The widely adoption of distributed renewable energy sources (DREs) effectively reduces carbon emission and beat atmospheric haze in developing countries. However, random disturbance issues emerge in power grids with DREs when applying traditional centralized automatic generation control (AGC) strategies. Therefore, a multi-agent distributed control strategy is proposed for AGC in this work, which is mainly based on the concept of deep reinforcement learning, and developed by the strategy of action discovery. Moreover, area control error and the amount of carbon emission are employed in reward functions to obtain optimal solutions in the implementing process of the proposed strategy. Simulations are provided in the work to show the effectiveness of the strategy, while comparisons are also offered, where the simulating results obtained by two other intelligent AGC algorithms are used as references, according to which, the superiority of the proposed strategy is confirmed.

As the conventional automatic generation control (AGC) is inadequate to deal with the strong random disturbance issues induced by the ever-increasing penetration of renewable energy to the power grids, this article proposes a deep-reinforcement-learning-based three-network double-delay actor-critic (TDAC) control strategy for AGC to handle the above problem, which is mainly developed by multiple neural networks to fit the system action strategies and evaluate the value. The proposed strategy can increase the exploration efficiency and the quality of AGC and improve the system control performance using the modified actor-critic (AC) method with incentive heuristic mechanism, while a novel iterative way of the value function is also used to reduce the bias of optimization effectively for achieving optimal coordinated control of the power grid. The simulations are provided in the work to show the control performance of the strategy. Compared with other smart methods, the simulation study demonstrates that TDAC has excellent exploratory stability and learning ability. Meanwhile, it also can improve the dynamic performance of the power system and achieve the regional optimal coordinated control.

With the global trend to develop digital substation automation systems, measurement devices are required to be reliable, of small size and light weight and of acceptable accuracy in a wide frequency band. This article presents a combined high voltage direct current measurement method which comprises the above-mentioned features that makes it suitable for smart grids protection and control applications. The proposed measurement method utilizes Hall sensor array for dc current measurement. DC voltage is measured using a voltage divider circuit while the harmonic currents are measured using a square Rogowski coil made of four straight bars along with a high precision digital integration algorithm. A four-spectral line interpolation fast Fourier transform algorithm based on trapezoidal convolution window is proposed to improve the extraction accuracy of the dc and harmonic components from the measured signal. Experimental results show that the error variation of the proposed method is less than 0.098% for voltage measurement while it is less than 0.104% for current measurement. The harmonic measurement ratio error is less than 0.2% and the angle error is less than 8'.

As the penetration rate of new energies, energy storage devices and electric vehicles increases continuously in power grid, power grid faces strong random disturbances, as well as the issues of downfall in frequency control ability induced by the factors such as system inertia reduction and frequency control under-capacity in traditional power units. Therefore, an algorithm of automatic generation control with DQ(σ, δ) is proposed for the multi-area interconnected power grid. By integrating the eligibility trace, DQ(σ, δ) adopts the principle of double Q learning to unify double Q(δ) and double Expected-Sarsa(δ), thereby the over-estimation of Q in the algorithm and the phenomenon of over-fitting can be avoided. The simulations are provided to demonstrate the effectiveness of the proposed algorithm, where the improved IEEE standard two-area load-frequency control model and the model of the multi-area interconnected power grid based on Central China Power Grid are adopted. The results show that the phenomena of random disturbances and frequency instability can be eliminated in multi-area interconnected power grid. The convergence is faster and the dynamic performance is better in the proposed algorithm compared with the traditional algorithms.

While frequency response analysis (FRA) is a well matured technique widely used by current industry practice to detect the mechanical integrity of power transformers, interpretation of FRA signatures is still challenging, regardless of the research efforts in this area. This paper presents a method for reliable quantitative and qualitative analysis to the transformer FRA signatures based on a decision tree classification model and a fully connected neural network. Several levels of different six fault types are obtained using a lumped parameter-based transformer model. Results show that the proposed model performs well in the training and the validation stages, and is of good generalization ability.

The uncertainty of high-permeability renewable energy output brings about great challenges to the operation control in distribution network. The traditional control mode has lower reliability, higher calculation and greater communication pressure. It is more difficult to realize the technical requirements of “plug and play” of power components. Therefore, a bi-level coordinated control model is proposed for the operation and energy management optimization of active distribution network with multi-microgrid in this paper. The consensus algorithm which exists in the multi-agent system is applied in the upper-level model and the capacity utilization ratio of the different microgrids is set as the consistent variable because the ratio of resistance and reactance is usually larger in distribution network and the interests in the different microgrid entities should be distributed fairly. Moreover, in the lower-level model, the lowest operating cost is the final goal and the model predictive control rolling optimization is utilized to reasonably allocate the output of the equipments in the microgrid according to the changing trend of renewable energy. Thereby the tracking of the upper-level control commands is realized. Finally, the simulations are conducted in the IEEE-33 nodes distribution system connected to a multi-microgrid to verify the feasibility and effectiveness of the proposed method, in which a reference for the optimal operation of higher penetration renewable energy to distribution network is provided.