查看文章

For the 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 the existing forecasting techniques for load flow balancing. The neural network (NN) based forecasting techniques are unable to consider the actual states of a power system, while the weighted least square state estimation (WLS) fails to counter non-linearity in the demand profile. In this paper, a hybrid approach is proposed for the short term load forecasting. The hybrid technique, comprises of WLS, NN, and adaptive neuro-fuzzy inference system (ANFIS), is called as WLANFIS. ANFIS itself is the combination of NN and fuzzy logic. It takes a refined dataset obtained through NN and WLS, which helps in determining the optimal number and types of membership function. It also helps in determining the effective fuzzy set ranges for an individual membership function that is utilized by the fuzzy system. The WLS provides estimated states in the realworld scenario while NN models the non-linearity in the demand profile and is tested on IEEE 14 and 30 bus systems as well on real-world collected datasets. 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 the mean absolute percentage error as low as 2.66%.