Analogue and Physical Reservoir Computing Using Water Waves: Applications in Power Engineering and Beyond

Abstract

More than 3.5 billion people live in rural areas, where water and water energy resources play an important role in ensuring sustainable and productive rural economies. This article reviews and critically analyses the recent advances in the field of analogue and reservoir computing that have been driven by the unique physical properties and energy of water waves. It also demonstrates that analogue and physical reservoir computing, taken as an independent research field, holds the potential to bring artificial intelligence closer to people living outside large cities, thus enabling them to enjoy the benefits of novel technologies that are already in place in large cities but are not readily available or suitable for regional communities. In particular, although the physical reservoir computing systems discussed in the main text are universal in terms of processing input data and making forecasts, they can be used to design and optimise power grid networks and forecast energy consumption, both at local and global scales. Thus, this review article will be of interest to a broad readership interested in novel concepts of artificial intelligence and machine learning and their innovative practical applications in diverse areas of science and technology.

Reservoir Computing Using Measurement-Controlled Quantum Dynamics

“…We stress that we deliberately choose to test the reservoir in the generative mode because, as shown in Refs. [12,[19][20][21]59,60], demonstrations of the operation in the predictive mode are technically straightforward. While the operation in the generative mode is a more challenging task, the practical importance of generative reservoirs is typically much higher since they can be used to solve a wide range of problems concerned with the prediction of difficult-to-analyse processes such as the behaviour of financial markets and variations in climate [12].…”

“…Despite its relative simplicity, this test task is nontrivial since it requires any RC system to adjust to constantly changing input conditions, also requiring strong output feedback needed to generate oscillations (for this reason, a conceptually similar test problem called frequency generator was used used to demonstrate the operation of the traditional RC algorithm by its creators [12,61]). Moreover, undertaking this specific task presents a considerable challenge to the reservoir due to a two-parameter space nature of the problem: the RC system should be trained to accurately simulate the dynamics of both frequency and amplitude.…”

“…However, to accomplish a computational task of arbitrary complexity, they may require impracticably large resources such as time and memory. To overcome this challenge, unconventional [1,2] and neuromorphic [3][4][5][6][7][8][9][10] approaches to computer engineering and data processing were proposed based on the idea that a computer should imitate the operation of a biological brain [11,12].…”

“…Reservoir computing (RC) is a resource-efficient neuromorphic information processing algorithm that is especially suitable for making forecasts of highly nonlinear and chaotic time series that underpin a number of essential natural and human-made phenomena, including the variation of climate, dynamics of Earth population, trends in financial markets, energy generation, and drug discovery [12,[20][21][22][23][24][25][26][27]. A typical RC algorithm [20,21] employs a randomly initialised task-dependent neural network (reservoir) that is connected to the input units through random connections.…”

“…A computational reservoir can also be created using a physical, either experimental or theoretical, nonlinear dynamical system that effectively recreates the dynamical properties of an update equation of the traditional RC algorithm [20]. Called the physical reservoir [11], this approach to computer engineering has been successfully validated using spintronic devices [28][29][30], electronic circuits [31,32], photonic systems [33,34], mechanical devices [35], and liquids [12,[36][37][38].…”