To address the shortcomings of the existing deep learning-based Non-Intrusive Load Monitoring （NILM） methods in capturing long-term dependencies and complex nonlinear dynamic features， an NILM method combining BiLSTM-Transformer and Kolmogorov-Arnold Network （KAN） was proposed， and a mix model BT-KAN was constructed. Firstly， the BiLSTM-Transformer module was designed to combine the advantage of the Bidirectional Long Short-Term Memory （BiLSTM） network in modeling bidirectional sequence dependencies with the capability of Transformer in modeling global context， and a multi-head attention mechanism was employed to capture long-term dependencies of power load effectively， thereby improving the disaggregation accuracy long-cycle appliances. Then， the KAN module was used to capture nonlinear dynamic features of power load signals more accurately through a hierarchical nonlinear mapping mechanism based on the Kolmogorov-Arnold representation theorem， thereby improving the disaggregation accuracy for complex load modes. Experimental results on the REDD （Reference Energy Disaggregation Dataset） and UK-DALE （UK Domestic Appliance-Level Electricity） datasets show that compared with four Transformer-based similar models， the proposed model achieves reduction of at least 1.6% and 5.5% in Mean Absolute Error （MAE）， the improvement of at least 8.3% and 0.7% in F1-score. It can be seen that the proposed method captures long-term dependencies and nonlinear dynamic features in power load signals more accurately and improves the disaggregation effect of complex appliance operating modes.

A Multi-Start Tabu Search (MSTS) algorithm was proposed for the maximum cut problem to improve the solution quality. The proposed algorithm included two key components, one of which was tabu search used to identify high-quality local optimal solutions and the other of which was the multi-start strategy used for the global exploration. Firstly, a local optimum solution was acquired by tabu search component. Secondly, new starting solution was produced by multi-start strategy and then tabu search procedure was restarted. Based on the random greediness, the proposed multi-start strategy integrated the constructive and perturbation methods to produce new starting solutions, thus escaping from being trapped in local optimum and finding higher quality solutions. Experiments on 21 standard maximum cut benchmark instances and comparisons with several state-of-the-art algorithms show that 18 best solutions was obtained by MSTS, higher than compared algorithms. The experimental results indicate that the proposed algorithm outperforms the reference algorithms in terms of the solution quality.