Abdollah Kavousi-Fard

A new hybrid Modified Firefly Algorithm and Support Vector Regression model for accurate Short Term Load Forecasting

Abstract Precise forecast of the electrical load plays a highly significant role in the electricity industry and market. It provides economic operations and effective future plans for the utilities and power system operators. Due to the intermittent and uncertain characteristic of the electrical load, many research studies have been directed to nonlinear prediction methods. In this paper, a hybrid prediction algorithm comprised of Support Vector Regression (SVR) and Modified Firefly Algorithm (MFA) is proposed to provide the short term electrical load forecast. The SVR models utilize the nonlinear mapping feature to deal with nonlinear regressions. However, such models suffer from a methodical algorithm for obtaining the appropriate model parameters. Therefore, in the proposed method the MFA is employed to obtain the SVR parameters accurately and effectively. In order to evaluate the efficiency of the proposed methodology, it is applied to the electrical load demand in Fars, Iran. The obtained results are compared with those obtained from the ARMA model, ANN, SVR-GA, SVR-HBMO, SVR-PSO and SVR-FA. The experimental results affirm that the proposed algorithm outperforms other techniques.

Optimal Distribution Feeder Reconfiguration for Reliability Improvement Considering Uncertainty

This paper proposes a new method to improve the reliability of the distribution system using the reconfiguration strategy. In this regard, a new cost function is defined to include the cost of active power losses of the network and the customer interruption costs simultaneously. Also, in order to calculate the reliability indices of the load points, the reconfiguration technique is considered as a failure-rate reduction strategy. Regarding the reliability cost, the composite customer damage function is employed to find the customer interruption cost data. Meanwhile, a powerful stochastic framework based on a two- point estimate method is proposed to capture the uncertainty of random parameters. Also, a novel self-adaptive modification method based on the clonal selection algorithm is proposed as the optimization tool. The feasibility and satisfying performance of the proposed method are examined on the 69-bus IEEE test system.

Reliability enhancement using optimal distribution feeder reconfiguration

Failure statistics show that distribution networks engage the most contribution to the customer unavailability services. Optimal reconfiguration of distribution systems has many advantages like total power losses reduction, voltage profile enhancement, reliability improvement and so on. Therefore, in this paper a new multiobjective improved shuffled frog leaping algorithm (ISFLA) is proposed to investigate the distribution feeder reconfiguration (DFR) problem from the reliability enhancement point of view. Nevertheless, since the total cost of MW loss is an important and attractive subject to the electric power utilities, the total active power losses is also considered as an objective function in the investigations. Therefore, the objective functions of the problem to be optimized are system average interruption frequency index (SAIFI), system average interruption duration index (SAIDI), average energy not supplied (AENS) and the total active power losses. During the optimization process, the proposed ISFLA finds a set of non-dominated optimal solutions referred to Pareto optimal solutions that are kept in an external memory called repository. As the result of the conflicting behavior of the objective functions investigated, a fuzzy clustering technique is employed to control the size of the repository in the predetermined limits. The feasibility and the efficiency of the proposed method are examined by a standard distribution test system.

A New Fuzzy-Based Combined Prediction Interval for Wind Power Forecasting

This paper makes use of the idea of prediction intervals (PIs) to capture the uncertainty associated with wind power generation in power systems. Since the forecasting errors cannot be appropriately modeled using distribution probability functions, here we employ a powerful nonparametric approach called lower upper bound estimation (LUBE) method to construct the PIs. The proposed LUBE method uses a new framework based on a combination of PIs to overcome the performance instability of neural networks (NNs) used in the LUBE method. Also, a new fuzzy-based cost function is proposed with the purpose of having more freedom and flexibility in adjusting NN parameters used for construction of PIs. In comparison with the other cost functions in the literature, this new formulation allows the decision-makers to apply their preferences for satisfying the PI coverage probability and PI normalized average width individually. As the optimization tool, bat algorithm with a new modification is introduced to solve the problem. The feasibility and satisfying performance of the proposed method are examined using datasets taken from different wind farms in Australia.

A new hybrid correction method for short-term load forecasting based on ARIMA, SVR and CSA

Accurate load-forecasting problem is a significant and vital issue, especially in the new competitive electricity market. The models that are employed for forecasting purposes would determine how reliable the last forecasted results are. Therefore, this paper proposes a new hybrid correction method based on autoregressive integrated moving average (ARIMA) model, support vector regression (SVR) and cuckoo search algorithm (CSA) to achieve a more reliable forecasting model. The proposed method gets use of the autocorrelation function (ACF) and the partial ACF to search the stationary or non-stationary behaviour of the investigated time series. In the case of non-stationary data, it will be differenced one or more times to become stationary. After that, Akaike information criterion is utilised to find the appropriate ARIMA model such that the linear component of the data would be captured. Therefore, the ARIMA residuals would contain the non-linear components that should be modelled by use of the SVR model. The role of CSA as a successful optimisation algorithm is to find the optimal SVR parameters for more accurate forecasting. Meanwhile, a novel self-adaptive modification method based on CSA is proposed to empower the total search ability of the algorithm effectively. The proposed method is applied to the empirical peak load data of Fars Electrical Power Company in Iran.

Expected Cost Minimization of Smart Grids With Plug-In Hybrid Electric Vehicles Using Optimal Distribution Feeder Reconfiguration

Stochastic charging behavior of plug-in hybrid electric vehicles (PHEVs) under different charging strategies brings new challenges for distribution networks such as feeder overloading and loss increase. In this way, the augmented penetration of these vehicles mandates employing new operative tools to inspect their impacts on electrical grids. Therefore, this paper proposes a novel optimal stochastic reconfiguration methodology to moderate the charging effect of PHEVs by changing the topology of grid using some remote controlled switches. Uncertainties associated with network demand, energy price, and PHEV charging behavior in different charging frameworks are handled with Monte Carlo simulation and the proposed stochastic problem is solved with krill herd optimization algorithm. Numerical studies on Tai-power distribution system verify the efficacy of proposed reconfiguration to improve the system performance considering PHEV charging loads.

Stochastic Reconfiguration and Optimal Coordination of V2G Plug-in Electric Vehicles Considering Correlated Wind Power Generation

This paper investigates the optimal operation of distribution feeder reconfiguration (DFR) strategy in the smart grids with high penetration of plug-in electric vehicles (PEVs) and correlated wind power generation. The increased utilization of PEVs in the system with stochastic volatile behavior along with the high penetration of renewable power sources such as wind turbines (WTs) can create new challenges in the system that will affect the DFR strategy greatly. In order to reach the most efficiency from the PEVs, the idea of vehicle-to-grid (V2G) is employed in this paper to make a bidirectional power flow (either charging/discharging or idle mode) strategy when providing the main charging needs of PEVs. In this regard, we suggest a new stochastic framework based on unscented transformation (UT) to model the uncertainties of the PEVs behaviors when considering the correlated power generation of WTs. The feasibility and satisfying performance of the proposed framework are examined on the IEEE 69-bus test system.

A hybrid fuzzy-PEM stochastic framework to solve the optimal operation management of distribution feeder reconfiguration considering wind turbines

This paper proposes a new stochastic framework based on point estimate method to solve the optimal operation management of Distribution Feeder Reconfiguration DFR considering several Wind Turbines WTs in the system. The proposed method can properly solve the complex and discrete DFR optimization problem by the use of an adaptive modification approach based on firefly algorithm FA. In addition, a new stochastic solution based on 2m Point Estimate Method 2m PEM is proposed to handle the uncertainty associated with the problem random variables including the active and reactive loads as well as the wind speed variations effectively. The problem is then formulated in a multi-objective optimization structure including four significant targets: 1 active power losses, 2 bus voltage deviation, 3 total system costs and 4 total pollution produced. As a result of the conflicting behavior of the four objective functions, a fuzzy based clustering technique is employed to reach the set of optimal solutions called Pareto solutions. The feasibility and satisfying performance of the proposed method is examined on the IEEE 32-bus standard test system.

A Novel Stochastic Framework Based on Cloud Theory and

Distribution feeder reconfiguration (DFR) is a precious operation strategy that can improve the system from different aspects including total cost, reliability, and power quality. Nevertheless, the high complexity of the new smart grids has resulted in much uncertainty in the DFR problem that necessities the use of a sufficient stochastic framework to deal with them. In this way, this paper proposes a new stochastic framework based on cloud theory to account the uncertainties associated with multiobjective DFR problem from the reliability point of view. Cloud theory is constructed based on fuzzy theory and probability idea. In comparison with the Monte Carlo simulation method, cloud models can give more information on the uncertainties associated with the problem. This special aspect of cloud models makes it possible to integrate the fuzziness and randomness of qualitative concepts through the cloud drops and then transforms them to the quantitative model. In order to solve the proposed problem, a fast and powerful optimization technique is required. To deal with this issue, a new optimization algorithm designated as θ-bat algorithm is proposed in this paper. The feasibility and satisfying performance of the proposed method are examined on the 32-bus and 69-bus IEEE distribution test system.

\theta

Integration of plug-in electric vehicle (PEV) will influence distribution systems in various aspects from network loss and operating costs to system reliability. PEVs can be either mobile loads or mobile storages dispersed in the network. In this paper, distribution feeder reconfiguration (DFR) technique is employed as a reliability-enhancing strategy to coordinate vehicle-to-grid (V2G) provision of PEV fleets in a stochastic framework. Uncertainties associated with network load demand, energy price, wind power generation, and PEV fleet behavior are considered. The proposed stochastic optimization problem is solved with a self-adaptive evolutionary algorithm based on symbiotic organism search (SOS). Numerical studies on standard test system verify the efficacy of the proposed DFR to improve the system reliability and optimal dispatch of V2G.