Search

Objective To investigate the role of tumor draining lymph nodes (TDLN) in the generation of memory CD8+ T cells under the context of neoadjuvant anti-PD-L1 therapy. Methods A mouse transplanted model of CT26/MC38-OVA colon cancer was established to recapitulate clinic neoadjuvant anti-PD-L1 therapy, and then the tumor masses and TDLN were removed in 15 d after transplantation. On day 30 after surgery, the effect of TDLN on the formation of immune memory was assessed under the condition of neoadjuvant PD-L1 antibody therapy by tumor re-challenge. The effect of neoadjuvant PD-L1 on tumor-specific CD8+ T cells was investigated by adoptive transfer CD45.1+ OT-Ⅰ cells. The distribution and phenotype of CD45+ CD8+T cells in various tissues were determined by flow cytometry at the time of surgery (effector phase) and 30 d after surgery (memory phase). Results The tumor mass was reduced significantly after receiving neoadjuvant anti-PD-L1 therapy (P < 0.05). After tumor re-challenge, tumor growth was significantly slowed in the mice treated with neoadjuvant PD-L antibody, whereas TDLN resection accelerated the tumor growth (P < 0.05). However, long-term survival of tumor re-challenge showed that all tumors were eventually subsided, whether or not the mice treated with neoadjuvant PD-L antibody. The results of adoptive reinjection indicated that the number of CD45.1+ CD8+ T cells being stored in TDLN and no-draining lymph nodes (NLN) was the highest (P < 0.05). Tcm (T central memory) cells and Trm (tissue-resident memory) cells were mainly distributed in TDLN and NLN in memory phase (P < 0.05). The distribution and memory phenotype of CD45.1+ CD8+ T cells in TDLN and NLN had no obvous changes after neoadjuvant anti-PD-L1 therapy. Conclusion TDLN is the primary site for the storage of memory CD8+ T cells, but under the condition of neoadjuvant PD-L1 antibody treatment, TDLN resection does not affect their long-term anti-tumor immunity.

Due to the volatility and intermittency of renewable energy, the integration of a large amount of renewable energy into the grid can have a significant impact on its stability and security. In this paper, we propose a tiered dispatching strategy for compressed air energy storage (CAES) and utilize it to balance the power output of wind farms, achieving the intelligent dispatching of the source–storage–grid system. The Markov decision process framework is used to describe the energy dispatching problem of CAES through the Actor–Critic (AC) algorithm. To address the stability and low sampling efficiency issues of the AC algorithm in continuous action spaces, we employ the deep deterministic policy gradient (DDPG) algorithm, a model-free deep reinforcement learning algorithm based on deterministic policy. Furthermore, the use of Neuroevolution of Augmenting Topologies (NEAT) to improve DDPG can enhance the adaptability of the algorithm in complex environments and improve its performance. The results show that scheduling accuracy of the DDPG-NEAT algorithm reached 91.97%, which was 15.43% and 31.5% higher than the comparison with the SAC and DDPG algorithms, respectively. The algorithm exhibits excellent performance and stability in CAES energy dispatching. [ABSTRACT FROM AUTHOR]

Owing to the volatility and intermittency of renewable energy generation units in microgrids, effective energy scheduling methods are essential for efficient renewable energy utilization and stable microgrid operation. In recent years, microgrid energy optimization scheduling based on deep reinforcement learning (DRL) has made significant progress. With the development of the microgrid, the drawbacks of the traditional DRL agent, such as long training time and poor convergence effect, are gradually revealed. This paper proposes a generative adversarial imitation learning method with Wasserstein distance for optimal energy scheduling in the microgrid. This method combines a proximal policy optimization algorithm to optimize energy scheduling and reduce microgrid operating costs. First, the agent adaptively learns the action exploration process by imitating expert trajectories. Second, based on the generative adversarial theory, a discriminator network is added, and the Wasserstein distance is introduced into the discriminator network to distinguish between the generative and expert strategies. This feedback assists in updating the neural network parameters. Finally, the effectiveness of the proposed method is verified through an arithmetic example analysis. [ABSTRACT FROM AUTHOR]