Load Forecasting Through Estimated Parametrized Based Fuzzy Inference System in Smart Grids

For optimal utilization of power generation resources, load forecasting plays a vital role in balancing the load flow in a power distribution network. There are several drawbacks associated with existing forecasting techniques for load flow balancing. Neural network (NN) based forecasting techniques are unable to consider the actual states of a power system, while weighted least squares state estimation (WLS) fails to counter nonlinearity in the demand profile. In this article, a hybrid approach is proposed for short term load forecasting. The hybrid technique, comprised of a WLS, NN, and adaptive neuro-fuzzy inference system (ANFIS), is termed WLANFIS. ANFIS itself is the combination of an NN and fuzzy logic. It takes a refined data set obtained through NN and WLS, which helps in determining the optimal number and types of membership functions. It also helps in determining the effective fuzzy set ranges for an individual membership function that is used by the fuzzy system. WLS provides estimated states in the real-world scenario while the NN models the nonlinearity in the demand profile and is tested on IEEE 14 and 30 bus systems as well on real-world data sets. Results show that the proposed algorithm has a higher generalization capability and provides accurate forecasting results even in the case of medium-term load forecasting. It outperforms other methodologies by achieving a mean absolute percentage error as low as 2.66%.

Automated summary

A hybrid approach named WLANFIS is proposed for short-term load forecasting in this article, combining WLS, NN, and ANFIS. The method shows higher generalization capability and provides accurate forecasting results in experiments.