Konstantinos Kampouropoulos

A Combined Methodology of Adaptive Neuro- Fuzzy Inference System and Genetic Algorithm for Short-term Energy Forecasting

1 Abstract—This document presents an energy forecast methodology using Adaptive Neuro-Fuzzy Inference System (ANFIS) and Genetic Algorithms (GA). The GA has been used for the selection of the training inputs of the ANFIS in order to minimize the training result error. The presented algorithm has been installed and it is being operating in an automotive manufacturing plant. It periodically communicates with the plant to obtain new information and update the database in order to improve its training results. Finally the obtained results of the algorithm are used in order to provide a short- term load forecasting for the different modeled consumption processes. I. INTRODUCTION With the continuously growing demand of the energy, it is getting more important to develop systems capable to optimize the energy use. Energy management is nowadays a subject of great importance because of the facing problems of the global warming and oil shortage. In the industrial sector, the energy management systems have focused so far on the monitoring and off-line management of energy as it is outlined in (1). The typical energy management systems are based on the collection of information about the plants operation using energy meters. Those systems help to monitor the operation of the installations, collect data and generate reports to identify the possible critical points of the consumptions. However, intelligent systems can improve the operation of the energy management systems, offering further functionalities such as predictive maintenance, energy optimization, fault diagnosis and energy forecast. Different approaches for energy savings and energy prediction have been studied over the past years. Evolutionary algorithms such as Particle Swarms (PSO), Gravitational Search Algorithms (GSA) and Simulated Annealing (SA) have successfully implemented in optimization and control applications (2). An implementation of a model based on Artificial Neural Network (ANN) was presented in (3-4) and (5) in order to estimate the load forecast in an electrical distribution system while in (6) a comparison between ANN and Fuzzy Logic is made on applications of short-term and medium-term load forecasting. An application of Neuronal Networks (NN) is presented in (7) in which it faces Multi-Input-Multi-Output (MIMO) applications with single input and output (SISO) net works. An ANFIS implementation for energy prediction of regional electrical loads in Taiwan was presented in (8), comparing its performance with other similar techniques (i.e., regression models, ANN-based models, Genetic algorithms and hybrid ellipsoidal fuzzy systems). A cellular multi-grid genetic algorithm is presented in (9) to face balancing problems in assembling lines. Techniques based on cultural algorithms are presented in (10) to resolve complex mechanical design optimization problems in an efficient and effective method. Thi s document presents the modeling and prediction algorithms that were developed in order to generate customizable mathematical models for different consumptions, as a way to improve the operation of a general energy monitoring system. The paper is organized as follows: section II describes an overview of the algorithm that has been used for the models training and the energy forecast while section III outlines a brief explanation about the Genetic Algorithms operation. In section IV, the proposed methodology is presented explaining the combination of the two algorithms in order to develop a system capable to train the consumption models autonomously. In Section V, the implementation of the system in the pilot plant is explained, presenting the different results that have been obtained during the test and the evaluation of the system. Finally, section VI summarizes the paper and discusses the different conclusions.

Evolutive ANFIS training for energy load profile forecast for an IEMS in an automated factory

In this paper an evolutive algorithm is used to train an adaptative-network-based fuzzy inference system (ANFIS), particularly a genetic algorithm (GA). The GA is able to train the antecedent and consequent parameters of an ANFIS, which is used for energy load profile forecasting in an automated factory. This load forecasting is useful to support an intelligent energy management system (IEMS), which enables the user to optimize the energy consumptions by means of getting the optimal work points, scheduling the production according to these points, etc. The proposed training algorithm showed excellent results with complex plants like industrial energy consumers in the user-side, where the randomness of the loads is higher than in utility loads. Real data from an automated car factory were used to test the presented algorithms. Appropriated results were obtained.

Load forecasting in the user side using wavelet-ANFIS

At present, the intelligent energy management systems (IEMS) are used to maximiz the relation between productivity and cost using a variety of energy sources. In this work, we present a method of short-time load forecasting, using the ANFIS model and a component of preprocessing based in the discrete wavelet transform; the models was implemented in the user-side, analyzing real data of a factory in order to test the proposed algorithm.

Study of large-signal stability of an inverter-based generator using a Lyapunov function

This document analyses the large-signal stability for an inverter-based generator such as photovoltaic and wind power sources. The objective of this study is to determine the stability region taking into account the electrical and control signal of the generator. The generator uses the concept of the electrostatic machine for the model of the generator. Finally, the applied procedure to find the Lyapunovs function is the Popov method, which not only permits to generate a valid function but also to determine the stability region of the system.

Multiobjective Optimization of Multi-Carrier Energy System Using a Combination of ANFIS and Genetic Algorithms

This paper presents a novel method for the energy optimization of multi-carrier energy systems. The presented method combines an adaptive neuro-fuzzy inference system, to model and forecast the power demand of a plant, and a genetic algorithm to optimize its energy flow taking into account the dynamics of the system and the equipment’s thermal inertias. The objective of the optimization algorithm is to satisfy the total power demand of the plant and to minimize a set of optimization criteria, formulated as energy usage, monetary cost, and environmental cost. The presented method has been validated under real conditions in the car manufacturing plant of SEAT in Spain in the framework of an FP7 European research project.

Disaggregation of HVAC load profiles for the monitoring of individual equipment

This paper presents a load disaggregation method for the monitoring and supervision of the load profiles of individual equipment in an HVAC installation. The method takes advantage of the wealth of sensor and actuation information found in Building Energy Management Systems in order to find correlations between the state of operation of each machine and the power demand of the installation. This enables to model the individual power of the equipment on account of their state, and in combination with other support variables that influence their load demand, such as weather conditions. The resulting array of equipment models can be evaluated in real-time to infer the expected power consumption of each machine. Then, allowing the tracking of their individual power consumption while at the same time significantly lowering the cost of the acquisition and monitoring infrastructure, because a single power meter can be used to accurately monitor several machines when following this approach. The presented method has been validated by means of experimental data from a pilot plant where the complete system has been implemented.

Enhanced load forecasting methodology by means of probabilistic prediction intervals estimation

The improvement of the forecasting accuracy for prediction of future loads has been object of exhaustive study in the recent years, to the point that a wide variety of methodologies which have been proved to be valid and practical exists. However, most methodologies for demand forecasting do not handle uncertainties of the resulting model, which leads to a nonproper interpretation of the forecasted outcomes. In this context, this work presents a novel load forecasting methodology in order to quantify the model uncertainties and complement the resulting information by means of adaptive confidence intervals. First, an input selection technique based on Genetic Algorithms is used to select the best combination of inputs in order to obtain a state-of-the-art model by means of Adaptive Neuro-Fuzzy Inference Systems. Then the data space is analyzed in terms of error probability of the model outcomes. The principal component analysis is used to visualize the error probability in a 2-D map. Finally, an Artificial Neural Network is used to perform the identification of the error probability associated to new measurements. In conjunction with the forecasting model, the proposed classifier extends the resulting information with an adaptive confidence intervals and its probability distribution. The effectiveness of this enhanced load forecasting methodology has been verified by experimental data obtained from an automotive plant.

Energy hub optimization applied on car manufacturing plants

The challenge of climate change is real and growing. Every car manufacturing plant must look deep into its operations and use every opportunity to play its part in reducing overall emissions. Furthermore, due to the increased competition of the sector, they must turn to solutions that can reduce their costs, but maintaining the products quality on high standards. One way to achieve that goal, which is also the focus of this work, is by reducing the energy use in the plants operation processes. This paper presents a hybrid optimization methodology, combined by neuro-fuzzy inference systems and the quadratic programming algorithm, to calculate the short-term demand forecasting of a plant, and to optimize its energy flow. Moreover, the dynamic models of the plants equipment are considered into the optimization process, to calculate the dynamic system response and the equipments inertias. Finally, the algorithm optimizes the operation of the plant with objective to fulfill the energy demand, minimizing several optimization criteria. The presented methodology has been tested and evaluated in an automotive factory plant of Spain using real production and consumption data.

Short-term load forecasting using Cartesian Genetic Programming: An efficient evolutive strategy: Case: Australian electricity market

Currently, the Cartesian Genetic Programming approaches applied to regression problems tackle the evolutive strategy from a static point of view. They are confident on the evolving capacity of the genetic algorithm, with less attention being paid over alternative methods to enhance the generalization error of the trained models or the convergence time of the algorithm. On this article, we propose a novel efficient strategy to train models using Cartesian Genetic Programming at a faster rate than its basic implementation. This proposal achieves greater generalization and enhances the error convergence. Finally, the complete methodology is tested using the Australian electricity market as a case study.

Stability analysis of a microgrid system based on inverter-interfaced distributed generators

This paper presents a phase-plane trajectory analysis and the appliance of Lyapunov´s methodology to evaluate the stability limits of a small signal model of a Microgrid system. The work done is based on a non-linear tool and several computer simulations. The study indicates how to analyze a Microgrid system that is subjected to a severe transient disturbance by using its large signal model without the necessity of the small signal analysis as it is commonly applied.