Cascade hydropower scheduling is a high-dimensional, tightly constrained multi-objective optimization problem in which classical genetic and evolutionary algorithms struggle to find feasible solutions. Under random initialization, algorithms such as the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the Non-dominated Sorting Genetic Algorithm III (NSGA-III), and the Constrained Two-Archive Evolutionary Algorithm (C-TAEA) rarely produce any feasible solution when the feasible region occupies a vanishingly small fraction of the search space. This paper presents a three-phase framework that combines physics-guided deep learning with evolutionary computation to accelerate both NSGA-II and NSGA-III. The method trains a Physics-Embedded Temporal Convolutional Network (PeTCN) as a differentiable surrogate model that explicitly incorporates physical constraints, applies gradient-based inverse optimization to obtain a feasible or near-feasible solution of high quality, and warm-starts NSGA-II or NSGA-III with that solution for efficient Pareto front exploration. Experiments on a real-world six-station cascade system show that, under a 1500 s fixed-time budget across 20 independent runs, Boosted NSGA-II and Boosted NSGA-III both find feasible solutions in all runs. Boosted NSGA-II and Boosted NSGA-III both reach the first feasible solution within roughly 50–60 generations of Phase 3 search on average, whereas standard NSGA-II produces no feasible run within the same budget and standard NSGA-III requires thousands of generations among its successful runs. The mean final hypervolume reaches for Boosted NSGA-II and for Boosted NSGA-III, and both boosted algorithms reach a target hypervolume of in all 10 target-hypervolume runs. These results demonstrate that coupling physics-embedded surrogates with gradient-based initialization is an effective strategy for constrained multi-objective problems in which feasible solutions are extremely sparse.
30 June 2025 in Highlights in Business, Economics and Management
Based on the perspective of game theory, this paper constructs a two-level game analysis framework for the coupon marketing strategy of shopping malls. The study adopts the Stackelberg game model to systematically examine the strategic interaction between shopping malls and consumers, as well as between shopping malls and competitors. In the vertical dimension, the influence mechanism of coupon issuance strategy on consumer purchase decision-making behavior is analyzed in detail; in the horizontal dimension, the dynamic impact of preferential competition among shopping malls on market share and operating income is deeply explored. Constructing theoretical models and numerical simulations reveals the formation conditions and action mechanisms of the optimal preferential strategy under different market environments. This study provides theoretical support for shopping malls to formulate differentiated coupon marketing plans in a complex competitive environment, which helps to achieve the dual goals of profit optimization and market position improvement and has important practical guiding value for the optimization of retail marketing strategies.
11 July 2025 in Advances in Economics, Management and Political Sciences
This paper delves into the influence of “the Interim Measures for the Interconnection of Interest Rate Exchange Markets between Mainland China and Hong Kong” or “Swap Connect”, a new EX futures regulation which was issued on May 15th , 2023. We deal with risk management and the way it reshapes the interest rate swap (IRS) and cross-currency swap market in China. To analyse the regulation, we describe the regulation in details and explore the mechanisms of interest rate swap market in China. We then compare how the market performs before and after the implementation of the regulation. Then, We analyze the risks of CHY/HKD exchange rate derivatives, which include IRS. The risks are volatility risk caused by fluctuation of exchange rate, liquidity risk caused by low settlement efficiency and credit risk caused by the default of the counterpart. We compare the risks before and after the implementation of the regulation and point out the regulation plays a positive role in risk management.