Short-term Electric Power Research Articles

Predicting short-term electric power demand using weather data

Predicting short-term electric power demand using weather data

Forecasting of short term electric power consumption for different types buildings using improved transfer learning: A case study of primary school in China

Accurate forecasting of electric power consumption is of great significance to the energy saving operation of buildings. However, in practice, few reliable historical data to be employed to forecast the electric power consumption of a building due to the non-availability of a complete system for monitoring of its energy consumption. In order to accurately predict the electric power consumption of a building with a small-size historical data sample, a model is proposed for forecasting daily electric power consumption using TrAdaBoost- Long short term memory (TAB-LSTM). Some new data is collected from the source building with the maximum mean dispersion (MMD), which is combined with the targeted data of the building to generate a training set. The weight of the training set is updated iteratively by transfer learning (TL) and LSTM to predict the daily electric power consumption. This approach is applied to the energy consumption data of a primary school located in the Northwest China. The experimental results show that the proposed TAB-LSTM approach could reduce the average error to 7.8%, and hence it can be used as an efficient tool for intelligent operation and maintenance of existing buildings.

A Platform Independent Web-Application for Short-Term Electric Power Load Forecasting on a 33/11 kV Substation Using Regression Model

Short-term electric power load forecasting is a critical and essential task for utilities of the electric power industry for proper energy trading and that enable the independent system operator to operate the network without any technical and economical issues. In this paper, machine learning model such as linear regression model is used to forecast the active power load one hour and one day ahead. Real time active power load data to train and test the machine learning model is collected from a 33/11 kV substation located in Telangana State, India. Based on the simulation results, it is observed that linear regression model can forecast the load with less mean absolute error i.e. 0.042 with training data and 0.045 with testing data in comparison with support vector regressor model for an hour ahead operation. Whereas in the case of the day ahead operation, linear regression model can forecast the load with less mean absolute error i.e. 0.055 with training data and 0.057 with testing data in comparison with support vector regressor model. A platform independent web application is developed to help the operators of the 33/11 kV substation which is located in Godishala, Telangana State, India.

Machine learning based demand response scheme for IoT enabled PV integrated smart building

The short-term forecasting of electric power consumption and renewable energy generation with high efficiency and advanced demand side management is essential for improving the energy flexibility provided by the smart buildings. However, the recent literature fails to present the mechanism for developing demand side management for energy flexibility. This article addresses the importance of developing an electric power consumption and renewable energy generation short-term forecasting model using a supervised machine learning approach. In this work, random forest and decision tree regression models are developed and used to forecast future electric power consumption and renewable energy generation. To validate the forecasting model performance using the MAE, RMSE, MAPE, and R2. This article proposes a day ahead dynamic pricing model for the demand response scheme. The day ahead dynamic pricing minimizes the peak time demand and end-user electricity tariff. A smart grid system must know the future short-term electric power consumption and renewable energy generation to enable the demand response scheme. The educational institute smart substation and weather station are integrated into the internet of things devices to enable real-time monitoring and control of the electric power consumption and renewable energy generation. The results show that the proposed DR scheme benefits end electricity users and smart grid operators.

Multi-step ahead forecasting for electric power load using an ensemble model

The multi-step prediction of electric power load is a crucial technology to promote power grid intelligence. Precise forecasting of short-term electric power will enhance the meticulous distribution management level of the grid and the dynamic balance between the supply and demand side of the power system. Conversely, a poor forecast of electric power load will lead to the unreasonable power supply to the grid. However, the electric power load is characterized by strong volatility and randomness, and it is a great challenge to precisely grasp the complex non-linear patterns hidden in power load sequences. For making the grid distribution more rational and efficient, a more precise electric power load prediction model needs to be explored. Thus, an ensemble model NeuralProphet-Lightgbm which combines the advanced NeuralProphet model and Lightgbm model is proposed in this paper. The experiments with different prediction horizons of 12, 24 and 48 h were conducted in this paper, and the root mean square error (RMSE), mean squared error (MSE), mean absolute percentage error (MAPE) and standard deviation (SD) are used as assessment metrics for prediction performance. In order to verify the effectiveness of the proposed model, the NeuralProphet-Quantile Regression Forest (QRF), Prophet, Autoregressive Integrated Moving Average model (ARIMA), Prophet-Lightgbm, NeuralProphet, Long Short Term Memory (LSTM) and LazyProphet models are used as benchmark models. The results of the proposed model significantly outperforms than the comparative models and is very robust as prediction horizons increasing. It is a good choice for efficiently forecasting electric power load.

Platform-Independent Web Application for Short-Term Electric Power Load Forecasting on 33/11 kV Substation Using Regression Tree

Short-term electric power load forecasting is a critical and essential task for utilities in the electric power industry for proper energy trading, which enables the independent system operator to operate the network without any technical and economical issues. From an electric power distribution system point of view, accurate load forecasting is essential for proper planning and operation. In order to build most robust machine learning model to forecast the load with a good accuracy irrespective of weather condition and type of day, features such as the season, temperature, humidity and day-status are incorporated into the data. In this paper, a machine learning model, namely a regression tree, is used to forecast the active power load an hour and one day ahead. Real-time active power load data to train and test the machine learning models are collected from a 33/11 kV substation located in Telangana State, India. Based on the simulation results, it is observed that the regression tree model is able to forecast the load with less error.

Short Term Electric Power Load Forecasting Using Principal Component Analysis and Recurrent Neural Networks

Electrical load forecasting study is required in electric power systems for different applications with respect to the specific time horizon, such as optimal operations, grid stability, Demand Side Management (DSM) and long-term strategic planning. In this context, machine learning and data analytics models represent a valuable tool to cope with the intrinsic complexity and especially design future demand-side advanced services. The main novelty in this paper is that the combination of a Recurrent Neural Network (RNN) and Principal Component Analysis (PCA) techniques is proposed to improve the forecasting capability of the hourly load on an electric power substation. A historical dataset of measured loads related to a 33/11 kV MV substation is considered in India as a case study, in order to properly validate the designed method. Based on the presented numerical results, the proposed approach proved itself to accurately predict loads with a reduced dimensionality of input data, thus minimizing the overall computational effort.

An MISOCP-Based Decomposition Approach for the Unit Commitment Problem with AC Power Flows

Unit Commitment (UC) and Optimal Power Flow (OPF) are two fundamental problems in short-term electric power systems planning that are traditionally solved sequentially. The state-of-the-art mostly uses a direct current (DC) approximation of the power flow equations. However, utilizing the DC approach in the UC-level may lead to infeasible or suboptimal generator commitment schedules for the OPF problem. In this paper, we aim to simultaneously solve the UC Problem with alternating current (AC) power flow equations, which combines the challenging nature of both UC and OPF Problems. Due to the highly nonconvex nature of the AC flow equations, we utilize the mixed-integer second-order cone programming (MISOCP) relaxation of the UC Problem as the basis of our solution approach. The MISOCP relaxation is utilized for finding both a lower bound and a candidate generator commitment schedule. Once this schedule is obtained, we solve a multi-period OPF problem to obtain feasible solutions for the UC problem with AC power flows. For smaller instances, we develop two different algorithms that exploit the recent advances in the OPF literature and obtain high-quality feasible solutions with provably small optimality gaps. For solving larger instances, we develop a Lagrangian decomposition based approach that yields promising results.

Short-term electric power load forecasting using random forest and gated recurrent unit

Short-term electric power load forecasting using random forest and gated recurrent unit

Backtracking search optimization applied to solve short-term electrical real power generation of hydrothermal plant

This article aims to determine the feasible optimal solution for the short-term hydrothermal scheduling (STHS) problem using the efficient backtracking search optimization technique. The problem formulation for hydrothermal systems is highly complex owing to its nonlinear nature. Hydrothermal scheduling is considered with two decision variables simultaneously: thermal states and water discharge. These two variables are instrumental in determining the optimal hourly schedule of power generation in hydrothermal power plants. The optimum solution is obtained using the backtracking search algorithm (BSA) with two primary operations, namely, mutation and crossover. The BSA is an optimization technique free from high-sensitivity control parameters, because it has only one control parameter for finding the optimal solution. It also has powerful exploration and exploitation capabilities. The simulation results corroborate that BSA is highly efficient compared to existing optimization techniques (e.g. oppositional real coded chemical reaction-based optimization, differential evolution) in terms of overall efficiency and the quality of the solutions.

Short-Term Power Forecasting Framework for Microgrids Using Combined Baseline and Regression Models

Short-term electric power forecasting is a tool of great interest for power systems, where the presence of renewable and distributed generation sources is constantly growing. Specifically, this type of forecasting is essential for energy management systems in buildings, industries and microgrids for optimizing the operation of their distributed energy resources under different criteria based on their expected daily energy balance (the consumption–generation relationship). Under this situation, this paper proposes a complete framework for the short-term multistep forecasting of electric power consumption and generation in smart grids and microgrids. One advantage of the proposed framework is its capability of evaluating numerous combinations of inputs, making it possible to identify the best technique and the best set of inputs in each case. Therefore, even in cases with insufficient input information, the framework can always provide good forecasting results. Particularly, in this paper, the developed framework is used to compare a whole set of rule-based and machine learning techniques (artificial neural networks and random forests) to perform day-ahead forecasting. Moreover, the paper presents and a new approach consisting of the use of baseline models as inputs for machine learning models, and compares it with others. Our results show that this approach can significantly improve upon the compared techniques, achieving an accuracy improvement of up to 62% over that of a persistence model, which is the best of the compared algorithms across all application cases. These results are obtained from the application of the proposed methodology to forecasting five different load and generation power variables for the Savona Campus at the University of Genova in Italy.

Research On Energy Distribution of Multi-Scene Hydropower System Through Improved Power Load Optimization Strategy

Taking the minimization of coal consumption in hydro-thermal power system as the objective function, this paper focuses on the static water abandonment strategy and improved dynamic water abandonment strategy, given the constraint conditions of hydropower station generation flow, reservoir water quantity, load balance constraint and power constraint. in this paper, the penalty cost of abandoned water is introduced into the existing model, and a short-term electric power balance model considering the cost of abandoned water is established. In view of the deficiency that it is difficult to effectively obtain feasible solutions that meet large-scale and complex constraints in the process of solving the model, the premature convergence and local optimization of the algorithm are avoided. An optimization algorithm is proposed to provide reference for solving the problem that the calculation efficiency of optimal dispatching of large-scale hydropower stations is the problem faced by hydropower and power system operation.

Short-Term Electricity Generation Forecasting Using Machine Learning Algorithms: A Case Study of the Benin Electricity Community (C.E.B)

Time series forecasting in the energy sector is important to power utilities for decision making to ensure the sustainability and quality of electricity supply, and the stability of the power grid. Unfortunately, the presence of certain exogenous factors such as weather conditions, electricity price complicate the task using linear regression models that are becoming unsuitable. The search for a robust predictor would be an invaluable asset for electricity companies. To overcome this difficulty, Artificial Intelligence differs from these prediction methods through the Machine Learning algorithms which have been performing over the last decades in predicting time series on several levels. This work proposes the deployment of three univariate Machine Learning models: Support Vector Regression, Multi-Layer Perceptron, and the Long Short-Term Memory Recurrent Neural Network to predict the electricity production of Benin Electricity Community. In order to validate the performance of these different methods, against the Autoregressive Integrated Mobile Average and Multiple Regression model, performance metrics were used. Overall, the results show that the Machine Learning models outperform the linear regression methods. Consequently, Machine Learning methods offer a perspective for short-term electric power generation forecasting of Benin Electricity Community sources.

High dimensional very short-term solar power forecasting based on a data-driven heuristic method

Improving the accuracy of solar power forecasting has become crucial for dealing with the negative effects of the integration of continually increasing solar power into power systems. This is a more challenging task when historical solar radiation data has not been recorded and no specific sky imaging equipment is available. This paper proposes a univariate data-driven method to improve the accuracy of very short-term electrical solar power forecasting. This approach includes defining new features that efficiently tackle the nonlinear characteristics of electrical solar power. An instance-based variable selection is also used to identify the best relevant features. Three state-of-the-art learning algorithms (i.e. neural networks, support vector regression, and random forest) have been used and compared as prediction algorithms of the proposed method. The effectiveness of the proposed approach is evaluated in a 15-min ahead prediction trial using a real solar power dataset and against three evaluation measures. The results show the proposed method significantly enhances the performance of very short-term solar power forecasting.

Short-term electric power demand forecastingusing a hybrid model of SARIMA and SVR

Short-term electric power demand forecasting is the most basic and important application of smart grid. With the rapid development of renewable energy and clean energy in recent years, power demand forecasting gains special attention again. It has a great impact on the planning of power generation units and the purchase and sale of power market. Furthermore, itis also conducive to the realization of demand response and resource allocation efficiency and reliability, thus contributing to the Photovoltaic power generation system as well. Although generous methods have been proposed, it remains to be an open challenge owing to its limited precision. In this paper, a hybrid method of Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and Support Vector Regression (SVR) is proposed for hourly forecasting, which overcomes the difficulty of generalization of a single model. The core thought of this model is using SARIMA to fit the linear part of the series and correcting the deviation by SVR. We tested the accuracy of this method on a public data set, and the result shows that it performs much better than the single SARIMA model on the fitting effect. Also, we compared our model with the recent three works, and it demonstrates a decrease of 18.102%,10.534% and 4.757% in forecasting error respectively. To our surprise, when we usedthe previous four hours of data to predict the current data by the single SVR, we got the best performance of all models. In the end, we analyzed the possible causes for this result.

Electric Power and Heat Generation Expansion Planning

A short-term electric power and heat generation augmentation planning (EPHGAP) is portrayed and evaluated here. The objective of EPHGAP is to find out the most cost-effective and dependable expansion plan for meeting the forecasted electrical power demand and heat demand over a long-range horizon while fulfilling a large number of technical, cost-effective, reliability, and social constraints. The EPHGAP problem is a big-dimensional highly constrained mixed integer nonlinear programing (MINLP) problem. The general algebraic modeling system (GAMS) environment has been used to implement the proposed formulation, and the EPHGAP problem is solved by using Basic Open-source Nonlinear Mixed Integer (BONMIN) solver. An archetypal test system with existing thermal power plants, cascaded hydropower plants, cogeneration units, heat-only units and candidate cogeneration units, and cascaded hydro plants is considered to evaluate the proposed methodology. Simulation outcomes of the test system have been matched up to those acquired by differential evolution and particle swarm optimization. It has been observed from the comparison that the recommended BONMIN solver has the capability to bestow with superior quality solution.

A comprehensive review on day‐ahead electricity market and important features of world's major electric power exchanges

Restructuring to the existing electric power system has transformed the conventional method in which electric power is traded around the globe. Now private players and entities having distributed generators can actively participate in restructured electricity market. It brings competition among different market players and leads to an overall fall in electricity prices. To further enhance competitiveness and bring transparency in the electric power trading mechanism, a common platform called power exchange (PX) has been established in many countries of the world. PX is a common internet-based online platform where various market players submit their offers/bids for selling/buying electrical energy or services. As in today's restructured electricity market, significant percentage of short-term electric power is traded through day-ahead market (DAM) of PX, the study of DAM is very important. Therefore, this article presents a comprehensive review of day-ahead electricity market and other important features of world's major electric power exchanges. It mainly focused on PX products, trading mechanism, DAM design issues, world's major PX, comparative analysis of DAM of world's major PX and future challenges.

Development of Demand Response Energy Management Optimization at Building and District Levels Using Genetic Algorithm and Artificial Neural Network Modelling Power Predictions

Demand Response (DR) is a fundamental aspect of the smart grid concept, as it refers to the necessary open and transparent market framework linking energy costs to the actual grid operations. DR allows consumers to directly or indirectly participate in the markets where energy is being exchanged. One of the main challenges for engaging in DR is associated with the initial assessment of the potential rewards and risks under a given pricing scheme. In this paper, a Genetic Algorithm (GA) optimisation model, using Artificial Neural Network (ANN) power predictions for day-ahead energy management at the building and district levels, is proposed. Individual building and building group analysis is conducted to evaluate ANN predictions and GA-generated solutions. ANN-based short term electric power forecasting is exploited in predicting day-ahead demand, and form a baseline scenario. GA optimisation is conducted to provide balanced load shifting and cost-of-energy solutions based on two alternate pricing schemes. Results demonstrate the effectiveness of this approach for assessing DR load shifting options based on a Time of Use pricing scheme. Through the analysis of the results, the practical benefits and limitations of the proposed approach are addressed.

The prediction of the impact of climatic factors on short-term electric power load based on the big data of smart city

The climate changes have great impact on the residents’ electricity consumption, so the study on the impact of climatic factors on electric power load is of significance. In this paper, the effects of the data of temperature, rainfall and wind of smart city on short-term power load is studied to predict power load. The authors studied the relation between power load and daily temperature, rainfall and wind in the 31 days of January of one year. In the research, the authors used the Matlab neural network toolbox to establish the combinational forecasting model. The authors trained the original input data continuously to get the internal rules inside the data and used the rules to predict the daily power load in the next January. The prediction method relies on the accuracy of weather forecasting. If the weather forecasting is different from the actual weather, we need to correct the climatic factors to ensure accurate prediction.

Mean shift densification of scarce data sets in short-term electric power load forecasting for special days

Short-term load forecasting plays an important role to the operation of electric systems, as a key parameter for planning maintenances and to support the decision making process on the purchase and sale of electric power. A particular case in this respect is the consumption forecasting on special days, which can be a complex task as it presents unusual load behavior, when compared to regular working days. Moreover, its reduced number of samples makes it hard to properly train and validate more complex and nonlinear prediction algorithms. This paper tackles this problem by proposing a new approach to improve the accuracy of the predictions amidst existing special days, employing an Information Theoretic Learning Mean Shift algorithm for pattern discovery, classifying and densifying the available scarce consumption data. The paper describes how this methodology was applied to an electrical load forecasting problem in the northern region of Brazil, improving the previously obtained accuracy held by the power company.