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.

Abstract Background For patients with locally advanced rectal cancer (LARC), total neoadjuvant therapy (TNT), namely, intensifying preoperative treatment through the integration of radiotherapy and systemic chemotherapy before surgery, was commonly recommended as the standard treatment. However, the risk of distant metastasis at 3 years remained higher than 20%, and the complete response (CR) rate was less than 30%. Several clinical trials had suggested a higher complete response rate when combining single-agent immunotherapy with short-course radiotherapy (SCRT). The CheckMate 142 study had shown encouraging outcomes of dual immunotherapy and seemingly comparable toxicity for CRC compared with single-agent immunotherapy in historical results. Therefore, dual immunotherapy might be more feasible in conjunction with the TNT paradigm of SCRT. We performed a phase II study to investigate whether the addition of a dual immune checkpoint inhibitor bispecific antibody, Cadonilimab, to SCRT combined with chemotherapy might further increase the clinical benefit and prognosis for LARC patients. Methods This single-arm, multicenter, prospective, phase II study included patients with pathologically confirmed cT3-T4N0 or cT2-4N + rectal adenocarcinoma with an ECOG performance score of 0 or 1. Bispecific antibody immunotherapy was added to SCRT combined with chemotherapy. Patients enrolled would be treated with SCRT (25 Gy in five fractions over 1 week) for the pelvic cavity, followed by 4 cycles of CAPOX or 6 cycles of mFOLFOX and Cadonilimab. The primary endpoint was the CR rate, which was the ratio of the pathological CR rate plus the clinical CR rate. The secondary endpoints included local–regional control, distant metastasis, disease-free survival, overall survival, toxicity profile, quality of life and functional outcome of the rectum. To detect an increase in the complete remission rate from 21.8% to 40% with 80% power, 50 patients were needed. Discussion This study would provide evidence on the efficacy and safety of SCRT plus bispecific antibody immunotherapy combined with chemotherapy as neoadjuvant therapy for patients with LARC, which might be used as a candidate potential therapy in the future. Trial registration This phase II trial was prospectively registered at ClinicalTrials.gov, under the identifier NCT05794750.

The optimal scheduling of home energy systems is influenced by the benefits of different stakeholders, with the hierarchical nature of user's needs being particularly significant. However, previous studies have largely neglected these factors. To bridge the research gaps, a many-objective optimal dispatch framework for home energy systems, which was inspired by Maslow's hierarchy of needs, was proposed. In the framework, user's needs for the optimal dispatch of home energy systems were categorized into various hierarchies referring to the Maslow's theory, which were fulfilled in a specific sequence during the scheduling optimization. In addition to the user's needs, the benefits of grid operators and policymakers were considered in the developed many-objective nonlinear optimal model, which includes six objective functions that capture the interests of end-users, grid operators, and policymakers. Simulation results obtained across the home energy systems with various configurations verified the effectiveness of the proposed framework. Results indicate that user's needs can be fully satisfied and a tradeoff among the benefits of end-users, grid operators, and policymakers was achieved. For various home energy systems, the optimal scheduling demonstrated reductions of 22.33 %-81.05 % in daily operation costs, 14.39 %-25.68 % in CO2 emissions, and 15.58 %-17.49 % in peak-valley differences, associated with increment of 5.37 %-15.51 % in self-consumption rate and 8.91 %-27.29 % in self-sufficiency rate, compared with the benchmark. The proposed framework provides valuable guidance for the optimal scheduling of various home energy systems in practical applications.