In this paper, an Improved Ant Colony Optimization (IACO) algorithm optimized fuzzy PID (FPID) controller is proposed for Load Frequency Control of multi area systems. The nonlinear incremental evaporation rate and improvement of pheromone increment updating are proposed in the IACO algorithm to improve the quality of solution. And, a modified objective function using integral time multiply absolute error (ITAE), overshoot, undershoot and settling time with appropriate weight coefficients is proposed to improve the performance of the controller. Initially, a two-area non-reheat thermal system is applied and the FPID controller parameters are optimized by the IACO algorithm with five different objective functions. The modified objective function has better performances than four conventional objective functions. To demonstrate the robustness of the proposed control method, sensitivity analysis is implemented under wide variation of operating conditions and system parameters. Further, the proposed approach is also extended to two-area four-sources hydro thermal power system with/without High Voltage Direct Current (HVDC) link. The superiority of the proposed approach is shown by comparing the results with ZN, GA and hPSO-PS algorithms. The robustness of the proposed method is verified under random load disturbances. Finally, the proposed approach is extended to a two-area power system with governor dead band nonlinearity and results show that the proposed approach can cope with nonlinearity well. The results obtained from all simulations show that the proposed algorithm and modified objective function achieves better performances, such as minimum objective values (ITAE=0.0255, ITSE=9.30e-5, ISE=1.91e-4 and IAE=0.0273) obtained for the two-area non-reheat thermal system.

In this paper, a novel hybrid firefly-bat algorithm with constraints-prior object-fuzzy sorting strategy (HFBA-COFS) is put forward to solve the strictly-constrained multi-objective optimal power flow (MOOPF) problems. The hybrid firefly-bat algorithm (HFBA) integrates the dimension-based firefly algorithm and the modified bat algorithm to improve the population-diversity and global-exploration ability of original algorithm. To handle the unqualified state variables and overcome the deficiency of traditional penalty function approach (PFA), the constraints-prior Pareto-dominant rule (CPR) which takes constraints-violation and objectives-value into consideration is proposed in this paper. Furthermore, an effective constraints-prior object-fuzzy sorting (COFS) strategy based on CPR rule is presented to seek the well-distributed Pareto optimal set (POS) in solving the MOOPF problems. To validate the great advantages of HFBA-COFS algorithm, ten MOOPF cases optimizing active power loss, total emission and fuel cost are simulated on the IEEE 30-bus, IEEE 57-bus and IEEE 118-bus systems. In addition, the generational distance and SPREAD evaluation indexes powerfully demonstrate that the proposed HFBA-COFS algorithm can achieve high-quality POS, which has great significance to realize the safe and economic operation of large-scale power systems.

To improve the accuracy of short term wind speed forecasting, a novel principle-subordinate prediction model based on Conv-LSTM network and BPNN is designed in this paper. The proposed model combines deep learning algorithms and improved neural network to deal with the problem of wind speed forecasting. In this model, the prediction sequence of each subseries is obtained by Conv-LSTM to form more smoother and characteristic series; the BPNN, optimized by MWOA (Modified Whale Optimization Algorithm), is trained with the reconstruction sequence, which processed for the prediction sequence by invert-EMD (inverse empirical model decomposition). Before prediction, singular spectrum analysis (SSA) and complete ensemble empirical model decomposition adaptive noise (CEEMDAN) are adopted to de-noise and decompose the original wind speed data into several subseries. This process is beneficial to improve the ratio of signal to noise and simply the features of wind speed data. In addition, the Conv-LSTM is tested on three datasets, the results proved that data process is advantaged to obtain higher quality wind speed datasets, and convolutional layer can deep extract the characteristics of each subseries, it can facilitate LSTM to make accurate prediction. The final prediction results, compared with other five different models, demonstrate that the proposed model can achieve higher precision. Such as the performance evaluation matrix (MAPE=2.62%, RMSE=0.151) are smallest obtained from experiments on three wind different wind speed datasets.

To overcome the premature-convergence of standard bat algorithm in solving the multi-objective optimal power flow (MOOPF) problems, a novel hybrid bat algorithm (NHBA) is proposed in this paper. The suggested NHBA algorithm modifies the local search manner by a monotone random filling model based on extreme (MRFME) and improves the population-diversity by mutation and crossover mechanisms. To obtain the uniformly-distributed Pareto optimal set (POS) with zero constraints-violation, an innovative non-dominated sorting method combined with constrained Pareto fuzzy dominant (CPFD) strategy is put forward in this paper. To verify the superiority of the proposed NHBA-CPFD algorithm, which is federated by the NHBA algorithm and the CPFD strategy, ten MOOPF simulation cases considering the basic fuel cost, the fuel cost with value-point loadings, the total emission and the active power loss are studied on the IEEE 30-node, IEEE 57-node and IEEE 118-node systems. In contrast to the NHBA, MOPSO and NSGA-III algorithms which adopt the constrain-prior Pareto-dominance method (CPM), numerous results validate the NHBA-CPFD algorithm can achieve more superior compromise solutions and preferable Pareto fronts (PFs) even in the large-scale systems. Furthermore, two performance metrics of generational distance (GD) and hyper-volume (HV) also demonstrate that the NHBA-CPFD algorithm has great advantages to obtain the feasible POS with evenly-distribution and favorable-diversity.

The short-term hydrothermal scheduling (STHS) is a complicated optimization problem, considering valve-point effect (VPE) and transmission losses, it exhibits the characteristics of nonlinearities and non-smoothness which increase the difficulty of solving the problem. Responding to these challenges, a hybrid algorithm that comprises chaotic local search technique, grey wolf optimizer, and dragonfly algorithm (CGWO-DA) is proposed to settle the STHS problem. The grey wolf optimizer (GWO) has strong local search ability with the slow convergence rate. The dragonfly algorithm (DA) owns superior global search capability and fast convergence rate, however, it exerts premature convergence and is easy to fall into local optimum. Using the chaotic local search as a supplement, the hybrid algorithm combined by two excellent algorithms can improve the shortcoming of each algorithm and enhance the exploration and exploitation of the algorithm simultaneously. In addition, two novel constraints handling strategies are presented to resolve the complicated equality constrains and guarantee the feasibility of solutions. Three systems have been tested by the proposed methodology. The solutions are compared with the ones from other available literatures, the feasibility and effectiveness of the proposed approach are well demonstrated, and the findings of case studies show that the proposed method has great competitive advantages to obtain better scheduling schemes.

Optimal Power Flow Using an Improved Hybrid Differential Evolution Algorithm