Showing papers in "IEEE Transactions on Power Systems in 2006"
TL;DR: In this article, the feasibility of control strategies to be adopted for the operation of a microgrid when it becomes isolated is evaluated and the need of storage devices and load shedding strategies is evaluated.
Abstract: This paper describes and evaluates the feasibility of control strategies to be adopted for the operation of a microgrid when it becomes isolated. Normally, the microgrid operates in interconnected mode with the medium voltage network; however, scheduled or forced isolation can take place. In such conditions, the microgrid must have the ability to operate stably and autonomously. An evaluation of the need of storage devices and load shedding strategies is included in this paper.
2,276 citations
TL;DR: In this paper, a new mixed-integer linear formulation for the unit commitment problem of thermal units is presented, which requires fewer binary variables and constraints than previously reported models, yielding a significant computational saving.
Abstract: This paper presents a new mixed-integer linear formulation for the unit commitment problem of thermal units. The formulation proposed requires fewer binary variables and constraints than previously reported models, yielding a significant computational saving. Furthermore, the modeling framework provided by the new formulation allows including a precise description of time-dependent startup costs and intertemporal constraints such as ramping limits and minimum up and down times. A commercially available mixed-integer linear programming algorithm has been applied to efficiently solve the unit commitment problem for practical large-scale cases. Simulation results back these conclusions
1,601 citations
TL;DR: In this article, real and reactive power management strategies of EI-DG units in the context of a multiple DG microgrid system were investigated. And the results were used to discuss applications under various microgrid operating conditions.
Abstract: This paper addresses real and reactive power management strategies of electronically interfaced distributed generation (DG) units in the context of a multiple-DG microgrid system. The emphasis is primarily on electronically interfaced DG (EI-DG) units. DG controls and power management strategies are based on locally measured signals without communications. Based on the reactive power controls adopted, three power management strategies are identified and investigated. These strategies are based on 1) voltage-droop characteristic, 2) voltage regulation, and 3) load reactive power compensation. The real power of each DG unit is controlled based on a frequency-droop characteristic and a complimentary frequency restoration strategy. A systematic approach to develop a small-signal dynamic model of a multiple-DG microgrid, including real and reactive power management strategies, is also presented. The microgrid eigen structure, based on the developed model, is used to 1) investigate the microgrid dynamic behavior, 2) select control parameters of DG units, and 3) incorporate power management strategies in the DG controllers. The model is also used to investigate sensitivity of the design to changes of parameters and operating point and to optimize performance of the microgrid system. The results are used to discuss applications of the proposed power management strategies under various microgrid operating conditions
1,531 citations
TL;DR: In this article, a method is proposed to let variable-speed wind turbines emulate inertia and support primary frequency control, where the required power is obtained from the kinetic energy stored in the rotating mass of the turbine blades.
Abstract: The increasing penetration of variable-speed wind turbines in the electricity grid will result in a reduction of the number of connected conventional power plants. This will require changes in the way the grid frequency is controlled. In this letter, a method is proposed to let variable-speed wind turbines emulate inertia and support primary frequency control. The required power is obtained from the kinetic energy stored in the rotating mass of the turbine blades.
1,106 citations
TL;DR: In this article, the authors presented an approach to compute annual energy losses variations when different penetration and concentration levels of distributed generation (DG) are connected to a distribution network, and the impact on losses of different DG technologies, such as combined heat and power, wind power, photovoltaic, and fuel-cells, was analyzed.
Abstract: High levels of penetration of distributed generation (DG) are a new challenge for traditional electric power systems. Power injections from DGs change network power flows modifying energy losses. Although it is considered that DG reduce losses, this paper shows that this is not always true. This paper presents an approach to compute annual energy losses variations when different penetration and concentration levels of DG are connected to a distribution network. In addition, the impact on losses of different DG technologies, such as combined heat and power, wind power, photovoltaic, and fuel-cells, is analyzed. Results show that energy losses variation, as a function of the DG penetration level, presents a characteristic U-shape trajectory. Moreover, when DG units are more dispersed along network feeders, higher losses reduction can be expected. Regarding DG technologies, it should be noted that wind power is the one that shows the worst behavior in losses reduction. Finally, DG units with reactive power control provide a better network voltage profile and lower losses.
619 citations
TL;DR: In this article, the authors show that the load flow problem of a radial distribution system can be modeled as a convex optimization problem, particularly a conic program, which facilitates the inclusion of the distribution power flow equations in radial system optimization problems.
Abstract: This paper shows that the load flow problem of a radial distribution system can be modeled as a convex optimization problem, particularly a conic program. The implications of the conic programming formulation are threefold. First, the solution of the distribution load flow problem can be obtained in polynomial time using interior-point methods. Second, numerical ill-conditioning can be automatically alleviated by the use of scaling in the interior-point algorithm. Third, the conic formulation facilitates the inclusion of the distribution power flow equations in radial system optimization problems. A state-of-the-art implementation of an interior-point method for conic programming is used to obtain the solution of nine different distribution systems. Comparisons are carried out with a previously published radial load flow program by R. Cespedes
592 citations
TL;DR: The proposed combined method outperforms other state-of-the-art algorithms in solving load dispatch problems with the valve-point effect.
Abstract: Evolutionary algorithms are heuristic methods that have yielded promising results for solving nonlinear, nondifferentiable, and multi-modal optimization problems in the power systems area. The differential evolution (DE) algorithm is an evolutionary algorithm that uses a rather greedy and less stochastic approach to problem solving than do classical evolutionary algorithms, such as genetic algorithms, evolutionary programming, and evolution strategies. DE also incorporates an efficient way of self-adapting mutation using small populations. The potentialities of DE are its simple structure, easy use, convergence property, quality of solution, and robustness. This paper proposes a new approach for solving economic load dispatch problems with valve-point effect. The proposed method combines the DE algorithm with the generator of chaos sequences and sequential quadratic programming (SQP) technique to optimize the performance of economic dispatch problems. The DE with chaos sequences is the global optimizer, and the SQP is used to fine-tune the DE run in a sequential manner. The combined methodology and its variants are validated for two test systems consisting of 13 and 40 thermal units whose incremental fuel cost function takes into account the valve-point loading effects. The proposed combined method outperforms other state-of-the-art algorithms in solving load dispatch problems with the valve-point effect.
587 citations
TL;DR: Various techniques are discussed and compared able to reduce the size of the clustering input data set, in order to allow for storing a relatively small amount of data in the database of the distribution service provider for customer classification purposes.
Abstract: The recent evolution of the electricity business regulation has given new possibilities to the electricity providers for formulating dedicated tariff offers. A key aspect for building specific tariff structures is the identification of the consumption patterns of the customers, in order to form specific customer classes containing customers exhibiting similar patterns. This paper illustrates and compares the results obtained by using various unsupervised clustering algorithms (modified follow-the-leader, hierarchical clustering, K-means, fuzzy K-means) and the self-organizing maps to group together customers with similar electrical behavior. Furthermore, this paper discusses and compares various techniques-Sammon map, principal component analysis (PCA), and curvilinear component analysis (CCA)-able to reduce the size of the clustering input data set, in order to allow for storing a relatively small amount of data in the database of the distribution service provider for customer classification purposes. The effectiveness of the classifications obtained with the algorithms tested is compared in terms of a set of clustering validity indicators. Results obtained on a set of nonresidential customers are presented.
476 citations
TL;DR: Results clearly show that HPSO is very competent in solving the UC problem in comparison to other existing methods.
Abstract: This paper presents a new approach via hybrid particle swarm optimization (HPSO) scheme to solve the unit commitment (UC) problem. HPSO proposed in this paper is a blend of binary particle swarm optimization (BPSO) and real coded particle swarm optimization (RCPSO). The UC problem is handled by BPSO, while RCPSO solves the economic load dispatch problem. Both algorithms are run simultaneously, adjusting their solutions in search of a better solution. Problem formulation of the UC takes into consideration the minimum up and down time constraints, start-up cost, and spinning reserve and is defined as the minimization of the total objective function while satisfying all the associated constraints. Problem formulation, representation, and the simulation results for a ten generator-scheduling problem are presented. Results clearly show that HPSO is very competent in solving the UC problem in comparison to other existing methods.
440 citations
TL;DR: In this article, the authors proposed an alternative approach, which leaves the traditional state estimation software in place, and discusses a novel method of incorporating the phasor measurements and the results of the state estimator in a postprocessing linear estimator.
Abstract: With the increasing use of real-time synchronized phasor measurement units, it is necessary to consider applications of these measurements in greater detail. One of the most natural applications of these measurements is in the area of state estimation. A straightforward application of state estimation theory treats phasor measurements of currents and voltages as additional measurements to be appended to traditional measurements now being used in most energy management system (EMS) state estimators. The resulting state estimator is once again nonlinear and requires significant modifications to existing EMS software. This paper proposes an alternative approach, which leaves the traditional state estimation software in place, and discusses a novel method of incorporating the phasor measurements and the results of the traditional state estimator in a postprocessing linear estimator. This paper presents the underlying theory and provides verification through simulations of the two alternative strategies. It is shown that the new technique provides the same results as the nonlinear state estimator and does not require modification of the existing EMS software
403 citations
TL;DR: 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).
Abstract: 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.
TL;DR: In this article, an adaptive neuro-fuzzy inference system was used to forecast wind vectors, rather than windspeed or power output, for very short-term wind prediction.
Abstract: This paper describes very short-term wind prediction for power generation, utilizing a case study from Tasmania, Australia. Windpower presently is the fastest growing power generation sector in the world. However, windpower is intermittent. To be able to trade efficiently, make the best use of transmission line capability, and address concerns with system frequency in a re-regulated system, accurate very short-term forecasts are essential. The research introduces a novel approach-the application of an adaptive neuro-fuzzy inference system to forecasting a wind time series. Over the very short-term forecast interval, both windspeed and wind direction are important parameters. To be able to be gain the most from a forecast on this time scale, the turbines must be directed toward on oncoming wind. For this reason, this paper forecasts wind vectors, rather than windspeed or power output.
TL;DR: In this paper, it is shown that with few extra PMUs, the bad data detection and identification capability of a given system can be drastically improved, and case studies carried out on different size test systems are presented.
Abstract: As the phasor measurement units (PMUs) start populating the substations, their benefits for different power system application functions are being debated. One of these functions is the bad data processing that is commonly integrated into the state estimation. Bad data detection is closely related to the measurement redundancy in that bad data appearing in critical measurements cannot be detected. Such measurements, however, can be transformed into redundant measurements by adding few PMUs at strategic locations. In this paper, it will be shown that with few extra PMUs, the bad data detection and identification capability of a given system can be drastically improved. Description of the placement algorithm is given, and case studies carried out on different size test systems are presented
TL;DR: An efficient method based on a new fuzzy neural network has inter-layer and feed-forward architecture with a new hypercubic training mechanism for short-term price forecasting of electricity markets and can provide more accurate results than other price forecasting techniques.
Abstract: In this paper, an efficient method based on a new fuzzy neural network is proposed for short-term price forecasting of electricity markets. This fuzzy neural network has inter-layer and feed-forward architecture with a new hypercubic training mechanism. The proposed method predicts hourly market-clearing prices for the day-ahead electricity markets. By combination of fuzzy logic and an efficient learning algorithm, an appropriate model for the nonstationary behavior and outliers of the price series is presented. The proposed method is examined on the Spanish electricity market. It is shown that the method can provide more accurate results than the other price forecasting techniques, such as ARIMA time series, wavelet-ARIMA, MLP, and RBF neural networks.
TL;DR: This paper reports on the development and subsequent use of the electric power and communication synchronizing simulator (EPOCHS), a distributed simulation environment that integrates multiple research and commercial off-the-shelf systems to bridge the gap.
Abstract: This paper reports on the development and subsequent use of the electric power and communication synchronizing simulator (EPOCHS), a distributed simulation environment. Existing electric power simulation tools accurately model power systems of the past, which were controlled as large regional power pools without significant communication elements. However, as power systems increasingly turn to protection and control systems that make use of computer networks, these simulators are less and less capable of predicting the likely behavior of the resulting power grids. Similarly, the tools used to evaluate new communication protocols and systems have been developed without attention to the roles they might play in power scenarios. EPOCHS integrates multiple research and commercial off-the-shelf systems to bridge the gap.
TL;DR: In this article, a new approach to adaptive underfrequency load shedding (UFLS), a procedure for protecting electric power systems from dynamic instability and frequency collapse, is presented, which consists of two main stages.
Abstract: In this paper, a new approach to adaptive underfrequency load shedding (UFLS), a procedure for protecting electric power systems from dynamic instability and frequency collapse, is presented. It consists of two main stages. In the first stage, the frequency and the rate of frequency change are estimated by the nonrecursive Newton-type algorithm. By using the simplest expression of the generator swing equation, in the second algorithm stage, the magnitude of the disturbance is determined. The UFLS plan is adapted to the magnitude estimated, obtaining in this way a more efficient system operation during emergency conditions. Results of procedure testing are demonstrated through the dynamic simulations by using: 1) a simple three-machine test system and 2) a ten-machine New England system
TL;DR: In this paper, an optimized dispatch control strategy for active and reactive powers delivered by a doubly fed induction generator in a wind park is proposed, which exploits a combination of pitch control and control of the static converters.
Abstract: This paper proposes an optimized dispatch control strategy for active and reactive powers delivered by a doubly fed induction generator in a wind park. In this control approach, wind turbines are supposed to operate over a deloaded maximum power extraction curve and will respond to a supervisory wind farm control after a request from a system operator for adjusting the outputs of the wind park. The definition of the active and reactive powers operating points, for each wind turbine, is defined from an optimization algorithm that uses the primal-dual predictor corrector interior point method. The control strategy used at the wind generator level exploits a combination of pitch control and control of the static converters to adjust the rotor speed for the required operation points. A small wind park is used to illustrate the effectiveness of the developed approach.
TL;DR: In this article, a stochastic programming approach is used to generate optimal wind power production bids for a short-term power market, and the imbalance costs resulting from this strategy are then compared to the case when wind power output is based directly on a wind speed forecast.
Abstract: Present power markets are designed for trading conventional generation. For wind generation to participate in a short-term energy market, lengthy wind power production forecasts are required. Although wind speed forecasting techniques are constantly improving, wind speed forecasts are never perfect, and resulting wind power forecast errors imply imbalance costs for wind farm owners. In this paper, a new method for minimization of imbalance costs is developed. Stochastic programming is used to generate optimal wind power production bids for a short-term power market. A Wind power forecast error is represented as a stochastic process. The imbalance costs resulting from this strategy are then compared to the case when wind power production bids on a short-term power market are based directly on a wind speed forecast
TL;DR: In this paper, a measurement-based composite load model is developed to model load from field measurements, and two cases are studied to illustrate the accuracy of the developed load model on describing the load dynamic characteristics in the actual power system.
Abstract: The accuracy of the load model has great effects on power system stability analysis and control. Based on our practice in China on modeling load from field measurements, this paper systematically develops a measurement-based composite load model. Principles guiding the load modeling practice are discussed based on detailed analysis on stochastic characteristics of the modeling procedure. The structure of the measurement-based composite load model is presented. A multicurve identification technique is described to derive parameters. The generalization capability of this built load model is also investigated in this paper. Two cases are studied to illustrate the accuracy of the developed load model on describing the load dynamic characteristics in the actual power system.
TL;DR: In this paper, a two-point estimate method (2PEM) is proposed to account for uncertainties in the optimal power flow (OPF) problem in the context of competitive electricity markets, where uncertainties can be seen as a by-product of the economic pressure that forces market participants to behave in an "unpredictable" manner; hence, probability distributions of locational marginal prices are calculated as a result.
Abstract: This paper presents an application of a two-point estimate method (2PEM) to account for uncertainties in the optimal power flow (OPF) problem in the context of competitive electricity markets. These uncertainties can be seen as a by-product of the economic pressure that forces market participants to behave in an "unpredictable" manner; hence, probability distributions of locational marginal prices are calculated as a result. Instead of using computationally demanding methods, the proposed approach needs 2n runs of the deterministic OPF for n uncertain variables to get the result in terms of the first three moments of the corresponding probability density functions. Another advantage of the 2PEM is that it does not require derivatives of the nonlinear function used in the computation of the probability distributions. The proposed method is tested on a simple three-bus test system and on a more realistic 129-bus test system. Results are compared against more accurate results obtained from MCS. The proposed method demonstrates a high level of accuracy for mean values when compared to the MCS; for standard deviations, the results are better in those cases when the number of uncertain variables is relatively low or when their dispersion is not large
TL;DR: In this article, a power system stabilizer for a wind turbine employing a doubly fed induction generator (DFIG) is presented, which can significantly influence the contribution that a DFIG-based wind farm can make to network damping.
Abstract: A power system stabilizer (PSS) for a wind turbine employing a doubly fed induction generator (DFIG) is presented. It is shown that this PSS can significantly influence the contribution that a DFIG-based wind farm can make to network damping. A simple, generic test network that combines synchronous and wind farm generation is used to demonstrate system performance contributions. The results of both eigenvalue analysis and time response simulation studies are presented to illustrate contributions to network dynamic and transient performance that the DFIG controller with its PSS can make. Performance capabilities superior to those provided by synchronous generation with automatic voltage regulator and PSS control are demonstrated.
TL;DR: In this paper, a new simulated annealing (SA) algorithm combined with a dynamic economic dispatch method is developed for solving the short-term unit commitment (UC) problem.
Abstract: A new simulated annealing (SA) algorithm combined with a dynamic economic dispatch method has been developed for solving the short-term unit commitment (UC) problem. SA is used for the scheduling of the generating units, while a dynamic economic dispatch method is applied incorporating the ramp rate constraints in the solution of the UC problem. New rules concerning the tuning of the control parameters of the SA algorithm are proposed. Three alternative mechanisms for generating feasible trial solutions in the neighborhood of the current one, contributing to the reduction of the required CPU time, are also presented. The ramp rates are taken into account by performing either a backward or a forward sequence of conventional economic dispatches with modified limits on the generating units. The proposed algorithm is considerably fast and provides feasible near-optimal solutions. Numerical simulations have proved the effectiveness of the proposed algorithm in solving large UC problems within a reasonable execution time.
TL;DR: In this paper, a dispatch model was developed that analyzes the impact that wind generation has on the operation of conventional plants and the resulting emissions of carbon dioxide (CO/sub 2/), sulphur dioxide (SO/sub dioxide), and oxides of nitrogen (NO/sub X/).
Abstract: With increasing concern over global climate change, policy makers are promoting renewable energy sources, predominantly wind generation, as a means of meeting emissions reduction targets. Although wind generation does not itself produce any harmful emissions, its effect on power system operation can actually cause an increase in the emissions of conventional plants. A dispatch model was developed that analyzes the impact that wind generation has on the operation of conventional plants and the resulting emissions of carbon dioxide (CO/sub 2/), sulphur dioxide (SO/sub 2/), and oxides of nitrogen (NO/sub X/). The analysis concentrates on a "forecasted" approach that incorporates wind generation forecasts in the dispatch decisions. It was found that wind generation could be used as a tool for reducing CO/sub 2/ emissions but alone, it was not effective in curbing SO/sub 2/ and NO/sub X/ emissions.
TL;DR: Three new particle swarm optimization (PSO) algorithms are compared with the state of the art PSO algorithms for the optimal steady-state performance of power systems, namely, the reactive power and voltage control.
Abstract: In this paper, three new particle swarm optimization (PSO) algorithms are compared with the state of the art PSO algorithms for the optimal steady-state performance of power systems, namely, the reactive power and voltage control. Two of the three introduced, the enhanced GPAC PSO and LPAC PSO, are based on the global and local-neighborhood variant PSOs, respectively. They are hybridized with the constriction factor approach together with a new operator, reflecting the physical force of passive congregation observed in swarms. The third one is based on a new concept of coordinated aggregation (CA) and simulates how the achievements of particles can be distributed in the swarm affecting its manipulation. Specifically, each particle in the swarm is attracted only by particles with better achievements than its own, with the exception of the particle with the best achievement, which moves randomly as a "crazy" agent. The obtained results by the enhanced general passive congregation (GPAC), local passive congregation (LPAC), and CA on the IEEE 30-bus and IEEE 118-bus systems are compared with an interior point (IP)-based OPF algorithm, a conventional PSO algorithm, and an evolutionary algorithm (EA), demonstrating the excellent performance of the proposed PSO algorithms
TL;DR: In this article, the authors used the Numerical algorithm for Subspace State Space System IDentification (N4SID) to extract dynamic parameters from phasor measurements collected on the western North American Power Grid.
Abstract: In this paper, the authors use the Numerical algorithm for Subspace State Space System IDentification (N4SID) to extract dynamic parameters from phasor measurements collected on the western North American Power Grid. The data were obtained during tests on June 7, 2000, and they represent wide area response to several kinds of probing signals, including low-level pseudo-random noise (LLPRN) and single-mode square wave (SMSW) injected at the Celilo terminal of the Pacific HVDC Intertie (PDCI). An identified model is validated using a cross validation method. Also, the obtained electromechanical modes are compared with the results from Prony analysis of a ringdown and with signal analysis of ambient data measured under similar operating conditions. The consistent results show that methods in this class can be highly effective, even when the probing signal is small
TL;DR: In this article, the authors proposed the use of nodal pricing that is often used in the pricing of short-term operations in transmission and showed significant price differences between buses reflecting high marginal losses.
Abstract: As distributed generation (DG) becomes more widely deployed, distribution networks become more active and take on many of the same characteristics as transmission. We propose the use of nodal pricing that is often used in the pricing of short-term operations in transmission. As an economically efficient mechanism, nodal pricing would properly reward DG for reducing line losses through increased revenues at nodal prices and signal prospective DG where it ought to connect with the distribution network. Applying nodal pricing to a model distribution network, we show significant price differences between buses reflecting high marginal losses. Moreover, we show the contribution of a DG resource located at the end of the network to significant reductions in losses and line loading. We also show the DG resource has significantly greater revenue under nodal pricing, reflecting its contribution to reduced line losses and loading.
TL;DR: In this article, the Tellegen's theorem and adjoint networks are used to derive a new, local voltage-stability index, which makes it possible to determine the Thevenin's parameters in a different way than adaptive curvefitting techniques, from two consecutive phasor measurements.
Abstract: In the paper, the Tellegen's theorem and adjoint networks are used to derive a new, local voltage-stability index. The new approach makes it possible to determine the Thevenin's parameters in a different way than adaptive curve-fitting techniques, from two consecutive phasor measurements. The new index was rigorously tested on different test systems. The results were obtained on a static two-bus test system and on the dynamic Belgian-French 32-bus test system that includes full dynamic models of all power-system components crucial to the voltage instability analysis. The results show advantages of the proposed index: it is simple, computationally very fast, and easy to implement in the wide-area monitoring and control center or locally in a numerical relay
TL;DR: In this article, the authors presented a ride-through simulation study of a 2MW wind-power doubly fed induction generator (DFIG) under a short-term unsymmetrical network disturbance.
Abstract: This paper presents a ride-through simulation study of a 2-MW wind-power doubly fed induction generator (DFIG) under a short-term unsymmetrical network disturbance. The DFIG is represented by an analytical two-axis model with constant lumped parameters and by a finite element method (FEM)-based model. The model of the DFIG is coupled with the model of the active crowbar protected and direct torque controlled (DTC) frequency converter, the model of the main transformer, and a simple model of the grid. The simulation results show the ride-through capability of the studied doubly fed wind-power generator. The results obtained by means of an analytical model and FEM model are compared in order to reveal the influence of the different modeling approaches on the short-term transient simulation accuracy
TL;DR: Test the ability of self-organizing maps (SOMs) to filter, classify, and extract patterns from distributor, commercializer, or customer electrical demand databases to show the suitability to improve data management and to easily find coherent clusters between electrical users.
Abstract: Different methodologies are available for clustering purposes. The objective of this paper is to review the capacity of some of them and specifically to test the ability of self-organizing maps (SOMs) to filter, classify, and extract patterns from distributor, commercializer, or customer electrical demand databases. These market participants can achieve an interesting benefit through the knowledge of these patterns, for example, to evaluate the potential for distributed generation, energy efficiency, and demand-side response policies (market analysis). For simplicity, customer classification techniques usually used the historic load curves of each user. The first step in the methodology presented in this paper is anomalous data filtering: holidays, maintenance, and wrong measurements must be removed from the database. Subsequently, two different treatments (frequency and time domain) of demand data were tested to feed SOM maps and evaluate the advantages of each approach. Finally, the ability of SOM to classify new customers in different clusters is also examined. Both steps have been performed through a well-known technique: SOM maps. The results clearly show the suitability of this approach to improve data management and to easily find coherent clusters between electrical users, accounting for relevant information about weekend demand patterns
TL;DR: In this paper, the authors proposed a novel approach to monthly electric energy demand time series forecasting, in which it is split into two new series: the trend and the fluctuation around it, and two neural networks are trained to forecast them separately.
Abstract: Medium-term electric energy demand forecasting is an essential tool for power system planning and operation, mainly in those countries whose power systems operate in a deregulated environment. This paper proposes a novel approach to monthly electric energy demand time series forecasting, in which it is split into two new series: the trend and the fluctuation around it. Then two neural networks are trained to forecast them separately. These predictions are added up to obtain an overall forecasting. Several methods have been tested to find out which of them provides the best performance in the trend extraction. The proposed technique has been applied to the Spanish peninsular monthly electric consumption. The results obtained are better than those reached when only one neural network was used to forecast the original consumption series and also than those obtained with the ARIMA method