Search

This paper proposed a user-friendly and adaptive home intelligent agent with self-learning capability for optimal scheduling of smart home energy systems. The intelligent agent autonomously identifies model parameters based on system operation data, eliminating the need for manual input and making it more user-friendly and practical to implement. It can also self-learn the latest energy consumption information from an updated dataset and adaptively adjust model parameters to accommodate changing conditions. Utilizing these determined models as input, the intelligent agent performs day-ahead optimal scheduling using the proposed many-objective integer nonlinear optimization model and automatically controls system operation. Experimental studies were conducted on a laboratory-based smart home energy system to verify the effectiveness of the developed intelligent agent in different scenarios. The results consistently demonstrate Mean Absolute Percentage Errors below -12.7 % across all three scenarios, indicating the accuracy of the intelligent agent. Furthermore, the optimal scheduling significantly enhances system performances. After optimization, daily operational costs, peak-valley differences, and CO2 emissions were reduced by 34.1 % to 81.6 %, 29.2 % to 36.7 %, and 19.6 % to 43.2 %, respectively. Moreover, the PV generation self-consumption rate and self-sufficiency rate improved by 29.6 % to 38.0 % and 40.5 % to 49.4 %, respectively. The proposed intelligent agent provides invaluable guidance for optimal dispatch of smart home energy systems in real-world settings.

The construction of the Electric Vehicle Integrated Energy Station (EV-IES) is a prerequisite for the rapid development of the EV industry. However, how to optimize the operation of the EV-IES is a problem worthy of study. Therefore, this paper designs an EV-IES model with PV and Energy Storage System (ESS). Fully consider the peak-valley time-of-use electricity price, user traffic flow, PV output, and other factors. On this basis, the three objectives of the maximum daily revenue of the EV-IES, the minimum exchanged energy between the EV-IES and the Regional Power System (RPS), and the minimum pollutant emission are optimized at the same time. Secondly, this paper proposes a Many-objective Stochastic Competition Optimization (MOSCO) algorithm, which is utilized to assess the DTLZ1-7 benchmark functions and the optimization scheduling problem of EV-IES. By comparing its simulation results with those of five other optimization algorithms, it is evident that the MOSCO algorithm outperforms the other five in terms of IGD, GD, HV, and Spread values. This indicates the effectiveness of the MOSCO algorithm in addressing many-objective optimization problems. Finally, in order to illustrate the feasibility of designing the EV-IES model, three comparative cases were designed. The Pareto solutions of these cases were obtained using the MOSCO algorithm, and the Entropy-Technique for Order Preference by Similarity to Ideal Solution (ETOPSIS) method was applied to determine the optimal solution for each case. Compared to the traditional charging station (case 1), the daily revenue of the EV-IES increased by 27.97%. Pollutant emissions were reduced by 25.29%.