Optimal Control of Solar Energy Resources in Loading Margin Enhancement for Peninsular Malaysia Network Using Artificial Neural Network (ANN) Model

Renewable energy invariably foreseen to be fully spurs by 2030-2050 and Malaysia has been seriously intensifies their capabilities on producing solar energy for generating amount of power to be injected into the national grid. The aim of this paper is to investigate the provision of photovoltaic generators quantitatively with respect to future load generation while considering the Loading Margin (LM) capability. Renewable energy resources are known with its ambiguity and commonly for rural electrifications each houses or buildings are installed with battery storage system which allows unused power during daytime to be stored and will be utilized at night. This kind of system would not experience big impact in conjunction of intermittent level of insolation due to its small requirement at receiving end. Conversely, in big cities located in the west region of Malaysia it becomes a big issue to cope with variations of load demand. In an explicit form of voltage deficiency caused by irregular operation on the grid, a fragile electrical nodes most likely vulnerable and PV generators are inevitably have to stay connected to the point of common coupling supporting grid’s voltage. Eventually at this stage, Grid System Operator (GSO) needs to have brisk respond to these online scenarios but in practice it could not be done at ease. Thus, an intelligent model of ANN which incorporated tremendous set of local data is developed in this paper to regulate loading margin (LM) at critical node by taking into account possible wheather condition at any given time and loading increments. This method employed a kind of supervised training and successfully yields smart predictive technique of LM in any certain correspond inputs. By having this, GSO can barely make the arrangement of reactive power injection throughout the network with the central coordination control among PV generators. Simulation results show the effectiveness of the proposed method and have been discussed thoroughly.

[1]  I. Green,et al.  Impacts of solar PV generators on power system stability and voltage performance , 2012, 2012 IEEE Power and Energy Society General Meeting.

[2]  S. Soares,et al.  MW and MVar management on supply and demand side for meeting voltage stability margin criteria , 2004, IEEE Transactions on Power Systems.

[3]  Dipti Srinivasan,et al.  Correlation analysis of solar power and electric demand , 2013, 2013 International Conference on Renewable Energy and Sustainable Energy (ICRESE).

[4]  T. Lotfi,et al.  Short and Mid-Term Wind Power Forecasting with ANN-PSO , 2014 .

[5]  Abbas Khosravi,et al.  Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Ya-Chin Chang.  Multi-Objective Optimal SVC Installation for Power System Loading Margin Improvement , 2012, IEEE Transactions on Power Systems.

[7]  Vivek Agarwal,et al.  Reactive Power Capacity Enhancement of a PV-Grid System to Increase PV Penetration Level in Smart Grid Scenario , 2014, IEEE Transactions on Smart Grid.

[8]  Biplab Bhattacharyya,et al.  Fuzzy based evolutionary algorithm for reactive power optimization with FACTS devices , 2014 .

[9]  Antonio Carlos Zambroni de Souza,et al.  Probabilistic voltage stability assessment considering renewable sources with the help of the PV and QV curves , 2013 .

[10]  Abdelaziz Laifa,et al.  Optimal FACTS location to enhance voltage stability using multi-objective harmony search , 2013, 2013 3rd International Conference on Electric Power and Energy Conversion Systems.

[11]  M. Z. Hussin,et al.  Status of a grid-connected MBIPV project in Malaysia , 2011, 2011 3rd International Symposium & Exhibition in Sustainable Energy & Environment (ISESEE).

[12]  Sancho Salcedo-Sanz,et al.  Prediction of Daily Global Solar Irradiation Using Temporal Gaussian Processes , 2014, IEEE Geoscience and Remote Sensing Letters.

[13]  Chul-Hwan Kim,et al.  Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction , 2013, IEEE Transactions on Sustainable Energy.

[14]  Vander Menengoy da Costa,et al.  A new modeling of loading margin and its sensitivities using rectangular voltage coordinates in voltage stability analysis , 2010 .