical implementations. [ABSTRACT FROM PUBLISHER]

This paper aims to develop a novel method to evaluate Conservation Voltage Reduction (CVR) effects. A multistage Support Vector Regression (MSVR)-based model is proposed to estimate the load without voltage reduction during the CVR period. The first stage is to select a set of load profiles that are close to the profile under estimation by a Euclidian distance-based index; the second stage is to train the SVR prediction model using the pre-selected profiles; the third stage is to re-select the estimated profiles to minimize the impacts of estimation errors on CVR factor calculation. Compared with previous efforts to analyze the CVR outcome, this MSVR-based technique does not depend on selections of control groups or assumptions of any linear relationship between the load and its impact factors. In order to deal with the variability of CVR performances, a stochastic framework is proposed to assist utilities in selecting target feeders. The proposed method has been applied to evaluate CVR effects of practical voltage reduction tests and shown to be accurate and effective. [ABSTRACT FROM PUBLISHER]

A novel functional time-series methodology for short-term load forecasting is introduced. The prediction is performed by means of a weighted average of past daily load segments, the shape of which is similar to the expected shape of the load segment to be predicted. The past load segments are identified from the available history of the observed load segments by means of their closeness to a so-called reference load segment. The latter is selected in a manner that captures the expected qualitative and quantitative characteristics of the load segment to be predicted. As an illustration, the suggested functional time-series forecasting methodology is applied to historical daily load data in Cyprus. Its performance is compared with some recently proposed alternative methodologies for short-term load forecasting. [ABSTRACT FROM PUBLISHER]

This paper presents a generic strategy for short-term load forecasting (STLF) based on the support vector regression machines (SVR). Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms. One of the objectives of the proposed strategy is to reduce the operator interaction in the model-building procedure. The proposed use of feature selection algorithms for automatic model input selection and the use of the particle swarm global optimization based technique for the optimization of SVR hyper-parameters reduces the operator interaction. To confirm the effectiveness of the proposed modeling strategy, the model has been trained and tested on two publicly available and well-known load forecasting data sets and compared to the state-of-the-art STLF algorithms yielding improved accuracy. [ABSTRACT FROM PUBLISHER]

Artificial Neural Network (ANN) has been recognized as a powerful method for short‐term load forecasting (STLF) of power systems. However, traditional ANNs are mostly trained by gradient‐based learning algorithms which usually suffer from excessive training and tuning burden as well as unsatisfactory generalization performance. Based on the ensemble learning strategy, this paper develops an ensemble model of a promising novel learning technology called extreme learning machine (ELM) for high‐quality STLF of Australian National Electricity Market (NEM). The model consists of a series of single ELMs. During the training, the ensemble model generalizes the randomness of single ELMs by selecting not only random input parameters but also random hidden nodes within a pre‐defined range. The forecast result is taken as the median value the single ELM outputs. Owing to the very fast training/tuning speed of ELM, the model can be efficiently updated to on‐line track the variation trend of the electricity load and maintain the accuracy. The developed model is tested with the NEM historical load data and its performance is compared with some state‐of‐the‐art learning algorithms. The results show that the training efficiency and the forecasting accuracy of the developed model are superior over the competitive algorithms. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is an essential instrument in power system planning, operation, and control. Many operating decisions are based on load forecasts, such as dispatch scheduling of generating capacity, reliability analysis, and maintenance planning for the generators. Overestimation of electricity demand will cause a conservative operation, which leads to the start-up of too many units or excessive energy purchase, thereby supplying an unnecessary level of reserve. On the other hand, underestimation may result in a risky operation, with insufficient preparation of spinning reserve, causing the system to operate in a vulnerable region to the disturbance. [ABSTRACT FROM PUBLISHER]

In this paper, the problem of short-term load forecasting is redefined and solved with a new metric, which is the extension of the conventional sum of squared error (SSE) metric. The proposed metric is a nonsymmetric penalty function with different penalties for over-forecasting and under-forecasting. Therefore, a large family of approaches that utilize gradient-based methods such as artificial neural networks with back propagation learning and regressions method with least squares estimate are not useful in this case. To solve this problem, a modified radial basis function (RBF) network, which uses the genetic algorithm to estimate the weights of the network is presented. This network has the ability to handle the new penalty function. In addition, a fuzzy inference system is combined with the modified RBF network to incorporate the impact of temperature on load. As a real case study, we tried to forecast the electric power load of Mazandaran area in Iran. The comparison between the proposed method and the well-known RBF network demonstrates the efficiency of the proposed method with the new forecasting metric. [ABSTRACT FROM PUBLISHER]

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. [ABSTRACT FROM AUTHOR]

In a deregulated environment, system operators are required to procure certain ancillary services, which, among others, may include compensation for active-power losses. This compensation usually involves long-term energy purchases and additional short-term energy purchases to cover the daily fluctuations. The short-term energy purchases require an accurate and quick short-term forecasting method that has to be efficiently applicable in day-ahead markets. This paper presents a novel short-term active-power-loss forecast method using power-flow analysis for the forecasted day. Specifically, this includes short-term load and generation forecasts as well as network-topology forecasts, which are used for the power-flow calculations and the resulting active-power loss calculations. To minimize the forecast errors, a fuzzy-weight grouping of the different short-term load and generation forecast results is proposed. An additional step for input-data pre-processing is presented, where the fuzzy clustering considers the patterns for training the forecasting models. The proposed approach was verified by using real data for the ENTSO-E interconnection and tested for the Slovenian power system. The forecasting results demonstrate the improved accuracy of the proposed approach. [ABSTRACT FROM PUBLISHER]

Short-term load forecasting (STLF) is the basis of power system planning and operation. With regard to the fast-growing load in China, a novel two-stage hybrid forecasting method is proposed in this paper. In the first stage, daily load is forecasted by time-series methods; in the second stage, the deviation caused by time-series methods is forecasted considering the impact of relative factors, and then is added to the result of the first stage. Different from other conventional methods, this paper does an in-depth analysis on the impact of relative factors on the deviation between actual load and the forecasting result of traditional time-series methods. On the basis of this analysis, an adaptive algorithm is proposed to perform the second stage which can be used to choose the most appropriate algorithm among linear regression, quadratic programming, and support vector machine (SVM) according to the characteristic of historical data. These ideas make the forecasting procedure more accurate, adaptive, and effective, comparing with SVM and other prevalent methods. The effectiveness has been demonstrated by the experiments and practical application in China. [ABSTRACT FROM PUBLISHER]

This paper presents two hybrid neural networks derived from fuzzy neural networks (FNN): wavelet fuzzy neural network (WFNN) using the fuzzified wavelet features as the inputs to FNN and fuzzy neural network (FNCI) employing the Choquet integral as the outputs of FNN. The learning through FNCI is simplified by the use of q-measure and the speed of convergence of the parameters is increased by reinforced learning. The underlying fuzzy models of these hybrid networks are a modified form of fuzzy rules of Takagi-Sugeno model. The number of fuzzy rules is found from a fuzzy curve corresponding to each input-output by counting the total number of peaks and troughs in the curve. The models can forecast hourly load with a lead time of 1 h as they deal with short-term load forecasting. The results of the two hybrid networks using Indian utility data are compared with ANFIS and other conventional methods. The performance of the proposed WFNN is found superior to all the other compared methods. [ABSTRACT FROM AUTHOR]