Combined Cooling, Heating and power(CCHP) system is an important way to improve the efficiency of energy utilization and wind power consumption. In this case, increasing the operational flexibility of CCHP systems can...
Combined Cooling, Heating and power(CCHP) system is an important way to improve the efficiency of energy utilization and wind power consumption. In this case, increasing the operational flexibility of CCHP systems can help increase renewableenergy consumption and reduce carbon emissions. So, it is necessary to provide real-time optimal energy management(OEM) for CCHP systems. In this paper. Firstly, a new training method is proposed for the LightGBM to improve the accuracy of real-time wind power prediction. In addition, to solve the nonlinear OEM of CCHP in real-time, a novel deep reinforcement learning algorithm-Soft Actor-Critic, is used in this paper. By combining the mechanism of CCHP with the reward function through knowledge fusion, the non-convex models can be translated into Markov Decision Processes(MDP), and then according to the Bellman optimal equation, the real-time optimized operation of the CCHP system is realized. Finally, the effectiveness of the proposed policy is verified by the actual operation data of a CCHP system in Northwest China.
The fault transient characteristics of power grids have undergone a fundamental transformation as a consequence of the advent of hybrid scale access to power grids by new energy sources. Nevertheless, the existing sta...
详细信息
The high percentage of renewableenergy sources presents unprecedented challenges to the flexibility of powersystems, and planning for the system's flexibility resources has become a necessary research area. Thus...
详细信息
The high percentage of renewableenergy sources presents unprecedented challenges to the flexibility of powersystems, and planning for flexibility resources has become a necessary research area. Thus, this study cons...
详细信息
The deep learning algorithm represented by CNN has achieved remarkable results in complex feature extraction, classification and regression. Since the CNN adopts an end-to-end training process, the carrier of acquisit...
详细信息
To solve slow response speed and poor stability of traditional MPPT algorithms under rapidly changing environmental conditions, a MPPT control strategy combining improved butterfly algorithm and disturbance observatio...
详细信息
ISBN:
(数字)9798350377460
ISBN:
(纸本)9798350377477
To solve slow response speed and poor stability of traditional MPPT algorithms under rapidly changing environmental conditions, a MPPT control strategy combining improved butterfly algorithm and disturbance observation method is proposed. Firstly, the butterfly position in the population is initialized by Tent map, increasing the search space; Secondly, Gaussian mutation strategy is introduced to make the algorithm break out of local extremes; Then, a dynamic probability switching mechanism is adopted to balance the weight relationship between global and local search, improving algorithm optimization efficiency; Finally, in the later stage, disturbance observation method is used to track the maximum power and reduce power oscillation. simulation examples show that the proposed algorithm can find the maximum power point quickly and accurately under both static and dynamic shading conditions, and the power output is more stable.
An MPPT control strategy based on the combination of adaptive nonlinear mutation particle swarm optimization algorithm is proposed. The algorithm uses the tanh function to control the inertia weight, balances the abil...
详细信息
ISBN:
(数字)9798350309638
ISBN:
(纸本)9798350309645
An MPPT control strategy based on the combination of adaptive nonlinear mutation particle swarm optimization algorithm is proposed. The algorithm uses the tanh function to control the inertia weight, balances the ability of particles to optimize globally and locally, uses the ISRU function to control the learning factor, balances the weight relationship between individual learning and social learning, and improves the convergence speed of the algorithm. The nonlinear Cauchy mutation operation is proposed to expand the scope of optimization; Finally, the perturbation and observation method is used to track locally near the maximum power point to reduce power oscillation. The simulation validates that the photovoltaic MPPT control strategy based on the improved particle swarm algorithm can effectively get the maximum power point under shading conditions and improve the output efficiency of the PV array.
With the improvement of the informatization of the powersystem, the risk of cyber attack is also increasing. This paper proposes a risk assessment and prevention strategy for cyber attack against substations. Firstly...
详细信息
Addressing the stability challenges posed by the unpredictability and intermittent nature of wind power output during grid integration, and aiming to enhance the understanding of factors influencing grid stability upo...
详细信息
This paper examines the path of new energy development in China against the backdrop of carbon maximum and carbon neutralization, and studies the risk of large scale new energypower transmission. In order to solve th...
详细信息
暂无评论